HCI Bibliography Home | HCI Conferences | AmI Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
AmI Tables of Contents: 101112131415

Proceedings of the 2014 European Conference on Ambient Intelligence

Fullname:AmI 2014: European Conference on Ambient Intelligence, Revised Selected Papers
Editors:Emile Aarts; Boris de Ruyter; Panos Markopoulos; Evert van Loenen; Reiner Wichert; Ben Schouten; Jacques Terken; Rob Van Kranenburg; Elke Den Ouden; Gregory O'Hare
Location:Eindhoven, Netherlands
Dates:2014-Nov-11 to 2014-Nov-13
Publisher:Springer International Publishing
Series:Lecture Notes in Computer Science
Standard No:DOI: 10.1007/978-3-319-14112-1 hcibib: AmI14; ISBN: 978-3-319-14111-4 (print), 978-3-319-14112-1 (online)
Links:Online Proceedings | Conference Website
Analyzing Sounds of Home Environment for Device Recognition BIBAKFull-Text 1-16
  Svilen Dimitrov; Jochen Britz; Boris Brandherm; Jochen Frey
Home environments are one of the subjects of study regarding ambient intelligent systems for various purposes, including development of assistance systems for the elderly and energy consumption optimization. Sensing the environmental state via different sensors is the first and crucial component of every ambient intelligent system. In this work we investigate the use of environmental sounds for touch-free audio-based device recognition in a home environment. For this purpose, we analyzed sound characteristics of typical home appliances using different processing techniques. We are using the acquired knowledge to develop a flexible set of features, which can be set manually or determined automatically. To classify the device-specific acoustic fingerprints -- consisting of a significant subset of our features -- we use established supervised learning techniques, whereby we optimized the straightforward ones. After building a recognition basis for the recognition of fixed length sound buffers on demand, we implemented a live recognition mode for real-time environment monitoring, providing runtime setup adjustments. We then extended our work with the recognition of untrained, simultaneously working, known devices by mixing their records, utilizing semi-supervised learning. We then anticipated promising results in our evaluation in various aspects, including recognition rate, performance for the different combinations of features, as well as to study the reliability of an automatic mixing of trained data.
Keywords: Ambient Intelligence; Smart Home; Sound-based Device Recognition
SALT: Source-Agnostic Localization Technique Based on Context Data from Binary Sensor Networks BIBAKFull-Text 17-32
  Filippo Palumbo; Paolo Barsocchi
Localization is a key component for many AAL systems, since the user position can be used for detecting user's activities and activating devices. While for outdoor scenarios Global Positioning System (GPS) constitutes a reliable and easily available technology, in indoor scenarios, in particular in real homes, GPS is largely unavailable. For this reason, several systems have been proposed for indoor localization. Recently, several algorithms fuse information coming from different sources in order to improve the overall accuracy in monitoring user activities. In this paper we propose a Source-Agnostic Localization Technique, called SALT, that fuses the information (coordinates) provided by a localization system with the information coming from the binary sensor network deployed within the environment. In order to evaluate the proposed framework, we tested our solution by using a previous developed heterogeneous localization systems presented at the international competition EvAAL 2013.
Keywords: Indoor Localization; Binary Sensor Network; Sensor Fusion; Ambient Assisted Living
Detecting Walking in Synchrony Through Smartphone Accelerometer and Wi-Fi Traces BIBAKFull-Text 33-46
  Enrique Garcia-Ceja; Venet Osmani; Alban Maxhuni; Oscar Mayora
Social interactions play an important role in the overall well-being. Current practice of monitoring social interactions through questionnaires and surveys is inadequate due to recall bias, memory dependence and high end-user effort. However, sensing capabilities of smart-phones can play a significant role in automatic detection of social interactions. In this paper, we describe our method of detecting interactions between people, specifically focusing on interactions that occur in synchrony, such as walking. Walking together between subjects is an important aspect of social activity and thus can be used to provide a better insight into social interaction patterns. For this work, we rely on sampling smartphone accelerometer and Wi-Fi sensors only. We analyse Wi-Fi and accelerometer data separately and combine them to detect walking in synchrony. The results show that from seven days of monitoring using seven subjects in real-life setting, we achieve 99% accuracy, 77.2% precision and 90.2% recall detection rates when combining both modalities.
Keywords: Social interactions; Accelerometer; Wi-fi; Ambient intelligence; Health and wellbeing
SIMDOMO: A Tool for Long-term Simulations of Ambient-Assisted Living BIBAFull-Text 47-50
  Massimo Zancanaro; Michele Marchesoni; Giampaolo Armellin
In this paper, we introduce SIMDOMO, a tool to simulate human activities in virtual sensorized houses. The purpose of the tool is to facilitate the generation of large amount of data for the design and evaluation of ambient-assisted living applications. Specifically, for experimenting with visualizations of home activities over long periods (years or decades); for training and testing algorithms to recognize changes of behaviors or anomalies that would be difficult to observe in real settings or in lab; testing infrastructures for robustness and scaling; as well as, for assessing business models. SIMDOMO allows defining "human behaviors" in terms of temporally anchored activities: these behaviors can then be automatically replicated introducing small random variations to make the data more varied. The time of the simulation can be accelerated by several factors allowing the generation of decades of simulated life in few hours. We believe that this tool addresses an urgent need in the field of Ambient-Assisted Living.
Recognition of Bed Postures Using Mutual Capacitance Sensing BIBAKFull-Text 51-66
  Silvia Rus; Tobias Grosse-Puppendahl; Arjan Kuijper
In recent years, mutual capacitive sensing made significant advances in the field of gathering implicit contextual data. These systems find broad usage in pervasive activity-recognition systems, installed stationary or made portable. In the domain of context recognition new ways of interaction with the environment opened up since conductive objects can be detected under certain conditions at distances up to 50 cm.
   This paper investigates an approach to recognize bed postures using mutual capacitance sensing. The overall goal is to develop a technological concept that can be applied to recognize bed postures of patients in elderly homes. The use of this contextual data may lead to many desired benefits in elderly care e.g. the better prevention of decubitus ulcer, a condition caused by prolonged pressure on the skin resulting in injuries to skin and underlying tissues. For this, we propose a low-cost grid of crossed wires of 48 measurement points placed between the mattress and the bed sheet. The experimental results analyze a set of five lying positions. We achieved for all tested individuals an accuracy of 80.76% and for several individuals of the same bodysize an accuracy of 93.8%.
Keywords: Activity recognition; Capacitive sensing; Ambient assisted living
SoPresent: An Awareness System for Connecting Remote Households BIBAFull-Text 67-79
  Pavan Dadlani; Tommaso Gritti; Caifeng Shan; Boris de Ruyter; Panos Markopoulos
Families and friends are often separated by distance making it difficult for them to stay in touch with each other. A prolific number of popular communication technologies and social are testimony how important informal and social communication with friends and family can be, and how this can drive industrial and business developments.
Multi-tenancy Aware Ambient Assisted Living Platforms in the Cloud BIBAKFull-Text 80-95
  Carsten Stocklöw; Alejandro M. Medrano Gil; Alvaro Fides Valero; Michele Girolami; Stefano Lenzi
Over the last years, Ambient Assisted Living (AAL) technologies have seen a remarkable grow up. Although this field has been researched for many years and different projects have investigated and proposed AAL platforms with a rich set of functionality, the current market situation still favors isolated solutions. A possible reason is that those platforms are too complex to be easily setup and maintained. Also, resource sharing is possible between services, but not between platforms. A promising alternative is provided by the cloud computing approach which integrates common services in a shared way.
   Thus, we propose to use an AAL platform as Platform-as-a-Service in the cloud to offer all functionalities of AAL platforms to services in the cloud while being able to connect to platforms running in each home. We discuss different aspects of this approach and propose a simple verification scenario. An exemplary adoption is discussed for the platform universAAL.
Keywords: AAL Platform; Cloud Computing; Smart Environments
Monitoring Patients' Lifestyle with a Smartphone and Other Devices Placed Freely on the Body BIBAKFull-Text 96-99
  Mitja Luštrek; Bozidara Cvetkovic; Vito Janko
Monitoring patients' lifestyle can result in an improved treatment, but it is often not critical enough to warrant dedicated sensors. However, many consumer devices, such as smartphones, contain inertial sensors, which can be used for such monitoring. We propose an approach to activity recognition and human energy-expenditure estimation for diabetes patients that uses a phone and an accelerometer-equipped heart-rate monitor. The approach detects which of the two devices is carried or worn, the orientation of the phone and its location on the body, and adapts the monitoring accordingly. By using this approach, the accuracy of the activity recognition was increased by up to 20 percentage points compared to disregarding the orientation and location of the phone, while the error of the energy-expenditure estimation was decreased.
Keywords: Activity recognition; Energy expenditure estimation; Smartphone; Heart-rate monitor; Accelerometer; Location; Orientation; Diabetes
Tell Me What to Eat -- Design and Evaluation of a Mobile Companion Helping Children and Their Parents to Plan Nutrition Intake BIBAKFull-Text 100-113
  Runhua Xu; Irena Pletikosa Cvijikj; Tobias Kowatsch; Florian Michahelles; Dirk Büchter; Björn Brogle; Anneco Dintheer; Dagmar I'Allemand; Wolfgang Maass
Obesity is a global issue and has a direct impact on the public and private healthcare system. In this paper we describe the design and evaluation of a novel mobile health application that supports obese children and their parents to improve their nutrition intake. First results from quantitative app usage logs, questionnaires and interviews indicate that the mobile health app provides relevant information to attain a balanced nutrition. A discussion of the results and an outline of future work conclude this paper.
Keywords: Children; Parents; Overweight; Obesity; Mobile App; Healthcare
The Impact of the Environment on the Experience of Hospitalized Stroke Patients -- An Exploratory Study BIBAKFull-Text 114-124
  Elke Daemen; Evert van Loenen; Roel Cuppen
The aim of this study is to understand neurology patients, family and caregivers experiences of in-patient care environments and to investigate the aspects of the healing process that can be supported by the environment. Our goal is to identify the role the environment plays during the process of being treated for and recovering from a stroke. The stroke patient's description of experiences during hospitalization will help researchers, medical professionals and architects in adjusting the environment according to their specific needs. A set of research methods was used to capture the experience, changing the role of researcher as an observer to a participatory approach, integrating the caregivers as creators of the research data [1], [2]. These methods included: shadowing, observation and interviewing, allowing nurses to describe their experiences and to obtain a voice in decision making. We built insights from healing environment literature combined with own field studies. Specific environmental needs identified include: dosing stimulus load, having social support, having access to single patient rooms, balancing clinical and personal environments, having a clear structure of the day, undisturbed sleeping and the need for information.
Keywords: Healing environments; Stroke; Contextual research
An Investigation into Perception-Altering Lighting Concepts for Supporting Game Designers in Setting Certain Atmospheres Within a Videogame Environment BIBAKFull-Text 125-139
  Hendrik Johannes Nieuwdorp; Martin Beresford; Vassilis-Javed Khan
Lighting in video games is used to set moods and atmosphere, or can serve as a gameplay tool. This paper examines the effects lighting concepts can have on a virtual game environment on the players' navigation within the game. Previously known lighting concepts were tested in a virtual environment to determine if they have a similar effect on the perception of the presented virtual space as they do in real life, as well as the effect they have on the navigational behavior of players. In a game-experiment with 50 male participants we show that the previously known lighting concepts apply to the virtual environment in a similar manner as they do in real life, although the effects on the navigational behavior of the participants remain inconclusive.
Keywords: Virtual lighting; Perception of atmosphere; Game design
Ambient Influence for Promoting Balanced Participation in Group Brainstorming BIBAKFull-Text 140-144
  Gianluca Schiavo; Eleonora Mencarini; Alessandro Cappelletti; Oliviero Stock; Massimo Zancanaro
In this paper we present an ambient persuasive system designed to promote balanced participation during group brainstorming. The system gets information from participants' attention behavior during a brainstorming session and provides visual messages for facilitating balanced participation. In the present study, we investigated the effect that using subtle visual animations and explaining to the users the meaning of the subtle message had on influencing group behavior. Objective measures from data acquired through depth sensors, and subjective responses to questionnaires on usefulness and perceived influence of the technology intervention were collected. The results suggest that the ambient system is better accepted when the persuasive message is expressed in a subtle manner and an explanation of the system's persuasive strategy is provided.
Keywords: Ambient Influence; Peripheral Displays; Ambient Persuasive Systems; Shared Displays; Group Conversation
Steering Gameplay Behavior in the Interactive Tag Playground BIBAFull-Text 145-157
  Robby van Delden; Alejandro Moreno; Ronald Poppe; Dennis Reidsma; Dirk Heylen
This paper deals with steering player behavior in the Interactive Tag Playground (ITP). The ITP, an ambient environment instrumented with contact-free sensor technology and ambient display capabilities, enhances the traditional game of tag by determining when a valid tag has been made and visualising the current tagger. We present three modifications of the ITP that aim to steer the gameplay actions of the players. The modifications are intended to influence who will be chased next by the tagger; to make good players easier to tag and less skilled players harder to tag; and to influence the locations visited by the players. We report on a user study showing that two of the three modifications have a significant effect on the behavior of players in the ITP and discuss opportunities for future research that follow from this study.
Impact of Blinds Usage on Energy Consumption: Automatic Versus Manual Control BIBAKFull-Text 158-173
  Bernt Meerbeek; Thijs van Druenen; Mariëlle Aarts; Evert van Loenen; Emile Aarts
This paper reports a study on the impact of different usage patterns of an automated blinds system on the energy consumption for heating and cooling in a Dutch office building. A five-month observational field study in 40 offices resulted into a dataset on the blinds usage of four types of blind users. This data was used to simulate the effect of the blinds usage on the energy consumption for heating and cooling. The results of the field study show that a majority of the building occupants switched off the automatic mode of the blinds system permanently. The simulation results indicate that this significantly impacts the energy consumption in the building. The total daily average energy consumption for heating and cooling was significantly lower for occupants using the automatic mode than for the three groups of manual users (871W/day versus 2573W/day; T=-5.98, p=0.000).
Keywords: Blinds; Daylight; User control; Ambient intelligence; Energy
Discrete Control for Smart Environments Through a Generic Finite-State-Models-Based Infrastructure BIBAKFull-Text 174-190
  Mengxuan Zhao; Gilles Privat; Eric Rutten; Hassane Alla
Drawing requirements and models from reactive and real-time systems, we propose a self-configurable data mediation infrastructure for Smart Environments and the Internet of Things, showing how it can be used to effect discrete control in smart home environments by mediating and adapting generic rules through finite-state-machine models drawn from a domain ontology, representing observable & controllable "things" and space entities in this infrastructure.
Keywords: System architecture; Middleware; Domain ontologies; Discrete-event control; Finite-state automata; Reactive systems; Control theory
Learning and Recognizing Routines and Activities in SOFiA BIBAFull-Text 191-204
  Berardina De Carolis; Stefano Ferilli; Giulio Mallardi
In order to promote an effective and personalized interaction, smart environments should be endowed with the capability of understanding what the user is doing. To this aim we developed a system called WoMan that, using a process mining approach, is able to incrementally learn user's activities and daily routines as workflow models. In order to test its efficacy in a real-world setting, we set up a smart office environment, SOFiA, equipped with a sensor network based on Arduino. Then we collected an annotated dataset of 45 days and from this dataset we learned the workflow models of the user daily routines and of the activities performed in the office. Then we performed some experiments that show how our approach perform in learning and recognizing activities and routines. In particular, we achieve in average the accuracy of 82% for tasks and the accuracy of 98% for the transitions among tasks. Moreover we test the real-time performance of the approach with sensor data coming from the SOFiA sensors and the system started to make a correct prediction since the fourth execution in 82% of the cases.
On-line Context Aware Physical Activity Recognition from the Accelerometer and Audio Sensors of Smartphones BIBAKFull-Text 205-220
  David Blachon; Doruk Coskun; François Portet
Activity Recognition (AR) from smartphone sensors has become a hot topic in the mobile computing domain since it can provide services directly to the user (health monitoring, fitness, context-awareness) as well as for third party applications and social network (performance sharing, profiling). Most of the research effort has been focused on direct recognition from accelerometer sensors and few studies have integrated the audio channel in their model despite the fact that it is a sensor that is always available on all kinds of smartphones. In this study, we show that audio features bring an important performance improvement over an accelerometer based approach. Moreover, the study demonstrates the interest of considering the smartphone location for on-line context-aware AR and the prediction power of audio features for this task. Finally, another contribution of the study is the collected corpus that is made available to the community for AR recognition from audio and accelerometer sensors.
Keywords: Data Science; Sensing and Reasoning Technology
Real-Time Event Detection for Energy Data Streams BIBAKFull-Text 221-225
  Aqeel H. Kazmi; Michael J. O'Grady; Gregory M. P. O'Hare
Appliance specific energy monitoring is perceived as a prerequisite for reducing energy usage in households. A number of approaches exist, however, Non-Intrusive appliance Load Monitoring is considered to be the most promising and scalable method. This method can also facilitate Ambient Intelligent applications with the hope activity recognition of the resident is of paramount importance. In this paper, we propose an event detection algorithm to support non-intrusive energy monitoring. A performance evaluation of this algorithm has been carried out on a reference dataset.
Keywords: Non-Intrusive Appliance Load Monitoring; Event Detection
Developing a Face Monitoring Robot for a Desk Worker BIBAKFull-Text 226-241
  Ryosuke Kondo; Yutaka Deguchi; Einoshin Suzuki
We have developed an autonomous mobile robot which monitors the face of a desk worker. The robot uses three kinds of information observed with its Kinect to search for the desk worker and adjusts its position for monitoring. The monitoring is based on incremental clustering of the faces. Our experiments revealed that not only Animation Units (AUs) features, which represent deviations from the neutral face, but also the pitch angle of the face normalized in a new way are necessary for a valid clustering under specific conditions. Our robot lost sight of a desk worker only once in experiments for 8 persons for about 50 minutes. The resulting clusters correspond to "yawning", "smiling", and "reading" for a half of the desk workers with high NMI (normalized mutual information), which is an evaluation measure often used in clustering.
Keywords: Human monitoring robot; Clustering; Face tracking
A Benchmarking Model for Sensors in Smart Environments BIBAKFull-Text 242-257
  Andreas Braun; Reiner Wichert; Arjan Kuijper; Dieter W. Fellner
In smart environments, developers can choose from a large variety of sensors supporting their use case that have specific advantages or disadvantages. In this work we present a benchmarking model that allows estimating the utility of a sensor technology for a use case by calculating a single score, based on a weighting factor for applications and a set of sensor features. This set takes into account the complexity of smart environment systems that are comprised of multiple subsystems and applied in non-static environments. We show how the model can be used to find a suitable sensor for a use case and the inverse option to find suitable use cases for a given set of sensors. Additionally, extensions are presented that normalize differently rated systems and compensate for central tendency bias. The model is verified by estimating technology popularity using a frequency analysis of associated search terms in two scientific databases.
Keywords: Benchmark; Smart environments; Modeling; Sensor technology
Multi-view Onboard Clustering of Skeleton Data for Fall Risk Discovery BIBAKFull-Text 258-273
  Daisuke Takayama; Yutaka Deguchi; Shigeru Takano; Vasile-Marian Scuturici; Jean-Marc Petit; Einoshin Suzuki
We propose a multi-view onboard clustering of skeleton data for fall risk discovery. Clustering by an autonomous mobile robot opens the possibility for monitoring older adults from the most appropriate positions, respecting their privacies, and adapting to various changes. Since the data that the robot observes is a data stream and communication network can be unreliable, the clustering method in this case should be onboard. Motivated by the rapid increase of older adults in number and the severe outcomes of their falls, we adopt Kinect equipped robots and focus on gait skeleton analysis for fall risk discovery. Our key contributions are new between-skeleton distance measures for risk discovery and two series of experiments with our onboard clustering. The experiments revealed several key findings for the method and the application as well as interesting outcomes such as clusters which consist of unexpected risky postures.
Keywords: Skeleton Clustering; Service-oriented DBMS; Human Monitoring; Mobile Robots
WATCHiT: A Modular and Wearable Tool for Data Collection in Crisis Management and Training BIBAKFull-Text 274-289
  Simone Mora; Monica Divitini
We present WATCHiT, a prototype of sensor-augmented wristband computer for data collection during crisis response work. During crises, information about the environment (e.g. to map the territory) and the rescuers (e.g. for assessment of workers' condition) offers help to support coordination of work, post-emergency debriefing and to build realistic training scenarios. Being each crisis nearly unique it is important to collect data from every single occurrence, yet it is difficult to foresee the type of data and context information that is relevant to capture. WATCHiT features: (1) wearable sensors, (2) easy customization of the type of information sensed, including both quantitative and qualitative data; (3) an intuitive, distraction-free user interface for controlling the data capturing procedure. Our design process has been driven by user studies during training events characterized by a high degree of realism; our prototype has been successfully evaluated with experts against technology acceptance.
Keywords: Wearable computers; Crisis response; Crisis training; Sensor data; Tangible interface
Truck Drivers as Stakeholders in Cooperative Driving BIBAKFull-Text 290-298
  Freek de Bruijn; Jacques Terken
Cooperative driving for trucks has been claimed to bring substantial benefits for society and fleet owners because of better throughput and reduced fuel consumption, but benefits for truck drivers are questionable. While most work on cooperative driving focuses on the technology, the current paper focuses on the consequences for drivers and how to deal with those. Two concepts are proposed and evaluated. One concept supports drivers in coordinating cooperative driving with other truck drivers to locate, join, and quit platoons. The other concept provides drivers of following trucks with situation awareness by means of a "see through" system displaying camera images from the lead vehicle. A user evaluation in a driving simulator confirms that cooperative driving may have largely negative benefits for truck drivers, and that concepts such as the ones described in this paper may help to improve the cooperative driving situation for truck drivers.
Keywords: Cooperative driving; Platooning; Human Factors; User Experience
Hands-on-the-Wheel: Exploring the Design Space on the Back Side of a Steering Wheel BIBAKFull-Text 299-314
  Alexander Meschtscherjakov; David Wilfinger; Martin Murer; Sebastian Osswald; Manfred Tscheligi
The phrase "eyes on the road and hands on the wheel" has gained acceptance as a maxim for safe driving. Many driver interfaces do not adhere to this simple rule. We explore interaction possibilities which follow this principle by introducing the Back-of-the-Steering-Wheel (BotSW) as an automotive input design space. Since the steering wheel is in the peripheral vision of the driver when looking ahead this space can be seen as an ambient interaction space for the driver. In order to explore this design space, we follow a research through design approach. We present the development of three "explorations" which we consider as evolutionary prototypes built to investigate the BotSW design space: two-sliders, six-buttons, and braille-keyer. Based on our experiences, we discuss the BotSW design space systematically by identifying its interaction design related properties: ring shape, rotating, not visible, supporting bimanual and multi fingers interaction. The intention of our work is to show possibilities of interaction at the back of the steering wheel and inspire designers to envision novel solutions to interact with the car while leaving the hands on the wheel.
Keywords: Automotive user interfaces; Back-of-device interaction; Design space; Exploration; Steering wheel
Driver-to-Driver Communication on the Highway: What Drivers Want BIBAKFull-Text 315-327
  Chao Wang; Jing Gu; Jacques Terken; Jun Hu
Drivers need to coordinate with each other to share the road infrastructure. The social relationship between drivers also influences the driving behavior. With everywhere available connectivity and the broad penetration of social network services, the relationship between drivers on the road may gain more transparency, enabling social information to pass through the steel shell of the cars and giving opportunities to reduce anonymity and strengthen empathy. In this paper, we investigate what sort of social communication drivers consider useful for a highway scenario and which factors influence their willingness to receive or send the information concerned. We utilized the "CoConstructing Stories" method to investigate 30 novel scenarios with 22 participants. We find that driver-to-driver communication relating to Safety and Efficiency is well accepted. In order to account for the acceptance of driver-to-driver communication concerning the Social relation between drivers and their Identity, additional information is required. Some relevant factors are considered in the discussion, and steps for future research are suggested.
Keywords: Social car; Connected car; Automotive User Interfaces; Interactive Vehicular Applications; Social Computing
Privacy Classification for Ambient Intelligence BIBAFull-Text 328-343
  Jasper van de Ven; Frank Dylla
In the field of ambient intelligence (AmI) privacy is recognized as one of the key factors regarding the acceptance of systems. However, this topic is mostly neglected or only addressed in a simplified form. Our approach is to understand privacy as a service, i.e., the AmI restricts its own knowledge rather than only hiding it. Through providing related vocabulary and a basic theory of privacy, we introduce a categorization of privacy related functionality and a classification of privacy affordances an AmI can provide. By investigating and evaluating small prototypical systems we propose a measure to compare different systems with respect to the balance between support provided and privacy.