HCI Bibliography Home | HCI Conferences | UBICOMP Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
UBICOMP Tables of Contents: 01020304050607080910111213-113-214-114-215

Adjunct Proceedings of the 2014 International Joint Conference on Pervasive and Ubiquitous Computing

Fullname:Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Editors:AJ Brush; Adrian Friday; Julie Kientz; James Scott; Junehwa Song
Location:Seattle, Washington
Dates:2014-Sep-13 to 2014-Sep-17
Volume:2
Publisher:ACM
Standard No:ISBN: 978-1-4503-3047-3; ACM DL: Table of Contents; hcibib: UBICOMP14-2
Papers:227
Pages:1408
Links:Conference Website
  1. UBICOMP 2014-09-13 Volume 2
    1. Posters
    2. Demos
    3. Video presentations
    4. Doctoral school
    5. Programming competition
    6. AwareCast 2014: Third Workshop on Recent Advances in Behavior Prediction and Pro-Active Pervasive Computing
    7. CEA 2014 -- Smart Technology for Cooking and Eating Activities
    8. How do you solve a problem like consent? Workshop addressing the challenge of user consent
    9. Disasters in Personal Informatics: the Unpublished Stories of Failure and Lessons Learned
    10. HASCA -- 2nd International Workshop on Human Activity Sensing Corpus and its Application
    11. HomeSys 2014
    12. 3rd International Workshop on Mobile Systems for Computational Social Science
    13. Collective Wearables: the Superorganism of Massively Deployed Wearables
    14. PETMEI -- 4th International Workshop on Pervasive Eye Tracking and Mobile Eye-Based Interaction
    15. SmartHealthSys 2014 -- ACM UbiComp Workshop on Smart Health Systems and Applications
    16. UPSIDE -- Workshop on Usable Privacy & Security for Wearable and Domestic Ubiquitous Devices
    17. WAHM 2014 -- Workshop on Ubiquitous Technologies for Augmenting the Human Mind

UBICOMP 2014-09-13 Volume 2

Posters

Protecting mobile users from visual privacy attacks BIBAFull-Text 1-4
  Mohammed Eunus Ali; Tanzima Hashem; Anika Anwar; Lars Kulik; Ishrat Ahmed; Egemen Tanin
An increasing number of people are using mobile devices in public places such as buses, trains, airports, coffee shops, and restaurants. Though the flexibility to work remotely using mobile devices make people more productive, this new working practice incurs un-authorized visual access of the mobile display by the bystanders, which we call visual privacy attack. Failing to prevent un-authorized people viewing sensitive information such as passwords, emails, and business information could lead to financial loss, public exposure, and embarrassment. In this paper, we propose a solution that captures the surrounding environment through user's mobile phone camera and determines whether any un-authorized person is obtaining visual access to the user's mobile screen. We develop an Android application, iAlert, that runs as a background process on a user's mobile device and alerts the user based on whether or not the displayed text on the screen is readable by bystanders.
Adding directional context to gestures using Doppler effect BIBAFull-Text 5-8
  Adeola Bannis; Shijia Pan; Pei Zhang
Human beings often give non-verbal instructions through motions of the hand and arm, such as pointing or waving. These motions convey not just actions, but the direction or target of those actions. In this paper, we integrate direction into gesture definitions by detecting frequency shifts created by relative motion between a receiver and transmitter and combining this with inertial motion data captured by a smartphone. With the combined data we are able separate similar gestures with 71.7% accuracy in a typical home use environment.
Locator: a self-adaptive framework for the recognition of relevant places BIBAFull-Text 9-12
  Paul Baumann; Johannes Klaus; Silvia Santini
A high number of algorithms for the recognition of users' relevant places exist. However, none of them provide an optimal solution across all users and scenarios. We present a preliminary design of Locator -- a self-adaptive framework for recognizing users' relevant places. Locator learns for different contextual situations, combinations of algorithms and location sensor data that achieve the best performance in recognizing relevant places. We conducted a 5-weeks study and collected sensor and ground-truth data from 6 users. Our preliminary results indicate the shortcomings of relying on one algorithm and sensor for recognizing places and thus motivates the rational behind our approach.
Portrait pigeon: an interactive photo messaging wall for seniors BIBAFull-Text 13-17
  Robin N. Brewer; Moritz Gellner; Anne Marie Piper
Considerable research has studied online communication for older adults. For some seniors, age-related disability presents barriers to using computers and going online. For others, lack of experience or lack of interest deters them from keeping in touch using modern communication platforms such as social media sites. Physical communication artifacts, such as printed photos, support important forms of offline communication for older adults, and we examine how physical photos can be augmented to facilitate lightweight online social communication. This approach embeds online messaging into a familiar and culturally-relevant artifact, physical photos. This paper presents Portrait Pigeon, a ubiquitous lightweight messaging platform for seniors that integrates in-home photo displays into online communication.
Holes, pits, and valleys: guiding large-display touchless interactions with data-morphed topographies BIBAFull-Text 19-22
  Debaleena Chattopadhyay; Said Achmiz; Shivin Saxena; Malvika Bansal; Davide Bolchini; Stephen Voida
Large, high-resolution displays enable efficient visualization of large datasets. To interact with these large datasets, touchless interfaces can support fluid interaction at different distances from the display. Touchless gestures, however, lack haptic feedback. Hence, users' gestures may unintentionally move off the interface elements and require additional physical effort to perform intended actions. To address this problem, we propose data-morphed topographies for touchless interactions: constraints on users' cursor movements that guide touchless interaction along the structure of the visualized data. To exemplify the potential of our concept, we envision applying three data-morphed topographies -- holes, pits, and valleys -- to common problem-solving tasks in visual analytics.
ContextSense: unobtrusive discovery of incremental social context using dynamic bluetooth data BIBAFull-Text 23-26
  Zhenyu Chen; Yiqiang Chen; Lisha Hu; Shuangquan Wang; Xinlong Jiang; Xiaojuan Ma; Nicholas D. Lane; Andrew T. Campbell
User-centric ambient social contexts can be effectively captured by dynamic bluetooth data. However, conventional approaches for training classifiers struggle with social contexts that are incrementally constructed and continuously discovered in everyday environments. Incremental social contexts can confuse a classifier because it assumes that the number and composition of context classes is fixed throughout training and inference phases. To address this challenge we propose ContextSense, an ELM-based learning method for continuous and unobtrusive discovery of new social contexts incrementally from dynamic bluetooth data. Experimental results show that ContextSense can automatically cope with "incremental social context" classes that appear unpredictably in the real-world.
Temperature sharing to support remote relationships BIBAFull-Text 27-30
  Chia-Fang Chung; James Hwang; Sean A. Munson
Among the data that can now be readily sensed and shared, we believe temperature has potential to support relationships, because people perceive warmth as intimate and temperature as indicative of comfort and wellness. We interviewed 20 participants who interacted with prototypes of temperature sensing and sharing systems. Participants believed that shared temperature information could make their remote relationships stronger by supporting coordination, reassurance, and intimacy. They also perceived many challenges common in UbiComp -- such as difficulty interpreting data and tradeoffs between intimacy and privacy. We discuss nuances and guidelines for using temperature information as "shared informatics" and how these results can inform future research and system designs.
A multi-tiered model for context-aware systems BIBAFull-Text 31-34
  Cristiano André da Costa; Jorge Luis Victoria Barbosa; Adenauer Corrêa Yamin; Rodrigo da Rosa Righi; Cláudio Resin Geyer
Context awareness is considered one of the most important challenges to be tackled in the field of ubiquitous computing (ubicomp). In this perspective, this paper describes a general model for context-aware systems. The model is organized in multiple tiers, each one addressing a specific design characteristic related to the area. The proposition can be applied in the design and assessment of context-aware systems.
Living with the user: design drama for dementia care through responsive scripted experiences in the home BIBAFull-Text 35-38
  Tim Coughlan; Michael Brown; Glyn Lawson; Derek McAuley; Allen Tsai; Therese Koppe; Meretta Elliott; Stephen Green; Sharon Baurley; Jen Martin
Participation in forms of drama and narrative can provoke empathy and creativity in user-centred design processes. In this paper, we expand upon existing methods to explore the potential for responsive scripted experiences that are delivered through the combination of sensors and output devices placed in a home. The approach is being developed in the context of Dementia care, where the capacity for rich user participation in design activities is limited. In this case, a system can act as a proxy for a person with Dementia, allowing designers to gain experiences and insight as to what it is like to provide care for, and live with, this person. We describe the rationale behind the approach, a prototype system architecture, and our current work to explore the creation of scripted experiences for design, played out though UbiComp technologies.
BiliCam: using mobile phones to monitor newborn jaundice BIBAFull-Text 39-42
  Lilian de Greef; James W. Stout; Mayank Goel; James A. Taylor; Min Joon Seo; Shwetak N. Patel; Eric C. Larson
Health sensing through smartphones has received considerable attention in recent years because of its promise to lower costs and provide more continuous data for tracking medical conditions. In this poster, we focus on using smartphones to sense newborn jaundice, which manifests as a yellow discoloration of the skin. Although jaundice is common in healthy newborns, early detection of extreme jaundice is essential to prevent brain damage or death. Current detection techniques, however, require clinical tests with blood samples or other specialized equipment. Consequently, newborns often depend on visual assessments of their skin color at home, which is known to be unreliable. We present BiliCam, a low-cost system that uses smartphone cameras to assess newborn jaundice.
Negative energy detector using cellphone bluetooth and contact list BIBAFull-Text 43-46
  Zhanwei Du; Chuang Ma; Yongjian Yang; Bo Yang
Individual mood is important for physical and emotional well-being. Despite the physiological reasons, emotional contagion between peoples is also pivotal to understand and further predict people's emotional change. However, an ignored yet important task is to find the behavior differences between easygoing and sharp-tongued persons in daily life.
   We present a novel metric to measure people's capacity to make their encounters negative. Then Latent Dirichlet Allocation topic model and multimodal exposure features (MME) are used to study the behavior differences, extracting the probable contact patterns of different kinds of people and how they contact with each other. Finally, to make practical, a MME Feed-forward Neural Network is given out to judge people's role in emotion contamination, with using people's own mobile-phones contact list. Taking the MIT Social Evolution dataset as an example, the experimental results verify the efficacy of our techniques on real-world data.
Extreme mediation: observing mental and physical health in everyday life BIBAFull-Text 47-50
  Anthony Faiola; Preethi Srinivas
The excessive use of smartphones resulting in extreme mediation has been identified to result in psychological problems including anxiety, depression, and an overall neural change that is impacting people of all ages on many levels. An exploratory study using Experience Sampling Method (ESM) concluded a significant increase in positive mood, conscious awareness of the surrounding environment, and an increased number of participants self-reporting physical activity lasting 15 minutes on days without smartphone use. Results suggest the need to avoid increased use of noninvasive technology such as smartphones resulting in deterioration of mental and physical health.
Future directions for providing better IoT infrastructure BIBAFull-Text 51-54
  Márcio Miguel Gomes; Rodrigo da Rosa Righi; Cristiano André da Costa
Internet of Things (IoT) supports a connection between objects and humans, enabling the ubiquitous computing in our daily lives. Future research directions in IoT infrastructure should consider real-time communication and scalability to provide a better experience to the users. We justify this sentence by developing an IoT micro-benchmark, which was evaluated over a real IoT middleware. Considering the observed gaps, this article describes the ideas on redesigning the IoT infrastructure, not imposing any modifications in the users' source code. The modeling combines cloud virtualization and elasticity, service decomposition and multithreading programming. The scientific contribution of the article consists of both a novel IoT infrastructure and the algorithms to control the functioning and scalability of each component.
SAP dissimilarity based high performance Wi-Fi indoor localization BIBAFull-Text 55-58
  Yang Gu; Yiqiang Chen; Junfa Liu; Xinlong Jiang
There are two longstanding issues: the fluctuation of wireless signal and the unstability of Access Point (AP), which greatly affect the performance of Wi-Fi based indoor localization. Most existing fingerprint based Wi-Fi localization methods adopt machine learning or data mining algorithms to get the location information; however, they ignore some intrinsic factors. According to massive observations, we discover some underlying characteristics of Wi-Fi indoor localization from the view of signal strength and AP. Hence, a new dissimilarity based localization method SAP (Signal-AP) is proposed to implement high performance indoor localization. The results show that SAP not only improves the localization accuracy, but also has desirable scalability of environment.
FlierMeet: cross-space public information reposting with mobile crowd sensing BIBAFull-Text 59-62
  Bin Guo; Xing Xie; Huihui Chen; Shenlong Huangfu; Zhiwen Yu; Zhu Wang
Bulletin boards serve an important function for public information sharing. Posted fliers advertise services, events and other announcements. However, fliers posted offline suffer from problems such as limited spatial-temporal coverage and inefficient search aid. In recent years, with the development of sensor-enhanced mobile devices, mobile crowd sensing has been used in a variety of application areas. In this paper we present FlierMeet, a crowd-powered sensing system for crossspace public information reposting, tagging and sharing. The tags are auto-labeled based on a set of visual and crowd-object interaction features. Initial deployments and experiments prove the effectiveness of our system.
Activity recognition exploiting classifier level fusion of acceleration and physiological signals BIBAFull-Text 63-66
  Haodong Guo; Gencai Chen; Ling Chen; Yanbin Shen
We investigate how to effectively combine physiological signals with acceleration signals to conduct activity recognition task. Firstly, features are extracted from acceleration and physiological signals, including heart rate variability (HRV). Secondly, classifier level fusion is utilized to combine the models built by acceleration and physiological features separately. Experiment results show that activity recognition task can benefit from HRV features, and classifier level fusion has its superiority over feature level fusion.
Designing a mobile system for public safety using open crime data and crowdsourcing BIBAFull-Text 67-70
  Yun Huang; Yang Wang; Corey White
With more cities opening up crime data and the proliferation of participatory sensing, we explore ways to improve public safety of a local community by using open crime data and crowdsourcing. We first conducted an online survey to better understand the public safety needs of the Syracuse University (SU) community. Inspired by the survey results, we developed and deployed an Android mobile app in collaboration with the Department of Public Safety (DPS) at SU; the app integrates published safety incidents on a Google Map and SU campus alerts. We present our experience of co-designing this system with the DPS, challenges and experience of our initial app release. To design effective crowdsourcing of public safety information, we conducted a lab experiment to investigate what factors affect people's sharing decisions. The results suggest that both time of day and type of location significantly affect people's sharing decisions. These insights inform a re-design of our system to "nudge" people to report safety related information timely.
Crowdsensing traces using bluetooth low energy (BLE) proximity tags BIBAFull-Text 71-74
  Shuja Jamil; Ahmed Lbath; Anas Basalamah
Designing massive scale crowdsensing experiments using smartphones can be very challenging. In this work, we define a new approach for designing massive crowdsensing applications where we offload the burden of sensing from smartphones to low cost off-the-shelf Bluetooth Low Energy (BLE) proximity tags. We discuss the usage of advertisements in BLE tags as a new energy-efficient sensing resource for massive scale crowd mobility trace collection. We performed a large experimental deployment with 600 tags and 10 smartphones conducted during the 5 days of the world largest annual gathering (The Hajj). We were able to achieve 90% detectability rate while effectively reconstructing the routes of the participants.
MugShots: everyday objects as social catalysts BIBAFull-Text 75-78
  Hsin-Liu Cindy Kao; Chris Schmandt
We explore how everyday objects can serve as social catalysts to increase social interaction in the workplace. As an initial exploration, we created MugShots, a coffee mug with a wireless OLED display. Users can wirelessly transmit images onto the mug, revealing different self-identities though an everyday object, in turn triggering interest and conversation with others. We present a prototype of MugShots along with a 10 person pilot study to gauge the feasibility of this idea.
Motivational affordances and personality types in personal informatics BIBAFull-Text 79-82
  Yamini Karanam; Hanan Alotaibi; Leslie Filko; Elham Makhsoom; Lindsay Kaser; Stephen Voida
Personal informatics applications have been gaining momentum with the introduction of implicit data collection and alert mechanisms on smart phones. A need for customized design of these applications is emerging and studies on tailoring UI design based on the personality traits of users are well established. This poster investigates how various affordances in gamified personal informatics applications affect motivation levels to track and achieve goals for users with different personality types. We conducted a study to examine how user personality traits relate to (1) motivational affordances in behavior tracking applications and (2) the specific behaviors users prefer to track.
Wearable computing for older adults: initial insights into head-mounted display usage BIBAFull-Text 83-86
  Kai Kunze; Niels Henze; Koichi Kise
With recent interest in industry, wearable computers with head-mounted displays are about to become mainstream. As it is typical for novel technologies, development is directed towards early adopters. This typically excludes special target groups such as older adults with age related special needs. However, it is necessary to consider their requirements when the technology matures, as they can benefit from wearable computing. In this paper we present an explorative, qualitative study with three older adults that used a wearable computer with a head mounted display during everyday activities. We derive requirements from the usage of existing applications, describe emerging usage patterns, highlight promising applications, and the reaction of the public.
Interfacing information in affective user studies BIBAFull-Text 87-90
  Kyeong-An Kwon; Dvijesh Shastri; Ioannis Pavlidis
In affective user studies, visual interfacing of data has received little attention. Such interfaces can support qualitative understanding, conveying insight about static and temporally evolving information; static information is exemplified by demographic data, while temporally evolving information is exemplified by physiological signals. In this paper we present User Portrait -- an abstraction and visualization method that condenses the essence of a study's data in a single figure. It is an inverted pyramid design, where the information abstraction is communicated on the top view, while the details are displayed on a need-to-know basis. The method has been applied to a longitudinal study of student affect vs. exam performance, effectively visualizing its voluminous data set.
Programming tool of context-aware applications for behavior change BIBAFull-Text 91-94
  Jisoo Lee; Winslow Burleson; Erin Walker; Eric B. Hekler
While users often have goals related to developing better habits (e.g., eating more healthy food, exercising more frequently), they are typically not very effective at achieving those goals. We have been developing a toolkit that provides hardware and software for users who have no programming experience to easily invent and test context-aware applications that can help them make changes in their behaviors. We have found that this toolkit needs to balance simplicity of interaction with the facilitation of a wide range of user experiences. To address this issue, we identified key temporal rule patterns from a user-generated collection of behavior change applications, and created programming elements with which users can compose applications of those patterns.
Logmusic: context-based social music recommendation service on mobile device BIBAFull-Text 95-98
  Mirim Lee; Jun-Dong Cho
Our choice of music in a daily life is greatly affected by our current mood and suggestions by others. We believe that people experience similar mood changes facing similar changes in weather, temperature, time, and location, and for this we suggest a service we named 'Logmusic', a context-based social music recommendation service. Using a prototype version, we performed a pilot test in order to determine if the hypothesis is valid. To conclude, songs recommended through this system scored significantly higher on both preference and appropriateness than randomly selected songs or popular songs. This service is expected to enhance user's music experience and promote sense of unity among users, and contribute to build unique cultures within local communities.
Eco-feedback for non-consumption BIBAFull-Text 99-102
  Veranika Lim; Joes Janmaat; Arvid Jense; Mathias Funk
Eco-feedback is a strategy to increase awareness of resource use and to encourage conservation. We applied eco-feedback on household food waste with the prospective to increase awareness and explore its impact on food related decision-making. In this paper we present a prototype of an eco-feedback system for food waste, which was deployed in a student house. In preliminary findings, participants indicated positive effects on dealing with leftovers, food preparation and reflection about food waste issues, when eco-feedback was deployed. Findings are used for the next design iteration of the concept and, for more concluding results, in a larger-scale evaluation.
MemoryRetrospect: lifelogging with social awareness BIBAFull-Text 103-106
  Lipeng Liu; Rong Li; Yongxiong Sun; Yinghan Li; Zhanwei Du; Qiuyang Huang
As a promising procedure of mobile application. So far, lifelogging has already some initial attempts on photos, audios and video records. However, they are just simple information recording tools, in which the receivers cannot feel the senders with empathy in space or time. In this poster, we propose a concept called MemoryRetrospect, which combines Lifelogging with Social Awareness. It considers not only our daily photos and videos, but also the weather, the locations and time. When and how to open the e-records can be set by the senders' willing. Thus the receivers have a chance to feel the true space-time meaning of the e-records. More exactly, every e-record will be packaged in a capsule, which the senders are able to set with kinds of scenes as the activation conditions for recipients. With this, the recipients can experience and understand senders' happiness, beautiful moments and emotions at some certain moment.
Detecting traffic congestions using cell phone accelerometers BIBAFull-Text 107-110
  Mingqi Lv; Daqiang Zhang; Ling Chen; Gencai Chen
In this paper, we propose a system that detects traffic congestions by using cell phone accelerometers, which have many advantages (e.g. energy-efficient, unobtrusive, impervious to environmental noise, etc.). However, it is challenging to extract well-targeted and accurate features (e.g. speed) for detecting traffic congestions in a complex daily-living environment using a single cell phone accelerometer. The proposed system comprises a vehicular movement detection module, and a module for likelihood estimation of traffic congestions. Experimental results based on real datasets have demonstrated the effectiveness of the proposed system.
The myth of subtle notifications BIBAFull-Text 111-114
  Afra Mashhadi; Akhil Mathur; Fahim Kawsar
Push notifications keep user informed and engaged with the events around the mobile applications. However not all the notifications are of the same importance level to the user. We explore how mobile notifications are regarded as increasing number of applications are adopting notification services. We logged notification management traces from 10 individuals for 15 days to understand how they perceived mobile notifications and their importance, accompanying our results with semi-structured interviews.
A safety assessment system for sidewalks at night utilizing smartphones' light sensors BIBAFull-Text 115-118
  Yuki Matsuda; Ismail Arai
Along with the popularization of smartphones, which have various sensors such as accelerometers and GPS, location based services are also growing in popularity. Additionally, with the growth demand of in security awareness, pedestrian navigation systems are required to provide safety information. Thus, we propose and develop an illuminance inferring method utilizing smartphone's light sensors for assessing a safety level of sidewalks at night.
Towards automated thermal profiling of buildings at scale using unmanned aerial vehicles and 3D-reconstruction BIBAFull-Text 119-122
  Matthew Louis Mauriello; Jon E. Froehlich
With increases in energy demand and problems due to climate change, governments are increasingly focused on building efficiency retrofits and renovations. To help inform these improvements, energy audits are often performed with thermal cameras that can detect poor insulation and air leakage; however, the data collection process is labor intensive and does not offer a comprehensive view of the buildings. We introduce our vision for a new, more scalable approach: automated 3D thermal profiling of buildings using unmanned aerial vehicles (UAV) and 3D-reconstruction. To demonstrate feasibility, we used an unmodified Parrot AR.Drone 2.0 and a FLIR thermal camera to collect RGB and thermal images of a building and generate 3D reconstructions.
3D FDM-PAM: rapid and precise indoor 3D localization using acoustic signal for smartphone BIBAFull-Text 123-126
  Masanari Nakamura; Masanori Sugimoto; Takayuki Akiyama; Hiromichi Hashizume
In this paper, we present an indoor 3D positioning method for smartphones using acoustic signals. In our proposed 3D Frequency Division Multiplexing -- Phase Accordance Method (3D FDM -- PAM), four speakers simultaneously emit burst signals comprising two carrier waves at different frequencies to enable the rapid calculation of the position of the smartphone. Through experiments, we show that 3D FDM -- PAM can achieve a standard deviation of less than 2.8 cm at 7.8 measurements per second. The worst positioning error was 48.3 cm at the 95th percentile. We investigate the causes of error and discuss potential improvements to the localization performance.
Influencing driver behavior through future expressway traffic predictions BIBAFull-Text 127-130
  Naoto Nakazato; Takuji Narumi; Toshiki Takeuchi; Tomohiro Tanikawa; Kyohei Suwa; Michitaka Hirose
Unlike trains or buses, automobiles are essentially uncontrollable for road management companies. However, we can influence driver behavior to a certain degree by displaying appropriate traffic information. When taking a break at the rest area of an expressway, many drivers are unaware of the future traffic conditions along the highway toward their destination. We propose a method for changing the driver's departure time by predicting the future traffic conditions and informing the driver on how long the driver will expect to wait in a traffic jam based on the time at which the driver chooses to depart from the rest area. We created a prototype system for implementing the proposed method using the driver's smartphone and big data regarding the traffic conditions on an expressway in real-time. In this paper, we report the survey results of an elementary questionnaire regarding the proposed method.
Smartphone application launch with smarter scheduling BIBAFull-Text 131-134
  David T. Nguyen; Ge Peng; Daniel Graham; Gang Zhou
The time it takes to launch a smartphone application is unpredictable. In this paper, we explore how these unpredictable launch times are affected by constraints associated with reading (writing) from (to) flash storage. We conduct the first large-scale measurement study on the Android I/O delay using the data collected from our Android application running on 1480 devices within 188 days. Among others, we observe that reads experience up to 626% slowdown when blocked by concurrent writes. We use this obtained knowledge to design a pilot solution, wherein by prioritizing reads over writes we are able to reduce the launch delay by up to 37.8%.
Atmos: a hybrid crowdsourcing approach to weather estimation BIBAFull-Text 135-138
  Evangelos Niforatos; Pedro Campos; Athanasios Vourvopoulos; Andre Doria; Marc Langheinrich
Motivated by the novel paradigm of participatory sensing in collecting in situ automated data and human input we introduce the Atmos platform. Atmos leverages a crowd-sourcing network of mobile devices for the collection of in situ weather related sensory data, provided by available on-board sensors, along with human input, to generate highly localized information about current and future weather conditions. In this paper, we share our first insights of an 8-month long deployment of Atmos mobile app on Google Play that gathered data from a total of 9 countries across 3 continents. Furthermore, we describe the underlying system infrastructure and showcase how a hybrid people-centric and environment-centric approach to weather estimation could benefit forecasting. Finally, we present our preliminary results originating from questionnaires inquiring into how people perceive the weather, how they use technology to know about the weather and how it affects their habits.
Attelia: sensing user's attention status on smart phones BIBAFull-Text 139-142
  Tadashi Okoshi; Hideyuki Tokuda; Jin Nakazawa
In progressing ubiquitous computing where number of devices, applications and the web services are ever increasing, human user's attention is a new bottleneck in computing. This paper proposes Attelia, a novel middleware that senses user's attention status on user's smart phones in real-time, without any dedicated psycho-physiological sensors. To find better delivery timings of interruptive notifications from various applications and services to mobile users, Attelia detects breakpoint[16] of user's activity on the smart phones, with our novel "Application as a Sensor"(AsaS) approach and machine learning technique. Our initial evaluation of Attelia shows it can detect breakpoints of users with accuracy of 80-90%.
Implicit gaze based annotations to support second language learning BIBAFull-Text 143-146
  Ayano Okoso; Kai Kunze; Koichi Kise
This paper explores if implicit gaze based annotations can support reading comprehension tasks of second language learners. We show how to use eye tracking to add implicit annotations to the text the user reads and we start by annotating physical features (reading speed, re-reading, number of fixation areas) to documents using eye tracking.
   We show initial results of an ongoing experiment. So far, we recorded the eye gaze of 2 students for 2 documents. We gather initial feedback by presenting the annotated documents to two English teachers.
   Overall, we believe implicit annotations can be a useful feedback mechanism for second language learners.
Non-invasive rapid and efficient firmware update for wireless sensor networks BIBAFull-Text 147-150
  Hui Ung Park; Jongsoo Jeong; Pyeongsoo Mah
To maintain software of sensor nodes in wireless sensor networks efficiently, it is necessary to minimize the size of transferred data in firmware update. We propose a non-invasive rapid and efficient incremental firmware update algorithm called MoRE. In MoRE algorithm, the host transfers only delta, which is the information of different parts between old and new firmware image, to reduce the size of transferred data. The sensor node makes new binary image from its current image and the transferred messages. The MoRE shows comparable performance to previous works without invasive methods. Unlike the previous works, MoRE does not require extra memory for metadata in sensor nodes and does not need to use relocatable code.
Cricking: browsing physical space with smart glass BIBAFull-Text 151-154
  Zulqarnain Rashid; Enric Peig; Rafael Pous; Joan Melià-Seguí
We are so used to surfing the web, clicking on links and getting instant feedback, that we often wonder why we cannot do the same on physical surfaces. We have coined crick as a portmanteau term blending click and brick (and mortar) to describe the action of selecting a point on a physical surface and receiving digital information about its content. In this paper we are presenting a browsable physical space with clicking solution. Our target space is a shelf equipped with Radio Frequency Identification (RFID) containing changing number of DVDs and books. The mouse is replaced by a smartphone acting as a touch pad, the cursor is replaced by a controllable moving head beam light that projects a spot on the shelf and the information about the products near the cursor's position is then shown on a heads-up display (HUD) such as Google Glass. The items can be localized and visualized at HUD with an accuracy of 99%. The system is developed in context to independent living i.e. wheelchair users.
Mobile augmented reality for browsing physical spaces BIBAFull-Text 155-158
  Zulqarnain Rashid; Marc Morenza-Cinos; Rafael Pous; Joan Melià-Seguí
Browsing, a concept usually reserved for the on-line world, consists in a sequence of media consumptions and clicks: reading text, looking at images, watching videos, interlaced with clicks that take us from one content to another. A similar concept does not yet fully exist in the physical world. In this paper we present a system that uses Radio Frequency Identification (RFID) to obtain information about the objects on a shelf, and Augmented Reality (AR) to let users click on a live image of that shelf shown on a handheld device, accessing the information about the objects located in the vicinity of the clicked spot. A smart shelf with RFID has been set up to which a AR marker has been added to be able to map physical to screen coordinates. Testing and validation of system is done with different number of books at different locations on a shelf. The resulting experience is close to browsing a shelf, clicking on it and obtaining information about the objects it contains.
Evaluating the use of ambient and tangible interaction approaches for personal indoor climate preferences BIBAFull-Text 159-162
  Markus Rittenbruch; Jared Donovan; Yasu Santo
In this paper we describe the preliminary results of a field study which evaluated the use of MiniOrb, a system that employs ambient and tangible interaction mechanisms to allow inhabitants of office environments to report on subjectively perceived office comfort levels. The purpose of this study was to explore the role of ubiquitous computing in the individual control of indoor climate and specifically answer the question to what extent ambient and tangible interaction mechanisms are suited for the task of capturing individual comfort preferences in a non-obtrusive manner. We outline the preliminary results of an in-situ trial of the system.
Wearable sensors in ecological rehabilitation environments BIBAFull-Text 163-166
  Gina Sprint; Douglas Weeks; Vladimir Borisov; Diane Cook
Rehabilitation after injury or stroke is a long process towards regaining function, mobility, and independence. Changes exhibited in these areas tend to be subtle and highly dependent on the patient, their injury, and the intensity of rehabilitation efforts. To provide a fine-grained assessment of patient progress, we undertook a study to quantitatively capture movements during inpatient rehabilitation. We utilized wearable inertial sensors to collect data from participants receiving therapy services at an inpatient rehabilitation facility. Participant performance was recorded in an ecological environment on a sequence of ambulatory tasks. A custom software system was developed to process sensor signals and compute metrics describing ambulation. A comparison of metrics one week apart suggests quantifiable changes in movement.
Providing services on demand by user action modeling on smart phones BIBAFull-Text 167-170
  Kumar Vishal; Romil Bansal; Anoop M. Namboodiri; C. V. Jawahar
We propose a novel approach to schedule services like Wi-Fi and 3G on smartphones. Using Wi-Fi as an example, we show that intelligent scheduling based on a user's activity level leads to lower power consumption without adversely affecting the user experience. Data from various sensors is used to model and predict a user's activity, which is then used to schedule the wireless services.
The proxemic web: designing for proxemic interactions with responsive web design BIBAFull-Text 171-174
  Ryan Sukale; Stephen Voida; Olesia Koval
Responsive web design has become one of the guiding principles for delivering a consistent viewing experience for the same World Wide Web content across devices of different sizes. However, this principle covers only half of the spectrum of a viewing experience, since it does not factor in proxemic interactions between a user and a single device. In this research, we propose an approach for adapting the construct of responsive web design to account for proxemic interactions and provide an example implementation.
Contexto: lessons learned from mobile context inference BIBAFull-Text 175-178
  Moshe Unger; Lior Rokach; Ariel Bar; Ehud Gudes; Bracha Shapira
Context-aware computing aims at tailoring services to the user's circumstances and surroundings. Our study examines how data collected from mobile devices can be utilized to infer users' behavior and environment. We present the results and the lessons learned from a two-week user study of 40 students. The data collection was performed using Contexto, a framework for collecting data from a rich set of sensors installed on mobile devices, which was developed for this purpose. We studied various new and fine-grained user contexts which are relevant to students' daily activities, such as "in class and interested in the learned materials" and "on my way to campus". These contexts might later be utilized for various purposes such as recommending relevant items to the students' context. We compare various machine learning methods and report their effectiveness for the purposes of inferring the users' context from the collected data. In addition, we present our findings on how to evaluate context inference systems, on the importance of explicit and latent labeling for context inference and on the effect of new users on the results' accuracy.
My data store: toward user awareness and control on personal data BIBAFull-Text 179-182
  Michele Vescovi; Bruno Lepri; Christos Perentis; Corrado Moiso; Chiara Leonardi
The increasing adoption of smartphones and their capability of collecting personal and contextual information have generated a tremendous increment in the production of (personal) data. The availability of such a huge amount of data represents an invaluable opportunity for organizations and individuals to enable new application scenarios. However, it has also significantly increased the public concern on data privacy. In this paper, we present My Data Store, a tool enabling people to control and share their personal data. We tested My Data Store with 63 participants that used it in order to manage their own data collected from mobile phones and through experience sampling applications. Preliminary results show improvement over the users' awareness of their personal data and the perceived usefulness of the tool.
SPELL: affecting thermal comfort through perceptive techniques BIBAFull-Text 183-186
  Annamaria Andrea Vitali; Donatella Sciuto; Marco Spadafora; Margherita Pillan; Alessandro A. Nacci
Thermostats allow people to set the temperature they desire, even if personal thermal comfort perception is tied to a number of external stimuli [9]. Here we investigate dependability of people's thermal comfort, from the multi-sensory features of environment (light colors). We want to prototype a system that influences people's thermal comfort through other stimuli instead of temperature changing. The preliminary Spell research envisions a smart system for heating control that proactively compensates temperature variations using light color variations, accomplishing both the objectives: to satisfy user request for thermal comfort, while optimizing energy consumption. Two preliminary experiments were made: one demonstrates that people's perceived temperature is different from the actual temperature in a space; the second one shows how lights color affects the temperature perceived by people. As a result we derived preliminary guidelines for the prototyping the Spell system.
Yet another approach for food recognition: monitoring power leakage from microwave oven BIBAFull-Text 187-190
  Wei Wei; Yoshihiro Kawahara; Akihiro Nakamata; Tohru Asami
In this paper, we demonstrate a food recognition method by monitoring power leakage from a domestic microwave oven. Universal Software Radio Peripheral (USRP) is applied as a low-cost spectrum analyzer to measure the microwave oven leakage as received signal strength indication (RSSI). We aim to recognize 18 categories of food that are commonly cooked with a microwave oven. By analyzing 184 features designed after analyzing the features of measured RSSI, we attain an average recognition accuracy of 82.3% with various distances between the microwave oven and the USRP and different data downsampling frequencies for raw data processing.
Plex: finger-worn textile sensor for mobile interaction during activities BIBAFull-Text 191-194
  Sang Ho Yoon; Ke Huo; Karthik Ramani
We present Plex, a finger-worn textile sensor for eyes-free mobile interaction during daily activities. Although existing products like a data glove possess multiple sensing capabilities, they are not designed for environments where body and finger motion are dynamic. Usually an interaction with fingers couples bending and pressing. In Plex, we separate bending and pressing by placing each sensing element in discrete faces of a finger. Our proposed simple and low-cost fabrication process using conductive elastomers and threads transforms an elastic fabric into a finger-worn interaction tool. Plex preserves an inter-finger natural tactile feedback and proprioception. We also explore the interaction design and implement applications allowing users to interact with existing mobile and wearable devices using Plex.
Arfid: a reconfigurable fabric of input devices for the internet of things BIBAFull-Text 195-198
  James Youngquist; Joshua R. Smith; Aaron Parks; Benjamin Ransford
Low-cost, easily deployable, reconfigurable, movable input devices can enable adaptive workflows in commercial, industrial, and home environments. A key limitation of previous reconfigurable control systems is their high cost or maintenance burden (e.g., battery changes or wiring setup). Our poster presents Arfid, a "fabric" for reconfigurable input devices that connects low-cost, battery-free inputs to arbitrarily specified functions in their surroundings via a buildingwide network of RFID readers. Users can reassign controllers' functions using a simple web interface.
LifeDelivery: recruiting participants to deliver users' daily goods! BIBAFull-Text 199-202
  Weidan Zhao; Zhanwei Du; Yongjian Yang; Chijun Zhang; Wu Liao
Crowdsourcing has emerged in recent years as an online, distributed problem-solving and production model. Based on crowdsourcing, kinds of systems are developed to deliver people's packages through crowd. These systems are applied in large area and based on vehicle-mounted movement mode. In contrast to prior work, we focus on system used in little communities with walking-based movement mode, which is capable of delivering people's daily goods (such as thermos, fruit, assignment, etc.) in campus. Due to the different demands and behavior features of students in the prior system, many students give others help just to make friends but not for money. Based on this difference, we presented LifeDelivery, a crowdsourcing service able to use the Friends Mechanism, which will regard strangers who offer help as friends, and the Cloud Perception Technology which can process, classify and percept all the requirement orders, to recruit participants to deliver the daily goods for users. And this will bring great convenience to users and help students, make friends and share life.

Demos

Memo-it: don't write your diary, sense it BIBAFull-Text 203-206
  Karl Aberer; Michele Catasta; Georgios Christodoulou; Ivan Gavrilovic; Filip Hrisafov; Mathieu Monney; Abdessalam Ouaazki; Boris Perovic; Horia Radu; Jean-Eudes Ranvier; Matteo Vasirani; Zhixian Yan
The profusion of sensors embedded in modern mobile devices collect an increasing amount of information about the activities performed by a user. Leveraging the episodic memory model defined by neuroscientists, Memo-it exploits this information to create a multi-scale structured representation of the user's activities in a semi-automated fashion, while preserving the privacy of the user's data. In addition to building a digital diary of the user, the semantic approach taken by Memo-it is able to answer multi-dimensional queries, and to enable the inter-operability of memories between users.
A tangible approach to time management BIBAFull-Text 207-210
  Ryan Ahmed; Michael Frontz; Alex Chambers; Stephen Voida
Information work generally occurs within a multitasking environment with attention focused on the computer screen, constant task switching and frequent interruptions. In this environment, software-based task management techniques may blend in too much to be optimally effective. The Time Machine is proposed as a physical interface distinctly separated from the task environment with real-world manifestations of arbitrary concepts of tasks and time, while providing constant visibility of status through an ambient display for self-reflection. The Time Machine aims to promote distributed cognition and utilize the stage-based model of personal informatics and the Pomodoro technique toward productive and enjoyable task management.
Expression: a dyadic conversation aid using Google Glass for people with visual impairments BIBAFull-Text 211-214
  Asm Iftekhar Anam; Shahinur Alam; Mohammed Yeasin
Limited access to non-verbal cues hinders the dyadic conversation or social interaction of people who are blind or visually impaired. This paper presents Expression -- an integrated assistive solution using Google Glass. The key function of the system is to enable the user to perceive social signals during a natural face-to-face conversation. Empirical evaluation of the system is presented with qualitative (Likert score: 4.383/5) and quantitative results (overall F-measure of the nonverbal expression recognition: 0.768).
RFID-die: battery-free orientation sensing using an array of passive tilt switches BIBAFull-Text 215-218
  Lars Büthe; Gerhard Tröster; Michael Hardegger; Patrick Brülisauer
We here demonstrate the combination of tilt switches with RFID for building fully passive orientation-sensitive devices. We show the functionality of this approach with a simple die that can be read out with an NFC-enabled smartphone. As the proposed orientation system does not require battery powering, it is of interest to various wearable-computing and smart-home applications that benefit from long system runtime.
Squeeze the moment: denoting diary events by squeezing BIBAFull-Text 219-222
  Ming Ki Chong; Jon Whittle; Umar Rashid; Chee Siang Ang
In this demonstration, we showcase SqueezeDiary, a novel mobile diary application that uses squeeze gestures for denoting instances of events. SqueezeDiary consists of a mobile phone and a small squeeze sensor that communicate over a Bluetooth connection. To record an event instance, the user simply squeezes the sensor, and the phone records memory cues for review later. SqueezeDiary provides features for users to swiftly record instances as they continue to live through the experience, and only reflect on the instances during their downtime.
Hunting relics: a collaborative exergame on an interactive floor for children BIBAFull-Text 223-226
  Franceli L. Cibrian; Ana I. Martinez-Garcia; Monica Tentori
Exergames on interactive floors are appropriate to promote exercise and socialization in ludic environments. However, they lack of mechanisms to help children of early age to develop age-appropriate motor skills. In this paper, we present the design and development of an exergame to promote the collaborative exercising in young children (4-6 years old) using interactive floors. Also we take advantage of the socialization aspects catalyzed by interactive floors to promote collaboration among potential users. We close discussing design considerations, we argue an interactive floor exergame should incorporate to appropriately promote exercise and collaboration in young children.
Stereoscopic 3D mobile maps for indoor navigation in multi-level buildings BIBAFull-Text 227-230
  Ashley Colley; Jonna Häkkilä; Juho Rantakari
Autostereoscopic 3D (S3D) displays, enabling the perception of depth without requiring the viewer to wear special glasses, are now commercially available in a variety of sizes, from phones to large displays. In this paper, we present our research demonstrator where S3D display equipped mobile devices are used to provide a user interface (UI) for indoor navigation. The design approach suits especially for aiding navigation within multi-level buildings, such as shopping malls, airports and museums. Compared to the current 2D design approach of displaying building floor levels side-by-side, the use of stereoscopic 3D offers potential to improve understanding of the space, glanceability of map based UIs, and the ability to navigate between locations on different floor levels.
An immersive fire training system using Kinect BIBAFull-Text 231-234
  Qiuhai He; Guoying Zhao; Xiaopeng Hong; Xinyuan Huang
Lack of awareness of potential fire hazards is a leading factor of fire, especially when the child is alone. This paper presents a simulation training system to help children learn fire hazards knowledge and escape skills. The first part of this system is an application designed for theoretical study, which is featured by gesture interaction using Microsoft Kinect and large screen display environment. It includes three modules, namely animation, quizzes, and a 3D serious game. The second part is a simulated environment of fire escape route, which aims to test learning outcomes. Experimental results show the fire escape skills of 100 children are greatly improved.
The moment: a mobile tool for people with depression or bipolar disorder BIBAFull-Text 235-238
  Sky Tien-Yun Huang; Chloe Mun Yee Kwan; Akane Sano
The Moment is a mobile application for people with depression or bipolar disorder to monitor their emotional ups and downs, reveal their emotional patterns, and eventually find a peaceful way to live with their emotions, rather than fighting with them. The system consists of two main components: a smartphone application for the users to track their feelings and memories about events, and a sensor recording their physiological responses. The data will then be visualized in several ways and can be shared with trusted individuals or mental health professionals. The goal is to make the user more aware of her mood swings and the precursors to them; to reveal patterns of the swings; to provide a record for healthcare providers; to build a library of personalized interventions for future use; and to create an effective network of social supports.
Smarter eyewear: using commercial EOG glasses for activity recognition BIBAFull-Text 239-242
  Shoya Ishimaru; Yuji Uema; Kai Kunze; Koichi Kise; Katsuma Tanaka; Masahiko Inami
Smart eyewear computing is a relatively new subcategory in ubiquitous computing research, which has enormous potential. In this paper we present a first evaluation of soon commercially available Electrooculography (EOG) glasses (J!NS MEME) for the use in activity recognition. We discuss the potential of EOG glasses and other smart eye-wear. Afterwards, we show a first signal level assessment of MEME, and present a classification task using the glasses. We are able to distinguish of 4 activities for 2 users (typing, reading, eating and talking) using the sensor data (EOG and acceleration) from the glasses with an accuracy of 70% for 6 sec. windows and up to 100% for a 1 minute majority decision. The classification is done user-independent.
   The results encourage us to further explore the EOG glasses as platform for more complex, real-life activity recognition systems.
Drone, your brain, ring course: accept the challenge and prevail! BIBAFull-Text 243-246
  Nataliya Kosmyna; Franck Tarpin-Bernard; Bertrand Rivet
Brain Computer Interface systems (BCIs) rely on lengthy training phases that can last up to months due to the inherent variability in brainwave activity between users. We propose a BCI architecture based on the co-learning between the user and the system through different feedback strategies. Thus, we achieve an operational BCI within minutes. We apply our system to the piloting of an AR.Drone 2.0 quadricopter with a series of hoops delimiting an exciting circuit. We show that our architecture provides better task performance than traditional BCI paradigms within a shorter time frame. We further demonstrate the enthusiasm of users towards our BCI-based interaction modality and how they find it much more enjoyable than traditional interaction modalities.
SHE: smart home energy management system for appliance identification and personalized scheduling BIBAFull-Text 247-250
  Ting Liu; Siyun Chen; Yuqi Liu; Zhanbo Xu; Yulin Che; Yufei Duan
The home appliance scheduling is a promising energy saving technique that has significant commercial potential. In this demo, Smart Home Energy Management System (SHE) is developed on Android platform to schedule users' appliances. SHE monitors the power consumption to identify the operations of home appliances using a privacy preserving technique called Non-Intrusion Load Monitoring (NILM). The operations are integrated with dynamic electric price and environment data to mine users' personal demand and preference on appliance operation. Finally, SHE generates personalized scheduling strategies to meet the different users' demands at the minimal cost.
Collaborative geometry-aware augmented reality with depth sensors BIBAFull-Text 251-254
  Yuhao Ma; Kyle Boos; Joshua Ferguson; Donald Patterson; Kevin Jonaitis
Augmented reality (AR) has progressed to the point where geometry-aware real-time applications involving multiple users are now possible. We present an approach for a collaborative augmented reality environment using an RGB-D camera and KinectFusion, collecting visual and depth data from a static environment that is used as a fiducial for multiple users. This allows for collaborative augmented reality environments where digital data and real world objects can appear to interact. We anticipate that the combination of technologies that we used in our prototype will soon be available in mobile devices and will support our approach to collaborative augmented reality.
Networked on-line audio dilation BIBAFull-Text 255-258
  John S., III Novak; Jason Leigh; Aashish Tandon; Robert V. Kenyon
Audio Dilation is a technique that slows down the tempo of audio signals without changing the pitch or otherwise distorting the sounds. Networked On-line Audio Dilation is an Android application that allows users to dilate audio while engaged in a full-duplex networked conversation. The capability can potentially be used to improve comprehension for hearing or cognitively impaired individuals, or for non-native speakers of foreign languages.
MiniOrb: a sensor interaction platform for indoor climate preferences BIBAFull-Text 259-262
  Markus Rittenbruch; Jared Donovan; Yasu Santo
We introduce the MiniOrb platform, a combined sensor and interaction platform built to understand and encourage the gathering of data around personal indoor climate preferences in office environments. The platform consists of a sensor device, gathering localised environmental data and an attached tangible interaction and ambient display device. This device allows users to understand their local environment and record preferences with regards to their preferred level of office comfort. In addition to the tangible device we built a web-based mobile application that allowed users to record comfort preferences through a different interface. This paper describes the design goals and technical setup of the MiniOrb platform.
ColPhone: a smartphone is just a piece of the puzzle BIBAFull-Text 263-266
  Ahmed Salem; Tamer Nadeem
Multiple smartphone coexistence has been a fact of life. However, each smartphone is though of as a single unit. We believe that cooperation between coexisting smartphones can provide users with a cheap hardware upgrade (e.g processing). In addition to sharing of sensing information that can be collected by only one phone saving others energy of redundant tasks (e.g. GPS readings). In this work, we propose COLlaboration smartPHONE (colPhone) a framework that manages the collaboration between smartphones. ColPhone aims to achieve mutual benefit for collaborators by utilizing idle resources on smartphone in the proximity.
Memory specs: an annotation system on Google Glass using document image retrieval BIBAFull-Text 267-270
  Katsuma Tanaka; Motoi Iwata; Kai Kunze; Koichi Kise
We present a system working on a wearable computer that can annotate and retrieve annotations for signs, posters, public displays etc. The only limitation of the system: the annotated objects need to contain at least 3-5 lines of text with fixed layout. We evaluate our system in a poster session scenario with 5 use cases: retrieving annotations, adding notes, taking pictures and recording audio and attaching them to posters. As a ubiquitous note taking and annotation application, we believe the system can bridge online and offline discussions and give the user a way to reflect on seen information by providing them a web interface to all the annotations they took together with the source material (in our case poster and paper publications), helping to organize their thoughts and improving their recall.
HoppingDuster: self-adaptive cleaning robot based on aerial vehicle BIBAFull-Text 271-274
  Kenji Tei; Kazuya Aizawa; Shunichiro Suenaga; Ryuichi Takahashi; Shun Lee; Yoshiaki Fukazawa
Home cleaning robots have become popular. Most of the home cleaning robots are based on ground vehicles. While the cleaning robots based on ground vehicles can vacuum or wash floors robustly and efficiently, but they only clean on floors, not on stairs or furnitures. In this demo, we show a new concept of cleaning robot, called HoppingDuster. HoppingDuster is based on an aerial vehicle, which can y to stairs or furnitures to be cleaned, and hop or hover to wipe or blow down dust on them toward the floor so that the ground cleaning robot can vacuum the dust. HoppingDuster adapts its behavior to finish it cleaning within designated time and battery capacity.
A noise map of New York city BIBAFull-Text 275-278
  Yilun Wang; Yu Zheng; Tong Liu
This demonstration presents a noise map of New York City, based on four ubiquitous data sources: 311 complaint data, social media, road networks, and Point of Interests (POIs). The noise situation of any location in the city, consisting of a noise pollution indicator and a noise composition, is derived through a context-aware tensor decomposition approach we proposed in [5]. Our demo highlights two components: a) ranking locations based on inferred noise indicators in various settings, e.g., on weekdays (or weekends), at a time slot (or overall time), and in a noise category (or all categories); b) revealing the distribution of noises over different noise categories in a location.
Physics education with Google Glass gPhysics experiment app BIBAFull-Text 279-282
  Jens Weppner; Paul Lukowicz; Michael Hirth; Jochen Kuhn
We present a fully functional application prototype gPhysics App based on the Google Glass platform which is designed to perform an educational physical experiment in the area of acoustics. The initial applications aims towards students whose task is to find the relationship between the frequency of the sound generated by hitting a water glass and the amount of water.
Shiny: an activity logging platform for Google Glass BIBAFull-Text 283-286
  Shoya Ishimaru; Jens Weppner; Andreas Poxrucker; Kai Kunze; Paul Lukowicz; Koichi Kise
We describe an activity logging platform for Google Glass based on our previous work. We introduce new multi-modal methods for quick non-disturbing interactions for activity logging control and real time ground truth labeling, consisting of swipe gesture, head gesture and laser pointer tagging methods. The methods are evaluated in user studies towards estimating their effectiveness.
Bring your own device: ubiquitous approach to digital affinity diagram collaboration BIBAFull-Text 287-290
  William Widjaja; Masayuki Sawamura
The rise of ubiquitous computing has simplified our lives by providing relevant information and tools wherever we are. However, technologies that allow collaboration between different form-factor devices are rare. While ubiquitous devices might serve individuals well, they don't support high levels of collaboration. We propose a system where groups can participate in onsite brainstorming using various form-factor devices: tablet, laptop, or desktop for collaboration. We utilize socket server technology to achieve a high level of synchronization for all individual actions during brainstorming. High rates of synchronization for real time collaboration is the key for usability and adaptability. Our system uses a method called affinity diagramming in which users illustrate, group and link their ideas to create an easily understood structure. Using ubiquitous devices -- both mobile and stationary -- in brainstorming can help teams work together to share resources, exchange and organize ideas to build solutions that enhance our lives.
Supporting walking school buses BIBAFull-Text 291-294
  Christopher Winstanley; Nigel Davies; Mike Harding; Sarah Norgate
Walking School Buses (WSBs) are becoming an increasingly popular way of reducing school gate congestion. They typically feature a coordinator who is assigned to walk a designated route, calling at several pick-up points that parents can use to join their children to the "bus". However, parents often feel limited by the rigidity of the scheduled walking bus arrival and departure times making it difficult to coordinate the delivery of children onto the bus with conflicting morning activities. As a result, most parents choose instead to rely on car journeys to the school. In this work we demonstrate a mobile system that allows parents to visualise real-time predictions of walking bus arrival times and thus supports more flexible travel coordination behaviours, providing greater opportunities for parents to utilise walking bus services and reduce car usage.
When your sensor earns money: exchanging data for cash with Bitcoin BIBAFull-Text 295-298
  Dominic Wörner; Thomas von Bomhard
Bitcoin is an emerging technology which allows two entities to exchange value overt the Internet without trust. Embracing that those entities could well be machines we present a system that allows a sensor to offer its measurement data directly to a world-wide data market. Thus, we describe a prototypical implementation of the process of exchanging data for electronic cash between a sensor and a requester by leveraging the Bitcoin network and discuss its current limitations.
Multi-device activity logging BIBAFull-Text 299-302
  Mattia Zeni; Ilya Zaihrayeu; Fausto Giunchiglia
In this paper we are presenting i-Log, a system which is able to collect user's personal information, generate streams of data from smartphone's integrated sensors and attached wearable devices. We decided to focus our attention on these general purpose devices as we believe they can generate truthful readings because of their easy integration with our day-life activities, while invasive dedicated logging devices can alter our normal routines. The system consists of a Mobile Application that collects sensor data from the smartphone and from additional external wearable devices through a Bluetooth connection. We designed it to be user friendly, transparent, unobtrusive and able to provide smart sensing strategies in order to preserve battery life. Moreover, i-Log has a back-end server that accepts streams of data from the application and stores them into a persistent storage system that can be queried for further real time analysis.

Video presentations

Walkthrough research: methodological potentials for head-mounted cameras as reflexive tools in museum contexts BIBAFull-Text 303-306
  Jamie Allen; Chris Whitehead; Dionísio Soares Paiva; Jakob Bak; Catherine Descure
This study investigates the potential of head-mounted video cameras as a technique for understanding human experience in museums. Goals of the research are to avoid over-determination of experience, instead providing digital tools for reflection and understanding. The work uses a head-mounted video camera, an interview, and a set of simple image processing techniques to explore methods for understanding relationships between people, objects, and museum spaces.
Exploring interactive furniture with EmotoCouch BIBAFull-Text 307-310
  Sarah Mennicken; James Scott; A. J. Bernheim Brush; Asta Roseway
People respond emotionally to other people, animals, or even objects like furniture. While current furniture is static in appearance, embedded electronics can enable furniture to change its appearance. A couch could show excitement during a party or anger when a pet scratches it. But would emotional furniture delight or annoy people? To explore the potential for emotional furniture, we built EmotoCouch. Through colored light, visual patterns, and haptic feedback, EmotoCouch expresses six emotional states: Excited, Happy, Calm, Depressed/Sad, Afraid, and Angry. This video describes the construction of EmotoCouch, feedback gathered through surveys and user interviews, and shows example EmotoCouch usage situations.
SoberDiary: a phone-based support system for assisting recovery from alcohol dependence BIBAFull-Text 311-314
  Kuo-Cheng Wang; Ming-Chyi Huang; Yi-Hsuan Hsieh; Seng-Yong Lau; Chi-Hsien Yen; Hsin-Liu (Cindy) Kao; Chuang-Wen You; Hao-Hua Chu; Yen-Chang Chen
Alcohol dependence is a chronic disorder associated with severe harm in multiple areas, and relapsing is easy despite treatment. After alcohol-dependent patients complete alcohol withdrawal treatment and return to their regular lives, they face further challenges in order to maintain sobriety. This study proposes SoberDiary, a phone-based support system that enables alcohol-dependent patients to self-monitor and self-manage their own alcohol use behavior and remain sober in their daily lives. Results from a 4-week user study involving 11 clinical patients show that, using SoberDiary, patients can self-monitor and self-manage their alcohol use behavior, reducing their total alcohol consumption and the number of drinking or heavy drinking days that occur following intervention.
MagicWatch: interacting & segueing BIBAFull-Text 315-318
  Feng Yang; Shugang Wang; Shijian Li; Gang Pan; Runhe Huang
Seeking for more friendly, more efficient, and more effective human-computer interaction ways is an eternal hot topic. This video demonstrates a MagicWatch that can sense user's gestures, understand user's intensions, and achieve expected tasks with the underlying core techniques and the support of a back-end context aware smart system on a cloud platform. The MagicWatch can act as a pointer, a remote controller, and an information portal. Just using hand, you can point a building, a person, or a screen; you can control a device, for instance, changing TV channels, adjusting temperature, or switching slides; and you can get necessary information from the cloud. Moreover, this video highlights MagicWatch's seamless interactions with objects in its surrounding and easy segueing in cyber-physical spaces.

Doctoral school

Ambient assisted living: towards a model of technology adoption and use among elderly users BIBAFull-Text 319-324
  Christina Jaschinski
Ambient Assisted Living (AAL) technologies offer a promising perspective on autonomous aging in place. This is in the interest of the older adults themselves, overburdened caregivers and policy makers who try to control health care budgets in the face of the ever growing older population. However, these technologies are still in their infancy and little is known whether the older adults are ready to adopt and use them. So far, most research efforts are of exploratory nature. While they identify factors which are important for the adoption and use of AAL technologies, only a few attempt to test and quantify the underlying relations between these factors. Furthermore, many studies focus on a pre-adoption stage (a technology has not been used yet) and do not consider post-adoption (users have used and experienced a technology). This dissertation seeks to fill this gap by constructing a model which tests the underlying relations between the various influencing factors across both pre-adoption and post-adoption stages.
Automated mobile systems for multidimensional well-being sensing and feedback BIBAFull-Text 325-330
  Mashfiqui Rabbi
In recent years, we have seen a prolific rise of mobile and wearable sensing in healthcare and fitness. Although the data generated is incredibly useful, state-of-the-art feedback technologies are often limited to either providing an overall status or serving large volume of multi-dimensional sensor data with little processing. My research falls into filling this gap. I work on developing systems that use sensors to understand different dimensions of well being, and subsequently devise interventions through personalized and actionable suggestions. Using simple machine learning techniques, my systems automatically mine user behaviors that influence specific well-being dimensions. Then utilizing decision theory and behavioral psychology theory, my systems create personalized actionable suggestions that are related to existing user's behaviors. In this proposal, I describe how I realize such automated systems for sensing and providing feedback.
Smart garments: an on-body interface for sensory augmentation and substitution BIBAFull-Text 331-336
  Halley P. Profita
The human sensory network provides an immediate interface by which to gauge ambient properties of the environment, registering pressure, sound, odor, etc. However, sensory loss can drastically diminish one's ability to process such ambient information, exposing an individual to potentially harmful situations. Smart Garments, capable of computation, communication, sensing, and actuation, have the ability to offset potentially hazardous circumstances associated with sensory loss by augmenting the human sensory capabilities. This research explores how Smart Garments can support those with a hearing impairment by leveraging the proximity and surface area of the human skin to provide contextual information (vibrotactile cues approximating the direction of critical environmental sounds) to a user.
Improving smartphone responsiveness through I/O optimizations BIBAFull-Text 337-342
  David T. Nguyen
Smartphones suffer various unpredictable delays, e.g., when launching an application. In this work, we investigate the behavior of reads and writes in smartphones. We conduct the first large-scale measurement study on the Android I/O delay using the data collected from our Android application running on 1480 devices within 188 days. Among others, we observe that reads experience up to 626% slowdown when blocked by concurrent writes. We use this obtained knowledge to design a pilot solution that reduces application delays by prioritizing reads over writes. The evaluation shows that our system reduces launch delays by up to 37.8%.
Designing specialized technology to aid assistance dogs BIBAFull-Text 343-348
  Charlotte Robinson
Interest is growing in studying canine and human relationships, especially working canines and their role in society. Interest is also growing in designing informed, user centered interactive technologies for animals. Combining these two themes, my doctoral research looks at creating user-centered, ethnographically informed designs for working animals (working dogs). The work examines existing design methodologies and posits new ones to contribute to a wider Animal-Computer Interaction (ACI) framework to design for and with animal users. Here I review the initial findings of the on-going work to develop an emergency alert alarm for assistance dog use.
Adaptive sensor cooperation for predicting human mobility BIBAFull-Text 349-354
  Paul Baumann
My thesis focuses on the prediction of human mobility. I am interested in gaining a deeper understanding of the factors that influence the performance of human mobility prediction algorithms. The main contributions of my work are: the analyses of different factors that influence the performance of mobility predictors, the design and development of a self-adaptive approach for detecting and recognizing users' relevant places, and estimating users' momentary predictability. The latter contribution aims to enable the possibility for the application scenarios to decide how much to trust the provided predictions and mobility data.
Bridging the gap between law & HCI: designing effective regulation of human autonomy in everyday ubicomp systems BIBAFull-Text 355-360
  Lachlan Urquhart
Ubicomp technologies pose challenges to human agency, and legal rights reliant on individual autonomy, for example informed consent to data processing. Existing regulatory measures designed to address these issues are working less adequately, and increased dialogue between design and law communities is necessary to decide how best to ensure effective regulation of human autonomy. This thesis seeks to understand the various regulatory issues posed by ubicomp technologies, through specific case studies, with the overall aim of creating legal and technological solutions that work in practice.

Programming competition

Connect the dots by understanding user status and transitions BIBAFull-Text 361-366
  Xuan Bao; Yilin Shen; Neil Zhenqiang Gong; Hongxia Jin; Bing Hu
Human lives are composed by series of events and activities. Considerable research effort has been made to probe, sense, and understand them. In our research, we are interested in exploring the intrinsic string that connects all these events together, that is, user status and transitions. Such transitions can be reflected from multiple activity dimensions, ranging from our daily mobility trajectories, app usage sequences, to communication patterns and motion state switches. In this paper, we aim to identify whether a personalized model can be learned to capture various user states from different sensing dimensions and whether a unified view can be established to explain the state transitions that drive the changes in user context during day-to-day routines.
   To this end, we have explored two types of traces -- connected wifi sequences and cell location trajectories. We first model the states among these two individual dimensions. In the end, the identified states from both dimensions are linked together to recognize the spatial-temporal relationship between them. As we evaluate with the DeviceAnalyzer dataset, our method is able to recognize a range of states such as "at home", "working", "commute" and the transitions between them, all in an unsupervised manner.
How the availability of Wi-Fi connections influences the use of mobile devices BIBAFull-Text 367-372
  Paul Baumann; Silvia Santini
Several aspects might influence the way users operate their mobile devices in a mobile context. In this work, we show how the presence or absence of a Wi-Fi connection influences the amount of data traffic generated by mobile devices. Our results show that the probability of users to generate data traffic while connected to Wi-Fi is twice as high as when a cellular connection only is available. Furthermore, we observe that an almost constant amount of data traffic is generated over a day, although it slightly increases in the late afternoon. Last but not least, we observe that fair-use policies do not seem to influence the behavior of mobile users with respect to the amount of traffic they generate over different weeks of a month. We ground our analysis on the Device Analyzers data set, which contains detailed records of mobile phone usage of more than 17,000 users from all over the world. Building upon these preliminary quantitative results, we outline how the availability of data for mobile users can be improved by combining mobility and phone usage prediction with knowledge about the temporal and spatial availability of Wi-Fi connections.
An analysis of the transitions between mobile application usages based on Markov chains BIBAFull-Text 373-378
  Charles Gouin-Vallerand; Neila Mezghani
By knowing more the usage of mobile application on smart phone, it is possible to predict which applications will be used next. This kind of information is particularly interesting from a recommendation system point of view. In this paper, we present an analysis of the transitions between application usages on the data collected by the University of Cambridge's Device Analyzer project. Among other results, we conclude that the transition probabilities between application usages are distinct information from the probabilities of usage based on periods of time, such as application launches in a same hour and in a same day.
Diversity in locked and unlocked mobile device usage BIBAFull-Text 379-384
  Daniel Hintze; Sebastian Scholz; Rainhard D. Findling; René Mayrhofer; Muhammad Muaaz
We analyze locked and unlocked mobile device usage of 1,960 Android smartphones. Based on approximately 10TB of mobile device data logs collected by the Device Analyzer project, we derive 6.9 million usage sessions using a screen power state machine based approach. From these session we examine the number of interactions per day, the average interaction duration as well as the total daily device usage time. Findings indicate that on average users interact with their devices 117 minutes a day, separated over 57 interactions -- while unlocking their device only 43% of the time (e. g. to check for notifications).
Exploring variety seeking behavior in mobile users BIBAFull-Text 385-390
  Kasthuri Jayarajah; Robert Kauffman; Archan Misra
Understanding the personality traits and current attitudes of individual consumers is crucial for retailers and mobile advertisers. In this paper, we investigate the phenomenon of "variety seeking tendencies" in mobile users in their (1) online (represented by their App usage behavior), and (2) physical (represented by their location visits) worlds. We show that different categories of users exhibit different levels of variety. Further, by analyzing at various time scales, we show that there exists correlation between when a person is likely to visit new places in the real world and when he/she is likely to explore new Apps in the online world.
Quality matters: usage-based app popularity prediction BIBAFull-Text 391-396
  Eric Malmi
In recent years, mobile application (app) economy has grown to a huge market but it is only the top apps that are able to turn this boom into significant revenues. In this paper, we study how the quality of an app, as reflected in how people start to use it, is linked to the popularity of the app. We show that features extracted from the Device Analyzer dataset, describing the aggregate usage of the app, can be used to predict its popularity. We also look at the connection between app popularity and the past popularity of other apps from the same publisher and find a surprisingly small correlation between the two.
Social context discovery from temporal app use patterns BIBAFull-Text 397-402
  Panagiotis Papapetrou; George Roussos
A key ingredient of mobile computing is automated adaptation of system behaviour to match user context. In this paper we investigate how temporal patterns of app use can reveal the social context of the user, in the sense of their specific social role during a period of interaction. Individual users typically have multiple distinct identities associated with different social roles such as professional and family members. We are specifically interested in exploring whether we can employ Device Analyzer data to construct distinct profiles for each of these roles. We introduce a temporal sequence clustering technique that successfully identifies periods associated with such distinct social contexts.
The device analyzer competition BIBAFull-Text 403-407
  Andrew Rice; Alastair R. Beresford
Device Analyzer is an Android app designed to collect user interaction data from smartphones. Over 18,000 study participants from around the world have run the app and provided us with usage statistics. Many study participants have allowed us to share their data with other researchers. This allows our community to research hypotheses or validate findings from other studies. We ran the 2014 Ubicomp Programming Competition to encourage the use of Device Analyzer data, and over 170 researchers around the world entered. The following papers were selected to be presented at the competition workshop. In this paper we provide background information for readers of these papers and share our experiences with others who might be considering sharing research datasets with the community. We describe how we ran the contest, provide a general overview of the responses and discuss the challenges that we encountered.
When did your smartphone bother you last? BIBAFull-Text 409-414
  Jeremiah Smith; Anna Lavygina; Alessandra Russo; Naranker Dulay
This paper is prompted by the overall question 'what is the most effective way to recognise disruptive smartphone interruptions?'. We design our experiments to answer 3 questions: 'Do users revise what they perceive as disruptive incoming calls as time goes by?', 'How do different types of machine-learners (lazy, eager, evolutionary, ensemble) perform on this task?' and 'Can we restrict the initial amount of data and/or the number of features we need to make predictions without degrading performance?'. We consider these questions using Cambridge University's Device Analyzer dataset.

AwareCast 2014: Third Workshop on Recent Advances in Behavior Prediction and Pro-Active Pervasive Computing

3rd workshop on recent advances in behavior prediction and pro-active pervasive computing BIBAFull-Text 415-420
  Klaus David; Stephan Sigg; Rico Kusber; Brian Ziebart; Sian Lun Lau
The 3rd Workshop on Recent Advances in Behavior Prediction and Pro-active Pervasive Computing (AwareCast 2014) focuses on scientific contributions concerning context prediction and its applications. Scientific advances concerning, e.g. activity detection in smart homes, and time synchronization for sensing context data are addressed. In particular, this year, the focus of the workshop is on the currently most pressing issues of prediction of contexts other than location, benchmarks and common data sets as well as common development frameworks.
A survey of proactive pervasive computing BIBAFull-Text 421-430
  Sebastian VanSyckel; Christian Becker
Pervasive computing applications are context-aware and adapt in order to cope with changes in their environment. In this, they should be as unobtrusive as possible. Proactive computing aims at acting on behalf of the user. Proactive adaptation allows to change the application and/or the context based on prediction. In this paper, we discuss and classify proactive pervasive computing research, as well as give an outlook on the field.
Multi-sensor physical activity recognition in free-living BIBAFull-Text 431-440
  Katherine Ellis; Suneeta Godbole; Jacqueline Kerr; Gert Lanckriet
Physical activity monitoring in free-living populations has many applications for public health research, weight-loss interventions, context-aware recommendation systems and assistive technologies. We present a system for physical activity recognition that is learned from a free-living dataset of 40 women who wore multiple sensors for seven days. The multi-level classification system first learns low-level codebook representations for each sensor and uses a random forest classifier to produce minute-level probabilities for each activity class. Then a higher-level HMM layer learns patterns of transitions and durations of activities over time to smooth the minute-level predictions.
Regression tree classification for activity prediction in smart homes BIBAFull-Text 441-450
  Bryan Minor; Diane J. Cook
The growing number of older adults in the population has created an increasing need for health-assistive systems, including prompting interventions to provide activity reminders. In this paper, we present a new regression-tree-based activity forecasting algorithm to predict the occurrence of future activities for prompting initiation of such activities. This automated algorithm extracts high-level features from sensor events and inputs these features to a machine learning algorithm which forecasts when a target activity will next occur. We compare this system to a standard linear regression classification using real data from smart homes. The forecasting algorithm is shown to provide lower error rates over the linear regression model.
Event driven time synchronization of mobile devices BIBAFull-Text 451-457
  Dennis Kroll; Rico Kusber; Klaus David
Mobile devices are increasingly used for context recognition. Recognition accuracies partly depend on the time synchronicity between the mobile devices used for data recording and labeling. Mobile device synchronization can be done via the Internet or GPS, but both are not available in all areas. This paper presents our novel approach "Event Driven Time Synchronization of Mobile Devices" that works anytime, anywhere. The idea is to trigger sensor events on each device as much as possible at the same time. The time difference of the sensor event occurrences is interpreted as the time difference between the devices, called time offset between the devices. Our prototype utilizes proximity events to enable this. Our evaluation shows that 99% of the time offsets vary not more than 60 ms. Compared to this, only 17% are within this variance when using Network Time Protocol via a mobile High Speed Downlink Packet Access Internet connection.
Beyond horizontal location context: measuring elevation using smartphone's barometer BIBAFull-Text 459-468
  Guangwen Liu; Khan Muhammad Asif Hossain; Masayuki Iwai; Masaki Ito; Yoshito Tobe; Kaoru Sezaki; Dunstan Matekenya
Accurate estimation of elevation is important for many location based services. Although, it is possible to obtain altitude from GPS, its accuracy is unreliable and applicable in outdoors only. It is possible to use barometers on smartphones to estimate elevation in both indoor and outdoor scenarios. To this end, we proposed an integrated framework to provide ubiquitous and accurate elevation measurement using smartphones. Experiments conducted in both indoor and outdoor with different geographical characteristics reveal that our system can provide elevation with an error less than 5 meters in 90% of the cases and less than 3 meters in 75% of the cases, which is sufficient for most practical applications.
Designing and evaluating active learning methods for activity recognition BIBAFull-Text 469-478
  Salikh Bagaveyev; Diane J. Cook
Activity recognition in smart home environments is a crucial step towards fully autonomous assistance and health monitoring. Due to the high variance in house configurations and sensor placements, it is important to collect and label sample sensor data that will be used to train a learning algorithm. Ground-truth activity labels must therefore be provided in some manner for this sample data. The abundance of sensor data makes it infeasible to label all of the data, and active learning can be used to intelligently pick the most informative data to be labeled. In this paper, we describe several active learning methods that we designed and implemented for their applicability to the activity recognition task. We evaluate the methods using the CASAS smart home sensor data and present a crowd-sourcing application for annotation.

CEA 2014 -- Smart Technology for Cooking and Eating Activities

Summary for the workshop on smart technology for cooking and eating activities (CEA'14) BIBAFull-Text 479-485
  Kiyoharu Aizawa; Takuya Funatomi; Yoko Yamakata
This paper summarizes the Workshop on Smart Technology for Cooking and Eating Activities (CEA'14) that was held in Seattle, Washington, U.S.A on 14th July 2014. Six full papers which were presented in the oral session are introduced in this paper. Besides full papers, short and poster papers have been accepted at the workshop. They are listed in this paper. We hope you will enjoy this workshop and related discussions about the potential of computer technologies for supporting human cooking and eating activities.
Discriminating practical recipes based on content characteristics in popular social recipes BIBAFull-Text 487-496
  Yohei Seki; Kouta Ono
Recipe websites sometimes contain vast collections of recipes, making it time-consuming for users to identify recipes that might suit them. In this study, we aim to support users in their recipe selection by discriminating "practical recipes" that are easy to understand, written concisely with sufficient description, and offer detailed tips and pointers. We performed a content analysis of popular recipes found on Cookpad, focusing on ten types of dishes, and decided to use seven content characteristics, such as "description of the heat level" and "description of the cooking time," as features to discriminate practical recipes. We have implemented a discriminator based on an SVM classifier that uses these features. The results of a discrimination experiment show that the mean value of the accuracy of the ten types of dishes is 0.813. This represents a significant difference from a baseline discriminator.
Recipe search for blog-type recipe articles based on a user's situation BIBAFull-Text 497-506
  Takuya Kadowaki; Shinsuke Mori; Yoko Yamakata; Katsumi Tanaka
Many homemakers feel stressed when deciding on the menu of the day [?]. Even though they have a vague idea of some dishes, it is not easy for them to make the idea clear. Therefore, this research proposes a system that finds recipes corresponding to the user's vague requirements. On the Web, many blog-type recipes describe not only a recipe itself, but also the reasons why a given recipe were created or selected by the page authors. Firstly, the system extracts the author's reasons for the creation or selection of a recipe from the blog-type recipes. Secondly, the system lets the user input his/her present situation or feelings which must include his/her vague requirement and mine his/her reasons for recipe selection from the input. Finally, the system outputs recipes that meet the user's vague requirements by associating the reasons for recipe selection from the user's input text with the reasons accompanying the blog-type recipes.
Construction of a cooking ontology from cooking recipes and patents BIBAFull-Text 507-516
  Hidetsugu Nanba; Toshiyuki Takezawa; Yoko Doi; Kazutoshi Sumiya; Miho Tsujita
A cooking ontology is an indispensable language resource for the language processing of cooking recipes. We have constructed a cooking ontology by means of pattern matching, statistical natural language processing techniques, and manual steps to identify hyponymy, synonymy, attributes, and meronymy.
Design and assessment of enabling environments for cooking activities BIBAFull-Text 517-526
  Farah Arab; Anaïs Giroux; Jérémy Bauchet; Sylvain Giroux; Hélène Pigot
Assistive technologies can help cognitively impaired people in planning and memory tasks [1]. To provide efficient assistance, pervasive environments should be able to adapt assistance to the user's capacities, the activity to perform and the context. This paper presents an analysis of a cooking activity performed by a user with intellectual disability in a pervasive environment, named Archipel. The objective is to assess the impact of this environment on the activity processing. The activity analysis is based on ergonomic and neuropsychological methods. The results show that Archipel has a positive impact on the user's self-determination and independence. Further improvements should take into account the cognitive deficits presented by the people and ergonomic principles to provide more appropriate assistance.
Using social media to change eating habits without conscious effort BIBAFull-Text 527-535
  Toshiki Takeuchi; Takuji Narumi; Tatsuya Fujii; Tomohiro Tanikawa; Kyohei Ogawa; Michitaka Hirose
Healthy eating habits are important for modern people; however, sustaining these habits is often difficult because it requires a strong will. In this paper, we propose a social media system, Yumlog, that enables people to begin eating meals that are more healthful naturally and without conscious effort. Using the proposed system, users share information on their meals and evaluate the yumminess and healthfulness of each other's meals. The satisfaction of a user with a meal increases with others' positive evaluations. In behavioral science, this effect is called expectation assimilation. In addition, Yumlog modifies others' evaluations, displaying evaluations of healthfulness as those of yumminess to the user consuming the meal. Thus, users tend to eat more foods that are evaluated as healthful foods and thereby, improve their eating habits without noticing it. We demonstrate the potential of the proposed system through user studies.
Feature optimization for recognizing food using power leakage from microwave oven BIBAFull-Text 537-546
  Akihiro Nakamata; Tohru Asami; Wei Wei; Yoshihiro Kawahara
This paper describes a feature optimization for a novel food recognition system based on the analysis of the power leakage from a microwave oven. Some microwave energy leak from the microwave oven and the leakage pattern changes according to the contents of the microwave oven and also the condition of these meals. Therefore, we collected the received signal strength indicator (RSSI) values during the heating process and analyzed these data by using machine learning method. We also evaluated the importance of each features to clarify which features are useful for food recognition or not. In the results, our study has successfully demonstrated that we can recognize what food is cooked in the microwave oven by monitoring the leakage.
Frequency statistics of words used in Japanese food records of FoodLog BIBAFull-Text 547-552
  Sosuke Amano; Makoto Ogawa; Kiyoharu Aizawa
Recording foods enable us to improve our dietary habits. In food records, there are a variety of descriptions of meals because there is no standard way to express meal names. In this study, we analyze Japanese food records from the view of word frequency. We show very small numbers of words are satisfactory to describe the majority of the record.
A framework for recipe text interpretation BIBAFull-Text 553-558
  Hirokuni Maeta; Shinsuke Mori; Tetsuro Sasada
In this paper we describe a method for converting a recipe text into a meaning representation. The meaning representation is a flow graph, whose vertices are important word sequences in cooking (recipe named entity; NE) and edges denote relationships among them.
   Our methods consists of three parts: word segmentation (WS), recipe NE recognition (NER), and flow graph construction. The first two processes are based on machine learning and are adapted to recipe texts. The last process is based on heuristic rules.
   As an evaluation we tested three processes on an annotated corpus. The results showed that WS and recipe NER achieved high accuracies and that flow graph construction is relatively difficult having a large room for improvement.
Automatic extraction of ingredient's substitutes BIBAFull-Text 559-564
  Corrado Boscarino; Nicole J. J. P. Koenderink; Vladimir Nedovic; Jan L. Top
Expert advice on how ingredients can be replaced in recipes is widely available on-line. However, these are general substitution rules, which do not take into account contextual factors such as culture, sensory perception, season, etc. We aim at tuning general rules to particular recipes. From an on-line food encyclopedia we extract explicit substitution rules. We also consider implicit substitution rules, derived by the categorisations in the same source. By applying Latent Dirichlet Allocation (LDA) onto a crawled dataset, we rank ingredients based on their likelihood of being interchangeable, given a recipe. The results show that our statistical approach can approximate manual judgments.
Automatic recipe cuisine classification by ingredients BIBAFull-Text 565-570
  Han Su; Man-Kwan Shan; Ting-Wei Lin; Janet Chang; Cheng-Te Li
With the growth of recipe sharing services, online cooking recipes associated with ingredients and cooking procedures are available. Many recipe sharing sites have devoted to the development of recipe recommendation mechanism. While most food related research has been on recipe recommendation, little effort has been done on analyzing the correlation between recipe cuisines and ingredients. In this paper, we aim to investigate the underlying cuisine-ingredient connections by exploiting the classification techniques, including associative classification and support vector machine. Our study conducted on food.com data provides insights about which cuisines are the most similar and what are the essential ingredients for a cuisine, with an application to automatic cuisine labeling for recipes.
Estimating nutritional value from food images based on semantic segmentation BIBAFull-Text 571-576
  Kyoko Sudo; Jun Shimamura; Kazuhiko Murasaki; Yukinobu Taniguchi
Estimating the nutritional value of food based on image recognition is important to health support services employing mobile devices. The estimation accuracy can be improved by recognizing regions of food objects and ingredients contained in those regions. In this paper, we propose a method that estimates nutritional information based on segmentation and labeling of food regions of an image by adopting a semantic segmentation method, in which we consider recipes as corresponding sets of food images and ingredient labels. Any food object or ingredient in a test food image can be annotated as long as the ingredient is contained in a training food image, even if the menu containing the food image appears for the first time. Experimental results show that better estimation is achieved through regression analysis using ingredient labels associated with the segmented regions than when using the local feature of pixels as the predictor variable.
A method for detecting gaze-required action while cooking for assisting video communication BIBAFull-Text 577-582
  Yoko Yamakata; Takuya Funatomi; Asuka Miyazawa; Michihiko Minoh; Atsushi Hashimoto
In this paper, under the situation that a teacher teaches a student how to cook via bi-directional video communication system, we propose a method to detect whether the student can watch the display and listen to the teacher's instruction without interrupting his/her cooking. Firstly, we investigates the properties of taking the gaze on/off during cooking action, and secondly we proposed methods to automatically detect gaze-required cooking actions on the captured cooking video.
KUSK dataset: toward a direct understanding of recipe text and human cooking activity BIBAFull-Text 583-588
  Atsushi Hashimoto; Shinsuke Mori; Tetsuro Sasada; Michihiko Minoh; Yoko Yamakata
In this paper, we provide a multimodal dataset for understanding cooking activities. To build the dataset, we instructed the subjects to perform cooking according to instructional texts shown on a display one by one. The instructional texts were generated from flow graphs, which were automatically extracted from recipes sampled from a Web site. The main identity of this dataset is the correspondence between the steps automatically extracted from recipes, and real human activities. Typical uses of our dataset are to construct classifiers for understanding human activities in the kitchen, text generation through observing the activities, and so on.
Food image recognition with deep convolutional features BIBAFull-Text 589-593
  Yoshiyuki Kawano; Keiji Yanai
In this paper, we report the feature obtained from the Deep Convolutional Neural Network boosts food recognition accuracy greatly by integrating it with conventional hand-crafted image features, Fisher Vectors with HoG and Color patches. In the experiments, we have achieved 72.26% as the top-1 accuracy and 92.00% as the top-5 accuracy for the 100-class food dataset, UEC-FOOD100, which outperforms the best classification accuracy of this dataset reported so far, 59.6%, greatly.
Unravelling the language of eating BIBAFull-Text 595-600
  Nicole J. J. P. Koenderink; Andrea van Doorn; Jan L. Top
Understanding eating behaviour requires observations of how consumers choose what to eat and of what they actually eat. Recognizing eating gestures is difficult and labour intensive. We propose an ontology of elementary eating gestures to make visual observations of eating behaviour objective and quantifiable. Moreover, this ontology facilitates automating this task. The eating gesture vocabulary is published as an ontology and is available for use.
Naturalistic control of conversation by meal: induction of attentive listening attitude through uneven meal distribution in co-dining BIBAFull-Text 601-606
  Tomoo Inoue
Having a meal with conversation is regarded to have good effects. However, all the existing research assumed that all the participants have meals, whereas this assumption is not always true in reality. Conversation often takes place where a part of the participants have meals. To better understand co-dining conversation, we should also pay attention to this uneven meal distribution setting. Thus this research investigated face-to-face dyadic conversation on uneven meal distribution setting, focused on the difference between the participant with meal and the one without meal in particular. Conversation scenes that one participant has a meal were videotaped, and questionnaires were asked to fill out. From the analysis, it was found that attentive listening was often likely to emerge in uneven meal distribution setting.
Application of an anthropomorphic dining agent to idea generation BIBAFull-Text 607-612
  Rui Liu; Tomoo Inoue
When we generate new ideas or think over existing ideas, talking to another person is often helpful. This is not really has to be a discussion. Rather, the person needs someone to talk to for reflecting himself/herself with the ideas. The other person is not necessarily be talkative, and may desirable to be attentive. In interpersonal communication over a meal, a person who does not have a meal is more likely to become a speaker than the other. The other person who has a meal is more likely to become an attentive listener. Thus in this paper, we developed an anthropomorphic agent that would automatically have dining behavior, and conducted an experiment to study its influence on the idea generations support. As a result, some interesting actions were observed, though effects on the idea generation was not significant.

How do you solve a problem like consent? Workshop addressing the challenge of user consent

How do you solve a problem like consent?: the workshop BIBAFull-Text 613-619
  Ewa Luger; Marina Jirotka; Tom Rodden; Lilian Edwards
Ubiquitous computing systems raise unprecedented challenges to how we currently elicit, secure and sustain user consent. Consent is the interactional process by which a user agrees to the terms of engagement with a system, and it represents the principle mechanism by which we protect our privacy online. However, whereas traditional online interactions are explicit, offering a series of moments at which one might inform and engage the user, the growing 'era of ubiquity' has decoupled users from devices, presenting no clear moment for consent to occur. Whilst there have been efforts to raise issues of consent within HCI and cognate disciplines, these remain disparate. The aim of this workshop is to bring together a solution-oriented community with a specific focus on consent issues within interactive environments. It will create a transnational, multidisciplinary platform for discussion and offer opportunities for collaboration, support and the development of a new research agenda.
Revisiting signals and noise for ethical and legal research using online data BIBAFull-Text 621-622
  Erin Kenneally
The stability of trust on the Internet has implications for political diplomacy, innovation, economic stability, social and civil relations, and individual self-determinism. The degree of online trust is a reflection of the gap between individual and collective Netizens' expectations formed by laws and ethics, and their capabilities enabled by technology. Law and ethics, just as with familiar offline society, act as ordering forces that inform the acceptability of our behaviors and relationships with other person and organizations. The migration of these analog activities online has exposed a rather sweeping gap between expectations and capabilities, where legal and ethical ordering forces are challenged to re-examine, -interpret, and --apply the tenets and principles upon which they moor. As this gap widens, so too does ambiguity between asserted rights, interests, and threats to same.
   This gap is manifest most prominently in the current industrial and geo-political struggle to define rules of engagement for cyber conflict and national security, as well as with online advertising and data brokering. A related context where ordering forces are challenged, lower on the public notoriety index but no less considerable, is information and communication technology (ICT) research. The controversy over the collection, use and disclosure of online data for research exposes gaps and deficiencies in the legal and ethical structures that directly and indirectly inform and reflect our expectations.
   Notably, "consent" has been a fundamental mechanism for protecting rights and interests in both law and ethics. As such, it serves as an institutionalized signal for persons' reasonable expectations. Yet, the ability to easily collect and combine massive amounts of existing, "publicly-available" information of a sensitive nature (personal or confidential) online exposes deficiencies in consent as an effective signal for expectations.
   More specifically, researchers increasingly encounter data online such as personal health, financial or behavioral records; usernames and passwords lists; corporate manuals and technical documents; email and voice communications databases; and, device vulnerabilities and machine-to-machine communications. It is located in various online locations ranging from normal websites and social networks to underground criminal forums, Internet relay chat rooms, and publicly-obscured/hidden sites. And, its availability is often a product of malicious, negligent, or ignorant collection or disclosure by a third party.
   In this context, consent as an expectation signal is strained along substantive and procedural dimensions. For example, some argue that the existence of other signals (i.e., the data was public and/or non-identifiable, the purpose of the research is to study a system or threat and not individual persons) pre-empts the need for consent. In addition, obtaining consent for what amounts to secondary use of online data may be impracticable in light of the distance between researchers and data subjects, or outweighed by countervailing intended benefits or academic freedom interests.
   With research using data available online, researcher conduct is not fully prescribed or proscribed by formal ethical codes of conduct or law because current expectations signals are ill-fitting. This presentation is intended to advance the collective dialogue toward a path that revisits and harmonizes ethical and legal signals for research using online data among researchers, oversight entities, policymakers and society. It does not dictate answers but aims to point out where current ordering forces breakdown in the context of online research and to suggest how to identify and respond to these grey areas by applying common legal and ethical tenets.
Who owns your data? BIBAFull-Text 623-628
  Gilad Rosner
Popular and professional discussions of personal data are often framed in terms of ownership -- that human data subjects own the data they emit and share. This framing has implications for consent concepts. Ownership, however, is an inappropriate way to conceive of personal data -- in most cases the law does not grant proprietary interests in much of the personal information that makes up the digital economy. This paper explores the question, "Who owns your data?" from policy, business, legal and philosophical viewpoints, arguing that a new discourse is required for people to understand how much control they actually have over their personal information in order to build a stronger foundation for consent within ubiquitous computing systems.
Do we really need an online informed consent?: discussion from a technocratic point of view BIBAFull-Text 629-634
  Javier Bustos-Jiménez
In this article we study the problem generated by "unread and accepted" informed consent and permissions granted to mobile applications and its impact on the users' privacy. We take a technocratic approach, that is: using the scientific method to resolve this issue.
   After observing that most of the time terms of use and applications permissions are unquestionably accepted, we conducted a survey to find out whether users actually read and understand the terms that they are accepting while installing computer applications.
   Then, noticing that less than 1/9 of users reads the informed consent document, we discuss several issues. We consider the professional ethics of computer engineers that state that developers must protect the privacy of personal data of users of systems. Based on that, we present a set of applied cryptography tools that should be used to protect the user's privacy despite their lack of consent not-understanding.
An emerging tool kit for attaining informed consent in UbiComp BIBAFull-Text 635-639
  Stuart Moran; Ewa Luger; Tom Rodden
Existing approaches to attaining informed consent are outdated and inappropriate for use in ubiquitous computing systems. The pervasiveness of the technology and the nature of user interaction require a rethinking of consent mechanisms. In this paper we briefly introduce and discuss several new approaches to consent acquisition developed specifically for the new era of ubiquitous computing.
Literatin: beyond awareness of readability in terms and conditions BIBAFull-Text 641-646
  Stuart Moran; Ewa Luger; Tom Rodden
Terms and Conditions (T&Cs) are frequently unread as a consequence of their complexity and length. Readability formulas are used to objectively measure this complexity, but ironically their outputs are also unreadable to many. This motivated the development of a chrome extension called Literatin that compares the complexity of popular fictional literature to T&Cs in order sensitise people to their complexity. In this paper we discuss whether this has been achieved, and outline plans to further develop the extension.
Usable consents: tracking and managing use of personal data with a consent transaction receipt BIBAFull-Text 647-652
  Mark Lizar; Mary Hodder
Privacy and terms of use policy infrastructures on the Internet are broken. Fixing this broken aspect of digital life is a critical component to safeguarding freedom in and for the democracy, and protecting privacy for individuals as well as companies and institutions.
   We propose creating an Open Notice and Consent Receipt architecture, as a part of public data control infrastructure, (including both the social web [7] and other digital life access points) in order to open the closed and custom format of policies and consents currently used. We believe this can be achieved with a common digital Consent Receipt Format standard. We hypothesize that this format, structured with the links to legally required consent notices across jurisdictions, will open up control of personal data in simple but usable way.
Consenting agents: semi-autonomous interactions for ubiquitous consent BIBAFull-Text 653-658
  Richard Gomer; m. c. schraefel; Enrico Gerding
Ubiquitous computing, given a regulatory environment that seems to favor consent as a way to empower citizens, introduces the possibility of users being asked to make consent decisions in numerous everyday scenarios such as entering a supermarket or walking down the street. In this note we outline a model of semi-autonomous consent (SAC), in which preference elicitation is decoupled from the act of consenting itself, and explain how this could protect desirable properties of informed consent without overwhelming users. We also suggest some challenges that must be overcome to make SAC a reality.
Sustaining consent through agency: a framework for future development BIBAFull-Text 659-664
  Ewa Luger; Tom Rodden
Whilst being addressed in terms of traditional online interactions, the concept of consent has only recently seen attention in respect of pervasive systems. This paper takes the position that consent (online), as it currently stands, is a fiction. It reflects only the most basic requirements of the original concept and, as such, should not be transferred to Ubicomp systems without careful reconfiguration. In a world of pervasive sensors, software agents and tick and click consent, where is the space for human agency? This paper draws on the findings of previous studies to suggest an emerging framework that seeks to move beyond securing consent, to sustaining user agency within the design of Ubicomp systems.
Studying MarathonLive: consent for in-the-wild research BIBAFull-Text 665-670
  Edward Anstead; Martin Flintham; Steve Benford
In-the-wild research projects offer new insights into how we use technology in a socially embedded environment. Ethical guidelines for technology research are challenged by these studies through the potential for implication of third parties and the convergence of data streams. We present the MarathonLive application as a case study of in-the-wild research and some of the ethical challenges faced. Our discussions focus on the capture of third parties and consider the importance of a flexible 'moment of consent' for these systems.

Disasters in Personal Informatics: the Unpublished Stories of Failure and Lessons Learned

Disasters in personal informatics: the unpublished stories of failure and lessons learned BIBAFull-Text 673-678
  Jon E. Froehlich; Jakob Eg Larsen; Matthew Kay; Edison Thomaz
Though never a desirable outcome, failure is an inevitable part of research. Too often, however, the tried but failed paths are lost in the translation of work to publication. With the pragmatics of publishing (e.g., page limits) and the academic emphasis on positive outcomes, failed processes, methodologies, study designs, and technologies are frequently not disclosed. This is a missed opportunity, particularly for nascent areas like Personal Informatics (PI) as well as other research areas, more generally, that share high costs in time, development, and recruitment for building and deploying testable systems. Thus, we propose a UbiComp2014 workshop focused on failures in PI research. Through short participant authored papers, breakout sessions, madness talks, and all-group discussions, our overarching workshop goals are to share "disaster" stories, reflect on lessons learned, and articulate promising paths forward.
Activity tracking: are we more than the sum of our programming? BIBAFull-Text 679-682
  Halimat Alabi; Yvonne Coady
Standard activity trackers preprocess raw personal data from accelerometers and gyroscopes, to provide meaningful results in the form of step counts, calories burned, and progress over time. What happens though, when the built-in algorithms are not calibrated to an individual's physiological characteristics? Specifically, is 16 consecutive days of an activity rating at "-1" a meaningful diagnostic or a data disaster?
   This paper highlights results from a preliminary study exploring the user experience of persons with chronic disease and/or cognitive disabilities with off-the-shelf wearable activity tracking devices. Results show that though these devices can be useful to determine baselines, trends and deviation in activity, their current one-size-fits-all analytics, coupled with their closed data policies, introduce a significant data disaster for this population.
Personal informatics for non-geeks: lessons learned from ordinary people BIBAFull-Text 683-686
  Gul Calikli; Blaine Price; Mads Schaarup Andersen; Bashar Nuseibeh; Arosha Bandara
We have been studying how ordinary people use personal informatics technologies for several years. In this paper we briefly describe our early studies, which influenced our design decisions in a recent pilot study that included junior doctors in a UK hospital. We discuss a number of failures in compliance and data collection as well as lessons learned.
Social networking use and RescueTime: the issue of engagement BIBAFull-Text 687-690
  Emily I. M. Collins; Jon Bird; Anna L. Cox; Daniel Harrison
The dramatic rise in the use of social network sites (SNS) has resulted in a number of users feeling stressed about the extent of their personal use. Previous work has established that daily retrospective estimations of SNS use and access to RescueTime not only improve accuracy of estimations but also reduce perceived stress. The present study aimed to extend this by also exploring the influence of prospective estimations on stress and perceived time management. However, the study was thwarted by incredibly low engagement with RescueTime and consequently, no improvement in estimation accuracy and no reduction in stress. This indicates substantial individual differences in engagement and a requirement for external sources of motivation for using personal informatics, beyond the tasks of the study.
The long tail issue in large scale deployment of personal informatics BIBAFull-Text 691-694
  Andrea Cuttone; Jakob Eg Larsen
We describe the challenges and the open questions arising during the design and deployment of SensibleJournal, a mobile personal informatics system with interactive visualizations of mobility and social interactions based on data acquired from embedded smartphone sensors. The SensibleJournal system was evaluated in a large scale (N=136) mobile sensing field study. We report issues in deployment, limitations in user engagement and uptake, and the challenges in measuring the effect of the system.
Failures in sharing personal data on social networking sites BIBAFull-Text 695-698
  Daniel A. Epstein; James Fogarty; Sean A. Munson
Sharing personal informatics data to social networking sites is a common and well-studied practice in both research and commercial applications, but there have been substantial mistakes and failures within this space that offer important lessons to application developers. We discuss three common types of failures salient in our own work, other research, and popular press stories. These failures surface important open questions to the field of personal informatics.
Tracking physical activity: problems related to running longitudinal studies with commercial devices BIBAFull-Text 699-702
  Daniel Harrison; Nadia Berthouze; Paul Marshall; Jon Bird
The problems with inactive and sedentary lifestyles are widely recognised. People believe that activity tracking systems, such as the Fitbit, may aid them in meeting recommended levels of physical activity. Similar systems have been the subject of previous research, but many of these studies were conducted over a short-term and some results may be attributable to reactivity or novelty effects. We ran a longitudinal mixed-methods effectiveness study using the Fitbit Zip activity tracker with 50 participants. In this paper we present two main challenges experienced during this study: the unreliability of the device and a lack of engagement by some of the participants. The issues we experienced can help inform the design of future studies.
Exploring users' creation of personalized behavioral plans BIBAFull-Text 703-706
  Jisoo Lee; Winslow Burleson; Erin Walker; Eric B. Hekler
As an initial effort in developing tools that support users' creation of their own behavior-change plans, we conducted a formative user study. We intended to explore people's creation of plans for their own behavioral goals, with minimal support to facilitate their goal-setting, implementation of behavior-change techniques, and self-monitoring. In this paper, we present lessons that we obtained from this initial study, and insights on shifts in our design tools for a follow-up formative study currently underway.
Lessons learned from an initial effort to bring a quantified self "meetup" experience to a new demographic BIBAFull-Text 707-710
  Victor R. Lee; Mary Briggs
Quantified Self "meetup" groups appear to appeal largely to middle-aged white males. What happens when the target demographic is changed to high school-aged Latina girls? This paper summarizes two lessons learned from an initial effort to enact a version of a Quantified Self meetup with youth from this population. Specifically, the appearances of the devices and limited access to resources outside of the meetup sessions were major concerns.
Be like water: suggestions for handling undesirable hardware outcomes in personal informatics fieldwork BIBAFull-Text 711-714
  Jason Zietz
Research in personal informatics (PI) depends heavily upon reliable hardware solutions. Unless they are developing the hardware themselves, PI researchers frequently find themselves at the mercy of hardware manufacturers. While working on EMPIRE, a sociotechnical system designed to help motivate people to reduce their electricity consumption, I have been shown repeatedly that I am not immune to this less-than-desirable outcome. In this paper, I will describe the numerous hardware-related roadblocks we encountered, explain how we handled (and continue to handle) these obstacles, and present suggestions to help PI researchers to be like water and adapt to challenging hardware-related problems that often come with PI fieldwork.

HASCA -- 2nd International Workshop on Human Activity Sensing Corpus and its Application

International workshop on human activity sensing corpus and its application (HASCA2014) BIBAFull-Text 715-719
  Nobuo Kawaguchi; Sozo Inoue; Nobuhiko Nishio; Susanna Pirttikangas; Daniel Roggen
Recent advancement of technology enables installations of small sized accelerometers or gyroscopes on various kinds of wearable/portable information devices. By using such wearable sensors, these devices can estimate its posture or status. However, most of current devices only utilize these sensors for simple orientation and gesture recognition. More deep understandings and recognition of human activity through these sensors will enable the next-generation human-oriented computing. To enable the real-world application by these kinds of wearable sensors, a large scale human activity sensing corpus might play an important role. Additionally, we have now a lot of high-performance mobile devices in real-world such as smart-phones. It is a great challenge to utilize such an enormous number of wearable sensors to collect a large-scale activity corpus. In recent years, there are several ongoing projects which are collecting human activities. Following on a huge success of last year's workshop, we are further planning to share these experiences of current research on human activity corpus and its applications among the researchers and the practitioners and to have a deep discussion for future of activity sensing.
A pedestrian flow analysis system using Wi-Fi packet sensors to a real environment BIBAFull-Text 721-730
  Yuki Fukuzaki; Nobuhiko Nishio; Masahiro Mochizuki; Kazuya Murao
The authors have been developing the system, which analyzes pedestrian flow using Wi-Fi packet sensors. The sensors collect Wi-Fi packet called probe request packet, which is transmitted from a smartphone to search Wi-Fi access points. In addition, the cloud storage server is running to manage observed packets centrally and to compute pedestrian flow in real time. Additionally, user movement history is vitally important and we have to pay close attention to handling that kind of data. Therefore, the system runs with an anonymization method and a cryptographic function. Some kinds of demonstration experiments were held in real environment. As a result, it was confirmed that we can analyze the rough tendency of pedestrian flow using the present system and simple analysis methods.
Room exit recognition using mobile accelerometers and illuminometers BIBAFull-Text 731-735
  Tatsuya Isoda; Shuji Kutsuna; Sozo Inoue; Masato Kawano
At present, office entrances and exits are controlled mainly using RFID tags, such as employee ID cards or admission cards. When using an RFID tag, the card reader is placed at the entrance and recognition only occurs when entering the room in most cases. Thus, the information required to enter is only recognized during entry but not when leaving. In this paper, we propose a method for exit recognition that uses an illuminometer and an accelerometer embedded in a mobile sensor, which assesses the changes in the illuminance and acceleration data for subjects. We analyze the walking data obtained from the feature values of the acceleration data and the exit data derived from the feature values of the illuminance. We found that this method achieves 87.60% of accuracy for exit recognition.
User activity recognition method based on atmospheric pressure sensing BIBAFull-Text 737-746
  Keisuke Komeda; Masahiro Mochizuki; Nobuhiko Nishiko
Several studies have been conducted on context recognition as well as hobby and preference extraction by analyzing the data obtained from the sensors in a smartphone. As a smartphone component, a barometer is expected to be useful for activity recognition because of its low power consumption. In this work, we propose an activity recognition method of classifying a user's state into indoor and outdoor states and using a barometer at each state. In the proposed method, the floor of a building on which a user is located is estimated by determining atmospheric pressure variations sensed in the indoor state, and the user's location is estimated by determining atmospheric pressure variations according to the user movement along a track in the outdoor state. In particular, this paper delineates the method of estimating the current floor on which the user is located. We confirmed that it is possible to closely estimate the current floor of the building in the case of user movement among eighteen floors.
Limitations with activity recognition methodology & data sets BIBAFull-Text 747-756
  Jeffrey W. Lockhart; Gary M. Weiss
Human activity recognition (AR) has begun to mature as a field, but for AR research to thrive, large, diverse, high quality, AR data sets must be publically available and AR methodology must be clearly documented and standardized. In the process of comparing our AR research to other efforts, however, we found that most AR data sets are sufficiently limited as to impact the reliability of existing research results, and that many AR research papers do not clearly document their experimental methodology and often make unrealistic assumptions. In this paper we outline problems and limitations with AR data sets and describe the methodology problems we noticed, in the hope that this will lead to the creation of improved and better documented data sets and improved AR experimental methodology. Although we cover a broad array of methodological issues, our primary focus is on an often overlooked factor, model type, which determines how AR training and test data are partitioned -- and how AR models are evaluated. Our prior research indicates that personal, hybrid, and impersonal/universal models yield dramatically different performance [30], yet many research studies do not highlight or even identify this factor. We make concrete recommendations to address these issues and also describe our own publically available AR data sets.
A method for tracking on-body sensor positions utilizing prior knowledge BIBAFull-Text 757-766
  Naoto Migita; Sozo Inoue; Takuya Yumiyama; Takeshi Nishida
In this research, we aim at estimating the positions and directions of on-body mobile devices such as smartphones with accelerometers and gyroscopes. We propose a method utilizing prior knowledge of positions and directions of sensors. We model the prior knowledge by neighborhood method trained from a motion capturing system, and combine with physical principles by Bayes' theorem. To assess our approach, we developed a system for collecting acceleration and position data using an accelerometer and motion capture, and experimented with data obtained using it. In contrast to the conventional method, the experimental result shows that the proposed method stably follows a trajectory.
On strategies for budget-based online annotation in human activity recognition BIBAFull-Text 767-776
  Tudor Miu; Paolo Missier; Daniel Roggen; Thomas Plötz
Bootstrapping activity recognition systems in ubiquitous and mobile computing scenarios often comes with the challenge of obtaining reliable ground truth annotations. A promising approach to overcome these difficulties involves obtaining online activity annotations directly from users. However, such direct engagement has its limitations as users typically show only limited tolerance for unwanted interruptions such as prompts for annotations. In this paper we explore the effectiveness of approaches to online, user-based annotation of activity data. Our central assumption is the existence of a fixed, limited budget of annotations a user is willing to provide. We evaluate different strategies on how to spend such a budget most effectively. Using the Opportunity benchmark we simulate online annotation scenarios for a variety of budget configurations and we show that effective online annotation can still be achieved using reduced annotation effort.
Cross-assistive approach for PDR and Wi-Fi positioning BIBAFull-Text 777-786
  Kazuya Miyazaki; Nobuhiko Nishio; Masahiro Mochizuki; Kazuya Murao
In indoor positioning using Wi-Fi, there is a problem that the accuracy is not stable by the occurrence of large errors. Large errors tend to occur when density of wireless LAN access points is low or the radio wave condition is unstable. Furthermore, as for positioning utilising smartphone, it takes a while to scan Wi-Fi beacons. Thereby, errors tend to occur while user is moving. Because it is difficult to observe exactly Wi-Fi beacons. Accordingly, the authors proposed Cross-Assistive Approach for PDR and Wi-Fi Positioning. First of all, fingerprinting that is often used Wi-Fi positioning is improved by confining fingerprints to location where is estimated by PDR. As a result, this approach improved the accuracy about 2 meters. Furthermore, in order to correct accumulated errors in PDR, the authors proposed a method that corrects PDR with accurate Wi-Fi positioning results. Additionally, the authors proposed a method that estimates the accuracy of Wi-Fi positioning results. The mean error of accurate Wi-Fi results estimated by the accuracy estimating method was 0.98 meters. Thus, the accuracy estimating method detected accurate Wi-Fi positioning results effectively. In the comprehensive evaluation, our approach improved an existing Wi-Fi method about 3.4 meters by assisted PDR with Wi-Fi positioning and assisted Wi-Fi positioning with PDR cooperatively. Moreover, this approach enabled accumulated errors in PDR to be corrected.
A recognition method for combined activities with accelerometers BIBAFull-Text 787-796
  Kazuya Murao; Tsutomu Terada
Many activity recognition systems using accelerometers have been proposed. Activities that have been recognized are "single" activities which can be expressed with one verb, such as sitting, walking, holding a mobile phone, and throwing a ball. In actual, however, "combined" activities including more than two kinds of state and movement are often taken place. Focusing on hand gestures, they are performed not only while standing, but also while walking and sitting. Though the simplest way to recognize such combined activities is to construct the recognition models for all the possible combinations of the activities, the number of combinations becomes immense. In this paper, we propose a recognition method for combined activities by learning single activities only. Evaluation results confirmed that our proposed method achieved 0.84 of recall and 0.85 of precision, which is comparable to the method that had learned all the combined activities.
Pedestrian dead reckoning based on human activity sensing knowledge BIBAFull-Text 797-806
  Yuya Murata; Kei Hiroi; Katsuhiko Kaji; Nobuo Kawaguchi
This research addresses improvement of the accuracy of pedestrian dead reckoning (PDR), which is one effective technique to estimate indoor positions using smartphone sensors. Even though various techniques using step lengths and their number have been previously proposed for PDR, insufficient accuracy is gotten from smartphone sensors. In this research, we define human activity sensing knowledge and propose improvements to PDR accuracy based on it. Human activity sensing knowledge consists of four kinds of information: pedestrian, environmental, activity, and terminal. Previous studies separately used these kinds of information; however, no study has systematically arranged them for use in PDR. We improved PDR accuracy by adjusting the step length in passages and on stairs and revised activity recognition error with human activity sensing knowledge. To investigate the effectiveness of that strategy, we used HASC-IPSC, which is an indoor pedestrian sensing corpus. After our investigation, activity recognition accuracy improved from 71.2% to 91.4%, and the distance estimation error was reduced from approximately 27 m to approximately 7 m using human activity sensing knowledge.
Towards a unified system for multimodal activity spotting: challenges and a proposal BIBAFull-Text 807-816
  Long-Van Nguyen-Dinh; Gerhard Tröster; Alberto Calatroni
In the existing multimodal systems for activity recognition, there is no single method to process different sensor modalities at different on-body positions. Moreover, sensor types are often selected and optimized so as to accord with the goal of application. The complexity makes those systems infeasible to be deployed for new settings. This paper proposes a unified system which works with any available wearable sensors placed on user's body to spot activities. Each data stream is treated uniformly through our proposed template matching WarpingLCSS to spot activities. With the uniformity in extracting activity-specific patterns from raw sensor signals, our proposed system is compatible with respect to modalities and body-worn positions.
   We evaluate our system on the Opportunity dataset of four subjects consisting of 17 hard-to-classify classes (e.g., open/close drawers at different heights) with 17 sensors belonging to three modalities (accelerometer, gyroscope and magnetic field) attached at different on-body positions. The system achieves good performances (63% to 84% in F1 score). Moreover, the robustness and efficiency to addition and removal of sensors as well as activity classes are also investigated.
Exploring combinations of missing data complement for fault tolerant activity recognition BIBAFull-Text 817-826
  Ren Ohmura; Ryoma Uchida
Disrupting the transmission of sensor data due to sensor failure or connection loss significantly decrease accuracy in existing activity recognition techniques. We introduce an approach towards managing missing sensor data which operates at each step of the standard activity recognition, beginning with raw sensor data, feature calculation, classification, and result, as well as their combination methods. Our evaluation showed that the F1-score increased from 0.61 in the case of sensor data loss to 0.68 with the combination of all methods. Moreover, by selecting the combination of methods according to the failed sensor position, the F1-score increased to 0.69.
Improving activity recognition via automatic decision tree pruning BIBAFull-Text 827-832
  Thomas Phan
Activity recognition enables many user-facing smartphone applications, but it may suffer from misclassifications when trained models attempt to classify previously-unseen real-world behavior. Our system mitigates this problem by first identifying spurious classifications and then automatically pruning a decision tree model to remove labels that tend to produce wrong inferences, resulting in a 10% classification improvement based on our data set.
Cost-sensitive feature selection for on-body sensor localization BIBAFull-Text 833-842
  Ramyar Saeedi; Brian Schimert; Hassan Ghasemzadeh
Activity recognition systems have demonstrated potential in a broad range of applications. A crucial aspect of creating large scale human activity sensing corpus is to develop algorithms that perform activity recognition in a way that users are not limited to wear sensors on predefined locations on the body. Therefore, effective on-body sensor localization algorithms are needed to detect the location of wearable sensors automatically and in real-time. However, power optimization is a major concern in the design of these systems. Frequent need to charge multiple sensor nodes imposes much burden on the end-users. In this paper, we propose a novel signal processing approach that leverages feature selection algorithms to minimize power consumption of node localization. With the real data collected using wearable motion sensors, we demonstrate that the proposed approach achieves an energy saving that ranges from 88% to 99.59% while obtaining an accuracy performance between 73.15% and 99.85%.
Adapting Wi-Fi samples to environmental changes automatically BIBAFull-Text 843-852
  Takashi Sakaguchi; Nobuhiko Nishio; Masahiro Mochizuki; Kazuya Murao
In recent years, a positioning method which utilizes wireless LAN without using GPS has attracted attention. Especially, in the case of a method which combines absolute position with a Wi-Fi radio environment in advance, the cost of operation and management becomes enormous. Therefore, by sampling Wi-Fi radio information observed at points where users stay frequently or in the long-term, a method which automates to collect and update the Wi-Fi radio information has been proposed. In the case of a long-term operating, the positioning accuracy, however, decreases because this method does not perform well in maintaining and managing samples. It cannot adapt samples to environmental changes although Wi-Fi radio signals change in case of long-term operating. Accordingly, this paper proposes a new calculation formula for improving a positioning accuracy. The formula is calculated with the weight of each base station for avoidance of ill-behaving stations. In addition, this paper also proposes the automated management system with two steps. It adapts samples to changes of Wi-Fi radio signals and a user's behavior. As a result, a positioning accuracy of the new system is higher than existing one.
Kraken.me: multi-device user tracking suite BIBAFull-Text 853-862
  Immanuel Schweizer; Benedikt Schmidt
An in-depths understanding of human activity is a relevant contribution to the design of interactive systems to support human activity. This is of explicit relevance for assistance systems building on prediction and recommendation.
   However, the understanding of human activity is limited. Albeit the omnispresence of smart phones and computers, the actual execution of complex activities with those devices in relation to context factors is not completely understood. One possible reason is the limited amount of activity related data to perform actual research.
   In this paper, we present the Kraken.me framework to address this lack of information. Kraken.me is the first tracking suite to offer integrated tools for mobile, social, and desktop tracking. It is also, to our knowledge, the first tool to emphasize the collection of data from both physical and soft sensors. In this paper, we will introduce the overall architecture, system components, and future research ideas for Kraken.me.
Training human activity recognition for labels with inaccurate time stamps BIBAFull-Text 863-872
  Takamichi Toda; Naonori Ueda; Sozo Inoue; Shota Tanaka
We generally use supervised learning when performing activity recognition using mobile sensor devices such as smartphones. In this application, case data associated with the sensor information and type of action is required. However, there is a possibility that a time shift occurs because this association is done manually on the audio and video that has been acquired along with the sensor information. In this paper, we propose a method of activity recognition that can recognize correct actions even if there is a time gap. In this method, we add labels that shift the original learning data label. We also implement multi-label machine learning. In addition, we propose a method for repeated learning based on the Expectation-Maximization (EM) algorithm. To evaluate this method, we conducted an experiment that recognized three types of behavior using a Naive Bayes classifier. In the evaluation, we pieced together three types of human action data into one dataset called pseudo sequence data. We slid the action labels of the pseudo sequence data and examined whether the recognition rate was improved by our proposed method. The results show that the proposed method can perform activity recognition with high accuracy, even if the action labels times are shifted.
CrowdSignals: a call to crowdfund the community's largest mobile dataset BIBAFull-Text 873-877
  Evan Welbourne; Emmanuel Munguia Tapia
Researchers from diverse backgrounds critically depend on mobile datasets. From training and testing activity recognition models, to verifying hypotheses in social science, mobile data is indispensable. Unfortunately, mobile data collection requires significant time and budget for infrastructure as well as subject recruiting, screening, training, legal agreements, equipment, and compensation. We estimate up to 70% of the resources in a study may be spent on data collection. Moreover, this massive investment can combine with institutional, legal, and political issues to create a disincentive to sharing with the community. In this paper, we propose and justify a crowdfunded and crowdsourced methodology for longitudinal mobile data collection that cuts researcher costs by orders of magnitude, removes barriers to data sharing, and boosts data value for all stakeholders. We also present CrowdSignals, a first instantiation which will generate the largest labeled mobile dataset available to the community.

HomeSys 2014

HomeSys 2014 BIBAKFull-Text 879-885
  Tim Coughlan; Rob Comber; Richard Mortier; Thomas Ploetz; Val Mitchell
HomeSys 2014 will provide an insightful and constructive setting for the growing community of researchers studying ubiquitous technology in domestic spaces. Homes have been a consistent setting for ubiquitous computing research and development. This continues to evolve, reflecting the spread of computing into ever more of the fabric of our everyday lives. Inspired by the success of HomeSys at previous UbiComp conferences, a new organising team will arrange a balance of presentations, panel and whole room discussions, and an interactive session to explore the challenges currently facing ubiquitous computing in the home. Through this, HomeSys can continue to support reflection and development in home-based ubiquitous computing research across disciplines, act as a companion to the main UbiComp conference, strengthen existing networks, and produce new collaborations and outcomes.
Keywords: Home, domestic, Internet of Things, Human-Computer Interaction, networking
Sensemaking in the autonomic smart-home BIBAFull-Text 887-894
  Robin Despouys; Rémi Sharrock; Isabelle Demeure
In the future smart living spaces the users will face more and more misunderstanding situations. In this paper we present an original scenario showing three aspects: the misunderstanding situations, the purpose requests and the causality requests. Autonomic computing is an approach to overcome the massive development of the Internet and the growing complexity of resources and services management in the IT domain. We state that since the smart-home has to self-managed they need to be autonomic. As a contribution we introduce a model that extends the autonomic architecture in order to manage misunderstanding situations and facilitate the sensemaking processes in the Autonomic Smart-Home. We name this extension IHMUNE which stands for Intelligent Home Manager for Understandable Novel Experiences. Then we discuss about the different kinds of collaborations that will arise in the smart-cities, the privacy concerns and the sensemaking.
Early lessons from the development of SPOK, an end-user development environment for smart homes BIBAFull-Text 895-902
  Joëlle Coutaz; Sybille Caffiau; Alexandre Demeure; James L. Crowley
This paper presents early lessons from the development of SPOK, an End-User Development Environment for smart homes. SPOK (Simple PrOgramming Kit) uses a pseudo-natural language as an end-user programming language and runs on top of an extension of OSGi/iPOJO to support the dynamic and resilient management of web services and devices from a variety of protocols including EnOcean, UPnP, and Watteco. The motivation for SPOK is to give the power back to end-users so that they can shape their own smart home at will. This paper reports lessons learned from the methods we have used to validate our hypotheses as well as a number of technical issues concerning development of this type of EUDE. A Video of SPOK in action as of October 2013 is accessible at: http://iihm.imag.fr/demos/appsgate/appsgate2013.mp4
An exploration of user recognition on domestic networks using NetFlow records BIBAFull-Text 903-910
  Anthony Brown; Richard Mortier; Tom Rodden
In this paper, we describe HomeNetViewer, a system for collecting, visualising and annotating domestic network NetFlow records from a domestic network gateway. HomeNetViewer is designed to collect ground truth data which, enables the linking of users to low level network traffic. We present our first annotated dataset from a real household in the UK and the results of our preliminary work to build a user identification system. Our initial classifier achieves a true-positive rate of 64% with false-positive rate of 28% when compared to the ground truth annotations. This work attempts to address the lack of transparency and accountability within the domestic network infrastructure by identifying the user behind the device.
A user demand and preference profiling method for residential energy management BIBAFull-Text 911-918
  Ting Liu; Yulin Che; Yuqi Liu; Zhanbo Xu; Yufei Duan; Siyun Chen
The home appliance scheduling is a promising energy saving technique that has significant commercial potential. In this paper, a novel method is proposed to profile user demand and preference for residential energy management. Non-Intrusion Load Monitoring (NILM) is applied to identify user operations on each appliance. The operations are integrated with dynamic electric price and environment data to mine users' personal demand and preference on various devices. Finally, the personalized scheduling strategy is generated to meet the different users' demands at the minimal cost. The major contributions of this paper are: 1) NILM is an low-cost and easy-accept solution to profile users' demand, since power meters have been widely deployed and power consumption data are less privacy-related. 2) Five preference indexes are firstly introduced, which can dramatically improve the user's satisfaction on scheduling strategies.
Placing information at home: using room context in domestic design BIBAFull-Text 919-922
  Nico Castelli; Corinna Ogonowski; Gunnar Stevens; Timo Jakobi
Residential and commercial buildings are responsible for about 40% of the EU's total energy consumption [2]. With current consumption feedback systems, dwellers have the opportunity to get disaggregated real-time energy feedback about their consumption. However, there is often an absence of additional context information, so that the user is not able to derive energy efficient behavior from their energy data. Against this background, this study presents a concept, where indoor-positioning data on room level are used to contextualize energy data. This makes it possible to expend visualizations of current consumption feedback systems and develop new kind of user-interfaces that support everyday-activities.
Finding roles for interactive furniture in homes with EmotoCouch BIBAFull-Text 923-930
  Sarah Mennicken; James Scott; A. J. Bernheim Brush; Asta Roseway
Furniture is the building block of the spaces we inhabit. Its design and its functions shape how we use spaces, as individuals and as groups. While being an integral part of our lives, furniture is unaware of what happens around it. But what if furniture could change its appearance? What situations should it respond to? How might it communicate its state to those around it? Can we use emotional expression for such communication? To find and explore roles for interactive furniture in domestic spaces, we built EmotoCouch: a provocative prototype that uses combinations of color, patterns, and haptics designed to convey emotions. We gathered feedback to the concept of an emotional couch from an online study with 138 participants and in a laboratory study with 14 parent-child pairs. Our findings identify promising future directions, use cases, and opportunities for the use of emotion for expressive communication by furniture.
Wearables or infrastructure: contrasting approaches to collecting behavioural data in the home BIBAFull-Text 931-938
  Victoria Shipp; Tim Coughlan; Sarah Martindale; Elizabeth Evans; Kher Hui Ng; Richard Mortier; Stuart Reeves
This paper examines and contrasts two approaches to collecting behavioural data within the home. The first of these involves filming from static video cameras combined with network logging to capture media consumption activities across multiple screens. The second utilises wearable cameras that passively collect still images to provide insights into food related behaviours. The paper compares the approaches from the perspective of the researchers and participants, and outlines the key benefits and challenges of each, with the aim of further mapping the space of possibilities now available when studying behaviour in the home.
CARL: activity-aware automation for energy efficiency BIBAFull-Text 939-946
  Brian L. Thomas; Diane J. Cook
Society is becoming increasingly aware of the impact that our lifestyle choices have on energy usage and the environment. This paper explores the hypothesis that ubiquitous computing technologies can be used to understand this impact and to provide activity-aware interventions to reduce energy consumption. Specifically, we introduce a method to provide energy-efficient home automation based on the recognition of activities and their associated devices. We describe CARL (CASAS Activity-based Resource Limitation), a prototype energy-efficient smart home, and evaluate the performance of our activity-aware automation when using both historic and real-time sensor data to drive intelligent home automation.
Smart heating control with occupancy prediction: how much can one save? BIBAFull-Text 947-954
  Wilhelm Kleiminger; Silvia Santini; Friedemann Mattern
Research results on smart heating systems based on occupancy prediction are often difficult to reproduce and to compare. Evaluating the performance of these systems through simulation or real experiments requires defining suitable scenarios and setting a large number of parameters. As different authors rely on different scenarios and parameter settings, comparing the reported performance results is often infeasible. In this paper, we argue that overcoming this problem is crucial to bring research on smart heating systems a step forward. We outline the main factors influencing the performance of such systems and we show how these factors can be integrated by proposing a simple yet thorough evaluation methodology for smart heating systems. Using parameters synthesised from real-world occupancy and weather data, we describe how this methodology can be used to establish performance bounds of smart heating systems.
The HomeCar organiser: designing for blurring home-car boundaries BIBAFull-Text 955-962
  Chandrika Cycil; Mark Perry; Rachel Eardley
Ubiquitous computing is having an important impact on family life with a wide range of technologies supporting and creating the need for connected and smarter homes. In particular, mobile devices are allowing families to connect activities across spaces, which include the home and the car. This paper presents a new design concept -- the HomeCar Organiser -- which is a connected system that enables families to coordinate schedules, activities and artifacts between the home and activities placed in the car. The design of HomeCar Organiser was informed by an empirical ethnographic study of family car travel practices in the UK over one and a half years. The study motivated us to consider how routine practices of everyday life are negotiated through and in the car while supported by a range of technologies.
Blurred lines: how does cross-disciplinary research work in practice BIBAFull-Text 963-970
  Becky Mallaband; Victoria Haines
This paper describes how cross-disciplinary research works in practice, illustrated through examples and experience from two large cross-disciplinary domestic energy research projects. The paper discusses the challenges of working across disciplines in this context and suggests a framework which helps to bridge the gap between technology developers or engineers and householders.
PORTS: an interdisciplinary and systemic approach to studying energy use in the home BIBAFull-Text 971-978
  Garrath T. Wilson; Tracy Bhamra; Kerstin Leder Mackley; Sarah Pink; Val Mitchell
In this paper, we present an alternative and novel approach to identifying energy demand reduction opportunities in the home. Through the creation of detailed narratives informed by our interdisciplinary research team of social scientists, designers and engineers, we employ a systemic view of how energy is consumed in the home. By interrogating clusters of people, objects and resources through time and space as they come together within our qualitative and quantitative research, we have identified opportunities for sustainable HCI design. This paper outlines our approach and presents an example product concept in relation to laundry.
Characteristic-based security analysis of personal networks BIBAFull-Text 979-986
  Andrew J. Paverd; Fadi El-Moussa; Ian Brown
The Personal Network (PN) is a logical network of interconnected components used by an individual. It encompasses the home network, the Personal Area Network (PAN), and the Vehicular Area Network (VAN) and includes cloud-based services. Previous security analyses, including ITU-T Recommendation X.1111, have focussed on the individual physical networks rather than the PN itself. By consolidating and structuring previous work, we propose an updated and enhanced security analysis for the PN. In our characteristic-based approach we identify the primary characteristics of the PN and its components and use these to develop an abstract PN asset model. From this, we derive the main attacker objectives and a list of attack vectors through which these could be achieved. We propose a mapping between the attack vectors and the PN component characteristics that can be used to determine the specific attacks to which a particular component is vulnerable. In this paper, we present a summary of this analysis and discuss its usage.
Beyond boundaries: the home as city infrastructure for smart citizens BIBAFull-Text 987-990
  Mara Balestrini; Paul Marshall; Tomas Diez
Low-cost sensing technologies that stream data into web platforms have become increasingly available for households, blurring the boundaries between the public and the private. In this paper we draw on our experience with the Smart Citizen crowdsensing project to present a vision of a future where households become city infrastructure through the data they produce. We highlight the challenges involved with this vision in the hope that they will contribute to both academic and industry discussions on the possibilities and difficulties around home-based crowdsensing technologies.

3rd International Workshop on Mobile Systems for Computational Social Science

3rd international workshop on mobile systems for computational social science BIBAFull-Text 991-994
  Junehwa Song
Mobile devices are opening unprecedented opportunities to conduct various social science studies in unobtrusive, large-scale, and longitudinal fashions. Rich dataset captured by smartphones such as communication records, application use patterns and physical sensory readings, serve as basis to understand behavior of human being in depth. Also, crowdsourcing platforms and open-data policy of organizations are enabling scalable data collection and access to such data. Moreover, mobile devices can be used as gateways for real-time intervention and feedback. Such powerful capabilities can enable larger-scale and timely social studies in a cost-effective way beyond traditional study methods such as self-reports, interviews, surveys, and observations under laboratory settings, etc. Many exploratory works have proven that mobile phones are a promising computational platform upon which we plan, develop, and conduct various experimental studies related to social science disciplines.
Inferring human mobility from sparse low accuracy mobile sensing data BIBAFull-Text 995-1004
  Andrea Cuttone; Sune Lehmann; Jakob Eg Larsen
Understanding both collective and personal human mobility is a central topic in Computational Social Science. Smartphone sensing data is emerging as a promising source for studying human mobility. However, most literature focuses on high-precision GPS positioning and high-frequency sampling, which is not always feasible in a longitudinal study or for everyday applications because location sensing has a high battery cost. In this paper we study the feasibility of inferring human mobility from sparse, low accuracy mobile sensing data. We validate our results using participants' location diaries, and analyze the inferred geographical networks, the time spent at different places, and the number of unique places over time. Our results suggest that low resolution data allows accurate inference of human mobility patterns.
Adding intelligence to your mobile device via on-device sequential pattern mining BIBAFull-Text 1005-1014
  Abhishek Mukherji; Vijay Srinivasan; Evan Welbourne
The next revolution in mobile user experience is predicted to be a smart device that can adapt to its user's lifestyle and surroundings to become a proactive personal assistant. We introduce the idea of Mobile Sequence Mining (MSM) engine that automatically learns phone usage sequential patterns over the rich context data captured within the device. The learned patterns can then enable variety of applications including proactive assistance for a variety of use cases. Unlike existing cloud-based intelligence services (e.g., GoogleNow) that rely on internet access and may compromise privacy, MSM provides device intelligence by leveraging mined longitudinal patterns while preserving privacy via on-device mining. MSM is generic and can provide sequential patterns and predictions over multiple data streams, also allowing individual mobile applications to stream their own private data to mine sequential patterns. In our preliminary tests by deploying MSM on 3 user devices, it mines frequent sequential patterns within 8 minutes over 7-53 days of longitudinal user context data including location, app usage and call logs spanning 137-312 unique contexts. We conclude the paper by enumerating future research challenges for mobile sequence mining.
LiPS: linked participatory sensing for optimizing social resource allocation BIBAFull-Text 1015-1024
  Mina Sakamura; Takuro Yonezawa; Jin Nakazawa; Kazunori Takashio; Hideyuki Tokuda
This paper proposes a concept of linked participatory sensing, called LiPS, that divide a complex sensing task into small tasks and link each other to optimize social resource allocation. Recently participatory sensing have been spreading, but its sensing tasks are still very simple and easy for participants to deal with (e.g. Please input the number of people standing in a queue. etc.). To adapt to high-level tasks which require specific skills such as those in engineering, the medical profession or authority such as the organizer of the event, we need to optimize social resource allocation because the number of such professionals are limited. To achieve the complex sensing tasks efficiently, LiPS enables to divide a complex sensing task into small tasks and link each other by assigning proper sensors. LiPS can treat physical sensors and human as hybrid multi-level sensors, and task provider can arrange social resource allocation for the goal of each divided sensing task. In this paper, we describe the design and development of the LiPS system. We also implemented an in-lab experiment as the first prototype of hybrid sensing system and discussed the model of further system through users' feedback.
Anticipatory mobile computing for behaviour change interventions BIBAFull-Text 1025-1034
  Veljko Pejovic; Mirco Musolesi
Behavioural change interventions represent a powerful means for tackling a number of health and well-being issues, from obesity to stress and addiction. In the current medical practice, the change is induced through tailored coaching, support and information delivery. However, with the advent of smartphones, innovative ways of delivering interventions are emerging. Indeed, mobile phones, equipped with an array of sensors, and carried by their users at all times, enable therapists to both learn about the user behaviour, and impact the behaviour through the delivery of more relevant and personalised information. In this work we propose harnessing pervasive computing to not only learn from users' past behaviour, but also predict future actions and emotional states, deliver interventions proactively, evaluate their impact at run-time, and over time learn a personal intervention-effect model of a participant.
Mobile monitoring of formal and informal social interactions at workplace BIBAFull-Text 1035-1044
  Aleksandar Matic; Venet Osmani; Oscar Mayora-Ibarra
This paper proposes using mobile technologies to provide an insight into social context at workplace. It provides takeaways for extracting features that are relevant for interpreting social context and types of social interactions, formal or informal. Our approach uses mobile phones and accelerometers to detect interpersonal spatial and speech related features, achieving accuracy of around 80% in classifying between formal and informal social interactions, based on the study of 53 social interactions. One of the potential impacts of this work is on studying communication channels to enable more efficient knowledge transfer between knowledge workers. There is an on-going debate in social sciences whether formal or informal social interactions foster productivity more. However, the consensus is that improving communication between workers requires deeper understanding of both formal and informal types of interactions.
Uncovering embarrassing moments in in-situ exposure of incoming mobile messages BIBAFull-Text 1045-1054
  Chulhong Min; Youngki Lee; Saumay Pushp; Seungwoo Kang; Seungchul Lee; Junehwa Song; Inseok Hwang
Mobile instant messengers serve as major interaction media for everyday chats. Contrary to the belief that a message is seen only by a designated receiver, it can be accidentally exposed to someone nearby and could result in embarrassing moments, for example, when the receiver is viewing pictures together with his friend upon the message arrival. To understand the significance of the problem and core factors that cause such embarrassments, we collected 961 in-situ responses from 14 participants upon the actual message arrival and analyzed them from the perspective of the receiver's situation. The results showed that 29% of message arrivals have the potential to cause embarrassment. We found out that the relationship with a message sender and a nearby person influences the effect of participants' perception about the message exposure.

Collective Wearables: the Superorganism of Massively Deployed Wearables

The socio-technical superorganism vision BIBAFull-Text 1055-1056
  Franco Zambonelli
We sketch the future vision of socio-technical superorganisms and overview two emerging application area heading towards the vision. Following, we identify the key challenges in engineering self-organizing ICT systems that can work as a superorganism.
Human aware superorganisms BIBAFull-Text 1057-1062
  Nicola Bicocchi; Damiano Fontana; Franco Zambonelli
Massive networks of wearable devices have recently become a key scenario for pattern recognition technologies. Applications range from implicit human-machine interactions, to autonomous monitoring of user habits and activities. This paper presents a framework providing developers with tools to orchestrate the continuous process of collecting and classifying data streams in aware-systems. It supports service oriented, reconfigurable components and provides a solid background to put at joint work specification- and data-driven approaches. It also provides an innovative meta-classification scheme allowing to implement applications by editing a simple state automata. Experimental results suggest that the approach could be integrated in a number of applications for: (i) improving energy efficiency, (ii) improving classification accuracy and (iii) improving software engineering of aware systems.
A web of wearables BIBAFull-Text 1063-1068
  Erik Wilde; Stefan Lüder; Jack Hodges; Florian Michahelles; Mareike Kritzler
Wearables are becoming the next Big Thing, and it is clear that they will become increasingly integrated into the Web of Things, instead of just being standalone resources that are not linked into the Web. Such a Web of Wearables will make wearables as easily accessible as other Web resources, allowing new classes of applications and systems to use them. This Web of Wearables will establish an ecosystem noticeably different from the current Web with more ties to the real world, more ties to personal information and data, and more ways to interact with the real world. It remains to be seen which applications and systems will emerge, but the designs of today will have an impact on what is possible tomorrow, so we should strive to make sure that the ecosystem we design is open, extensible, and flexible.
Collective wristwear: the world in the hands of humankind BIBAFull-Text 1069-1070
  Alois Ferscha
Personalized wearable ICT systems presented in fashionable and appealing lifestyle-designs have gained critical user acceptance, and comprise momentum to bring wearable computing to a socio-technical mass phenomenon within the next few years. Early indicators for this expected wearable systems 'tsunami' are the 'spring tide' of some 5.3 billion mobile phone platforms (i.e. mobile subscribers) as of the end of 2013, and an assessed market potential for 300 million smart watches in 2014 [1]. This technological and market evolution raises questions on the potentials and opportunities of turning these massively deployed wearable systems to a globe spanning superorganism of socially interactive personal digital assistants. While the individual wearables are of heterogeneous provenance and typically act autonomously, we can assume that they can (and will) self-organize into large scale cooperative collectives, with humans being mostly out-of-the-loop [2]. We could refer to these emerging massive collectives of wearables as a "superorganism" [3], since it exhibits properties of a living organism (like e.g. 'collective intelligence') on its own.
Goal oriented smart watches for cyber physical superorganisms BIBAFull-Text 1071-1076
  Gerold Hoelzl; Alois Ferscha; Peter Halbmayer; Welma Pereira
We didn't start the fire, it was always burning since technology became integrated into wearable things that can be traced back to the early 1500s. This earliest forms of wearable technology were manifested as pocket watches. Of course technology changed and evolved, but again it might be the watch, now in form of a wrist worn smart watch, that could carve the way towards an always on, large scale, planet spanning, body sensor network. The challenge arises on how to handle this enormous scale of upcoming smart watches and the produced data. This work highlights a strategy on how to make use of the massive amount of smart watches in building goal oriented, dynamically evolving network structures that autonomously adapt to changes in the smart watch ecosystem like cells do in the human organism.
The superorganism of massive collective wearables BIBAFull-Text 1077-1084
  Alois Ferscha; Paul Lukowicz; Franco Zambonelli
Personalized wearable ICT systems presented in fashionable and appealing lifestyle-designs have gained critical user acceptance, and comprise momentum to bring wearable computing to a socio-technical mass phenomenon within the next few years. Early indicators for this expected wearable systems "tsunami" are the "spring tide" of 5.3 billion mobile phone platforms (i.e. mobile subscribers) as of the end of 2013, an assessed market potential for 300 million smart watches in 2014, and a possible market for more than 200 million smart eye-wear systems in 2015 [1].
   This workshop asks the questions on the potentials and opportunities of turning these massively deployed wearable systems to a globe spanning super-organism of socially interactive personal digital assistants. While the individual wearables are of heterogeneous provenance and typically act autonomously, we can assume that they can (and will) self-organize into large scale cooperative collectives, with humans being mostly out-of-the-loop [2]. We may not assume a common objective or central controller, but rather volatile network topologies, co-dependence and internal competition, non-linear and non-continuous dynamics, and sub-ideal, failure prone operation. We could refer to these emerging massive collectives of wearables as a "super-organism" [7], since it exhibits properties of a living organism (like e.g. 'collective intelligence') on its own. In order to properly exploit such super-organisms, we need to develop a deeper scientific understanding of the foundational principles by which they operate.

PETMEI -- 4th International Workshop on Pervasive Eye Tracking and Mobile Eye-Based Interaction

4th international workshop on pervasive eye tracking and mobile eye-based interaction BIBAFull-Text 1085-1091
  Thies Pfeiffer; Sophie Stellmach; Yusuke Sugano
Previous work on eye tracking and eye-based human-computer interfaces mainly concentrated on making use of the eyes in traditional desktop settings. With the recent growth of interest in smart glass devices and low-cost eye trackers, however, gaze-based techniques for mobile computing is becoming increasingly important. PETMEI 2014 focuses on the pervasive eye tracking paradigm as a trailblazer for mobile eye-based interaction and eye-based context-awareness. We want to stimulate and explore the creativity of these communities with respect to the implications, key research challenges, and new applications for pervasive eye tracking in ubiquitous computing. The long-term goal is to create a strong interdisciplinary research community linking these fields together and to establish the workshop as the premier forum for research on pervasive eye tracking.
Guiding visual search tasks using gaze-contingent auditory feedback BIBAFull-Text 1093-1102
  Viktor Losing; Thies Pfeiffer; Lukas Rottkamp; Michael Zeunert
In many applications it is necessary to guide humans' visual attention towards certain points in the environment. This can be to highlight certain attractions in a touristic application for smart glasses, to signal important events to the driver of a car or to draw the attention of a user of a desktop system to an important message of the user interface. The question we are addressing here is: How can we guide visual attention if we are not able to do it visually? In the presented approach we use gaze-contingent auditory feedback (sonification) to guide visual attention and show that people are able to make use of this guidance to speed up visual search tasks significantly.
Daily activity recognition combining gaze motion and visual features BIBAFull-Text 1103-1111
  Yuki Shiga; Andreas Dengel; Takumi Toyama; Koichi Kise; Yuzuko Utsumi
Recognition of user activities is a key issue for context-aware computing. We present a method for recognition of user daily activities using gaze motion features and image-based visual features. Gaze motion features dominate for inferring the user's egocentric context whereas image-based visual features dominate for recognition of the environments and the target objects. The experimental results show the fusion of those different type of features improves performance of user daily activity recognition.
Eye gaze tracking using an RGBD camera: a comparison with a RGB solution BIBAFull-Text 1113-1121
  Xuehan Xiong; Qin Cai; Zicheng Liu; Zhengyou Zhang
Most commercial eye gaze tracking systems are based on the use of infrared lights. However, such systems may not work outdoor or may have a very limited head box for them to work. This paper proposes a non-infrared based approach to track one's eye gaze with an RGBD camera (in our case, Kinect). The proposed method adopts a personalized 3D face model constructed off-line. To detect the eye gaze, our system tracks the iris center and a set of 2D facial landmarks whose 3D locations are provided by the RGBD camera. A simple onetime calibration procedure is used to obtain the parameters of the personalized eye gaze model. We compare the performance of the proposed method against the 2D approach using only RGB input on the same images, and find that the use of depth information directly from Kinect achieves more accurate tracking. As expected, the results from the proposed method are not as accurate as the ones from infrared-based approaches. However, this method has the potential for practical use with upcoming better and cheaper depth cameras.
Gaze-controlled gaming: immersive and difficult but not cognitively overloading BIBAFull-Text 1123-1129
  Krzysztof Krejtz; Cezary Biele; Dominik Chrzastowski; Agata Kopacz; Anna Niedzielska; Piotr Toczyski; Andrew Duchowski
A user study is described focusing on the cognitive and usability consequences of cueing visual attention in gaze-controlled gaming. Results show that such cueing influences performance and affects the subjective gaming experience. Accordingly, visual cues make the experience less enjoyable and less immersive. Interestingly, gaze-controlled gaming appears not to require additional cognitive effort. Taking into account previous findings, results suggest that applicability of overt cuing may depend on the game type. Our study shows the potential for optimization of interaction of gaze-controlled arcade games with visual cueing.
Identification of purchasing scenarios through eye-tracking features BIBAFull-Text 1131-1140
  Yannick Lufimpu-Luviya; Pierre Drap; Djamel Merad; Thierry Baccino; Véronique Drai-Zerbib; Bernard Fertil
Eye-tracking-based methods are generating a growing interest in marketing research. Nevertheless, most of the studies are focusing on intention, emotion or the evaluation of the products by the customer. The work that is presented here investigates two of the main purchasing scenarios: the routine purchasing act and the impulse purchasing act. The purpose is to propose a predictive model that best distinguishes the first scenario from the second scenario. To reach this goal, we extract statistically relevant eye-tracking descriptors. We use a supervised learning algorithm, Support Vector Machines (SVM), to build the model and reach performances of 82.5% of good identification.
Gaze and mouse coordination in everyday work BIBAFull-Text 1141-1150
  Daniel J. Liebling; Susan T. Dumais
Gaze tracking technology is increasingly common in desktop, laptop and mobile scenarios. Most previous research on eye gaze patterns during human-computer interaction has been confined to controlled laboratory studies. In this paper we present an in situ study of gaze and mouse coordination as participants went about their normal activities. We analyze the coordination between gaze and mouse, showing that gaze often leads the mouse, but not as much as previously reported, and in ways that depend on the type of target. Characterizing the relationship between the eyes and mouse in realistic multi-task settings highlights some new challenges we face in designing robust gaze-enhanced interaction techniques.
Pupil: an open source platform for pervasive eye tracking and mobile gaze-based interaction BIBAFull-Text 1151-1160
  Moritz Kassner; William Patera; Andreas Bulling
In this paper we present Pupil -- an accessible, affordable, and extensible open source platform for pervasive eye tracking and gaze-based interaction. Pupil comprises 1) a light-weight eye tracking headset, 2) an open source software framework for mobile eye tracking, as well as 3) a graphical user interface to playback and visualize video and gaze data. Pupil features high-resolution scene and eye cameras for monocular and binocular gaze estimation. The software and GUI are platform-independent and include state-of-the-art algorithms for real-time pupil detection and tracking, calibration, and accurate gaze estimation. Results of a performance evaluation show that Pupil can provide an average gaze estimation accuracy of 0.6 degree of visual angle (0.08 degree precision) with a processing pipeline latency of only 0.045 seconds.
Compensation of head movements in mobile eye-tracking data using an inertial measurement unit BIBAFull-Text 1161-1167
  Linnéa Larsson; Marcus Nyström; Andrea Schwaller; Martin Stridh; Kenneth Holmqvist
Analysis of eye movements recorded with a mobile eye-tracker is difficult since the eye-tracking data are severely affected by simultaneous head and body movements. Automatic analysis methods developed for remote-, and tower-mounted eye-trackers do not take this into account and are therefore not suitable to use for data where also head- and body movements are present. As a result, data recorded with a mobile eye-tracker are often analyzed manually. In this work, we investigate how simultaneous recordings of eye- and head movements can be employed to isolate the motion of the eye in the eye-tracking data. We recorded eye-in-head movements with a mobile eye-tracker and head movements with an Inertial Measurement Unit (IMU). Preliminary results show that by compensating the eye-tracking data with the estimated head orientation, the standard deviation of the data during vestibular-ocular reflex (VOR) eye movements, was reduced from 8.0° to 0.9° in the vertical direction and from 12.9° to 0.6° in the horizontal direction. This suggests that a head compensation algorithm based on IMU data can be used to isolate the movements of the eye and therefore simplify the analysis of data recorded using a mobile eye-tracker.
Privacy considerations for a pervasive eye tracking world BIBAFull-Text 1169-1177
  Daniel J. Liebling; Sören Preibusch
Multiple vendors now provide relatively inexpensive desktop eye and gaze tracking devices. With miniature-ization and decreasing manufacturing costs, gaze trackers will follow the path of webcams, becoming ubiquitous and inviting many of the same privacy concerns. However, whereas the privacy loss from webcams may be obvious to the user, gaze tracking is more opaque and deserves special attention. In this paper, we review current research in gaze tracking and pupillometry and argue that gaze data should be protected by both policy and good data hygiene.

SmartHealthSys 2014 -- ACM UbiComp Workshop on Smart Health Systems and Applications

SmartHealthSys 2014: ACM ubicomp international workshop on smart health systems and applications BIBAFull-Text 1179-1185
  Hassan Ghasemzadeh; Parisa Rashidi; Michael Ong; Diane Cook; Roozbeh Jafari; George Demiris; Misha Pavel; Marjorie Skubic
SmartHealthSys 2014 will be a cross-disciplinary workshop that brings researchers from engineering, computer science, and medicine together to discuss latest findings in this area and advance the field. This interactive workshop will be inspiring for anyone conducting research in the area of mobile and connected health. This includes research in technology design and development as well as clinical studies and novel application areas. The workshop is one day long and includes a keynote, paper presentation sessions, and several discussion sessions.
Using electronic health records to predict severity of condition for congestive heart failure patients BIBAFull-Text 1187-1192
  Costas Sideris; Nabil Alshurafa; Behnam Shahbazi; Majid Sarrafzadeh; Mohammad Pourhomayoun
We propose a novel way to design an analytics engine based exclusively on electronic health records (EHR). We focus our efforts on Congestive Heart Failure (CHF) patients, although our approach could be extended to other chronic conditions. Our goal is to construct statistical models that predict a CHF patient's length of stay and by extension the severity of his/her condition. We show that it is possible to predict length of hospital stay based on physiological data collected from the first day of hospitalization. Using 10-fold cross validation we achieve accurate predictions with a root mean square error of 3.3 days for hospital stays that are less than 15 days in duration. We also propose a clustering of patients that organizes them to risk groups according to their estimated severity of condition.
Modeling visit behaviour in smart homes using unsupervised learning BIBAFull-Text 1193-1200
  Ahmed Nait Aicha; Gwenn Englebienne; Ben Kröse
Many algorithms on health monitoring from ambient sensor networks assume that only a single person is present in the home. We present an unsupervised method that models visit behaviour. A Markov modulated multidimensional non-homogeneous Poisson process (M3P2) is described that allows us to model weekly and daily variations and to combine multiple data streams, namely the front-door sensor transitions and the general sensor transitions. The results from nine months of sensor data collected in the apartment of an elderly person show that our model outperforms the standard Markov modulated Poisson process (MMPP).
Digital memory notebook: experimental evaluation of motivational reward strategies BIBAFull-Text 1201-1208
  Christa Simon; Ramyar Saeedi; Chris Cain; Maureen Schmitter-Edgecombe; Shervin Hajiammini; Diane Cook
Prompting technology can help individuals with cognitive impairments complete independent activities of daily living (IADL). Although the prompt delivery is an effective way to remind an adult to record a completed activity, this potential benefit may not be sufficient to motivate the adult to comply with the prompt on a consistent basis. In this work we extend activity-aware prompting techniques to utilize alternative reward structures. Our reward mechanism will allow adults to observe game progress as a result of their decisions to comply with the prompts. In our study with volunteer participants, the activity-aware reward-based prompting method increased the compliance rate compared to activity-aware prompting without rewarding the adults.
Longitudinal ambient sensor monitoring for functional health assessments: a case study BIBAFull-Text 1209-1216
  Saskia Robben; Margriet Pol; Ben Kröse
Ambient monitoring systems offer great possibilities for health trend analysis in addition to anomaly detection. Health trend analysis helps care professionals to evaluate someones functional health and direct or evaluate the choice of interventions. This paper presents one case study of a person that was followed with an ambient monitoring system for almost three years and another of a person that was followed for over a year. A simple algorithm is applied to make a location based data representation. This data is visualized for care professionals, and used for inspecting the regularity of the pattern with means of principal component analysis (PCA). This paper provides a set of tools for analyzing longitudinal behavioral data for health assessments. We advocate a standardized data collection procedure, particularly the health metrics that could be used to validate health focused sensor data analyses.
Smart home-based longitudinal functional assessment BIBAFull-Text 1217-1224
  Prafulla Dawadi; Diane J. Cook; Maureen Schmitter-Edgecombe
In this paper, we investigate methods of performing automated cognitive health assessment from smart home sensor data. Specifically, we introduce an algorithm to quantify and track changes in activities of daily living and in the mobility of a smart home resident over time using longitudinal smart home sensor data. We use an automated activity recognition algorithm to recognize a smart home resident's activities of daily living from the generated sensor data, and introduce a Compare and Count (2C) algorithm to quantify the changes in everyday behavior. We test our approach using a longitudinal sensor dataset that we collected from 18 single-resident smart homes for nearly two years and study the relationship between observed changes in the sensor-based everyday functioning parameters and changes in standard clinical health assessment scores. The results suggest that we may be able to develop sensor-based change algorithms that can predict specific components of cognitive and physical health.
Evolving health consultancy by predictive caravan health sensing in developing countries BIBAFull-Text 1225-1232
  Eiko Kai; Ashir Ahmed; Sozo Inoue; Atsushi Taniguchi; Naoki Nakashima; Yasunobu Nohara; Masaru Kitsuregawa
In this paper, we introduce the predictive way to evolve the process of the health consultancy by predictive methods with machine learning. We have tried health consultancy for over 22,000 patients with caravan health sensing in Bangladesh during 2012-2014. In health consultancy with caravan health sensing, doctors' task becomes the bottleneck of the whole process because of the cost and the huge workload, and we try to delegate some of them to health workers who are less skilled. In this paper, we propose a method to predict the advices of doctors from the inquiry, vital data, and the chief complaints of the patients, and to delegate the task to health workers, resulting in eliminating the bottleneck. We also evaluate the accuracy of the prediction of advices from the 931 patients who have taken the doctors' consultancy out of the above experiment. We got the predict accuracy 76.24% with inquiry and vital data, and 82.55% with adding chief complaints data.
User-centric exergaming with fine-grain activity recognition: a dynamic optimization approach BIBAFull-Text 1233-1240
  Bobak Mortazavi; Sunghoon Ivan Lee; Majid Sarrafzadeh
Exergaming, the use of activity, exercise, and information in video games, has been a growing field for the promotion of wellness and for preventing and treating obesity. Realistic exergaming requires movements that are adapted from detailed, fine-grain motions. An appropriate, active exergame requires a user-centric design, allowing for accurate motion recognition as well as a real-time responsiveness, often balancing accuracy with latency. This paper presents a framework for such an exergaming system, specializing on human interaction. This system includes a method for dynamically altering the algorithm to analyze the trade-off between classification accuracy and real-time responsiveness, allowing for a unique, tailored, interactive experience.
A new illness recognition framework using frequent temporal pattern mining BIBAFull-Text 1241-1247
  Zahra Hajihashemi; Mihail Popescu
Living alone in their own residence, older adults are at-risk for late assessment of physical or cognitive changes due to many factors such as their impression that such changes are simply a normal part of aging or their reluctance to admit to a problem. Sensors networks have emerged in the last decade as a possible solution to older adult health monitoring and early illness recognition. Typical early illness recognition approaches are either concentrated on the detection of a given set of activities such as a fall or walks, or on the detection of anomalies such as too many bathroom visits. In this paper we propose a new illness recognition framework, MFA, based on detecting a missing frequent activity from the daily routine. MFA is implemented using a frequent temporal pattern detection algorithm and demonstrated on a pilot dataset collected in TigerPlace, an aging in place community from Columbia, Missouri.
Accuracy-coverage tradeoff of nocturnal vital sign estimation in smart beds BIBAFull-Text 1249-1256
  Daniel Waltisberg; Oliver Amft; Gerhard Tröster
We introduce a novel evaluation approach for smart bed systems that continuously measure vital signs. In particular, we demonstrate that estimation accuracy (or error) and measurement coverage time are key performance metrics, describing a performance tradeoff in practical smart bed systems. Based on a typical smart bed system that uses a force sensor array placed between bed mattress and frame, we evaluate the effect of different signal filtering options to illustrate viable design choices using our accuracy-coverage tradeoff analysis. In a full night recording study with six participants focusing on respiration rate estimation, we show that measurement coverage is an essential metric that should be analysed together with accuracy, when assessing the performance of smart bed systems.
Friend recommendation for weight loss app BIBAFull-Text 1257-1264
  Anming Li; Hareton Leung; Yvette Lui
Although social network had been identified as an effective way to enhance overweight and obesity intervention in literature, the specific measures for integrating social network and weight loss are very limited until now. In this study, we developed a measure for recommending friends for weight loss apps in the context of social networks. In addition to network and profile similarities that have been well documented, our measure provided methods to model weight gain related behaviors and used obtained scores to construct a "behavior network". For evaluation, we proposed two measurements and conducted an experiment on a real dataset complemented with computer generated social graph. Results validated that presented measure is able to recommend friend conducting healthier lifestyle when compared with other friend recommendation measures.
Collaborative opportunistic sensing with mobile phones BIBAFull-Text 1265-1272
  Luis A. Castro; Jesús Favela; Jessica Beltrán; Edgar Chávez; Moisés Perez; Marcela Rodriguez; Eduardo Quintana; René Navarro
Mobile phones include a variety of sensors that can be used to develop context-aware applications and gather data about the user's behavior, including the places he visits, his level of activity and how frequently and with whom he socializes. The collection and analysis of these data has been the focus of recent attention in ubiquitous computing, giving rise to the field known as mobile sensing. In this work, we present a collaborative extension to InCense, a toolkit to facilitate behavioral data gathering from populations of mobile phone users. InCense aims at providing people with little or no technical background with a tool that assists in the rapid design and implementation of mobile phone sensing campaigns. By extending the architecture of InCense to support distributed sensing campaigns we are able to incorporate several strategies aimed at optimizing battery, storage, and bandwidth. These issues represent significant challenges in sensing campaigns that generate considerable amounts of data (i.e., collecting audio) or quickly drain the battery in the device (i.e., GPS), given the limitations of mobile devices. In this work, collaborative sensing is used to decide which mobile phone should capture audio when two or more devices are potentially recording a similar audio signal.
Beyond sensors: reading patients through caregivers and context BIBAFull-Text 1273-1277
  Greg Barish; Eric Elbogen; Patricia Lester; William R. Saltzman
Mobile technology for remotely sensing key health indicators about patients receiving long-term or outpatient care continues to become more affordable and more easily embedded, but there remain certain patient variables, especially mental health and adaptive functioning characteristics, that are difficult to automatically detect or problematic to self-report. To address this problem, we are working on technology that integrates input from caregivers (as well as patients) with enhanced context reporting. We describe how leveraging both methods in an application designed for use by PTSD/mTBI patients and their caregivers can potentially lead to more informed clinical care teams, better family engagement of the care process, and potentially better treatment outcomes.

UPSIDE -- Workshop on Usable Privacy & Security for Wearable and Domestic Ubiquitous Devices

Workshop on usable privacy & security for wearable and domestic ubiquitous devices (UPSIDE) BIBAFull-Text 1279-1282
  Jaeyeon Jung; Tadayoshi Kohno
The primary goal is to bring together researchers and practitioners focusing on usable security and privacy for wearable devices (e.g., Google Glass, Fitbit) and other connected personal and domestic devices (e.g., Withings scale, sleep monitors) to identify and discuss fundamental research challenges and to start addressing them at the workshop. The secondary goal is to bootstrap collaboration amongst researchers from multiple disciplines (ubiquitous computing, security, HCI, systems) as these technologies are inherently multidisciplinary.
Augmented reality: hard problems of law and policy BIBAFull-Text 1283-1288
  Franziska Roesner; Tadayoshi Kohno; Tamara Denning; Ryan Calo; Bryce Clayton Newell
Augmented reality (AR) technologies are poised to enter the commercial mainstream. Using an interdisciplinary research team, we describe our vision of AR and explore the unique and difficult problems AR presents for law and policy -- including around privacy, free speech, discrimination, and safety.
MarkIt: privacy markers for protecting visual secrets BIBAFull-Text 1289-1295
  Nisarg Raval; Landon Cox; Animesh Srivastava; Ashwin Machanavajjhala; Kiron Lebeck
The increasing popularity of wearable devices that continuously capture video, and the prevalence of third-party applications that utilize these feeds have resulted in a new threat to privacy. In many situations, sensitive objects/regions are maliciously (or accidentally) captured in a video frame by third-party applications. However, current solutions do not allow users to specify and enforce fine grained access control over video feeds.
   In this paper, we describe MarkIt, a computer vision based privacy marker framework, that allows users to specify and enforce fine grained access control over video feeds. We present two example privacy marker systems -- PrivateEye and WaveOff. We conclude with a discussion of the computer vision, privacy and systems challenges in building a comprehensive system for fine grained access control over video feeds.
Reactive security: responding to visual stimuli from wearable cameras BIBAFull-Text 1297-1306
  Robert Templeman; Apu Kapadia; Roberto Hoyle; David Crandall
Consumer electronic devices like smartphones increasingly feature arrays of sensors that can 'see', 'hear', and 'feel' the environment around them. While these devices began with primitive capabilities, newer generations of electronics offer sophisticated sensing arrays that collect high-fidelity representations of the physical world. For example, wearable cameras are becoming more prevalent with new consumer lifelogging products including the Narrative Clip, Autographer, and Google Glass. These wearable cameras give computing devices a persistent sense of sight, raising important concerns about protecting people's privacy. At the same time, these devices also provide opportunities for enhancing security, by allowing trusted devices to observe and react to the physical environment surrounding the user and the device. We propose Attribute Based Access Control (ABAC) to mediate access to sensors and their data using attributes of the context and content of sensor information. Attributes extracted from sensor data could be used to trigger policy actions ranging from sharing or not sharing images, to invoking system changes in reaction to outside visual stimuli such as automatically shutting down network interfaces when in the presence of unknown people. While prior work has addressed some specific actions, like preventing potentially private images from being shared based on their location, in this paper we present and advocate for a more general working definition of ABAC that applies to sensors and sensor data. We also present use cases for how this reactive security approach may help protect the privacy and security of users.
Courteous glass BIBAFull-Text 1307-1312
  Jaeyeon Jung; Matthai Philipose
Small and always-on, wearable video cameras disrupt social norms that have been established for traditional hand-held video cameras, which explicitly signal when and which subjects are being recorded to people around the camera-holder. We first discuss privacy-related social cues that people employ when recording other people (as a camera-holder) or when being recorded by others (as a bystander or a subject). We then discuss how low-fidelity sensors such as far-infrared imagers can be used to capture these social cues and to control video cameras accordingly in order to respect the privacy of others. We present a few initial steps toward implementing a fully functioning wearable camera that recognizes social cues related to video privacy and generates signals that can be used by others to adjust their privacy expectations.
To have and have not: variations on secret sharing to model user presence BIBAFull-Text 1313-1320
  Quentin Staórd-Fraser; Graeme Jenkinson; Frank Stajano; Max Spencer; Chris Warrington; Jeunese Payne
We address the problem of locking and unlocking a device, such as a laptop, a phone or a security token, based on the absence or presence of the user. We detect user presence by sensing the proximity of a subset of their possessions, making the process automatic and effortless. As in previous work, a master key unlocks the device and a secret-sharing scheme allows us to reconstruct this master key in the presence of k-out-of-n items. We extend this basic scheme in various directions, e.g. by allowing items to issue a dynamically variable number of shares based on how confident they are that the user is present. The position we argue in this paper is that a multi-dimensional approach to authentication that fuses several contextual inputs, similar to that already adopted by major web sites, can also bring advantages at the local scale.
Exploring the design space for geo-fenced connected devices and services at home BIBAFull-Text 1321-1327
  Geert Vanderhulst; Marc Van den Broeck; Fahim Kawsar
This paper offers a reflection on the design space for a geo-fenced connected device and service (GFS) -- a specification enforcing that a connected device can only be used within a virtual perimeter. Many connected devices are nowadays being accessed through applications running on mobile devices instead of tangible controls. Whilst this ubiquitous access is highly convenient, it is also making connected devices more vulnerable. As such, we reintroduce location-constrained interaction, adapted to connected devices present in a modern home, and explore three design cardinals: (i) spatial granularity, (ii) roles and delegation, and (iii) access control. We report on a qualitative study that explored this design space through a prototype geo-fenced connected lighting system. Our findings suggest that users would like to have geo-fencing for a subset of connected devices, prefer to define geo-fences statically but with different granularities for different devices, and desire access control through location verification and credentials.
My thoughts are not your thoughts BIBAFull-Text 1329-1338
  Benjamin Johnson; Thomas Maillart; John Chuang
Authenticating users of computer systems based on their brainwave signals is now a realistic possibility, made possible by the increasing availability of EEG (electroencephalography) sensors in wireless headsets and wearable devices. This possibility is especially interesting because brainwave-based authentication naturally meets the criteria for two-factor authentication. To pass an authentication test using brainwave signals, a user must have both an inherence factor (his or her brain) and a knowledge factor (a chosen passthought). In this study, we investigate the extent to which both factors are truly necessary. In particular, we address the question of whether an attacker may gain advantage from information about a given target's secret thoughts.

WAHM 2014 -- Workshop on Ubiquitous Technologies for Augmenting the Human Mind

WAHM 2014: workshop on ubiquitous technologies for augmenting the human mind BIBAFull-Text 1339-1345
  Tilman Dingler; Albrecht Schmidt; Kai Kunze; Marc Langheinrich; Nigel Davies; Niels Henze
Ubiquitous sensing will soon allow us to record any moment of our lives. These moments can be restored and used to create radically new ways of aiding human memory. The goal with memory aids is: recalling what matters. This implies retrieving relevant information at the right time to the right extent and in a context-driven way.
   We are looking for visions and research projects that aim to re-think and re-define the notion of memory augmentation. The goal is to combine technological innovations in ubiquitous computing with basic research questions in memory psychology, thereby elevating memory augmentation technologies from a clinical niche application to a mainstream technology and initiating a major change in the way we use technology to remember and to externalize memory.
   This workshop will bring together researchers, designers and practitioners at the intersection of technology and cognitive psychology to discuss elements and viewpoints of forms of e-memory and new forms of memory aids.
Recall your actions!: using wearable activity recognition to augment the human mind BIBAFull-Text 1347-1353
  Manuel Dietrich; Kristof van Laerhoven
In this position paper we will focus on wearable activity recognitions tools in regard to their function of detecting human activities and thus enabling the user to recall everyday experience in a new way. The capabilities of activity recognition to detect, store and present activities to the person who has performed it can not only help to recall the activities but also encourage the user to remember experiences related to the activities. In order to demonstrate this, we present two projects (cases) in which wearable activity recognition is used to support the users' recall capabilities. In the next step, we present a narrative theory of action and mind, which focuses on how humans retrospectively interpret and structure personal experience in their minds, their so called autobiographical memory. Finally, we present some further concepts and distinctions about what it means to memorize and recall personal data.
My good old kodak: understanding the impact of having only 24 pictures to take BIBAFull-Text 1355-1360
  Evangelos Niforatos; Marc Langheinrich; Agon Bexheti
Today's abundance of cheap digital storage in the form of tiny memory cards put literally no bounds on the number of images one can capture with one's digital camera or camera phone during an event. However, studies have shown that taking many pictures may actually make us remember less of a particular event. In this position paper, we propose to re-introduce the paradigm of old film camera in the context of modern smartphones. The purpose is to investigate how users will behave when a significant capture limitation is imposed in a picture-taking context, and in what kind of pictures this will result. Ultimately, we are interested in the effect on memory recall of such a limitation, and describe a potential study setup that will help us explore this question.
Recording events, interactions, and annotations to communicate reasoning in medical situations BIBAFull-Text 1361-1368
  Dawood Al-Masslawi; Rodger Lea; Sidney Fels; Leanne M. Currie
In recent years data collection and communication has become increasingly ubiquitous, to the extent where it is possible to capture and communicate many parts of live experiences. In a novel approach, we propose recording of events, interaction, and annotations in order to access characteristics that communicate the reasoning behind the decision-making of care providers. Recording is done with free-form and implicit data collection, and communication of spatio-chronological characteristics of events, interactions, and annotations are done with augmented interfaces. This enables care providers, who make decisions, to identify what factors have played the most significant role in the decision-making. In the context of chronic care, this research is aiming at, better understanding how to capture and communicate the medical decision-making process. Our preliminary experiments show success in communicating the reasoning processes of the document analysis sessions in a lab environment. We have started to look at how this improves reliability and practice outcomes of the decision-making in real-life medical environment.
Augmenting the home to remember: initial user perceptions BIBAFull-Text 1369-1372
  Ashley Colley; Jonna Häkkilä; Juho Rantakari
In today's world, there are increasingly many things to remember. Often the information is linked to physical world objects -- for instance usage instructions, personal histories, access codes or expiring guarantee dates. Mobile augmented reality (MAR) can provide a design approach, where we can utilize our everyday surroundings and attach information to the items without seemingly modifying their outlook. In this paper, we explore selected MAR scenarios from the augmented human memory point of view. We evaluated these scenarios in a online survey with 19 participants.
Exploring the role of prospective memory in location-based reminders BIBAFull-Text 1373-1380
  Yao Wang; Manuel A. Pérez-Quiñones
Ubiquitous technology has prompted the use of location-based reminders (LBRs) to help people remember to do things while being away from their desks. However LBRs are still not an effective tool for mobile users. Our work explores how to make LBRs better by using theories of memory, in particular prospective memory, and treating the system that captures the LBRs as an external memory aid. With the knowledge from these two pre-existing literature (prospective memory and external memory aids), we set out to explore how to influence the design and the use of LBRs. In this paper, we propose a framework that uses knowledge and principles from cognitive psychology and present how we might be able to improve LBRs. Our ultimate goal is to facilitate human memory recall for prospective tasks.
Wearable digitization of life science experiments BIBAFull-Text 1381-1388
  Philipp M. Scholl; Kristof Van Laerhoven
Experimental work in Life Sciences is done with protective garment to contain harmful agents and to avoid contaminations. This limits the amount of documentation that can be done during experimentation, since pen'n'paper and other equipment is hardly allowed in those environments. Relying on her memory, the scientist has to reconstruct the important details of her experiment later on. Wearable computers, like Google Glass or wrist-worn Smartwatches, can enhance the scientist's ability to record key information while conducting his experiment. Especially the possibility of hands-free, and implicit interaction with the wearable system creates new possibilities for augmenting the scientist's memory.
Déjà vu -- technologies that make new situations look familiar: position paper BIBAFull-Text 1389-1396
  Albrecht Schmidt; Marc Langheinrich; Nigel Davies; Geoff Ward
In this position paper we outline a technology concept for making new situations and encounters more familiar and less threatening. Going to new places, interacting with new people and carrying out new tasks is part of everyday life. New situations create a sense of excitement but in many cases also anxiety based on a fear of the unknown. Our concept uses the metaphor of a pin board as peripheral display to automatically provide advance information about potential future experiences. By providing references to and information about future events and situations we aim at creating a "feeling of having already experienced the present situation" (term Déjà vu as defined in the Oxford Dictionary) once people are in a new situation. This draws on the positive definition of the concept of déjà vu. In this paper we outline our idea and use scenarios illustrate its potential. We assess different ways the concept can be realized and chart potential technology for content creation and for presentation. We also present a discussion of the impact on human memory and how this changes experiences.
Lifelogging for 'observer' view memories: an infrastructure approach BIBAFull-Text 1397-1404
  Sarah Clinch; Paul Metzger; Nigel Davies
Lifelogging has much to offer human memory. Traditional lifelogging techniques use wearable cameras to capture a first-person or 'field' view. We propose an alternative or complementary approach in which fixed infrastructure cameras provide a third-person or 'observer' view of daily events. In this paper we identify key advantages and challenges for a fixed infrastructure approach to lifelogging.
Position paper: brain teasers -- toward wearable computing that engages our mind BIBAFull-Text 1405-1408
  Shoya Ishimaru; Kai Kunze; Koichi Kise; Masahiko Inami
The emerging field of cognitive activity recognition -- real life tracking of mental states -- can give us new possibilities to enhance our minds.
   In this paper, we outline the use of wearable computing to engage the user's mind. We argue that the more personal technology becomes the more it should also adopt to the user's long term goals improving mental fitness. We present a the concept of computing to engage our minds, discuss some enabling technologies as well as challenges and opportunities.