HCI Bibliography Home | HCI Conferences | PETRA Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
PETRA Tables of Contents: 0809101112131415

Proceedings of the 2012 International Conference on PErvasive Technologies Related to Assistive Environments

Fullname:Proceedings of the 5th International Conference on PErvasive Technologies Related to Assistive Environments
Editors:Fillia Makedon
Location:Heraklion, Crete, Greece
Dates:2012-Jun-06 to 2012-Jun-09
Standard No:ISBN: 978-1-4503-1300-1; ACM DL: Table of Contents; hcibib: PETRA12
Links:Conference Website | Conference Series Home
Summary:The PETRA Conference has as its mission to bring together diverse disciplines and experts in different areas of computer technology in order to address human-centric challenges and improve the quality of life. Whether it is to improve the potential of a person in the work environment with better training tools, or help the elderly age in place with unobtrusive technologies, fundamentally new computer science and engineering approaches are needed.
    People's living environments are particularly important in an increasingly crowded and complex world where the need for inclusiveness and connectivity with the rest of the world is key. From smart energy recommendation tools, to game-driven therapy for cognitive or motor disabilities such as cerebral palsy, PETRA will introduce the participant to exciting and transformational new applications of computer technology.
  1. Signal and image processing for ambient intelligence and pervasive computing
  2. Tools, infrastructures, architectures and techniques for deploying pervasive applications in assistive environments
  3. Cognitive systems and pattern analysis tools for assistive environments
  4. Pervasive systems for the aging society
  5. Robotic devices, HCI and multimodal interfaces I
  6. Robotic devices, HCI and multimodal interfaces II
  7. Data modeling and information management for pervasive assistive environments
  8. Smart homes and intelligent environments
  9. Discovery and ongoing work "DISCO"
  10. Poster session
  11. Workshop on affect and behaviour related assistance in support for the elderly
  12. Workshop on social networks and sensor networks in assistive environments
  13. Workshop on robotics in assistive environments

Signal and image processing for ambient intelligence and pervasive computing

Near real-time human silhouette and movement detection in indoor environments using fixed cameras BIBAFull-Text 1
  A. Christodoulidis; K. K. Delibasis; I. Maglogiannis
The automated human behavior modeling is highly desired in the context of an assistive environment. In this paper, we describe a software video processing and analysis system to assist the near real time detection of human activity. The video data are acquired indoors from fixed cameras in the living environment. The proposed system uses image-processing techniques to segment the human figure from the background, suppress the appearance of its shadow and detect the path and velocity of its motion. Detail performance measurements of the proposed algorithm are given in terms of execution time. Initial results are presented for a small number of video sequences.
Audio-visual speech recognition using depth information from the Kinect in noisy video conditions BIBAFull-Text 2
  Georgios Galatas; Gerasimos Potamianos; Fillia Makedon
In this paper we build on our recent work, where we successfully incorporated facial depth data of a speaker captured by the Microsoft Kinect device, as a third data stream in an audio-visual automatic speech recognizer. In particular, we focus our interest on whether the depth stream provides sufficient speech information that can improve system robustness to noisy audio-visual conditions, thus studying system operation beyond the traditional scenarios, where noise is applied to the audio signal alone. For this purpose, we consider four realistic visual modality degradations at various noise levels, and we conduct small-vocabulary recognition experiments on an appropriate, previously collected, audiovisual database. Our results demonstrate improved system performance due to the depth modality, as well as considerable accuracy increase, when using both the visual and depth modalities over audio only speech recognition.
Privacy preserving neural networks in iris signature feature extraction BIBAFull-Text 3
  Egidijus Paliulis; Manolis Maragoudakis; Alexandros Panteli
The iris signature is used in "Iridology", for person identification and calculation of torsional eye movements in video-oculography. Iris data are expensive and difficult to be acquired and their amount plays an important role in recognition accuracy when data mining methods are used. However, privacy issues often restrict open exchange of data between stakeholders. The present article presents a privacy-preserving neural network protocol, for horizontally-partitioned datasets, i.e. datasets that share common attributes but contain different records at each party. The proposed protocol assumes a malicious user model and does not use homomorphic cryptographic methods which are inherently only suited for a semi-trusted user environment. The performance analysis shows that the communication overhead is low enough to warrant its use while the computational complexity is identical in most cases with the centralized computation scenario (e.g. a trusted third party). The accuracy of the output model is only marginally subpar to a centralized computation on the union of all datasets. Another important aim of this work is to search proper choice of the part of the iris signature for person identification and calculating torsional eye movements. Also, estimate changes of the iris contour, sections of the iris and elements of the iris signature. The mathematical model of formation of the iris image on the plane was compared with the real image of the iris.

Tools, infrastructures, architectures and techniques for deploying pervasive applications in assistive environments

Role and quality of communication in collaborative training for Multiple Sclerosis patients BIBAFull-Text 4
  Anastasiia Beznosyk; Peter Quax; Karin Coninx; Wim Lamotte
Social support provided by family and friends plays an important role in the rehabilitation of people suffering from various types of disabilities, in particular, Multiple Sclerosis (MS). Unfortunately due to the necessity of spending a substantial amount of time in rehabilitation centers, most MS patients experience lower social interaction with their immediate surroundings. To overcome this, we utilize a collaborative game played over the Internet that facilitates interaction during absence. While staying at the rehabilitation center for intense and necessary training programs, patients can play this game with relatives or friends communicating through audio and/or video channels.
   In the research presented in this paper, we firstly investigate how patients perceived communication with a remote person. Secondly, the influence of network quality (i.c. presence of packet loss) on this perception was analyzed. Results show that patients prefer to see their game partners while interacting remotely. When exposed to varying levels of multimedia quality, they point out that the quality of audio is relatively more important than the quality of video.
A survey of query-by-humming similarity methods BIBAFull-Text 5
  Alexios Kotsifakos; Panagiotis Papapetrou; Jaakko Hollmén; Dimitrios Gunopulos; Vassilis Athitsos
Performing similarity search in large databases is a problem of particular interest in many communities, such as music, database, and data mining. Although several solutions have been proposed in the literature that perform well in many application domains, there is no best method to solve this kind of problem in a Query-By-Humming (QBH) application. In QBH the goal is to find the song(s) most similar to a hummed query in an efficient manner. In this paper, we focus on providing a brief overview of the representations to encode music pieces, and also on the methods that have been proposed for QBH or other similarly defined problems.
Finding representative objects using link analysis ranking BIBAFull-Text 6
  Panagiotis Papapetrou; Tatiana Chistiakova; Jaakko Hollmén; Vana Kalogeraki; Dimitrios Gunopulos
Link analysis ranking methods are widely used for summarizing the connectivity structure of large networks. We explore a weighted version of two common link analysis ranking algorithms, PageRank and HITS, and study their applicability to assistive environment data. Based on these methods, we propose a novel approach for identifying representative objects in large datasets, given their similarity matrix. The novelty of our approach is that it takes into account both the pair-wise similarities between the objects, as well as the origin and "evolution path" of these similarities within the dataset. The key step of our method is to define a complete graph, where each object is represented by a node and each edge in the graph is given a weight equal to the pairwise similarity value of the two adjacent nodes. Nodes with high ranking scores correspond to representative objects. Our experimental evaluation was performed on three data domains: American sign language, sensor data, and medical data.
On-demand security service BIBAFull-Text 7
  Jiafeng Zhu; Jingji Zheng; Xinwen Zhang; Zhengyi Le; Min Luo
Traditional secure channels use a secure session key to encrypt communication messages within a time limit. For website cases, browsers can not initiate a request for a secure session, and sometimes it is not necessary to encrypt the entire session. Our On-Demand Security Service (ODSS) addresses these problems by designing an "in session" protocol on top of internet and wireless communication protocol. It could be used in gaming, internet browsing, and messaging environments. A service provider opens ODSS as a service, and offers users a choice of applying protection when needed. This approach provides user-defined security and also improves communication efficiency.
Plantar pressure sensing using loop antenna sensors BIBAFull-Text 8
  Irshad Mohammad; Haiying Huang
Foot complications associated with diabetes might lead to foot ulcers. Foot ulcers if neglected can cause foot infection and subsequent amputation. Ulceration is believed to be contributed by stresses acting over the foot. Therefore, measurement of plantar pressures is important in diagnosis and foot ulcer evaluation. However, current plantar pressure measurement systems are either expensive or have a low resolution. This paper investigates the feasibility of employing a loop antenna sensor printed on a dielectric substrate (Rogers 4350B) to detect plantar pressure distribution. This flexible, low profile, inexpensive, high resolution sensor can be easily embedded in shoes to measure the plantar pressures in real-time. The most important advantages of the antenna sensor are they can be multiplexed and wirelessly interrogated. The principal of operation, sensor fabrication, experimental setup, experimental procedure and results are presented. Preliminary results show that the loop antenna sensors have a very low hysteresis loss and respond to pressure with good repeatability. Finally, a technique to wirelessly interrogate the loop antenna sensor is proposed.

Cognitive systems and pattern analysis tools for assistive environments

Assistive systems in production environments: exploring motion recognition and gamification BIBAFull-Text 9
  Oliver Korn; Albrecht Schmidt; Thomas Hörz
In this paper we share our experiences with the design and use of motion recognition for assistive systems in production environments (ASiPE) and introduce a concept for gamification. While simple manual production tasks have been widely replaced by automation, more complex assembly tasks still use manual production. We expect that the need for manual assembly tasks will grow as we move towards more individualized products. In developed countries impaired workers and people with disabilities often work on simple manual production tasks. To empower these people to carry out more challenging and rewarding tasks we investigate assistive systems, and in particular systems using motion recognition to guide the assembly task. We argue that gamification in the design of assistive systems for production has the potential to improve both the workers' motivation and the quality of the work and the products. We outline how user interfaces for assistive systems in manual production can be designed to include gamification aspects. Our contribution is three-fold and materializes in i) reasons for the growing need for assistive systems in production, ii) a description of how motion recognition can be used in assistive systems for production and which obstacles occur and iii) a perspective on how gamification can be integrated into assistive systems.
Developing a mobile recommender system BIBAFull-Text 10
  Nikos Nakas; Vana Kalogeraki
The proliferation of powerful, programmable mobile devices along with the availability of wide-area connectivity has created opportunities to sense and share location, motion, acoustic and visual data in a network of mobile devices. In this paper we present a mobile recommender system that exploits the individual data collected by multiple users on their mobile phones. Our aim is to exploit the potential of the computational capabilities of modern mobile devices to provide personalized and better services to the end users. The system has been developed on a MapReduce framework that simplifies the programmability and deployment of the applications on the mobile devices and implements distributed clustering over user rating data. Experimental results over a testbed of Nokia smartphones illustrate the performance and effectiveness of our approach.
Needs & motivations of senior travelers for AAL BIBAFull-Text 11
  Ozge Subasi; Eva Reithner
In this paper, we present the results of two focus groups (9 seniors) from a European Project (STIMULATE), in the area of mobility and travel planning support for older people and people with special needs. The overall user studies were conducted in two countries (Austria and France), included 51 individuals (including experts), of which 31 were older adults (age between 55-92), other 8 were experts working with people with special needs. The findings from the first two focus groups (include 9 seniors) show four extended categories of requirements for the adoption of such travel assistance systems among older people, that are not yet fully addressed in the area of travel assistance and ambient assisted living. These can be summarized as non-reductive, personalised-in-context, aligned with non-functional, accompanying.
How busy is my supervisor?: Detecting the visits in the office of my supervisor using a sensor network BIBAFull-Text 12
  Ahmed Nait Aicha; Gwenn Englebienne; Ben Kröse
Existing research on the recognition of Activities of Daily Living (ADL) from simple sensor networks assumes that only a single person is present in the home. In real life there will be situations where the inhabitant receives visits from family members or professional health care givers. In such cases activity recognition is unreliable. In this paper, we investigate the problem of detecting multiple persons in an environment equipped with a sensor network consisting of binary sensors. We conduct a real-life experiment for detection of visits in the office of the supervisor where the office is equipped with a video camera to record the ground truth. We collected data during two months and used two models, a Naive Bayes Classifier and a Hidden Markov Model for a visitor detection. An evaluation of these two models shows that we achieve an accuracy of 83% with the NBC and an accuracy of 92% with a HMM, respectively.

Pervasive systems for the aging society

Redesigning web sites for older adults BIBAFull-Text 13
  Evelina Patsoule; Panayiotis Koutsabasis
Practical approaches and examples that incorporate the requirements of older adults into the development lifecycle are particularly useful for web design practice. In this paper, we present a case study of the redesign of a touristic Web portal that presents holiday destinations and supports online hotel booking for older adults. The redesign process involved (a) the identification of a set of 7 principles and 45 guidelines for Web design for older adults; (b) the validation of the identified set with heuristic evaluation; (c) the redesign of the website in a working prototype. The evaluation process compared the existing and the redesigned Web sites through a summative usability test that involved 12 older users and post-hoc interviews and questionnaires. The results showed that the redesigned web site was significantly more usable than the existing one. Finally, we discuss a number of practical issues on the basis of our reflection and experience.
On an advanced ICT-enabled system for the social inclusion of the elderly BIBAFull-Text 14
  Tero Kivimäki; Konstantinos Liolis; Ulcay Yildizoglu; Lasse Kaila; Antti-Matti Vainio; Stratis Konakas; Polyxeni Katsiouli; Harri Pensas; Kasperi Summanen; Spyros Pantazis; Heikki Moisio; Ilias Andrikopoulos; Jukka Vanhala
Aging people are in risk of social isolation due to direct or indirect effects of ageing. Social isolation decreases the quality of life, affects health and acts against independent living, which is important for both the elderly and the society. Social networking can provide elderly a sense of presence with their "safety-net", that is, relatives, friends and healthcare personnel that counteract the effects ageing causes to their social connections. In this paper, the design of an advanced socially assistive networking system is presented which provides the elderly the opportunity to enforce their connectivity with their safety-net. Specifically, attention is given to the design of a core service platform managing all requests between elderly and their safety-net, and to the design of elderly home terminal as well as to the design of mobile and Web pervasive applications for the members of the safety-net. Moreover, a user-centered approach is presented for the design of the overall system where special emphasis is put on usability and HCI.
Requirement of AAL systems: older persons' trust in sensors and characteristics of AAL technologies BIBAFull-Text 15
  Frederick Steinke; Tobias Fritsch; Daniel Brem; Svenja Simonsen
The objective of the study was to analyze older people's trust in sensor technology, modes of sensor attachment as well as trust in various characteristics of Ambient Assisted Living (AAL) technology. Therefore, 50 participants aged between 60 and 90 years (average age 71.26 years) were surveyed within the context of a requirement analysis, about the perceived positives and negatives of using technological support in everyday life. The analysis was based on data collected in semi-structured, face-to-face interviews from February to March 2011. The study revealed that men had distinctly higher levels of trust in sensor technology than women (7.64 vs. 6.83). The most interesting target audience for AAL technology, older people who are living in a single household, showed lower trust values in sensors than people living together with another person (6.41 vs. 7.83). Another result, important for developing AAL technology, was that fixed attachment of sensors in the accommodation was considered more reliable (7.80) than attachment to clothing or on/in the body. Regarding which characteristics formed the basis for trust in technology; reliability (9.72) and ease of use (9.52) were assessed as highly important. Visibility (8.45) and brand name (5.02) were seen as less important, whereas high costs (3.90) only slightly influenced reliance in AAL technology. Based on these results, further research regarding different stratification criteria, such as gender and housing situation, is needed. In order to gain a holistic model of elderly persons' trust in AAL further surveys, including this target audience, must be performed.
The role of tea parties to elicit technology requirements to support the mobility of older adults BIBAFull-Text 16
  Lynne Coventry; Emma Jones
Mobility is fundamental to aging well, maintaining independence and quality of life. Physical mobility is a fundamental component of overall mobility. This paper presents our "technology tea party" methodology. We have used this method to explore older adults' reaction to utilizing different technologies to maintain their mobility, in particular, games consoles to promote exercise at home. At our tea party, participants experienced problems with initially getting started with the console but with minimal support were able to interact with the system and start to explore the benefits they could gain from using such a system. They saw the benefits not only as exercise but also as promoting social interaction. We are now using this method in the design process for an "intelligent" walking aid to improve the ability of older adults to walk around shopping centres. In this paper we advocate the involvement of older adults throughout the design process and we present tea parties as a potential method to use in early stages to elicit requirements.

Robotic devices, HCI and multimodal interfaces I

A survey of assistive devices for cerebral palsy patients BIBAFull-Text 17
  Christopher McMurrough; Shahina Ferdous; Alexandros Papangelis; Angie Boisselle; Fillia Makedon Heracleia
In this paper, we present a survey of recent advances in assistive technologies used to foster rehabilitation and improved quality of life for children with Cerebral palsy. The survey focuses specifically on robotics and interactive games used in rehabilitative therapy, as well as general electronic assistive devices for everyday use. The systems and clinical studies discussed show that Cerebral palsy treatment can benefit greatly from emerging technologies.
Smart insole: a wearable system for gait analysis BIBAFull-Text 18
  Wenyao Xu; Ming-Chun Huang; Navid Amini; Jason J. Liu; Lei He; Majid Sarrafzadeh
Gait analysis is an important medical diagnostic process and has many applications in rehabilitation, therapy and exercise training. However, standard human gait analysis has to be performed in a specific gait lab and operated by a medical professional. This traditional method increases the examination cost and decreases the accuracy of the natural gait model. In this paper, we present a novel portable system, called Smart Insole, to address the current issues. Smart Insole integrates low cost sensors and computes important gait features. In this way, patients or users can wear Smart Insole for gait analysis in daily life instead of participating in gait lab experiments for hours. With our proposed portable sensing system and effective feature extraction algorithm, the Smart Insole system enables precise gait analysis. Furthermore, taking advantage of the affordability and mobility of Smart Insole, pervasive gait analysis can be extended to many potential applications such as fall prevention, life behavior analysis and networked wireless health systems.
A game system for remote rehabilitation of cerebral palsy patients BIBAFull-Text 19
  Alexandros Papangelis; Giannis Mouchakis; Angela Boisselle Texas; Dimitrios Kosmopoulos; Vangelis Karkaletsis; Fillia Makedon
Cerebral Palsy (CP) is a condition that affects many people and causes paralysis or disability due to brain dysfunctions. Though incurable, physical rehabilitation has proven to improve the patients' quality of life. Some of them, however, may need extra motivation to go through the rehabilitation process. Thus, to engage them in rehabilitative actions, video games, virtual reality games and robots that combine rehabilitation with play have been developed. We propose a game system targeted for rehabilitation of young CP patients and a graphical Event Recognition (ER) Authoring Tool with which a therapist can define ER rules that allow monitoring the rehabilitation progress of a patient and adjusting the therapy accordingly. Our aim is to develop a remote CP rehabilitation platform, that combines rehabilitative actions with play and employs inexpensive, off the shelf technologies that can be used with minimal supervision. This platform is targeted both at young CP patients and also therapists.
SmartGlove for upper extremities rehabilitative gaming assessment BIBAFull-Text 20
  Ming-Chun Huang; Wenyao Xu; Yi Su; Belinda Lange; Chien-Yen Chang; Majid Sarrafzadeh
This paper presents a quantitative assessment solution for an upper extremities rehabilitative gaming application [1]. This assessment solution consists of a set of stand-alone hardware, including SmartGlove and Kinect, a depth capturing sensor made by Microsoft. SmartGlove is a specially designed motion and finger angle extraction device which is packaged in an easy-to-wear and adjustable manner for a patient with an upper extremity impairment. Sensor data extraction, alignment, and visualization algorithms were designed for integrating hand-mounted sensors data streams into skeleton coordinates captured by the Kinect. This enhanced skeleton information can be summarized and replayed as upper extremity joint coordinate animations which can be used for physical therapists to quantify rehabilitation progress. In addition, to serve as an assessment tool, enhanced skeleton information can be used to extend the capability of the Kinect vision system, such as providing motion capture of the upper extremities, even when the testing subject is out of camera scope or one's upper extremities are occluded by the body.

Robotic devices, HCI and multimodal interfaces II

Implementation of interactive arm playback behaviors of social robot Zeno for autism spectrum disorder therapy BIBAFull-Text 21
  Nahum A. Torres; Nathan Clark; Isura Ranatunga; Dan Popa
In this paper, we describe control algorithms accomplishing human-robot interaction through mimicking behaviors between the humanoid robot Zeno and humans. Specifically, arm and torso motions of the robot follow closely those of the human, this mimicking behavior, can be used for clinical treatment and diagnosis during robot therapy of subjects suffering from Autism Spectrum Disorders (ASD). In this paper, we describe algorithms and results of implementing simple position control schemes on Zeno via visual feedback from Kinect data. The behavior can be used by therapists to achieve desired poses of the robot that may be beneficial to children with ASD by enhancing their motor skills as well as social interaction. Results show that in this case, simple actuators, sensors and control schemes can generate smooth and responsive robot trajectories.
Low-cost head position tracking for gaze point estimation BIBAFull-Text 22
  Christopher McMurrough; Jonathan Rich; Vangelis Metsis; An Nguyen; Fillia Makedon
In this paper, we present a low-cost solution for real-time tracking of a human user's head position with respect to a video display source for eye gaze estimation in an assistive setting. The solution utilizes a wearable headset equipped with sensors found in commercially available off-the-shelf video gaming devices in order to minimize hardware complexity and expense. A pair of Nintendo Wiimote imaging sensors are used to create a stereo camera for 6DOF position tracking of the headset, while a modified Playstation Eye monocular camera is used to track the pupil position. The resulting tracking hardware is able to measure the 3D position of four infrared LEDs mounted at known locations on the video display using triangulation of the stereo camera data. Integration of the head tracking estimate with a computer vision based pupil tracking solution in order to compute the user's point of gaze is also described.
Collision-free trajectory generation on assistive robot Neptune BIBAFull-Text 23
  Isura Ranatunga; Dan O. Popa
This work demonstrates the integration of existing open source robotics tools to develop a collision free trajectory generation system for assistive environments and evaluates its performance. Trajectory generation and obstacle avoidance abilities were applied in the Neptune assistive robot developed in our lab. Such abilities are essential for safe operation of the robot in an assistive living environment. The Robot Operating System (ROS) is used as the software framework within which collision-free algorithms are executed. Prior to deploying the code on the Neptune hardware, the kinematics was modeled and simulated. Furthermore, a Kinect sensor was used to gain information about the environment and detect obstacles. Experiments were then performed on the robotic system to demonstrate the obstacle avoidance behavior during trajectory generation between randomly generated and selected end effector poses.

Data modeling and information management for pervasive assistive environments

Towards a semi-automatic personal digital diary: detecting daily activities from smartphone sensors BIBAFull-Text 24
  Sebastian Hammerl; Thomas Hermann; Helge Ritter
This paper presents a diary system which reduces the time to keep and maintain a diary by assisting the user with automatic suggestions for possible events and activities. The system uses a smartphone app reading the internal sensors to detect the current situation. It interrupts the user when unsure in prediction of the current situation. No external hardware is used to assure a broad audience of later endusers. The overall goal is to create a multimedia enriched digital personal diary. A study has been conducted where 16 participants collected data over two weeks from the built-in sensors of an ordinary smartphone. The data has been annotated by the users with labels of daily activities. We applied different classification algorithms to test the feasibility to detect these activity labels from the collected sensor data only. The experiments show that a perfect classification of activities of daily living is not possible but a system like this is usable to assist the journaling by suggestions and semi-automatic logging. The digital diary keeping process should take less time and is more versatile than an old-fashioned handwritten diary. A diary like this can be used to revive past events and help people with dementia to remember the past.
Comparing metadata quality in the Europeana context BIBAFull-Text 25
  Sarantos Kapidakis
The quality of the metadata affects the interoperability of the collections and the quality of all search results, and is important to the success of Europeana. It is not obvious how to define quality metrics, on different kinds of metadata and collections, and many different perceptions may be valid. Nevertheless, a metadata quality metric will help the collection administrators detecting and improving the weaknesses of their metadata, and Europeana locating the most problematic collections, in terms of metadata quality, and prompt their administrators to improve their descriptions. We developed an adaptive quantitative metadata quality metric and a system to implement it for Europeana Local that takes into account the significance of the different metadata elements in the record, and also the values that they contain. In controlled values, their distribution is of importance, while for free text values the length of the description is used. We applied this metric to collections outside Europeana to find reasonably expected thresholds and weights for each individual value in the Europeana context and both outside and inside Europeana, and compared the results, to get a general quantitative and qualitative feeling of the diversity in the record descriptions, to produce the appropriate advice for the collection administrators and make quality observations.
User activities outlier detection system using principal component analysis and fuzzy rule-based system BIBAFull-Text 26
  Sawsan M. Mahmoud; Ahmad Lotfi; Caroline Langensiepen
In this paper, a user activities outlier detection system is introduced. The proposed system is implemented in a smart home environment equipped with appropriate sensory devices. An activity outlier detection system consist of a two-stage integration of Principal Component Analysis (PCA) and Fuzzy Rule-Based System (FRBS). In the first stage, the Hamming distance is used to measure the distances between the activities. PCA is then applied to the distance measures to find two indices of Hotelling's T2 and Squared Prediction Error (SPE). In the second stage of the process, the calculated indices are provided as inputs to FRBSs to model them heuristically. They are used to identify the outliers and classify them. Three case studies are reported to demonstrate the effectiveness of the proposed system. The proposed system successfully identifies the outliers and helps in distinguishing between the normal and abnormal behaviour patterns of the Activities of Daily Living (ADL).
Hefestos: a model for ubiquitous accessibility support BIBAFull-Text 27
  João Tavares; Jorge Barbosa; Cristiano Costa; Adenauer Yamin; Rodrigo Real
This paper presents the Hefestos Model, designed to provide ubiquitous accessibility. The project aims at supporting accessibility for People With Disability (PWD) and elderly in various situations of their everyday life. Offering context awareness, user profiles and trails management, the model is a base for applying assistive technologies that fulfills accessibility needs. Moreover, in the proposed model, we devised an ontology. Besides the benefits of intrinsic semantic representation, the use of an ontology fosters future integration with others solutions. We also present a case study based on a prototype, which was developed to evaluate the model. This assessment used a smart wheelchair, operated by a paraplegic person, which is under development at University of the Sinos Valley (Unisinos).

Smart homes and intelligent environments

Active life home: a portal-based home care platform BIBAFull-Text 28
  Petri Vuorimaa; Panu Harmo; Matti Hämäläinen; Timo Itälä; Raimo Miettinen
Assistive devices help elderly persons to live longer in their homes. Unfortunately, the devices on the market are incompatible with each other. Also, integration to higher-level services is an open issue. In this article, we propose a portal-based home care platform that integrates together multiple assistive devices and their online services. The integration is done at three levels: service, information, and device. At the service level, we use portal technology to integrate together Personal Health Record (PHR), external services, and web-based device user interfaces. At the information level, we integrate the different devices and services to the PHR using REST-based web services. At the device level, we use a home automation gateway to connect the different devices to the PHR and portal. We tested the architecture in a living lab environment. The results show that multiple integration levels improve the flexibility of home health care systems.
Guidelines to efficient smart home design for rapid AI prototyping: a case study BIBAFull-Text 29
  Kevin Bouchard; Bruno Bouchard; Abdenour Bouzouane
Advances in ubiquitous technology have moved us towards the dream of creating intelligent houses that can help human in their everyday life. The next step in the completion of this vision is to make major breakthroughs in artificial intelligence. In fact, it is the key component for allowing sensors and effectors to give useful services when it is appropriate. In consequence, researchers need to conduct more experiments in realistic setting (e.g. smart home). In order to face this challenge, many research teams try to build new experimental infrastructures without any background experience, guidance or even a real idea of their research needs and issues. Our team is composed of specialists in AI for cognitive assistance and has worked with four major smart home infrastructures. From that experience, we propose, in this paper, a set of guidelines for designing and implementing an efficient smart home architecture on both hardware and software perspective. This paper aims to be a major step toward the AI development (rapid prototyping) and smart home research. Moreover, we share our recent experience with the construction of a new smart home and clinical trials conducted at our laboratory with real Alzheimer's subjects.
Smart homes for people with Alzheimer's disease: adapting prompting strategies to the patient's cognitive profile BIBAFull-Text 30
  Jessica Lapointe; Bruno Bouchard; Julie Bouchard; Audrey Potvin; Abdenour Bouzouane
Smart home technologies constitute a potential solution to allow people with Alzheimer's disease (AD) to remain in their home. These intelligent houses contain technological devices aiming to provide adapted cognitive assistance (prompts) when needed. However, a literature review of the field revealed a predominant use of verbal prompts with little knowledge about their real effectiveness. To contribute solving this important issue, we propose, in this paper, comprehensive guidelines to help smart homes researchers to maximize the efficiency by adapting the form of prompts to the specific cognitive profiles of patients with AD. First, we identify the main deficits of AD that influence the effectiveness of prompts. Second, we details which prompting strategy to use accordingly. Third, we propose an experimental protocol, based on a well-known test, and a new prompting software, which allows to validate the proposed guidelines. Finally, we present the preliminary results of a first experiment conducted in our lab with participants having mild to moderate AD.
User centred approach for home environment designing BIBAFull-Text 31
  S. Ceccacci; M. Germani; M. Mengoni
Highly usable human-system interfaces can have a large benefit on the quality of life for the elderly and disabled. New emerging product design technologies, such as Virtual Reality (VR) and Augmented Reality (AR), give many opportunities to evaluate and improve system usability in the early design stages. In this way different design alternatives can be evaluated in terms of physical and cognitive performance. In this context the present paper describes a systematic approach for designing highly usable home environments and optimizing human-machine interaction. VR/AR technologies are adopted for user interface evaluation. The approach will be applied to the design of a new kitchen.

Discovery and ongoing work "DISCO"

Using Google™ facets as implicit feedback for query expansion in database searching BIBAFull-Text 32
  Anna Mastora; Sarantos Kapidakis
The purpose of this study is to examine the Google facets, namely the suggestions found occasionally under the section "Searches related to" on the Google results page. The study focuses on whether they constitute good candidate terms for implementing expansion of queries submitted to databases. The thought behind this is to benefit from the Google recommendations and see if they relate in a satisfactory proportion with the initial user queries so that the first can provide reliable information on the context of the second, especially in cases where no results are returned for the initial query. During our study we have recorded the conditions under which Google creates facets, their informational characteristics as well as various problems concerning the available features of the Greek version of Google. After submitting our collection of 750 zero-hit queries to Google, we retrieved facets for 302 of them, which correspond to 95 of the initial users' queries. Finally, we found that 12.67% of otherwise zero-hit queries would return results with the use of Google facets.
Geospatial data in library collections BIBAFull-Text 33
  Ifigenia Vardakosta; Sarantos Kapidakis
While several surveys and studies focus on developing GIS services in libraries, however, there is no recent research concerning the data that academic libraries organize and offer to their users. This study tries to cover this gap, as we examine the types and forms of digital geospatial data held by academic libraries worldwide, after an investigation carried out to their web pages during June-August 2011.
   Among the 331 researched libraries only 136 were found providing GIS services while 24 of them had geospatial collection development policies.
   The results of this exploratory study indicate an overwhelming acceptance of various sources (e.g. digital maps, spatial data, remote sending files, statistical data, satellite images etc) and formats in academic libraries derived from public and commercial sector, without free and open data being excluded. Furthermore, the specific kinds of collections are related to the provided services, and enhance added value services in academic libraries.

Poster session

A social network framework for the Carolina software BIBAFull-Text 34
  S. Cuomo; A. Murano; F. Piccialli; E. Del Giudice
The study of medical protocols for monitoring and analyzing the cognitive development of children with disabilities is a fundamental research area. A well established curriculum-based assessment is the Carolina Curriculum for Infants and Toddlers with Special Needs (CCITSN). This is a medical protocol for monitoring and analyzing the cognitive development of children with disabilities. A full web-application software implementing all features of CCITSN, named Carolina, has been recently developed. Critically, CCITSN does not allow to share experiences between all actors enrolled in the curriculum program. To address this problem, we extend here the Carolina software by means of a communication social networking framework, conceived ad-hoc.
Light-ECV: an intelligent lightweight framework for embedded computer vision applications BIBAFull-Text 35
  Agwad El-Sayed; Mohamed ElHelw
Recent developments in embedded systems open up a new realm of computer vision applications in surveillance and healthcare delivery, etc. However, such applications require high computational resources, which is challenging for embedded devices that are characterized by constrained processing power and limited memory capacity. In this paper we present a novel intelligent framework that enables building computer vision applications with optimal throughput and maintaining the performance of such applications at run-time.
A survey on multi person identification and localization BIBAFull-Text 36
  Shahina Ferdous; Kapil Vyas; Fillia Makedon
In this paper, we present a survey of technology and algorithms used to identify and localize multiple people simultaneously in an assistive environment. The survey summarizes localization approaches based on video cameras and RFID, as well as describes identification methods based on RFID tags or wearable devices. The paper also describes state-of-the-art multimodal data fusion methods that estimate the identification and location of every person more precisely.

Workshop on affect and behaviour related assistance in support for the elderly

A discussion of using mental models in assistive environments BIBAFull-Text 37
  Mario Aehnelt; Christian Peter; Petra Müsebeck
The design of assistive environments often follows technological potentials and constraints in order to react on people's behavior and assist them in everyday life situations. In this paper we discuss the role of mental models for improving the usability and user experience with assistive environments. We argue for a user-centered design including interaction design which provides intentional support in building, shaping and confirming the mental model of the user. The paper aims to motivate a wide discussion on design principles for assistive environments focusing on better user experiences and assistance qualities.
A sociable robotic aide for medication adherence BIBAFull-Text 38
  Michael J. Gonzales; Laurel D. Riek
In the United States, approximately 125,000 people die each year due to complications related to medication adherence, which costs the country approximately $100 -- $300 billion dollars annually. The problem of medication adherence stems largely from people either having too many medications, causing confusion and making management harder, or taking larger dosages than prescribed. We propose a solution for improving medication adherence using a physically embodied social robot as a motivating factor. In particular, the robot's interaction will be similar to that of a digital pet game, except users will care for the pet by caring for themselves (i.e., taking their medication.) The robot will also leverage social-network support factors to promote the emotional and positive affective behaviors of patients.
Ambient interaction by smart watches BIBAFull-Text 39
  Gerald Bieber; Thomas Kirste; Bodo Urban
The availability of new hardware allows new interaction and visualization metaphors for work environment and private life. Smart watches with integrated acceleration sensors and vibration feedback enable a new kind of interaction. In complement with a matrix display and connectivity to the Internet, smart watches provide assistance in ambient surroundings. This work presents challenges and opportunities of smart watches and introduces a concept of non-obtrusive interaction with smart watches by using physical activity recognition. Hereby the paper presents a prototype application of maintenance assistance and shows possible applications for ambient assistant living environments. In combination of information visualization, permanent sensing and notification, the smart watch becomes the next technology step in the row of smart devices for home-consumer and industrial users.
Creating and benchmarking a new dataset for physical activity monitoring BIBAFull-Text 40
  Attila Reiss; Didier Stricker
Physical activity monitoring has recently become an important field in wearable computing research. However, there is a lack of a commonly used, standard dataset and established benchmarking problems. In this work, a new dataset for physical activity monitoring -- recorded from 9 subjects, wearing 3 inertial measurement units and a heart rate monitor, and performing 18 different activities -- is created and made publicly available. Moreover, 4 classification problems are benchmarked on the dataset, using a standard data processing chain and 5 different classifiers. The benchmark shows the difficulty of the classification tasks and exposes some challenges, defined by e.g. a high number of activities and personalization.
Fall-detection simulator for accelerometers with in-hardware preprocessing BIBAFull-Text 41
  Sebastian Fudickar; Christian Karth; Philipp Mahr; Bettina Schnor
Mobile fall-detection systems that use accelerometers (as the ADXL 345) with data pre-processing capabilities, enable processors to remain longer in low power modes and therefore can achieve extended device lifetimes. Since fall-detection on these accelerometers is partially executed in hardware, the development and comparison of fall-detection algorithms requires direct evaluation on the hardware and increases complexity. We introduce a fall-detection simulator for the development and comparison of fall-detection algorithms for accelerometers with and without partial in-hardware pre-processing. In addition comprehensive records of fall-situations and daily living activities were generated for the simulator from recording movements. With the help of the simulator, the sensitivity of a given fall-detection algorithm could be improved from 33% to 93%.
Seniors in charge of ICT innovation BIBAFull-Text 42
  E. L. Waterworth; J. A. Waterworth; C. Peter; S. Ballesteros
We present the user-driven AGNES project (aal-2008-1-014). The project has three user groups, one in each of Sweden, Spain and Greece, who have participated as full members of the project team. The method used for developing this novel ICT was an extension of the ELITE design approach for user driven innovation. The results presented in the paper are on how the users' attitudes changed during the project due to their having the expert role in the development process and how they accepted and acted in that role. To start with, the elderly users were very polite, often negative about and frightened of technology. Some did not have a computer of their own and did not have any or much experiences of new communication technologies. During the project the users were introduced to an interactive social network, generated design ideas for new ICT and also tested ICT solutions related to using the social network and connected devices. The paper gives examples of how the user attitudes towards technology changes during the project and discusses how they became true experts able to express their knowledge and in that way exert control over the technical design in the project. The result is that the users have become bold, good at expressing their knowledge, and good at marketing the project and the use of technology to other people, and in the process increasing their social life both on the net and in the physical world.
The AGNES system for ambient social interaction BIBAFull-Text 43
  Christian Peter; Andreas Kreiner; Martin Schröter; Gerald Bieber; John Waterworth
This paper describes the AGNES system, a technology for connecting people at home with their social network be means of off-the-shelf sensing devices and an Internet-based social network. The system provides the user with relevant information of the network by use of traditional information and communication technology as well as dedicated ambient and tangible devices. We describe briefly the requirements on such technology that were elaborated in the frame of the AGNES project, and give an overview of the system developed.
The role of ICT and networking in healthy ageing BIBAFull-Text 44
  S. Ballesteros; C. Peter; E. L. Waterworth; J. A. Waterworth
In this paper, we report the results from the psychological assessment conducted using a test battery composed of cognitive and social wellbeing tests and questionnaires performed by users and controls that participated in the AGNES project in Spain, Sweden and Greece at the beginning of the study and after the deployment of the first prototype. The project carries out novel technological interventions in an emerging area in ageing research. The main innovation is the integration of different technological components and social networking to provide a novel solution to the ageing population living at home. The motivation was based on relevant findings on the psychology of ageing and the need for technologies to support the ageing population. End-users have been heavily involved, providing design input, continuum evaluation and feedback. The project focuses on improving the mental and physical wellbeing of elderly people living at home, who often suffer the effects of social and physical isolation including cognitive decline, low activity levels and poor mood states. The main results were that the users but not the control participants improved cognitive performance and the feeling of being treated with respect, being independent, self-realization and greater achievement.

Workshop on social networks and sensor networks in assistive environments

Benchmarking link analysis ranking methods in assistive environments BIBAFull-Text 45
  Konstantinos Georgatzis; Panagiotis Papapetrou
Several assistive applications exhibit a network structure. Characterizing the structure of such networks is critical in many assistive applications. Existing methods in the of social network analysis aim to detect, analyze, and summarize interesting or surprising components and trends in the network. In this paper, we provide a benchmark of two graph ranking methods: pagerank and HITS. The methods are tested on real social network data from three different domains: citation graphs, road networks, and a subgraph of Google. Our findings suggest that the quality of the ranking as well as the speed of convergence of both algorithms highly depends on the underlying network structure.
Dictionary data structures for smartphone devices BIBAFull-Text 46
  Alexandros Bentevis; Ioannis Kerkinos; Vana Kalogeraki
The popularity of portable electronics such as smartphones, PDAs and mobile devices and their increasing processing capabilities has enabled the development of mobile multiplayer social games on networks of smartphones. The paper presents resource-efficient dictionary data structures for smartphone devices. The system addresses the space constraints of the smartphone devices and provides efficient and low-latency execution, by employing a number of techniques for the dictionary of the game, including a Cache Based Dictionary, and a String compression technique. We have implemented our techniques in a network of Android-based smartphones and present our experimental results.
Fast variable selection for memetracker phrases time series prediction BIBAFull-Text 47
  Yoan Miche; Tatiana Chistiakova; Anton Akusok; Amaury Lendasse; Rui Nian; Alberto Guillén
This paper proposes a methodology using a fast variable selection as a modified version of the Forward-Backward algorithm. This methodology is adapted to the specificities of the data used: very small number of samples and high number of variables. Such data is generated using underlying dependencies and seasonality assumptions, from Meme phrases volume data. By the use of a resampling technique along with the proposed variable selection scheme, significant results are obtained, and the test Normalized Mean Square Error performances are improved. The results indicate that with the assumptions made on the data structure, variable selection is desirable. Also, the obtained information on the selected variables seem to cluster the time series in two very different classes: a set of approximately 600 series, which yield good NMSE, and seem to require very similar sets of variables for the prediction; and another set of 300-400 series, for which only the previous series value is of interest for the prediction. This first analysis clearly illustrates the future need to perform a more thorough analysis of the selected variables for each of the batch of series.
   Also, taking a close look at the possible dependences between the series inside a batch should give information as to why and how they are similar and have found themselves to be grouped under the same batch.
Mixture modeling of gait patterns from sensor data BIBAFull-Text 48
  Jaakko Hollmén
Sensor data can be used for monitoring, modeling, and recognition of human activities during daily life or in special situations. In assistive environments, modeling of characteristic walking styles have been studied as well as preventing the falls of the elderly. In this paper, we pre-process and analyze a time series collection of sensor recordings which is publicly available. More specifically, we transform the raw pressure sensor data in the insoles of the shoes to yield binary pressure patterns to indicate contact between the shoe and the ground. We model the marginal probability distributions of the resulting 0-1 data with mixture models of multivariate Bernoulli distributions. We interpret the identified mixture model in terms of gait phases.

Workshop on robotics in assistive environments

A comparative study of calibration methods for Kinect-style cameras BIBAFull-Text 49
  Aaron Staranowicz; Gian-Luca Mariottini
Kinect-style (or Depth) cameras use both an RGB and a depth sensor that acquire color and per-pixel depth data (depth-map), respectively. Due to their affordable price and rich data they provide, depth cameras are being extensively used on research in assistive environments. Most of the robotic and computer-vision systems that use these Kinect-style cameras require an accurate knowledge of the camera-calibration parameters. Traditional calibration methods, e.g., those that use a checker-board pattern, cannot be straight-forwardly used to calibrate the Kinect-style cameras since the depth sensor can not distinguish patterns. Several calibration methods have emerged that try to calibrate depth cameras. In this paper, we present a comparative study of some of the most important Kinect-style calibration algorithms. Our work includes an implementation of these methods along with a comparison of their performance in both simulation and real-world experiments.
RoDiCA: a human-robot interaction system for treatment of childhood autism spectrum disorders BIBAFull-Text 50
  Isura Ranatunga; Nahum A. Torres; Rita Patterson; Nicoleta Bugnariu; Matt Stevenson; Dan O. Popa
In this paper, we describe the implementation of interactive robotics in virtual environments accomplishing human-robot interaction for treatment of Autism Spectrum Disorders (ASDs). Interaction between our system and children suffering from ASDs is accomplished by teaching them body language such as hand and arm motion, facial expressions and speech to encourage them to engage in social interaction with other humans and for improving their motor skills. A Kinect sensor is used to allow direct control of the humanoid robot, Zeno, by the therapist or child to enable dynamic interaction. The motions of Zeno and the child are recorded simultaneously by a motion capture system to assess the interaction. Specifically, we compare arm and torso motions of the child which should closely follow those of the robot. This behavior can be used for clinical treatment and diagnosis during robot assisted therapy. Therapists can take advantage of this interactive behavior to achieve desired poses of the robot that may be beneficial to children with ASDs to enhance their motor skills as well as their social interaction skills. In order to compare the motion characteristics of robots and subjects, we use various metrics such as cross correlation and signal 2-norm. Results show that the child's motion follows the robot's motion closely and the analysis techniques are reasonable indicators to compare the similarity of the human and robot motions.
Vibrotactile haptic feedback for human-robot interaction in leader-follower tasks BIBAFull-Text 51
  Stefano Scheggi; Francesco Chinello; Domenico Prattichizzo
In this paper we explore a vibrotactile feedback paradigm which allows the human to intuitively interact in human-robot applications. In particular we focus on a haptic bracelet which helps the human to move along trajectories that are feasible for the leader-follower formation tasks. The bracelet consists of three vibrating motors circling the forearm and represents a non invasive way to provide essential information to the human. Experiments performed on a public of 15 subjects revealed the effectiveness of the proposed device.