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

Proceedings of the 2013 International Conference on PErvasive Technologies Related to Assistive Environments

Fullname:Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments
Editors:Fillia Makedon; Margrit Betke; Magy Self El-Nasr; Ilias Maglogiannis
Location:Island of Rhodes, Greece
Dates:2013-May-29 to 2013-May-31
Standard No:ISBN: 978-1-4503-1973-7; ACM DL: Table of Contents; hcibib: PETRA13
Links:Conference Website
  1. Rehabilitation robotics and multimodal interfaces
  2. Pervasive systems for the aging society
  3. Networking and communication for assistive environments
  4. Tools, infrastructures, architectures and techniques for deploying pervasive applications in assistive environments I
  5. Usability and HCI issues
  6. European projects USEFIL
  7. Tools, infrastructures, architectures and techniques for deploying pervasive applications in assistive environments II
  8. Signal and image processing for ambient intelligence and pervasive computing
  9. Data modeling and information management for pervasive assistive environments
  10. Cognitive systems and pattern analysis tools for assistive environments
  11. Poster session
  12. Workshop on robotics in assistive environments
  13. Workshop on participatory sensing in assistive environments

Rehabilitation robotics and multimodal interfaces

A smart wheelchair based on ubiquitous computing BIBAFull-Text 1
  João Tavares; Jorge Barbosa; Cristiano Costa; Adenauer Yamin; Rodrigo Real
This paper presents the Hefestos Smart Wheelchair, a wheelchair with sensing capability, designed to provide ubiquitous accessibility. The project aims at supporting accessibility for wheelchair users in various situations of their everyday life. Offering context awareness, user profiles, and trails management. We also present the evaluation of the prototype based on an academic experiment. This assessment used the smart wheelchair, which is under development at University of the Rio dos Sinos Valley (Unisinos). The prototype was operated by ten wheelchair users.
Toward a 3D body part detection video dataset and hand tracking benchmark BIBAFull-Text 2
  Christopher Conly; Paul Doliotis; Pat Jangyodsuk; Rommel Alonzo; Vassilis Athitsos
The purpose of this paper is twofold. First, we introduce our Microsoft Kinect-based video dataset of American Sign Language (ASL) signs designed for body part detection and tracking research. This dataset allows researchers to experiment with using more than 2-dimensional (2D) color video information in gesture recognition projects, as it gives them access to scene depth information. Not only can this make it easier to locate body parts like hands, but without this additional information, two completely different gestures that share a similar 2D trajectory projection can be difficult to distinguish from one another. Second, as an accurate hand locator is a critical element in any automated gesture or sign language recognition tool, this paper assesses the efficacy of one popular open source user skeleton tracker by examining its performance on random signs from the above dataset. We compare the hand positions as determined by the skeleton tracker to ground truth positions, which come from manual hand annotations of each video frame. The purpose of this study is to establish a benchmark for the assessment of more advanced detection and tracking methods that utilize scene depth data. For illustrative purposes, we compare the results of one of the methods previously developed in our lab for detecting a single hand to this benchmark.
An assistance system for guiding workers in central sterilization supply departments BIBAFull-Text 3
  Stefan Rüther; Thomas Hermann; Maik Mracek; Stefan Kopp; Jochen Steil
The reprocessing of medical devices is an essential process to keep a hospital functional. It is carried out in the Central Sterilization Supply Department (CSSD). Failures during reprocessing can endanger patients' safety and increase costs. The benefits of an assistance system helping workers in preventing failures are therefore obvious, whereas challenging requirements arise through process complexity, legislation, integration and hygiene restrictions. We propose an assistance system that supports the worker in the unclean area of a CSSD under these requirements. It provides a user interface for context-aware guidance and collection of process relevant data from the worker. 'Virtual touches' fulfill the hygiene requirements and are realized with a depth camera and a projected user interface. Business process models control the workflow and maintain a valid database for quality assurance and worker guidance. We evaluated the system with a user study focusing on failure prevention, task completion time and usability.
A development and evaluation platform for non-tactile power wheelchair controls BIBAFull-Text 4
  Christopher McMurrough; Isura Ranatunga; Alexandros Papangelis; Dan O. Popa; Fillia Makedon
This paper presents an intelligent wheelchair designed to be used as a development and evaluation platform for alternative, non-tactile power wheelchair controls. The system is designed to be highly modular such that new human-computer interface devices and methods can be quickly integrated and evaluated as necessary. The current configuration provides full proportional steering and speed control outputs using a combination of voice commands, video-occulography (eye tracking), and a single point electrode based electroencephalography (EEG) brain-computer interface.
Capacitive sensor-based hand gesture recognition in ambient intelligence scenarios BIBAFull-Text 5
  Andreas Braun; Tim Dutz; Felix Kamieth
Input devices based on arrays of capacitive proximity sensors allow the tracking of a user's hands in three dimensions. They can be hidden behind materials such as wood, wool or plastics without limiting their functionality, making them ideal for application in Ambient Intelligence (AmI) scenarios. Most gesture recognition frameworks are targeted towards classical input devices and interpret two-dimensional data. In this work, we present a concept for adapting classical gesture recognition methods for capacitive input devices by realizing an extension of the feature set to three dimensional input data. This allows more robust gesture recognition for free-space interaction and training specific to capacitive input devices. We have implemented this concept in a prototypical setup and tested the device in various Ambient Intelligence scenarios, ranging from manipulating home appliances to controlling multimedia applications.

Pervasive systems for the aging society

Enabling health literacy for older adults through anamorphic perspective BIBAFull-Text 6
  Robert Ball
The US Institute of Medicine defines health literacy as "the degree to which individuals have the capacity to obtain, process, and understand basic health information and services needed to make appropriate health decisions." As more health resources move to computer access it is important that people are able to obtain the information and understand it from computers. This is especially important for older adults that might be less able to read and understand health resources from a stationary or bedridden situation. In this paper, we describe a new visualization technique for helping stationary older adults better read from computers. We use the concept of anamorphic perspective and large displays to extend stationary adults' reading area thus allowing the benefits of large displays from a stationary position. We present two experiments on the technique and show that it has potential to help stationary individuals read from far away distances.
Activity recognition in smart homes based on electrical devices identification BIBAFull-Text 7
  Corinne Belley; Sebastien Gaboury; Bruno Bouchard; Abdenour Bouzouane
Activity recognition constitutes the key challenge in the development of smart home assistive systems. In this paper, we propose a new algorithmic method for activity recognition in a smart home, based on load signatures of appliances. Most recognition approaches rely on distributed and heterogeneous sensors (ex. RFID), which are intrusive require complex installation, deployment and maintenance. On the other hand, most applications of appliance load monitoring (signal analysis) refer to the energy saving and the costs reducing of energy consumption. Consequently, our proposal constitutes an original application and new algorithmic method based on steady-state operations and signatures. The extraction process of load signatures of appliances is carried out in a three-dimensional space through a single power analyzer, which is non-intrusive (NIALM). We have rigorously tested this new approach by conducting an experiment in our smart home prototype by simulating daily scenarios taken from clinical trials previously done with Alzheimer patients. The promising results we obtained are presented and compared to other approaches, showing that, with an exceptionally minimal investment and the exploitation of relatively limited data, our method can efficiently recognize activities of daily living for providing assistive services.
Go-myLife: a context-aware social networking platform adapted to the needs of elderly users BIBAFull-Text 8
  Maria Haritou; Athanasios Anastasiou; Ioannis Kouris; Sergio García Villalonga; Idoia Olalde Gancedo; Dimitris Koutsouris
In our increasingly dislocated and mobile society, online social network sites are proving valuable in bridging distances and facilitating interaction and communication. People are spending a significant amount of time at the top social networking websites in order to manage existing relationships with friends, reconnect with old friends, share media and find new contacts that have similar interests.
   Fulfilling these needs are just as important for elderly people as it is for everyone else, but can become more difficult. Many are no longer at work so they do not have a daily set of activities with the same group of people. This, combined with increasing frailty, can lead to a habit of staying at home, which adds to the feeling of loneliness and isolation.
   In spite of this need for social contact, elderly people, even those who use the internet, tend to miss out on the benefits of online social networking platforms.
   Elderly people are keen to maintain contact with the different generations of their family. Many older people have already invested significant time in building contact lists and relationships within the major social networks. Go-myLife has therefore not attempted to set up a new social network but rather a platform from where elderly people can post messages and receive updates and take part in discussions across a variety of platforms, thus bringing existing communities together.
   In this paper, the authors present a context-aware social networking platform, the "Going online: my social life" platform, which is adapted to the needs of elderly users.
Assistive technology for older adults: psychological and socio-emotional design requirements BIBAFull-Text 9
  Aimée K. Bright; Lynne Coventry
The EU-funded multi-disciplinary DALi (Devices for Assisted Living) project aims to develop a semi-autonomous, intelligent mobility aid for older adults, which supports navigation in crowded and unstructured environments. We demonstrate the necessity to consider hitherto underexplored user-inclusive requirements which address psychological and socio-emotional needs of users. Using a qualitative methodology, including focus groups and interviews, our results showed that the design of the intelligent walker for older adults has to address issues of anticipated or experienced socio-emotional and psychological costs, including self-consciousness, pride, embarrassment, fear of being stigmatised and not wanting to admit a need. We suggest potential design strategies to increase emotional benefits and reduce psychological and emotional costs associated with use of assistive technology, thus facilitating product adoption.
Assistive living robot: a remotely controlled robot for older persons living alone BIBAFull-Text 10
  Sebastian Hening; Peter Cottrell; Mircea Teoderescu; Sri Kurniawan; Pat Mantey
This paper describes the development of an assistive living robot, which is affordable and can be steered over the Internet by family member to remotely monitor and help assess the wellbeing of an older relative living alone. A commercially available iRobot Create platform was used as a starting point for the Assistive Living Robot. Our system (i) takes advantage of commercially available systems to reduce development cost and effort, (ii) acts as a video and audio communication tool between older persons and their family members or caregivers and (iii) can analyze the video feed to detect heart rate and breathing rate. The proposed system could be integrated with in-home monitoring sensors, which could be the trigger for alerting family members that an out of ordinary event is occurring, therefore, our robot could be woken up and sent to be used as over the Internet watchful eye.
Location-independent fall detection with smartphone BIBAFull-Text 11
  Stefan Mehner; Ronny Klauck; Hartmut Koenig
Due to demographic changes in developed industrial countries and a better medical care system, the number of elderly people who still live in their home environment is rapidly growing because there they feel more comfortable and independent as in a clinical environment or in a residential care home. The elderly often live alone and receive only irregular visits. Due to impaired physical skills the probability of falls significantly increases. The detection of falls is a crucial aspect in the care of elderly. Falls are often detected very late with severe consequential damages. There are existing approaches for automatic fall detection. They usually deploy special external devices. Elderly people often do not accept these devices because they expose their frailty. In this paper, we present a location-independent fall detection method implemented as a smartphone application for an inconspicuous use in nearly every situation of the daily life. The difficulty of our approach is in the low resolution range of integrated acceleration sensors and the limited energy supply of the smartphone. As solution, we apply a modular threshold-based algorithm which uses the acceleration sensor with moderate energy consumption. Its fall detection rate is in the average of current relevant research.

Networking and communication for assistive environments

A general conformance testing framework for IEEE 11073 PHD's communication model BIBAFull-Text 12
  Linbin Yu; Yu Lei; Raghu N. Kacker; D. Richard Kuhn; Ram D. Sriram; Kevin Brady
ISO/IEEE 11073 Personal Health Data (IEEE 11073 PHD) is a set of standards that addresses the interoperability of personal healthcare devices. As an important part of IEEE 11073 PHD, ISO/IEEE 1107-20601 optimized exchange protocol (IEEE 11073-20601) defines how personal healthcare devices communicate with computing resources like PCs and set-top boxes. In this paper, we propose a general conformance testing framework for IEEE 11073-20601 protocol stack. This framework can be used to ensure that different implementations of the protocol stack conform to the specification and are thus able to interoperate with each other. We are developing a prototype research tool that applies the proposed framework to Antidote, an open-sourced IEEE 11073-20601 protocol stack. We report some preliminary testing results.
Antenna designs for wearable body sensor communication BIBAFull-Text 13
  Dinesh Bhatia; A. L. Praveen Aroul
Wireless body-centric telemedicine systems have gained considerable attention in the past decade because of continued miniaturization of electronic devices and technological advancements in wireless communications. These systems have potential applications in medical therapy and diagnosis, health monitoring, disease, obesity and overweight management. Recent advances in wireless sensor network (WSN) technology and the overall miniaturization of their associated hardware are leading to several potential applications in the medical industry. This paper addresses the path loss performance and the packet error rate of the flexible antenna designs. These have been studied at different environmental conditions and in the presence of the human body.
NFC-triggered IMS flow mobility across different devices BIBAFull-Text 14
  Vassilis Zafeiris; Petros Belsis; Christos Skourlas
Smartphones are gradually providing support for advanced user applications with high computation and network bandwidth requirements. However, their usually restricted size raises usability issues. A need is emerging for utilization and collaboration with devices in the user's reach that provide advanced capabilities. The 3GPP IP Multimedia Subsystem (IMS) is making an important contribution toward this direction, through specifications for distribution and replication of a multimedia session's media components to multiple devices that either belong to the same or different subscriptions. The IMS Service Continuity capability enables the transfer of one or more media components of an IMS session across different user devices. Although IMS can handle the media flow transfer, the user is still required to be engaged in a tedious device discovery and configuration process. We propose an out-of-band signaling mechanism, based on Near Field Communication (NFC) connectivity for fast and effortless initialization of a collaborative multimedia session between devices in close proximity that may involve the transfer of one or more media flows among them. We specify the utilization of an intuitive NFC touch interface for (a) user and device discovery and (b) negotiation of media stream properties (e.g. encoding, transport protocol) during the transfer of a media flow among different devices.
Detecting intrusive activities from insiders in a wireless sensor network using game theory BIBAFull-Text 15
  Ioanna Kantzavelou; Panagiotis F. Tzikopoulos; Sokratis K. Katsikas
Compromised nodes in a Wireless Sensor Network disrupt its specified normal operation. To identify and isolate such nodes is essential in pervasive computing environments where WSNs have numerous applications. We model a three player non-cooperative game, to study the interactions between an insider and the Intrusion Detection Systems used in a WSN. By solving the game, we locate the Nash equilibria to determine how players should play it. Examining these equilibria, useful suggestions for recommended strategies can be made. Properly selected strategies assist a compromised node's identification and its subsequent isolation.

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

Exploiting the universAAL platform for the design and development of a physical activity monitoring application BIBAFull-Text 16
  Vassilis Kilintzis; Ioannis Moulos; Vassilis Koutkias; Nicos Maglaveras
While various technical approaches for constructing Ambient Assisted Living (AAL) applications/services have been proposed, it has become apparent that interoperability of AAL systems is the key challenge that has to be tackled for exploiting AAL technologies in their full potential. Equally important, there is a lack of tools that can support AAL system/application developers to implement systemic and affordable solutions. The objective of this work is to illustrate the design and development of a basic AAL application devoted to physical activity monitoring by exploiting the universAAL open platform and tools. Our main goal is to illustrate the procedure that developers have to follow for such a development as well as the benefits offered from the adoption of universAAL in terms of extensibility and interoperability.
Exploring ambient assisted living job profiles BIBAFull-Text 17
  Theodor Panagiotakopoulos; Aspasia Theodosiou; Achilles Kameas
Ambient Assisted Living (AAL) is meeting wide acceptance and implementation, becoming a rapidly growing economic sector and creating new jobs. Nevertheless, proper education for qualifying employees in the AAL area is still massively lagging behind. CompAAL is an EU funded project aiming to develop a set of qualification profiles for players in the field of AAL. This paper presents the preliminary results of user analysis regarding AAL qualifications and training needs, as well as the research methodology used for collecting and processing related data.
Inconspicuous on-bed respiratory rate monitoring BIBAFull-Text 18
  Ming-Chun Huang; Wenyao Xu; Jason Liu; Lauren Samy; Amir Vajid; Nabil Alshurafa; Majid Sarrafzadeh
The monitoring of human respiratory rate is essential in many clinical applications including the detection and monitoring of sleep disorders, the monitoring of newborns for Sudden Infant Death Syndrome (SIDS), and identifying patients at high risk up to 24 hours before an adverse event like stroke and cardiac arrest [1]. Traditional noninvasive respiratory rate measurements in a hospital setting rely on clinical staff to visually track a patient's chest movement for a period of time to derive the respiratory rate from the number of movements observed. Failure to perform continuous and quantified measurements of respiratory rate could result in an inability to rescue a patient exhibiting respiratory distress. Severe after effects hinder recovery and result in loss of time, cost, or even life. This paper proposes an e-textile pressure sensitive bed sheet to non-invasively and accurately measure respiratory rate by analyzing time-stamped pressure distribution sequences. The bed sheet provides a 24/7 quantified on-bed respiratory rate monitoring service. It is made of e-textile and is similar to a regular bed sheet in comfort. As a result, it can seamlessly fit in common clinical or home environments, reducing the possible interference with a patient's regular sleeping habits and resulting in a type of inconspicuous monitoring.
Liftacube: a prototype for pervasive rehabilitation in a residential setting BIBAFull-Text 19
  Marijke Vandermaesen; Tom De Weyer; Karin Coninx; Kris Luyten; Richard Geers
Persons with neurological disorders or spinal cord injuries, such as Cerebrovascular Accident (CVA) or Paraplegia patients, experience significantly reduced physical abilities during their activities of daily living. By frequent and intense physical therapy, these patients can sustain or even enhance their functional performance. However, physical therapy, whether or not it is supported by technology, can currently only be followed in a rehabilitation centre under supervision of a therapist. To provide technology-supported physical therapy for independent use by the patient in the home situation, our current research explores pervasive technologies for rehabilitation systems. In this paper, we describe our pervasive prototype 'Liftacube' for training of upper extremities. An initial evaluation with patients with a neurological disorder or spinal cord injury (CVA and paraplegia patients) and their therapists reveals a great appreciation for this motivating pervasive gaming prototype. Reflections on the technical set-up (such as size, form factor, and materials) and interaction preferences (such as feedback, games, and movements for interaction) for pervasive rehabilitation systems in a residential environment are elaborated upon.
The visually pervasive augmented world BIBAFull-Text 20
  Paul Sassaman; Eric Becker; Fillia Makedon
In this paper, we describe several existing Augmented Reality projects that illustrate critical yet currently disparate applications of Augmented Reality. This paper then describes a partially implemented system (the Visually Pervasive Augmented World) that has begun work on merging all of these applications together in an attempt to provide as much functionality as possible, while keeping the hardware requirements as accessible to the general public as possible. Once completed, this system will offer complete customizability to users, allowing them to interact with and modify their augmented world through user-submitted static and animated 3D models, text, a custom scripting language, and location and object based Augmented Reality.

Usability and HCI issues

Augmented manufacturing: a study with impaired persons on assistive systems using in-situ projection BIBAFull-Text 21
  Oliver Korn; Albrecht Schmidt; Thomas Hörz
Production work requires a high level of awareness and especially manual assembly work is prone to human errors. At the same time the demand for manual assembly grows. Assistive systems in production environments (ASiPE) have to be augmented to improve the overall performance and reduce skill requirements.
   In this study the prototype of an augmented ASiPE is applied in an experiment with impaired persons. It uses in-situ projection (i.e. the projection of work-relevant information directly into the working space, Figures 1, 8) to cognitively assist users in assembly and to improve their inclusion in regular work processes. The aim is to observe their behavior with this new form of human computer interaction and to empirically quantify the effects on performance both in time and quality.
   The results show that the augmentation has a catalytic effect: The test subjects assembling slowly could not cope with the augmented ASiPE and performed worse than their counterparts without augmentation. The test subjects who worked faster than average assembled the product significantly better, both with respect to time (14.5% reduction) and especially to quality (45.8% error reduction). The ability to access the potential of augmented workplaces seems to be related to a worker' cognitive potential which is not adequately mapped by the competence ratios sheltered work organizations currently use.
Lessons from our elders: identifying obstacles to digital literacy through direct engagement BIBAFull-Text 22
  Shreya Kumar; Leo C., II Ureel; Harriet King; Charles Wallace
In today's world, technological change outpaces many people's ability to comprehend or trust it, let alone embrace it. It is vitally important that developers of pervasive technology for the elderly are grounded in the needs, experience, and capabilities of the people they seek to help. We have organized and participated in an ongoing outreach program that trains elderly residents of our rural community in digital literacy skills. The attendees at our help sessions, having been left behind in earlier iterations of the technological revolution, exemplify the challenges facing the designers of tomorrow's assistive technology. We report on the lessons we have learned in this regard through the interactions with our elderly participants. We identify three recurring themes: anxiety stifles exploration, details obscure abstraction, lag complicates adoption -- illustrating them with real stories gleaned from our records. We offer our program as a model for engagement with the elderly, helping them overcome their obstacles to literacy and giving us researchers a non-invasive perspective on their situation.
User interface for social networking application for the elderly BIBAFull-Text 23
  Tero Kivimäki; Petra Kölndorfer; Antti-Matti Vainio; Harri Pensas; Timo Vuorela; Markus Garschall; Jukka Vanhala
Elderly people with no or limited skills of using computers are in risk of social isolation as social life moves to the Internet. This paper describes the design process and implementation of a user interface and device for the elderly for a social networking application. The idea is that people with no previous experience on using computers are able to use the device immediately and that the device is not considered to be a computer. An iterative and user-centred design process is used to ensure that all the needs and views from the users are taken into account. The user interface and the device have been tested in long lasting field trials and the results are presented in this paper. Based on the results the implemented device seems to qualify the needs of elder users.
Preliminary investigation of the impact of visual feedback on a camera-based mouse-replacement system BIBAFull-Text 24
  Wenxin Feng; Ming Chen; Margrit Betke
This paper reports the design, implementation, and results of a carefully designed experiment that examined the performance of a camera-based mouse-replacement interface that was supported with visual feedback. Four different visual feedback modes were tested during the pointing-task experiment. Quantitative results, based on three metrics, do not show statistically significant difference between these modes. Qualitative feedback from the participants of the experiments, however, shows that user experience is improved by static and animated visual feedback during the pointing task.
A qualitative study to support a blind photography mobile application BIBAFull-Text 25
  Dustin Adams; Lourdes Morales; Sri Kurniawan
Both sighted and visually impaired people value having a photographic memento of a place or an event. However, due to the visually oriented nature of photography and the lack of non-visual cues to indicate the content of the photo, the common belief is that it is difficult for people with limited vision to take, organize and share pictures. However, we did not find a structured study on the photographic practice of those with limited vision. We ran a survey among 54 totally blind, light perception, and legally blind participants to investigate their photo taking, browsing, and online sharing. Based on this survey, we developed a mobile app to help blind persons take and recognize picture content using non-visual cues. The application was tested with five legally and totally blind persons with mostly positive results.

European projects USEFIL

Event recognition for assisted independent living BIBAFull-Text 26
  Nikos Katzouris; Alexander Artikis; Fillia Makedon; Vangelis Karkaletsis; George Paliouras
We present the application of a recently proposed probabilistic logical formalism, on the task of sensor data fusion in the USEFIL project. USEFIL seeks to extract valuable knowledge concerning the well-being of elderly people by combining information coming from low-cost, unobtrusive monitoring devices. The approach we adopt to device its data fusion component is based on the Event Calculus and the stochastic logic programming language ProbLog and aims towards constructing a semantic representation of the received data, usable by a Decision Support System that will assist elderly people in their every day activities and will provide to doctors, relatives and carers insights on the user's behaviour and health.
Towards a hierarchically-structured decision support tool for improving seniors' independent living: the USEFIL decision support system BIBAFull-Text 27
  Antonis S. Billis; Elpiniki I. Papageorgiou; Christos Frantzidis; Evdokimos I. Konstantinidis; Panagiotis D. Bamidis
In the current work, we present our position towards the modeling of a decision support system for health assessment and prevention of risky situations in the life of seniors. A two-layer architecture based on the Fuzzy Cognitive Maps (FCMs) methodology is considered as the main tool to encode medical knowledge and reason about the health status of seniors. This is the initial step, since outputs of several discrete FCM models are then combined to form the input concepts for an upper level schema (the health status of the senior) of upper-level concepts and relationships, so as to infer about recommended individualized therapies and interventions that would help therapists to prevent risky situations and enhance the independence and quality of life of the seniors. A modeling sample of the depression assessment is presented at the first level of the proposed architecture, while am integration schema of the proposed approach provides a view of our future extended model.

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

Evaluation of respiration quality using smart phone BIBAFull-Text 28
  Neeraj K. Gupta; Ram Dantu
Breathing is one of the vital signs that are considered important from medical point of view. The quality of breathing is evaluated by considering several factors. In this paper we present the results of experiments that use a smart phone to evaluate some of the factors to determine the quality of breathing. The accelerometer in the smart phone is used to measure the breathing. We measure subjects with normal breathing, slow breathing, fast breathing and irregular breathing. Our results show that we can evaluate the rate of breathing using a smart phone with an accuracy ranging from 95% to 100%. We can also evaluate the regularity and the effort of breathing.
Robust offline topological map estimation using visual loop closures BIBAFull-Text 29
  Dimitrios Kosmopoulos; Ilias Maglogiannis; Fillia Makedon
A framework employing the Student-t pdf is introduced for offline map estimation and robot localization using visual loop closures. The framework uses the Student-t pdf (a) as an observation model of a Hidden Markov Model to represent a topological map (b) to represent the robot motion model. The map and the motion model are calculated in an expectation maximization (EM) framework. We show that the estimator converges at linear time and that the provided accuracy is higher compared to using a conventional Gaussian mixture pdf, due to higher noise resiliency, as well as compared to using a fixed robot motion model. The task is assisted by unsupervised landmark definition through the EM-based clustering of the observations and by scene representation using the complex Zernike moments, which provide rich rotation-invariant information. The validity of the method has been verified experimentally using the input from an omnidirectional camera.
Using CAVE in physical rehabilitation exercises for rheumatoid arthritis BIBAFull-Text 30
  Shawn N. Gieser; Eric Becker; Fillia Makedon
Rheumatoid Arthritis is a chronic disease that leads to swelling and inflammation of the joints and even spread to surrounding tissues and blood vessels. Physical therapy has been used successfully to slow the effects of this degenerative disease. Patients, however, do not want to do these exercises due to the fact they are boring and repetitive. In this paper, we introduce the first steps in creating a virtual environment using a CAVE System for the physical therapy sessions where the user will be engaged and motived to complete the exercises prescribed by his or her doctor.
A comprehensive system for locating medical services BIBAFull-Text 31
  David Allen; Ovidiu Daescu
The changing nature of healthcare has created a demand for new tools to support both seekers and providers of medical services in order to ensure that the optimal delivery of care is provided. Recent advances in health related technologies as well as new modes of patient/provider interaction have created a unique set of novel challenges. Patients often face the daunting task of sifting through large amounts of options when it comes to choosing a medical service provider to receive care from. Several factors including the availability, cost, quality, and physical location of specific services must all be considered by the patient when choosing a provider. In this paper we describe a novel mobile application that allows users to query a database of medical providers to find the set of best possible options tailored to the user's specific needs and situation. The user makes a query by specifying a geographic search range centered on a polyline, and can further filter results by defining constraints such as insurance coverage and treatment cost.
Design sketching for assistive travel services BIBAFull-Text 32
  Ozge Subasi
This paper outlines some important qualities of sketching as a design technique for assistive technologies. During the design process of a collaborative project, we studied four different types of sketches with seniors. Through these sketches we discussed ideas around tourism, human values and interaction issues with special regards to the context of aging. The design process, insights and results from studies with fifty senior travelers showed that, design sketching has different impacts based on the sketch type. This further impacts the nature of data gathered from multi-faceted design space of AAL for future products. As visual and corporate design of AAL products are becoming increasingly important for the adoption of such products, the detailed understanding of related design techniques such as sketching is equally important for the development of such products.

Signal and image processing for ambient intelligence and pervasive computing

Multiresolution similarity search in time series data: an application to EEG signals BIBAFull-Text 33
  Amalia Charisi; Fragkiskos D. Malliaros; Evangelia I. Zacharaki; Vasileios Megalooikonomou
Time series constitute a prevalent data type that arise in several diverse disciplines (e.g., biomedical data, sensor data, images, video data), and therefore analyzing time series is a significant task with a plethora of important applications. In this paper, we study the general problem of similarity search in time series databases and we propose a novel multiresolution indexing (i.e., representation) and retrieval method for time series similarity search. Our approach is motivated by the idea that if we examine a time series at different resolution levels, we could possibly acquire further insights about the data. The proposed algorithm adopts a combined, two-step pruning (filtering) strategy to further reduce data dimensionality by discarding irrelevant time series (i.e., false alarms). At a first level, the time series are represented by line segments and filtered by the triangular inequality property. Then, a Vector Quantization like scheme is applied to encode data and thus to reduce dimensionality.
   We test and demonstrate the performance of the proposed method, analyzing EEG time series data for retrieval of one of the constituent brain waveforms in EEG recordings, the K-complex, but the method can as well be applied for retrieval of other patterns of interest in time series analysis. The automatic detection and categorization of the EEG patterns will allow the advanced correlation analysis of large amounts of data and will lead to advanced decision making capabilities assisting diagnosis by medical professionals.
Kinesiologic electromyography for activity recognition BIBAFull-Text 34
  Maurizio Caon; Francesco Carrino; Antonio Ridi; Yong Yue; Omar Abou Khaled; Elena Mugellini
This paper presents a wearable system based on kinesiologic electromyography that recognizes the user activity in real time. In particular, the system recognizes the following five activities: "walking", "running", "cycling", "sitting" and "standing". We conducted a study in order to select the opportune muscles and sensors placement. Furthermore, we evaluated the system conducting two analyses: impersonal and subjective. The impersonal analysis evaluated the system behavior when it was trained on several users' data; on the opposite, the subjective analysis evaluated the system when it was specialized on a single subject data. In the impersonal analysis, the accuracy rate was 96.8% for the 10-fold cross-validation and 91.8% for the leave one subject out. The system accuracy rate for the subjective analysis was 99.4%.
Speech adventure: using speech recognition for cleft speech therapy BIBAFull-Text 35
  Zak Rubin; Sri Kurniawan
Children with cleft palate or lip learn to speak in a way that compensates for the cleft. Their speech becomes unintelligible even after surgery to correct the cleft. Most children undergo speech therapy for many years after the surgery. The boring nature of the cleft speech therapy often causes children to abandon home exercises. We posit that a game that can effectively motivate these children to practice at home would speed up recovery. However, currently, very little has been done in gaining an understanding of the children's, parents' and speech pathologists' needs and requirements. This paper discusses the design and development of the speech recognition system. From this work we developed a speech recognition system capable of detecting the omissions, substitutions, and compensations characteristic in cleft speech with extremely high accuracy.
Thermal imaging for affect detection BIBAFull-Text 36
  Verónica Pérez-Rosas; Alexis Narvaez; Mihai Burzo; Rada Mihalcea
In this paper, we explore a thermal imaging approach to sensing affective state. Using features extracted from a thermal map of the face, obtained from a dataset consisting of 70 recordings of positive, negative, or neutral states, we show that we can effectively predict the presence of affect, with an error reduction of up to 50% as compared to a majority class baseline.
Fisheye camera modeling for human segmentation refinement in indoor videos BIBAFull-Text 37
  K. K. Delibasis; T. Goudas; V. P. Plagianakos; I. Maglogiannis
In this paper, we concentrate on refining the results of segmenting human presence from indoors videos acquired by a fisheye camera, using a 3D mathematical model of the camera. The model has been calibrated according to the specific indoor environment that is being monitored. Human segmentation is implemented using a standard established technique. The fisheye camera used for video acquisition is modeled using a spherical element, while the parameters of the camera model are determined only once, using the correspondence of a number of user-defined landmarks, both in real world coordinates and on the acquired video frame. Subsequently, each pixel of the video frame is inversely mapped to the direction of view in the real world and the relevant data are stored in look-up tables for very fast utilization in real-time video processing. The proposed fisheye camera model enables the inference of possible real world positions of a segmented cluster of pixels in the video frame. In this work, we utilize the constructed camera model to achieve a simple geometric reasoning that corrects gaps and mistakes of the human figure segmentation. Initial results are also presented for a small number of video sequences, which prove the efficiency of the proposed method.
Myoelectric transradial prosthesis prototype with intuitive single-grasp capability BIBAFull-Text 38
  Fred, Jr. Clark
An electromyography (EMG) acquisition/analysis circuit was created to facilitate intuitive, real-time control for a human/computer interface (HCI). Electrical activity in the user's target muscular region, which exceeds a specified threshold, translates into actuation of the designated primary grasp for the commercial product, MechaTE robotic hand. The interface was successful in a real-time demonstration where a user was able to catch a billiard ball moving across a pool table. This prototype provides the foundation for a more advanced HCI, with dexterous, multi-grasp capabilities. Future work aims to create a novel non-invasive brain computer interface (BCI) which can be used to restore partial functionality to transradial amputees.

Data modeling and information management for pervasive assistive environments

Mining usage data for adaptive personalisation of smartphone based help-on-demand services BIBAFull-Text 39
  William Burns; Liming Chen; Chris Nugent; Mark Donnelly; Kerry Louise Skillen; Ivar Solheim
Mobile computing devices and their applications that encompass context aware components are becoming increasingly more prevalent. The context-awareness of these types of applications typically focuses on the services offered. In this paper we describe a framework that supports the monitoring and analysis of mobile application usage patterns with the goal of updating user models for adaptive services and user interface personalisation. This paper focuses on two aspects of the framework. The first is the modelling and storage of the usage data. The second focuses on the data mining component of the framework, outlining the five different capabilities of the adaptation in addition to the algorithms used. The proposed framework has been evaluated through specific case studies, with the results attained demonstrating the effectiveness of the data mining capabilities and in particular the adaptation of the User Interface. The accuracy and efficiency of the algorithms used are also evaluated with three users. The results of the evaluation show that the aims of the data mining component were achieved with the personalisation and adaptation of content and user interface, respectively.
Natural interaction expressivity modeling and analysis BIBAFull-Text 40
  George Caridakis; Konstantinos Moutselos; Ilias Maglogiannis
Behavior, including non verbal, expressiveness is an integral part of the communication process since it can provide information on the emotional state and the user's performance when the aim of the interaction is measurable. Long term temporal measurements can also assist in monitoring the user for either emergencies or long term mood instabilities. Current article presents research work on the computational formalization and analysis of full body 3D expressivity in Natural (bodily) Interaction within the framework of Pervasive Assistance. Expressivity dimensions are selected as the most complete approach to body expressivity modeling, since they cover the entire spectrum of expressivity parameters related to emotion and affect. In this study five expressivity parameters are computationally formalized, using different approaches based on silhouette, limbs position and joints rotation, for each expressivity feature. These approaches are then evaluated in terms of their effectiveness in modeling the expressivity aspect in question. The modeling effectiveness of each approach is assessed using Linear Discriminant Analysis (LDA) and its coefficients on the automatically extracted parameters, defined in the computational formalization, against an experimental dataset consisting of extreme expressions (positive and negative) of the investigated expressivity aspects. The experimental results confirm that the proposed Fading Silhouette Motion Volumes (FMSV) approach, is the most effective in modeling body expressivity.
Application of data mining techniques to determine patient satisfaction BIBAFull-Text 41
  Georgios Galatas; Dimitrios Zikos; Fillia Makedon
In this paper, we describe a novel methodology which employs machine learning as an alternative means to explore hospital characteristics and client satisfaction, for decision making and improved quality of care. We applied well known feature selection and data mining algorithms such as forward selection and Naïve Bayes respectively, to determine patient satisfaction, which is an important indicator of quality of care in hospital settings. Our dataset comprised of three types of data, (i) patient perception about received care, (ii) nurse perception about the working environment and (iii) organizational attributes of the hospital. Our experimental results exhibited high classification accuracy (87%), allowing valid conclusions to be reached about the organizational and workforce factors which attribute to patient satisfaction. Our findings were validated using traditional statistical methods such as binomial correlation and linear regression.
Remote smartphone monitoring for management of Parkinson's Disease BIBAFull-Text 42
  Teresa H. Sanders; Annaelle Devergnas; Thomas Wichmann; Mark A. Clements
Parkinson's Disease (PD) is a disabling neurodegenerative disease that affects approximately 1 million people in the United States. PD symptoms such as tremor, rigidity, bradykinesia and gait disturbances can be alleviated with drug treatments or deep brain stimulation; however, these treatments need to be appropriately adjusted over time. Monitoring the disease severity during intermittent physician visits for this purpose is notoriously imprecise. Remote and continuous monitoring of the severity of parkinsonism in these patients could therefore significantly improve the patient's health and quality of life. In recent work, we showed it is possible to discriminate between varying levels of parkinsonism and normal brain activity, based on motor cortex electroencephalograms (EEGs). We believe it may be possible to detect similar patterns in ambulatory human EEGs collected periodically during home health care visits. In this study, we investigate how these EEG readings can be used together with continuous smartphone gyroscope and accelerometer movement measurements to allow improved management of Parkinson's Disease treatments.
Mobile learning for clinical practice guidelines implementation: a medical app for pediatric acute gastroenteritis BIBAFull-Text 43
  Emanuele Nicastro; Francesco Piccialli; Andrea Lo Vecchio; Alfredo Guarino; Salvatore Cuomo
Clinical practice guidelines (CPGs) are systematically developed documents that assist healthcare practitioners in making decisions about appropriate care for specific diseases based on evidence. In this context, acute gastroenteritis (AGE) in pediatrics is a suitable model for guidelines implementation and CPGs are available and very straightforward. Unfortunately, CPGs for AGE are poorly applied and most children receive not needed interventions. Mobile learning is a collaborative form of learning that can be used as a strategy of implementation for CPGs, for its portability and spreading capacity at a reasonable cost. In this paper we describe the development of a smartphone/tablet application for physicians providing guided decision making and carrying guidelines content about pediatric AGE in order to implement the pivotal recommendations from the CPGs and to foster their diffusion.

Cognitive systems and pattern analysis tools for assistive environments

Genre classification of symbolic music with SMBGT BIBAFull-Text 44
  Alexios Kotsifakos; Evangelos E. Kotsifakos; Panagiotis Papapetrou; Vassilis Athitsos
Automatic music genre classification is a task that has attracted the interest of the music community for more than two decades. Music can be of high importance within the area of assistive technologies as it can be seen as an assistive technology with high therapeutic and educational functionality for children and adults with disabilities. Several similarity methods and machine learning techniques have been applied in the literature to deal with music genre classification, and as a result data mining and Music Information Retrieval (MIR) are strongly interconnected. In this paper, we deal with music genre classification for symbolic music, and specifically MIDI, by combining the recently proposed novel similarity measure for sequences, SMBGT, with the k-Nearest Neighbor (k-NN) classifier. For all MIDI songs we first extract all of their channels and then transform each channel into a sequence of 2D points, providing information for pitch and duration of their music notes. The similarity between two songs is found by computing the SMBGT for all pairs of the songs' channels and getting the maximum pairwise channel score as their similarity. Each song is treated as a query to which k-NN is applied, and the returned genre of the classifier is the one with the majority of votes in the k neighbors. Classification accuracy results indicate that there is room for improvement, especially due to the ambiguous definitions of music genres that make it hard to clearly discriminate them. Using this framework can also help us analyze and understand potential disadvantages of SMBGT, and thus identify how it can be improved when used for classification of real-time sequences.
mCOPD: mobile phone based lung function diagnosis and exercise system for COPD BIBAFull-Text 45
  Wenyao Xu; Ming-Chun Huang; Jason J. Liu; Fengbo Ren; Xinchen Shen; Xiao Liu; Majid Sarrafzadeh
COPD (Chronic Obstructive Pulmonary Disease) is a serious lung disease that causes difficulty in breathing. COPD patients require lung function examinations and perform breathing exercises on a regular basis in order to manage and be more aware of their health status. In this paper, we designed and developed a mobile-phone based system for lung function diagnosis, called mCOPD. Besides enabling accurate COPD examinations at home, the mCOPD system also offers a video-game based guidance system for breathing exercises. We evaluated mCOPD in controlled and uncontrolled environments with 40 subjects. The experimental results show that our system is a promising tool for remote medical treatment of COPD.
Quantifying cognitive impairment due to physical or mental stress BIBAFull-Text 46
  Neeraj K. Gupta; Ram Dantu
In this paper, we study impairment caused by physical stress and impairment caused by alcohol consumption. We first base line the EEG waves in a meditation state. Then we measure the EEG waves during the physical activities such as walking, climbing stairs and doing sit-ups. We also measure the effect on brain as a person spins while sitting in a revolving chair (simulating a mental stress). Finally, we measure the EEG waves after consumption of alcohol. Our study shows that EEG waves do capture the physical activities that cause impairment. The magnitude of EEG waves increases with increased intensity of stress as measured by physical exercise or alcohol consumption. The magnitude is highest for sit-ups as compared to other activities and the magnitude for sit-ups after alcohol is even higher when compared with magnitude before alcohol consumption. A higher magnitude means lower level of alertness. The results could be used to improve the care of elderly and plan the intensity of their physical activity.
The role of dictionary learning on sparse representation-based classification BIBAFull-Text 47
  Soheil Shafiee; Farhad Kamangar; Vassilis Athitsos; Junzhou Huang
This paper analyzes the role of dictionary selection in Sparse Representation-based Classification (SRC). While SRC introduces interesting results in the field of classification, its performance is highly limited by the number of training samples to form the classification matrix. Different studies addressed this issue by using a more compact representation of the training data in order to achieve higher classification speed and accuracy. Representative selection methods which are analyzed in this paper include Metaface dictionary learning, Fisher Discriminative Dictionary Learning (FDDL), Sparse Modeling Representative Selection (SMRS), and random selection of the training samples. The first two methods build their own dictionaries via an optimization process while the other two methods select the representatives directly from the original training samples. These methods, along with the original method which uses all training samples to form the classification matrix, were examined on two face datasets and one digit dataset. The role of feature extraction was also studied using two dimensionality reduction methods, down-sampling and random projection. The results show that the FDDL method leads to the best classification accuracy followed by the SMRS method as the second best. On the other hand, the SMRS method requires a much smaller learning time which makes it more appropriate for dynamic situations where the dictionary is regularly updated with new samples. The accuracy of the Metaface dictionary learning method was specifically less than the other two methods. As expected, using all the training samples as the dictionary resulted in the best recognition rates in all the datasets but the classification times for this approach were far larger than the required time using any of the three dictionary learning methods.
Using SWRL and ontological reasoning for the personalization of context-aware assistive services BIBAFull-Text 48
  Kerry-Louise Skillen; Liming Chen; Chris Nugent; Mark Donnelly; William Burns; Ivar Solheim
The prevalence and advancements of existing context-aware applications are limited in their support of personalization for the user. The increase in the use of context-aware technologies has sparked growth in assistive applications and there is now a need to enable the adaptation of such technologies to reflect the changes in user behaviors. This paper describes the conceptualization and development of a personalization mechanism that can be integrated into a context-aware application for the purposes of providing an adaptable, mobile-based service to a user. We highlight the use of an ontological User Profile Model to provide a detailed representation of a user for use within adaptive applications. Special emphasis is placed on the use of rule-based reasoning using the Semantic Web Rule Language (SWRL). The paper details how these rules are created and used alongside the User Profile for the purposes of application personalization. We present a case study to illustrate the use of SWRL within the User Profile Model. Specifically, the case study focuses on providing personalized travel assistance to older users, with the use of self-service ticket machines via an 'on-demand' context-aware smart-phone.

Poster session

An adaptive dialogue system for assessing post traumatic stress disorder BIBAFull-Text 49
  Alexandros Papangelis; Robert Gatchel; Vangelis Metsis; Fillia Makedon
In this paper, we present a system which is able to interact through natural dialogue, with PTSD patients, as well as to guide the conversation aiming to elicit enough information to make an assessment of their condition, in a manner similar to a self assessment test. Our system is able to adapt to each individual patient and can operate in two modes: one that stores information about previous sessions with a patient to provide a sense of trust and relationship; and one that does not store information to preserve anonymity.
Assistive technologies to track ocean forests: data visualization and clustering for large scale systems BIBAFull-Text 50
  David Paulk
P. oceanica is a species of seagrass indigenous to the shallow water seabeds in Mediterranean Sea. The large underwater meadows it forms span the shallower waters around the islands and are vital to the sustainability of its encompassing marine ecosystem. Recently, environmental impacts have resulted in an irreversible degradation of the species. Stronger evidence of degradation is needed to provide reason for changing policy on activities that are potential sources of environmental impact. By running a classification algorithm on aerial imagery containing visible P. oceanica, data points that circumscribe the species in polygons can be created. By projecting this data on the original images, information about the species' environmental presence is visualized. Accuracy of the data can be verified by collecting ground truthing data. When repeated over multiple years, a history of the environment and the species' coverage can be built, providing evidence of environmental trends.
Biomedical sensor properties of flexible PolyVinyliDene flouride BIBAFull-Text 51
  Vasiliki N. Ikonomidou; A Jayadeva; Robert W. Newcomb; Mona Zaghloul
The flexible piezoelectric material PVDF is discussed with respect to its properties for uses in biomedical engineering.
Exploring voice user interfaces for seniors BIBAFull-Text 52
  S. Schlögl; G. Chollet; M. Garschall; M. Tscheligi; G. Legouverneur
Recent product releases such as Apple's Siri and Google's Voice Search have strongly emphasized the use of voice as a modern interaction modality. Seniors, in particular, might appreciate an alternative to small mobile phone keypads, touchpads and computer mice. This paper presents initial explorations of how elderly people would interact with language-technology-driven interfaces, how these interactions measure up against traditional physical interaction channels, and what features they may require to satisfy the needs of this very specific user group.
Operational effects of a mobile robot system for cleaning ventilation ducts BIBAFull-Text 53
  Wootae Jeong; Seung-Woo Jeon; Duckshin Park
Eliminating various contaminants and particular matters accumulated inside the ventilation system of the confined space such as subway stations becomes key issue for conserving high air quality and green indoor environment. Accumulated various pollutants at inner duct surface can cause secondary air contamination and injure subway passengers' respiratory system and health. In fact, periodic duct cleaning works can improve indoor air quality, but cleaning entire ventilation system takes high cost and manpower. This study addresses the effectiveness of duct cleaning based on the developed autonomous duct cleaning robot. In particular, the new duct cleaning robot equipped with compliance rolling brushes enables to operate robot in a constant cleaning force to the target duct surface. Control method with the compliant device has also been analyzed. The proposed design of autonomous duct cleaning robot is expected to save the operating cost of subway ventilation system and sustain clean indoor air quality by providing easier and faster cleaning tools.
Patterns of inquiry in computer literacy help sessions for the elderly BIBAFull-Text 54
  Shreya Kumar; Charles Wallace
The worldwide demographic shift toward an aging population in developed countries highlights the need for more technology-based assistance for the elderly. The success of any assistive technology system depends on motivated, literate users; hence it is important to study how elder users learn and what their motivations for learning technology are. Our volunteer computer literacy sessions at the local library are a rich source of communication, providing insights into the learning process for elders. Using a small sample of these conversations, we apply a communication pattern language to qualitatively analyze the communication strategies and tactics that tutors and learners use. We are able to shed light on the patterns of learning technology use for elder users, to be able employ those principles in system design.
User requirements for navigation assistance in public transit for elderly people BIBAFull-Text 55
  Stefanie Müller; Felix Kamieth; Andreas Braun; Tim Dutz; Peter Klein
In the last decades the demographic change in Europe has become apparent. In Germany already 20% of the population are older than 65. This age group is particularly affected by the increasing complexity of modern public transit systems. In this paper we present the results of a user requirements elicitation of a navigation assistant for elderly people in public transit. This system shall have a targeted user experience and takes into account the personal profile of the different users, e.g. modeling mobility deficiencies that require walking aids and prevents paths that would be impassable. We have performed an exhaustive user evaluation in expert interviews and focus groups to identify suitable interface choices and in the process were able to exclude some systems that were considered obvious in initial assessments.

Workshop on robotics in assistive environments

Developing visual competencies for socially assistive robots: the HOBBIT approach BIBAFull-Text 56
  K. Papoutsakis; P. Padeleris; A. Ntelidakis; S. Stefanou; X. Zabulis; D. Kosmopoulos; A. A. Argyros
In this paper, we present our approach towards developing visual competencies for socially assistive robots within the framework of the HOBBIT project. We show how we integrated several vision modules using a layered architectural scheme. Our goal is to endow the mobile robot with visual perception capabilities so that it can interact with the users. We present the key modules of independent motion detection, object detection, body localization, person tracking, head pose estimation and action recognition and we explain how they serve the goal of natural integration of robots in social environments.
Evaluating the accuracy of a mobile Kinect-based gait-monitoring system for fall prediction BIBAFull-Text 57
  Aaron Staranowicz; Garrett R. Brown; Gian-Luca Mariottini
Accurately and pervasively monitoring the human walking pattern (or gait) is fundamental to predict falls and functional decline, which are among the leading causes of injury and death in older adults. Existing gait-monitoring devices are not routinely used in clinical practice since they lack accuracy, ease-of-use, and unobtrusiveness. We present a novel breakthrough Kinect-based robotic system to accurately monitor the human gait during normal daily-life activities. Our system combines many interesting features: it has unlimited capturing volume, it is low cost, and does not require fiducial markers on the person. We present an extensive study of its accuracy in computing fall-prediction parameters when compared to the Vicon motion-capture system.
Adding obstacle avoidance to a robotic platform for human robot interaction BIBAFull-Text 58
  Christopher Abrego; Panos S. Shiakolas
In this paper, we describe the development and current state of an inexpensive platform for educational purposes and research in human robot interaction. The platform is based on the ubiquitous LabVIEW programming language and an in-house developed two degree of freedom non-holonomic robot. The platform includes multiple interaction modalities between the robot and the user. In this paper, we will describe the procedures followed for the successful software and hardware implementation and demonstration of an obstacle avoidance path planning algorithm thus augmenting the existing modalities. The algorithm uses a vision system to identify the location and size of an obstacle and generate the robot path to reach a desired goal while avoiding the obstacle. Current research focuses on algorithm development and implementation of path planning in the presence of multiple obstacles.
Development of an omniwheel-based holonomic robot platform for rough terrain BIBAFull-Text 59
  Christopher McMurrough; Harris Enotiades; Scott Phan; Stephen Savoie; Fillia Makedon
In this paper, we present an ongoing effort to develop a robust omnidirectional robotic platform for outdoor operation on non-smooth surfaces. The design of an off-road, low-cost omniwheel is presented along with a suspension system that will allow the platform to traverse rough terrain. We also provide a control architecture based on the open-source Robotic Operating System (ROS).
Physical human-robot interaction with a mobile manipulator through pressure sensitive robot skin BIBAFull-Text 60
  Joe Sanford; Isura Ranatunga; Dan Popa
In this paper we discuss a physical human-robot interaction system, resulting from the integration of existing open source robotics tools, sensor elements and a robotic mobile manipulator platform. A KUKA youBot ® mobile manipulator was sensorized using 7 FlexiForce® piezo-resistive sensors, attached to the surface of the manipulator arm. ROS transfers frame and Kinematics libraries transferred interaction pushing forces measured by the sensors to velocity commands to the robot. These results transformations were verified using a derived Denavit-Hartenberg table. Resulting robot movement is always parallel to the axis of detected forces, regardless of orientation of the sensors relative to the mobile manipulator's base, or the number of sensors detecting forces. Verification of this behavior was conducted during two separate experiments. This system and behavior will be used in future physical human-robot interaction research to perform assistive tasks.
An assistive object manipulation system BIBAFull-Text 61
  Alexandros Papangelis; Isura Ranatunga; Christopher McMurrough; Fillia Makedon
In this paper, we present a system targeted for assistive living environments, that is able to control the actuators of a robot and manipulate objects that lie on a table. An adaptive dialogue system is responsible for interacting with the user, retrieving his/her intentions and reacting accordingly. Our system is able to learn in real time how to solve complicated tasks by combining solutions to simpler ones, thus reusing previous knowledge. It is also able to effectively plan and execute table top object manipulation, which can have a great impact in the quality of life of an elderly, disabled or injured person.
A German-Chinese speech-gesture behavioural corpus of device control in a smart home BIBAFull-Text 62
  Dimitra Anastasiou; Cui Jian; Christoph Stahl
This paper reports on empirical studies on the use of speech and gesture interaction for device control in the Bremen Ambient Assisted Living Lab (BAALL) at the German Research Center for Artificial Intelligence at the University of Bremen. Our goal is to create and evaluate a multimodal corpus of device control (turn on lights, open sliding door, etc.). A Wizard-of-Oz user study was conducted in this lab with German and Chinese participants in order to carry out a comparative analysis of cross-lingual spatial spoken and gesture commands and report on cultural differences. The long-term goal is to design and develop a speech and gesture combining multimodal interactive system, while considering relevant behavioural aspects, such as cultural differences presented in this paper.
Designing a travel companion for mature age BIBAFull-Text 63
  Özge Subasi
Designing travel companions to assist older people is an important outcome of pervasive technologies for assistive environments. Building inclusive systems and interfaces that meet user requirements are reported to be key aspects for acceptance of such supportive technologies. Based on a value centered agenda and a participatory design approach, our explorations with senior travelers reveal in which ways senior travelers relate travel assistance to their lifestyles. Our findings from design research studies showed that, senior travelers associate certain values related to travelling and travel assistance, and they want to see these basic values as integrated visual components of such systems. We discuss the identified core values such as 'companionship' 'local awareness' and 'valuing volunteerism' and their relation to designing a travel assistant.
Feedback presentation for mobile personalised digital physical activity coaching platforms BIBAFull-Text 64
  Randy Klaassen; Rieks op den Akker; Harm op den Akker
User interface design and feedback are important in personalised behavior change support systems. This paper discusses two service platforms that monitor user's physical activity through wearable sensors and that present the user personalised feedback. Important principles for effectiveness of such systems are personalisation or tailoring, context-awareness, feedback and interaction. We focus here on the presentation of feedback to the user. We present results of a number of short and long term user studies in which we compare different forms of feedback presentation: text, graphics and with or without an anthropomorphic graphical talking character. Results show that although some users like the talking character they don't have a positive effect on adherence to the activity program. The outcomes of the user evaluations support our beliefs that personal motivation is of primary importance for the effectiveness of these systems. Technical challenges ahead are to support more personal and context-aware feedback, more variations as well as the possibility for more interaction with the coaching system.
Modeling the effect of attention deficit in game-based motor ability assessment of Cerebral Palsy patients BIBAFull-Text 65
  Michael Gardner; Vangelis Metsis; Eric Becker; Fillia Makedon
Cerebral Palsy (CP) is a central nervous system disorder affecting 2 out of every 1000 births. CP limits a person's muscular function. Rehabilitative, touch-screen gaming promises to assist in developing muscle tone and dexterity for hemi-paretic CP patients as well as help therapists keep track of a patient's performance over time. However, most systems fail to take into account other factors of the disorder that could affect the scoring of a patient differently on various assessment days -- specifically attention deficit or distraction. Cerebral Palsy is frequently associated with diagnosed Attention Deficit (Hyperactive) Disorder (ADD/ADHD), but even if a child does not fall within that definition, pediatric CP patients are often easily distracted. In this work we perform attention deficit simulation experiments with able-bodied users playing three rehabilitative games as well as similar computer generated data and propose a methodology to model and eliminate the effects of attention deficit or distraction from the scoring scheme used to evaluate the patient's motor abilities and progress over time.
MoodWings: a wearable biofeedback device for real-time stress intervention BIBAFull-Text 66
  Diana MacLean; Asta Roseway; Mary Czerwinski
Stress has a wide range of negative impacts on people, ranging from declines in real-time task performance to development of chronic health conditions. Despite the increasing availability of sensors and methods for detecting stress, little work has focused on automated stress interventions and their effect. We present MoodWings: a wearable butterfly that mirrors a user's real-time stress state through actuated wing motion. We designed MoodWings to function both as an early-stress-warning system as well as a physical interface through which users could manipulate their affective state. Accordingly, we hypothesized that MoodWings would help users both calm down and perform better during stressful tasks. We tested our hypotheses on a common stressful task: driving. While users drove significantly more safely with MoodWings, they experienced higher stress levels (physiologically and self-perceived). Despite this, users were enthusiastic about MoodWings, expressing several alternative contexts in which they would find it useful. We discuss these results and future design implications for building externalized manifestations of real-time affective state.
Sensor requirements for activity recognition on smart watches BIBAFull-Text 67
  Gerald Bieber; Marian Haescher; Matthias Vahl
The new generation of watches is smart. Smart watches are connected to the internet and provide sensor functionality that allows an enhanced human-computer-interaction. Smart watches provide a gesture interaction and a permanent monitoring of physical activities. In comparison to other electronic home consumer devices with integrated sensors, Smart watches provide monitoring data for 24h per day, many watches are water resistant and can be worn constantly. The integrated sensors are varying in performance and are not intended to distinguish between different states of activity and inactivity. This paper reports on identified requirements on sensors of smart watches for detection of activity, inactivity as well as sleep detection. Hereby a new measurement quantity is introduced and applications of heart beat detection or wearing situation are presented.

Workshop on participatory sensing in assistive environments

Using smart mobile devices for monitoring in assistive environments BIBAFull-Text 68
  Dimitrios Kotsakos; Panos Sakkos; Vana Kalogeraki; Dimitrios Gunopulos
Over the last few years, the vast majority of smart devices has been equipped with a variety of sensors, including acceleration, light and gravity sensors, magnetometers etc. Moreover, mobile smart devices possess high computational power, storage in the order of gigabytes, whereas high battery capacity and high bandwidth are available. The biggest advantage of the wide presence of mobile smart devices is that all this distributed computing power is already at hands of people, being idle for the most time. This fact presents a chance of utilizing this distributed computational infrastructure with the goal of building participatory sensing systems with various applications for environmental support, like health or structure monitoring. In this paper we are presenting a generic distributed framework consisting only of mobile smart devices and operating only in the network. We utilize a scalable, fault-tolerant communication protocol, that performs best-effort time synchronization of the nodes and present a first approach in an example application of distributed structural health monitoring (SHM).
Exploiting social networks for healthcare BIBAFull-Text 69
  Juliana Litou; Vana Kalogeraki
The proliferation of sensor networks, smartphone devices and social networking in the recent years have made it possible to use these technologies to monitor relationships established among humans in order to understand and capture social dynamics for assistive living and healthcare support. This evolution is now driven by participatory sensing systems where users use their phones as sensing devices and provide personal data for the benefit of the community, enabling new social, healthcare applications. One challenging question in these settings is detecting relationships between users of social networks. We initiate a study and propose an approach to measure the strength of social bond between individuals. Our goal is to highlight the capabilities of participatory sensing techniques in assistive living environments.