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

Proceedings of the 3rd International Conference on PErvasive Technologies Related to Assistive Environments

Fullname:Proceedings of the 3rd International Conference on PErvasive Technologies Related to Assistive Environments
Editors:Fillia Makedon
Location:Samos, Greece
Dates:2010-Jun-23 to 2010-Jun-25
Publisher:ACM
Standard No:ISBN: 1-4503-0071-5, 978-1-4503-0071-1; ACM DL: Table of Contents hcibib: PETRA10
Papers:71
Pages:452
Links:Conference Home Page
  1. Usability and HCI issues, multimodal interfaces
  2. Cognitive systems and machine learning for assistive environments
  3. Tools, infrastructures, architectures and techniques for deploying pervasive applications in assistive environments I
  4. Tools, infrastructures, architectures and techniques for deploying pervasive applications in assistive environments II
  5. Signal and image processing for ambient intelligence and pervasive computing
  6. Healthcare privacy and data security
  7. Pervasive systems for the aging society
  8. Data modeling and information management for pervasive assistive environments
  9. Networking technologies for healthcare information storage, transmission, processing, and feedback
  10. Workshop on Affect and Behaviour Related Assistance for the Elderly
  11. Workshop on Light-Weight Signal Processing for Computationally Intensive BSN Applications
  12. Workshop on Workflow and Event Analysis for Assistive Environments
  13. Poster session

Usability and HCI issues, multimodal interfaces

Assistive technologies and the visually impaired: a digital ecosystem perspective BIBAKFull-Text 1
  David J. Calder
Assistive technology devices for the visually impaired form a small part of a much wider support infrastructure of people and systems that cluster about a particular disability. Various disabilities, in turn, form part of a greater ecosystem of sometimes isolated support teams. These may cluster about a nucleus of various specific disabilities, such as vision impairment, speech or hearing loss, each focusing on their own particular disability category. Teams are comprised of therapists, caregivers, trainers, as well as device manufacturers, who design and produce computer-based systems such as mobility aids. There is, however, little evidence of any real crossover collaboration or communication between different disability support teams and a disparate cottage industry of manufacturers. The author proposes a collaborative digital ecosystem framework that may assist this challenge. Although this paper is not a survey of all available devices, examples of some commercial systems are cited in order to draw attention to user interface challenges that confront both those who rely on them.... and those who design them.
Keywords: ambient sound cues, assistive technology, disabled, infrared, laser, long cane, obstacle warning displays, portable electronic device, sensory channels, sound interface displays, ultrasonic pulse-echo, visually impaired
Haptic emulation of games: haptic Sudoku for the blind BIBAKFull-Text 2
  René Gutschmidt; Maria Schiewe; Francis Zinke; Helmut Jürgensen
For blind persons, information is often presented through substitute media. We explore the possibility of emulating visual perception through haptic perception completely using a new haptic display and using games as a paradigm. We describe an implementation of Sudoku which utilizes the capabilities of the display: representing the full Sudoku square in its natural form; entering numbers and notes in the boxes of the square; emulating visual scanning for information through scanning by touch; interacting by finger movement (gestures). The only non-haptic component consists of sounds played to signal the outcome of actions. This demonstrates the advantages of the planar touch-sensitive refreshable haptic display when compared with other interaction modes for blind persons.
Keywords: Sudoku, board games, gestural interaction, haptics, nonvisual communication, visually impaired
Voice commands for a mobile reading device for the visually impaired BIBAKFull-Text 3
  Robert Keefer; Sundaram Narayanan; Nikolaos Bourbakis
In this paper, we describe the interaction design of a mobile reader for visually impaired users. A prototype of the design was created and tested on eight blind users. The results of this usability test are reported here, and demonstrate that the proposed interaction design is an improvement over currently available interaction mechanisms.
Keywords: interaction design, visually impaired, voice user interface
Identification of static and dynamic muscle activation patterns for intuitive human/computer interfaces BIBAKFull-Text 4
  Fred, Jr. Clark; Dan Nguyen; Gutemberg Guerra Filho; Manfred Huber
The goal of this pilot research was to create an intuitive human-computer interface that would allow control of a robotic arm using the electromyographic (EMG) signals from a person's own arm movements (or muscle activations). There is enough information contained within EMG data to accurately differentiate between different movements based on the observed muscle strategy. After designing an algorithm, accurate prediction of arm movements was obtained; it determined whether the test subject's arm was moving up, down, left, right, or closing a fist, and also what base position the test subject was in if not moving. A successful interface was designed for using EMG data with a robotic arm, moving the robotic arm in the same direction that the test subject's arm moved, replicating a static position with the arm, and grabbing a piece of Styrofoam. With further research and refinement, this library of kinesiological movements can be expanded to encapsulate the spectrum of human arm movement.
Keywords: EMG interface, HCI, movement identification
Acoustical implicit communication in human-robot interaction BIBAKFull-Text 5
  Yong (Yates) Lin; Zhengyi Le; Eric Becker; Fillia Makedon
Explicit communication addresses the use of distinct language or protocol to convey the idea. Implicit communication helps to compensate many hidden meanings omitted from the explicit language. In some situations, implicit communication may even take the place of explicit communication. For the autonomous robot, implicit communication provides an alternative way to interact with people. This paper introduces the acoustic techniques for implicit communication in human-robot interaction, and the design of acoustical implicit communication based robot games.
Keywords: acoustic communication, human-robot interface, implicit communication

Cognitive systems and machine learning for assistive environments

Cognitive optimization in the development of assistive living systems BIBAKFull-Text 6
  Alan Bowling
This paper presents a preliminary exploration of the characteristics and structure of a cognitive architecture for control of assisted living systems. In this work the key aspects of the cognitive system considered are self-organization, communication, and the use of a priori knowledge. These aspects are used to explore a cognitive approach to optimization, which is considered to be a key aspect of a cognitive system. Test problems are examined in order to determine whether the cognitive structures proposed by psychologists can also perform optimization. The approach followed is to gift the cognitive optimization with a priori knowledge of how to solve optimization problems. This involves adapting and combining traditional optimization techniques, such as the bracketing, gradient search, and branch and bound, into a cognitive architecture. The algorithm is implemented as different processes that communicate and learn from each other by passing messages in order to organize around a solution. This approach is applied to four different problems with different levels of difficulty in order to gain insights into the structure and characteristics of cognitive optimization.
Keywords: assistive living system, cognitive control, optimization
Emotion detection via discriminative kernel method BIBAKFull-Text 7
  Hua Wang; Heng Huang; Yanzi Hu; Mindi Anderson; Pamela Rollins; Fillia Makedon
Human emotion detection is of substantial importance in diverse pervasive applications in assistive environments. Because facial expressions provide a key mechanism for understanding and conveying emotion, automatic emotion detection through facial expression recognition has attracted increased attention in both scientific research and practical applications in recent years. Traditional facial expression recognition methods normally use only one type of facial expression data, either static data extracted from one single face image or motion dependent data obtained from dynamic face image sequences, but seldom employ both. In this work, we propose a novel Discriminative Kernel Facial Emotion Recognition (DKFER) method to integrate these two types of facial expression data using a hybrid kernel, such that the advantages of both of them are exploited. In addition, by using Linear Discriminant Analysis (LDA) to transform the two types of original facial expression data into two more discriminative lower-dimensional subspaces, the succeeding classification for emotion detection can be carried out in a more efficient and effective way. Encouraging experimental results in empirical studies demonstrate the practical usage of the proposed DKFER method for emotion detection.
Keywords: discriminative learning, emotion detection, facial expression recognition, facial feature, kernel
Heart murmurs identification using random forests in assistive environments BIBAKFull-Text 8
  Euripides Loukis; Manolis Maragoudakis
The aging population in many countries, in combination with high government deficits and financial resources limitations, necessitates new methods for the home care of the elderly at reasonable costs based on the exploitation of modern information and communication technologies (ICT). This requires the installation of assistive environments at the homes of elderly people, which include various types of sensors, generating biosignals of other types of signals, which are transferred through networks to local health centers or hospitals in order to be monitored. However, scaling up the application of such ICT-based methods of elderly home care is going to increase tremendously the workload of the medical staff of local health centers or hospitals. Therefore it is of critical importance to develop capabilities for an automated first screening of these signals and identification of abnormal elements and diseases. In this direction the present paper proposes a system for the automatic identification of murmurs in heart sound signals, and also for the classification of them as systolic or diastolic, using a new generation of advanced Random Forests classification algorithms, which are aggregating the prediction of multiple classifiers (ensemble classification). The proposed system has been applied and validated in a representative global dataset of 198 heart sound signals, which come both from healthy medical cases and from cases having systolic and diastolic murmurs. Also, some alternative classifiers have been applied to the same data for comparison purposes. It has been concluded that the proposed systems shows a good performance, which is higher than the examined alternative classifiers.
Keywords: assistive environments, bio-signals processing, heart sounds diagnosis, random forests
Abnormal human behavioral pattern detection in assisted living environments BIBAKFull-Text 9
  Kyungseo Park; Yong Lin; Vangelis Metsis; Zhengyi Le; Fillia Makedon
In recent years, there is a growing interest about assisted living environments especially for the elderly who live alone, due to the increasing number of aged people. In order for them to live safe and healthy, we need to detect abnormal behavior that may cause severe and emergent situations for the elderly. In this work, we suggest a method that detects abnormal behavior using wireless sensor networks. We model an episode that is a series of events, which includes spatial and temporal information about the subject being monitored. We define a similarity scoring function that compares two episodes taking into consideration temporal aspects. We propose a way to determine a threshold to divide episodes into two groups that reduces wrong classification. Weights on individual functions that consist the similarity function are determined experimentally so that they can produce the good results in terms of area under curve in receiver operating characteristic (ROC) curve.
Keywords: abnormal behavior detection, assisted living environment, classification, similarity function, threshold value
Activity monitoring using an intelligent mobile phone: a validation study BIBAKFull-Text 10
  Yan Huang; Huiru Zheng; Chris Nugent; Paul McCullagh; Suzanne M. McDonough; Mark A. Tully; Sean O. Connor
This research examines both the practicalities and feasibility of using a smart phone in the monitoring of gross daily activity, namely step counts. An Adaptive Step Detection (ASD) algorithm has been proposed and evaluated, based on where the phone is worn on the body. Experiments involved collection of data from a participant who wore two mobile phones (placed at difference positions) while walking on a treadmill at a controlled speed for periods of five minutes. A video recording and pedometer were used to independently record the number of steps in addition to a count by human observation. A step detection calibration factor was determined via a data driven approach, i.e, for each recording, a calibration factor was obtained by learning from two thirds of the acceleration data gleaned from the accelerometer within the smart phone. The remainder of the data was used to test the algorithm. The step counts from the acceleration sensor were validated by the video recordings, which were consistent with the pedometer and human observation. The results show that the step counts detected by the proposed algorithm achieved accuracy of 100% when the mobile phone was placed in the right thigh positions, and achieved above 95% accuracy when the mobile phone was placed in the right breast pocket, bag over right shoulder and right ankle.
Keywords: acceleration signal processing, activity monitoring, adaptive step detection algorithm, intelligent mobile phone, wearable position validation

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

Optimizing pervasive sensor data acquisition utilizing missing values substitution BIBAKFull-Text 11
  M. Michalopoulos; C. Anagnostopoulos; Charalampos Doukas; Ilias Maglogiannis; S. Hadjiefthymiades
Acquisition of pervasive sensor data can be often unsuccessful due to power outage at nodes, time synchronization issues, interference, network transmission failures or sensor hardware issues. Such failures can lead to inadequate data delivery to the monitoring applications resulting in erroneous conclusions. This paper presents a missing values substitution framework that addresses the aforementioned issue. The presented framework has been evaluated within a pervasive sensor monitoring environment that collects and transmits patient health related data and results have been presented.
Keywords: healthcare data transmission, missing values substitution, pervasive sensors
An agent-based application of personal health record in homecare BIBAKFull-Text 12
  V. Koufi; F. Malamateniou; G. Vassilacopoulos
Homecare is an important component of the continuum of care as it provides the potential to improve quality of life and quality of healthcare delivery while containing costs. Personal Health Record (PHR) systems constitute a technological infrastructure that can support greater flexibility for healthcare professionals and patients, thus allowing for more effective homecare services. In particular, PHRs are intended to reach patients outside of care settings, influence their behaviors, and satisfy their demand for greater information and access. To this end, PHR technology needs to evolve well beyond providing a consolidated patient record, in ways that make it more widely applicable and valuable to health systems. The development of applications and tools on top of PHR systems can allow the PHR to function as a platform for patients to exchange information and interact with the health system (e.g., scheduling appointments electronically). This paper presents a prototype PHR-based system that aims at supporting chronic disease management. The system has been developed on the grounds of a service-oriented architecture where healthcare process automation is realized by means of dynamic, patient-related workflows.
Keywords: homecare, personal health record, software agents, workflow systems
Pervasive technology to facilitate wellness BIBAKFull-Text 13
  P. J. McCullagh; M. Beattie; C. D. Nugent
In this paper we evaluate the state of the art in systems with the ability to monitor health and wellness. We report on three categories of system: home telehealth monitoring, accelerometer based systems for classifying movement and state, and systems designed to provide feedback for athletes and sports enthusiasts. As these latter two approaches become pervasive, they can find application as systems that promote wellness in the general population. This can be particularly appropriate to the ageing population, if the systems can be tuned to their requirements, with particular reference to usability.
Keywords: feedback, home monitoring, mobile monitoring, wellness
Sensor placement and coordination via distributed multi-agent cooperative control BIBAKFull-Text 14
  Alexandros Papangelis; Vangelis Metsis; John Shawe-Taylor; Fillia Makedon
This paper examines the problem of sensor placement and coordination to maximize the sensor utilization when monitoring different types of environments. Our assumption is that the sensors are mobile and each sensor can have more than one type of sensing capabilities which can be active or not at each specific moment. The goal is to maximize the amount of information collected from the environment, given the limited amount of resources that the total of the available sensors can provide, and at the same time to be fault tolerant in failures of individual sensors by using a decentralized approach that re-organizes their placement in case of failures.
   We tackle this problem by employing a decentralized multi-agent coordination framework using message passing and the Max-Sum algorithm for building and maintaining a common picture of the area to be monitored. We show that by representing each sensor as an independent agent which can take decisions individually and at the same time can affect the decisions of its neighbouring sensor-agents we can provide a robust and efficient system for the monitoring of life-critical environments such as assistive environments or governmental infrastructures.
Keywords: max-sum algorithm, mobile sensors, multi-agent systems, sensor placement and coordination
A mobile robot for self-selected gait velocity assessments in assistive environments: a robotic driven approach to bring assistive technologies into established homes BIBAKFull-Text 15
  Melina Brell; Jochen Meyer; Thomas Frenken; Andreas Hein
This paper presents a novel idea on how mobile robots can be used to implement mobility assessments in home environments. The demographic change leads to an increasing demand of care, especially for elderly people. Falls are one major problem due to hospital stays, slow recovery time, and subsequent impairments. Assisting technologies from the field of Ambient Assisted Living could offer new diagnostic approaches and provide home assistance. Installing required technologies in a home environment is often difficult and costly. Here, mobile robots provide a new solution to bring sensors and actors into the home environment without any installation. Especially laser range scanners for robot navigation provide several possibilities to perform mobility assessments at home. In this paper results of a self-selected gait velocity assessment done with the aid of a laser range scanner are presented. The results show that it is possible to use a laser range scanner to compute the movement trajectory of a person and several parameters of gait. This offers new possibilities to transfer clinical assessment into the home environment. Mobility assessments in the domestic environment could be used for early and more objective detection of impairments and gait disorders.
Keywords: AAL, ambient assisted living, assessment, mobility, navigation, robot, robotic measurement
Fun to develop embodied skill: how games help the blind to understand pointing BIBAKFull-Text 16
  Francisco Oliveira; Heidi Cowan; Bing Fang; Francis Quek
We discuss how gaming can be used as a training strategy for students who are blind or visually impaired (SBVI) to develop embodied skill in use of haptic assistive technology. The technology takes the form of a haptic glove that is designed to give SBVI access to the pointing behavior of teachers in mathematics/science instruction that is performed in conjunction with speech and the use of instructional graphics. Our initial studies show that significant 'embodied skill' was required to afford fluent multimodal communication between the instructor and student. We developed a gaming strategy, employing flow theory to enhance the fun and engagement of the SBVI to promote extensive perceptual training. Our results showed significant improvement and interaction gains as the game-play progressed over multiple sessions. Results also indicate that skills developed through game play were persistent, and transferable to complex multimodal situated discourse conditions.
Keywords: ACM proceedings, assistive technology, embodied skill, gaming, multimodal discourse

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

A new tourist audio guide service for elderly people integrated in the mobile phone: preliminary results BIBAKFull-Text 17
  Unai Díaz; Álvaro García; Alejandro de Felipe
VITAL (Vital Assistance for the elderly) is a EC funded 6th Framework program project whose objective is to develop a set of technologies and applications with the aim to provide remote assistance to active 60+ years old users with normal cognitive ageing to improve their social network and context interaction, preventing them of being isolated and improving their quality of life. Within this context, the application known as Tourist Audio Guide is an innovative application for elderly tourists at their destination. The basic approach is to develop an audio guide that can be downloaded in a mobile phone to perform a simulation as close as possible to a human guide in the sense that the users will receive most of the information about a topic in "real time", allowing them to hear the explanations while they focus their attention on the "real thing". This paper describes the evaluation of the first prototype of this device with a small group of elderly users from the Community of San Sebastian (Spain), enhancing the problems and needs for further development addressed by them, which will be taken into account for a future improvement of the system's feasibility, usability and acceptability.
Keywords: VITAL, elderly, mobile services, user-centered design
A privacy-preserving protocol for finding the nearest doctor in an emergency BIBAKFull-Text 18
  Georgios Drosatos; Pavlos S. Efraimidis
In this work, we define the Nearest Doctor Problem (NDP) for finding the closest doctor in case of an emergency and present a secure multi-party computation for solving it. The solution is based on a privacy-preserving cryptographic protocol and makes use of the current location of each participating doctor. The protocol is efficient and protects the privacy of the location of all doctors. A prototype implementing the proposed solution for a community of doctors that use mobile devices to obtain their current location is presented.
Keywords: location privacy, peer-to-peer network, personal data, privacy-preserving protocol
Health monitoring using gait phase effects BIBAKFull-Text 19
  Richard Byrne; Parisa Eslambolchilar; Andrew Crossan
The need to monitor patients after they leave the hospital or clinics is of growing concern and doctors may need the facility to monitor certain patients more than others. For example patients with high blood pressure are sometimes fitted with a mobile monitor which can be used to track the patients blood pressure over time. Patients suffering from depression, however, may also need to be monitored to ensure that they are in a happy emotional state. In this paper we introduce an alternative approach to mood detection and tracking based on built-in accelerometer sensors found in common mobile phones. Our method can be seen to compliment the need to monitor such patients allowing for doctors to get in touch with them when their mood has altered. We build a system based on neural networks which takes the gait information and learns the associated mood of the user. This trained model is then used to detect the mood of the individuals. We demonstrate preliminary results on mood detection using a mobile prototype system.
Keywords: gait, gait phase, gait phase effects, health monitoring, mood detection, mood tracking, tracking
Sensor based micro context for mild dementia assistance BIBAKFull-Text 20
  J. Biswas; K. Sim; W. Huang; A. Tolstikov; A. Aung; M. Jayachandran; V. Foo; P. Yap
Due to decline in their cognitive function, elderly people with mild dementia living alone at home are at risk of making errors in their activities of daily living (ADLs). In order to help such people, most activity recognition systems for assistive living in smart homes attempt to classify activities from coarse grained context such as location or time of day. Location by itself however, does not provide adequate context information for the recognition of ADLs and instrumental ADLs. It does not help to know that a person is in the kitchen if we are interested in knowing whether or not he has taken his meal (ADL) or prepared it (iADL). Additional information about the activity is needed. In this paper micro-context is introduced as a key aspect both for activity recognition as well as for prompted correction. Initial results from our laboratory experiments are presented herein, and it is shown that micro-context is useful for both activity recognition and prompted error correction.
Keywords: activities of daily living (ADLs), ambient intelligence, assistance for ADLs, prompts and reminders, sensor based activity recognition
Computer based cognitive training for patients with mild cognitive impairment (MCI) BIBAKFull-Text 21
  Zafeiropoulos Stavros; Kounti Fotini; Tsolaki Magda
Brain activation through computer training of attention and executive function could stimulate brain plasticity in patients with Mild Cognitive Impairment (MCI). Aim: The study aimed to investigate the effectiveness of a computer based training on visual spatial abilities, visual attention, executive function and visual memory, in MCI patients. Method: The participants were 59 MCI patients, age 68.08 (7.25), education 9.17 (3.93), and MMSE 27.73 (1.35), classified in one experimental (N=30) and one control group (N=29). The groups were matched in age (p= 0.60), education (p= 0.06), drugs (0.51) and gender (p= 0.52). The experimental group attended 20 weekly sessions in a period of 6 months, including tasks of visual attention, visual spatial abilities, visual memory, and executive function. The control group did not participate in any type of intervention and was in a waiting list. Neuropsychological assessment was performed at baseline and at the end of the training. Results: At baseline, there were no between groups differences in cognitive abilities. At the end of the training, between groups comparison yielded differences in favor of the experimental group in attention (p≤ 0.00), verbal fluency (p= 0.00), visual memory (p= 0.01), verbal memory (p=0.00) and learning through feedback (p=0.00). Within group analysis of the experimental group's performance has shown improvement in attention (p=0.00) and daily function (p=0.00). Controls have shown an improvement in perseverant responses and cognitive flexibility (p≤0.00) and naming (p=0.02), and deterioration in abilities of attention (p≤0.00). Conclusion: Computer cognitive training helped the experimental group to improve attention abilities and the improvement was generalized in verbal memory and in ADL as well.
Keywords: MCI, assistive technology, cognitive training, dementia
ConstructFinder: web site interaction made easier BIBAKFull-Text 22
  Thomas Beer; Ilvio Bruder; Martina Weicht
This paper introduces ConstructFinder, a Firefox add-on to find semantic constructs in web pages. It uses the Unstructured Information Management Architecture (UIMA), developed by IBM, to analyse web sites in order to find semantic units like search fields or login forms. These constructs are then highlighted for easy visual access as well as focussed for screen reader users.
   Using the ConstructFinder in Firefox allows easier access to semantic constructs in cluttered web sites -- both for sighted and for visually impaired computer users.
Keywords: Firefox add-on, UIMA, screen reader, structural analysis, web sites

Signal and image processing for ambient intelligence and pervasive computing

Blink and wink detection for mouse pointer control BIBAKFull-Text 23
  Eric Missimer; Margrit Betke
A Human-Computer Interaction (HCI) system that is designed for individuals with severe disabilities to simulate control of a traditional computer mouse is introduced. The camera-based system monitors a user's eyes and allows the user to simulate clicking the mouse using voluntary blinks and winks. For users who can control head movements and can wink with one eye while keeping their other eye visibly open, the system allows complete use of a typical mouse, including moving the pointer, left and right clicking, double clicking, and click-and-dragging. For users who cannot wink but can blink voluntarily the system allows the user to perform left clicks, the most common and useful mouse action. The system does not require any training data to distinguish open eyes versus closed eyes. Eye classification is accomplished online during real-time interactions. The system had an accuracy of 8027/8306 = 96.6% in classifying sub-images with open or closed eyes and successfully allows the users to simulate a traditional computer mouse.
Keywords: assistive technology, eye image analysis, mouse replacement system, video based human computer interface
Shape recognition, with applications to a passive assistant BIBAKFull-Text 24
  Antonella Di Lillo; Giovanni Motta; Kevin Thomas; James A. Storer
We address the problem of retrieving an object description, in the form of a silhouette, from a database of shapes, in a way that is robust with respect to translation, rotation, scale change, and distortion. Algorithms to solve this problem can be a key step in passive assistant software that receives information from available sensors and databases, and provides useful information about the local environment to a visually disabled user (where the assistant input may be in the form of audio). Experiments show significant gains in retrieval accuracy over previous work.
Keywords: image processing, passive assistant, shape recognition
Experiments with computer vision methods for fall detection BIBAKFull-Text 25
  Zhong Zhang; Eric Becker; Roman Arora; Vassilis Athitsos
The goal of a fall detection system is to automatically detect cases where a human falls and may have been injured. A natural application of such a system is in home monitoring of patients and elderly persons, so as to automatically alert relatives and/or authorities in case of an injury caused by a fall. This paper describes experiments with three computer vision methods for fall detection in a simulated home environment. The first method makes a decision based on a single frame, simply based on the vertical position of the image centroid of the person. The second method makes a threshold-based decision based on the last few frames, by considering the number of frames during which the person has been falling, the magnitude (in pixels) of the fall, and the maximum velocity of the fall. The third method is a statistical method that makes a decision based on the same features as the previous two methods, but using probabilistic models as opposed to thresholds for making the decision. Preliminary experimental results are promising, with the statistical method attaining relatively high accuracy in detecting falls while at the same time producing a relatively small number of false positives.
Keywords: Gaussian model, fall detection, non-parametric model
Development of holistic physical therapy management system using multimodal sensor network BIBAKFull-Text 26
  Aung Aung Phyo Wai; Jit Biswas; Foo Siang Fook; Lin Jinhong Kenneth; Sanjib Kumar Panda; Philip Yap
Rehabilitation with physical therapy exercises is important to maintain and regain desirable physical strength to patients who underwent surgery or suffer temporary physical impairments. This process generally requires the patient to perform exercises regularly and correctly with assistance from therapist at a rehabilitation clinic. But this approach results in costly, resource intensive and subjective assessments in managing physical therapy exercises. In order to alleviate these drawbacks, holistic physical therapy management system for tele-rehabilitation is proposed leveraging on multimodal sensor network, intelligent motion analysis, collaborative user interactions and communication framework. With employing proposed system in patients' home and rehabilitation clinic, exercises monitoring, assessment and interaction with multiple patients and a therapist can be established in convenient and cost-effective manners.
Keywords: multimodal sensor network, physical therapy, physical therapy management system, rehabilitation
Extending event-driven experiments for human activity for an assistive environment BIBAKFull-Text 27
  Eric Becker; Roman Arora; Scott Phan; Jyothi K. Vinjumur; Fillia Makedon
Many different aspects go into the generation of the data and methods needed to recognize human activity within an ambient assistive living environment. The Heracleia @Home apartment has been configured to include both wireless sensor networks as well as wired sensors of multiple types to capture information about subjects in the living space. The responses of these sensors are then analyzed to create key episodic events that occur at each time and place. Once these sensors are equipped to recognize a set of events, the data can then be processed by applying a Hidden Markov Model approach and by an adaptation of the Baum-Welch algorithm to identify different human activities within the assistive living environment. An application has been created to help manage and track the different sensors placed within the environment.
Keywords: Baum-Welch modification, assistive environments, database, episodic events, events of interest, human activity, wireless sensor networks
From dialogue management to pervasive interaction based assistive technology BIBAKFull-Text 28
  Yong (Yates) Lin; Kyungseo Park; Fillia Makedon
Dialogue management system is originated when human-computer interaction (HCI) was dominated by a single computer. With the development of sensor networks and pervasive techniques, the HCI has to adapt into pervasive environments. Pervasive interaction is a form of HCI derived under the context of pervasive computing. This paper introduces a pervasive interaction based planning and reasoning system for individuals with cognitive impairment, for their activities of daily living. Our system is a fusion of speech prompt, speech recognition as well as events from sensor networks.
   The system utilizes Markov decision processes for activity planning, and partially observable Markov decision processes for action planning and executing. Multimodal and multi-observation is the characteristics of a pervasive interaction system. Experimental results demonstrate the flexible effect the reminder system works for activity planning.
Keywords: POMDP, assistive environment, multimodal, pervasive interaction

Healthcare privacy and data security

The security and privacy implications of using social networks to deliver healthcare BIBAKFull-Text 29
  Carrie Gates; Matt Bishop
Healthcare technologies have tended to focus on electronic health records and devices (e.g., devices within the home for patients or handheld devices for nurses and physicians), and the interaction between the two. However, no one to date has investigated how social networking technologies might be used to provide an assistive environment for patients who participate in group therapy. In this paper we propose such an environment and go on to discuss the privacy requirements and security implications in developing an appropriate support mechanism.
Keywords: healthcare technologies, privacy, security, social networks
An authentication model for delegation, attribution and least privilege BIBAKFull-Text 30
  Ebrima N. Ceesay; Coimbatore Chandersekaran; William R. Simpson
The need to share information while maintaining privacy and security is a growing problem in health, finance, defense, and other distributed environments. Mitigating threats in a distributed computing environment is a difficult task and requires constant vigilance and defense-in-depth. Most systems lack a secure model that guarantees an end-to-end security. In this paper, we devise a model that mitigates a number of threats to the distributed computing pervasive in corporate and institutional information technology enterprises. This authentication process is part of a larger information assurance systemic approach that requires that all active entities (users, machines and services) are named, and credentialed. Authentication is bilateral using PKI credentialing, and authorization is based upon Security Assertion Markup Language (SAML) attribution statements. Communication across domains is handled as a federation activity using WS-* protocols. We present the architectural model, elements of which are currently being demonstrated and tested in a functional prototype in a boundary protected area processing center. The architecture is also applicable to a private cloud.
Keywords: WS-*, attribution, authentication, authorization, credentialing, delegation, least privilege, public key infrastructure, security assertion markup language (SAML)
Threat analysis of online health information system BIBAKFull-Text 31
  Azadeh Nematzadeh; L. Jean Camp
Electronic health records are increasingly used to enhance availability, recovery, and transfer of health records. Newly developed online health systems such as Google-Health create new security and privacy risks. In this paper, we elucidate a clear threat model for online health information systems. We distinguish between privacy and security threats. In response to these risks, we propose a traitor-tracing solution, which embeds proof to trace an attacker who leaks data from a repository. We argue that the application of traitor-tracing techniques to online health systems can align incentives and decrease risks.
Keywords: information health systems, legal aspects, privacy, traitor-tracing schemes
Misco: a MapReduce framework for mobile systems BIBAKFull-Text 32
  Adam Dou; Vana Kalogeraki; Dimitrios Gunopulos; Taneli Mielikainen; Ville H. Tuulos
The proliferation of increasingly powerful, ubiquitous mobile devices has created a new and powerful sensing and computational environment. Software development and application deployment in such distributed mobile settings is especially challenging due to issues of failures, concurrency, and lack of easy programming models. We present a framework which provides a powerful software abstraction that hides many of such complexities from the application developer. We design and implement a mobile MapReduce framework targeted at any device which supports Python and network connectivity. We have implemented our system on a testbed of Nokia N95 8GB smartphones and demonstrated the feasibility and performance of our approach.
Keywords: distributed real-time systems, map reduce, mobile systems
Applying data warehousing technique in pervasive assistive environment BIBAKFull-Text 33
  Shahina Ferdous; Leonidas Fegaras; Fillia Makedon
Radio Frequency Identification (RFID) is an automatic identification (Auto-ID) Technology, which is most commonly used now days in healthcare for tracking and identifying objects. In the context of assistive environment, statistical query analysis over the history of Data generated from RFID Applications as well as real time monitoring of the patients or the elderly people (people who need assistance) are really important. But Data generated from these types of healthcare applications can be very large, if each individual object becomes RFID-Tagged. As a result, the RFID technology is also imposing a greater challenge to provide efficient query responses over these Data. In this paper, we show how to apply traditional Data Warehousing techniques to model these massive amounts of RFID Data. In short, we describe how to construct an RFID Warehouse so that important query analyses can be performed very efficiently. We also show how to process a continuous stream of RFID Data to answer real time queries using Sliding Window techniques. By the help of using synthetic Datasets, we conclude that querying over Data Warehouse is much faster than traditional Relational DBMS. We also find that the aforesaid performance improvement is expected to be much higher as the size of the Dataset increases.
Keywords: RFID cuboids and hyper cubes, RFID data warehouse, active and passive RFID, assistive environments, cleansed RFID data set

Pervasive systems for the aging society

An exploration of real-time environmental interventions for care of dementia patients in assistive living BIBAKFull-Text 34
  Lisa Rebenitsch; Charles B. Owen; Reza Ferrydiansyah; Corey Bohil; Frank Biocca
Patients in the early stages of dementia are often subject to a variety of dangerous symptoms and behaviors including depression, wandering, and aggression. These conditions severely influence both quality of life and the degree of caretaker intervention that is necessary. Non-pharmacological interventions can alleviate these symptoms in some cases and are preferred as an alternative to medication when possible. This paper explores alternatives to the traditional definition of intervention, wherein the involvement of a caregiver is assumed, using a new modality wherein interventions are automatically instigated in response to conditions detected by physiological and behavioral measures. The environment is automatically manipulated in these methods in response to detected symptoms, intervening without the immediate assistance of a caregiver.
Keywords: assistive living, behavioral interventions, psychophysiology
An interactive user interface system for Alzheimer's intervention BIBAKFull-Text 35
  Fillia Makedon; Rong Zhang; Georgios Alexandrakis; Charles B. Owen; Heng Huang; Andrew J. Saykin
Alzheimer's Disease (AD) is a neurological affliction that impacts primarily the aged due to brain tissue deterioration. It has been shown that this deterioration can be slowed down by engaging the person with daily interactive activities that include gaming, social interaction, memory exercises and physical activity. In this paper, we describe ZPLAY, a game-based user interface system which is designed to be web-based and to provide intervention therapy for AD. ZPLAY has two versions: the @lab version which is designed for diagnosis and used to measure different brain activation responses of AD and the @home version which is used to promote subject engagement and rehabilitation in a home environment in-between visits to the clinic.
Keywords: Alzheimer's, Dementia, data stream synchronization, functional near infrared (fNIR) imaging, game design, human computer interaction, machine learning, motion capture, physical therapy, rehabilitation
Using mobile phones to improve medication compliance and awareness for cardiac patients BIBAKFull-Text 36
  Islam Qudah; Peter Leijdekkers; Valerie Gay
Improving cardiac patients' medication compliance is a major factor in reducing mortality rate and reducing hospitalization rate. This paper describes a novel medication compliance management system. Its novelty lies in the combination of functionalities that helps the patient to comply with their medication regimen, together with a personal health monitoring system that monitors their health and collects vital signs data using a mobile phone and wireless bio sensors. The system is designed to collect and analyse medication compliance, side effects and symptom responses and transfers the collected data in real time to a web based system for remote monitoring by caregivers and health professionals. Health professionals can use the system to assess the effect of the medication regimen on their patients' health and adapt it to reduce side effects and maximise the patient's wellbeing.
Keywords: ambulatory monitoring, cardiac rehabilitation, medication compliance, tele-monitoring
Web based medicine intake tracking application BIBAKFull-Text 37
  Jyothi K. Vinjumur; Eric Becker; Shahina Ferdous; Georgios Galatas; Fillia Makedon
One of the issues in healthcare systems or medical information systems is the reduction of medical errors to ensure patient safety. Inside an assistive environment, we apply RFID tags to monitor drug taking pattern and its consequences are reported to the care giver. This paper talks about an application which tracks the medicine intake pattern for the elderly using RFID readers and tags, motion sensors, and a wireless sensor mote. With the adoption of this ambient assistive technology in healthcare systems, the concept of heterogeneous sensor data management becomes an issue. In this paper, using a Web Based Caregiver Module makes the process of monitoring medicine intake for health-related matters of the elderly living alone simpler and easier. We also propose to use an energy efficient technique by using multiple sensor devices which employ a sequence of in-network data fusion as needed.
Keywords: RFID, assistive environments, data fusion, energy efficiency, hidden Markov model

Data modeling and information management for pervasive assistive environments

FoodManager: a cooking, eating and appliance controlling support system for the elderly BIBAKFull-Text 38
  Rosa Iglesias; Ibai Ibarguren; Nuria Gómez de Segura; Julen Ugalde; Leticia Coello; Miren Iturburu
These days, many support systems are being developed to improve independence and quality of life of elderly and impaired people at home. Most of them have been hitherto focused on providing home healthcare-related services, and little attention has been paid to cooking and eating activities. On the one hand, the role of supporting eating activities is likely to become increasingly important. Since old age is often associated with memory impairments, it would be useful to provide them with menus including a variety of healthier meals. Furthermore, it is of paramount importance that these suggested meals are built up based on disease pathologies, health condition and user preferences. On the other hand, comprehensive cooking guidelines and food and shopping list handling are also needed. With regard to cooking directions, it seems desirable that users do not need to manage complex household appliances like the oven. This can be achievable thanks to the technologies developed in the area of Home Automation.
   In this paper, a cooking support system, namely FoodManager, is discussed. This was designed and developed to deal with all the requirements described above. Its interface design and navigation was specially designed for the elderly. Testing performed with ten elderly people (ages from 58 to 81) provided some understanding about its usability and simplicity to use.
Keywords: ambient assisted living, cooking, eating, elderly people, smart kitchen
BlueS: semantic caching approaches for data reuse in smart environments data management in healthcare scenarios BIBAKFull-Text 39
  Andre Peters; Dortje Löper; Andreas Heuer
Pervasive technologies are essential at any field of healthcare issues. Especially the growing number elderly necessitates the development of measures to support care-dependent people at their private homes. One important research field are so called Smart-Rooms, local agglomerations of smart appliances, whose composition is prone to frequent, unforeseeable, and substantial changes. These compositions are able to react on the user's needs by interaction of individual appliances. Normally, these environments are equipped with smart sensors to infer the activities of the user. In case the environments know the current activity they can try to infer the next possible actions the user will take, thus assist the user pro-active. On the other side, these environments should be able to manage information or data the user 1 is interested in. Therefore it is necessary to offer solutions for data access and information exchange in ubiquitous environments with respect to the users needs and skills. Therefore, we present BlueS (Bluetooth-Services), our service based solution for data access and information exchange in spontaneous linked smart environments, e.g. Bluetooth networks. In this paper we want to focus on smart caching approaches for data reuse. A full description of BlueS can be found in [10].
Keywords: distributed data management, mobile databases, pervasive computing, semantic caching
Communicating through preferences BIBAKFull-Text 40
  Nicolas Spyratos; Dimitris Kotzinos
This paper is concerned with the creation and management of events in a community of persons with common interests. We introduce concepts and tools for performing the following activities by members of the community: (a) proposing events in which the members of the community can participate (b) expressing preferences over a set of proposed events (c) choosing the events that best fit the community with respect to the expressed preferences and (d) announcing to the community the chosen events that are to take place. We focus on the design of communication and collaborative decision making, and we outline the design of an online system that supports these activities. Our proposal can be seen as a generalization of existing tools like Doodle, an online system for setting up meeting times.
Keywords: communication, event, keywords, meeting, preference

Networking technologies for healthcare information storage, transmission, processing, and feedback

Context-aware optimized information dissemination in large scale vehicular networks BIBAKFull-Text 41
  Yves Vanrompay; Ansar-UI-Haque Yasar; Davy Preuveneers; Yolande Berbers
Context-aware inter-vehicular communication is considered to be vital for inducing intelligence through the use of embedded computing devices inside vehicles. Vehicles in a scalable environment may disseminate information about certain road traffic conditions, traffic incidents, free parking space or other relevant information to the neighboring vehicles in the vicinity. In this paper, we optimize the dissemination of such context information by predicting traffic patterns in a geographical region, including traffic hotspots. We optimized the relevance backpropagation algorithm with prediction capabilities to efficiently disseminate information. We evaluate our approach with the OMNET++ network simulator using realistic large scale data sets. Our experimental results show that by optimizing information dissemination we significantly improve the Network Traffic, availability and relevant information delivery in a large scale vehicular network.
Keywords: context-awareness, inter-vehicular, optimization, predictions, scalability
A secure ubiquitous healthcare system based on IMS and the HL7 standards BIBAKFull-Text 42
  Stefanos A. Nikolidakis; Emmanouil Georgakakis; Vasileios Giotsas; Dimitrios D. Vergados; Christos Douligeris
Body sensors are small devices close or attached to the human body that gather information regarding vital signs (e.g. body temperature, blood pressure, heartbeat rate etc.) or other physiological data. The Health Level Seven (HL7) has published the Clinical Document Architecture (CDA) which is a document markup standard that specifies the structure and semantics of a clinical document. CDA documents are encoded in Extensible Markup Language (XML) and are used for exchanging documents in heterogeneous environments. In this paper we are introducing an architecture to enable the collection of medical data in real time from body sensors, with the use of a hand held device (e.g. PDA) and their secure transmission to a central party, essentially a hospital, from where medical personnel will be able to access it, and assess the patients health status. When it comes to exchanging critical medical information the need for QoS (Quality of Service) is imperative. The IP (Internet Protocol) Multimedia Subsystem (IMS) can be used to provide Internet services (including realtime multimedia services) with QoS, and integrate different services as well. The data gathered by the sensors are transmitted to the PDA. They are converted to CDA format, digitally signed, encrypted and then transmitted over IMS to the hospital from where data can be accessed by doctors using their own PDAs'.
Keywords: IP multimedia subsystem, health level 7, pervasive healthcare, wearable sensor networks
An overview of body sensor networks in enabling pervasive healthcare and assistive environments BIBAKFull-Text 43
  Charalampos Liolios; Charalampos Doukas; George Fourlas; Ilias Maglogiannis
The use of sensor networks for healthcare, well-being, and working in extreme environments has long roots in the engineering sector in medicine and biology community. With the growing needs in ubiquitous communications and recent advances in very-low-power wireless technologies, there has been considerable interest in the development and application of wireless networks around humans. With the maturity of wireless sensor networks, body area networks (BANs), and wireless BANs (WBANs), recent efforts in promoting the concept of body sensor networks (BSNs) aim to move beyond sensor connectivity to adopt a system-level approach to address issues related to biosensor design, interfacing, and embodiment, as well as ultra low-power processing / communication, power scavenging, autonomic sensing, data mining, inferencing, and integrated wireless sensor microsystems. As a result, the system architecture based on WBAN and BSN is becoming a widely accepted method of organization for ambulatory and ubiquitous monitoring systems. This review paper presents an up-to-date report of the current research and enabling applications and addresses some of the challenges and implementation issues.
Keywords: body sensor networks, healthcare applications, ubiquitous computing, wireless body area networks
Optimizing trajectories of mobile beacons to localize sensor networks BIBAKFull-Text 44
  Awais Iqbal; Lanjiang Zhou; Manfred Huber; Gergely Záruba
This paper deals with localizing nodes in a sensor network. More precisely, we consider the situation where sensor nodes localize themselves off a mobile beacon node traveling over the deployment area. We describe a genetic approach to derive semioptimal paths for a mobile beacon, where the optimal path is defined as the beacon trajectory resulting in the highest overall localization precision for sensor nodes, with certain constraints on path length. For this, we assume that the beacon periodically broadcasts its location. The sensors can extract this location information as well as the signal strength from received packets to estimate their location. In such localization scenarios, the trajectory of the beacon heavily affects the accuracy of location estimate. To evaluate paths, we employ Cramer Rao bounds (CRB) which provide an unbiased evaluation regardless of the location estimation algorithm. A genetic approach is employed to evolve paths toward an optimal trajectory, with a C++ simulator calculating sensor node CRB estimates as the objective function. We provide a description of the approach and provide insights on what the influence of our genetic algorithm is on the accumulative overall localization CRB.
Keywords: distributed localization, genetic algorithm, sensor network
Android vs Windows Mobile vs Java ME: a comparative study of mobile development environments BIBAKFull-Text 45
  Tor-Morten Grønli; Jarle Hansen; Gheorghita Ghinea
In this paper we look at three mobile development environments: Windows Mobile, Java ME and Android. Through platform comparison, the different environments are examined closely and strengths and weaknesses are brought to life. In all three environments example applications are written to compare the environments in action on respective devices. Environment specific deployment files are created to illustrate amount of boilerplate code and overhead during deployment. Different key areas such as implementation aspects, performance aspects and quality assurance are compared to give an in depth overview of the status of the different platforms. Our results show that although the three environments are similar in some aspects they still represent three distinctive fields each with their respective characteristics. Through our code examples and platform comparison we come to the conclusion that the Windows Mobile and Android platform provides a better development environment, whereas Java ME still struggles with poor emulator support and incompatible implementations. The main features they have in common are also seen in trends directly visible in the programming languages such as unit testing, language features and end user distribution strategies. Big differences are highlighted when inspecting community environments, hardware abilities and platform maturity. This will have large influence on the choice of development platform for creating novel assistive environment applications.
Keywords: Android, Java ME, Windows Mobile, mobile development environment, programming languages
Modeling reliability for wireless sensor node coverage in assistive testbeds BIBAKFull-Text 46
  Zhengyi Le; Eric Becker; Dimitrios G. Konstantinides; Chirs Ding; Fillia Makedon
Wireless Sensor Networks (WSNs) is a prevailing technology in assistive environments. Assistive environments may include both home and work spaces such as factories, military installations, industrial spaces, and offices. Critical quality-of-service properties of WSN are reliability, availability, and serviceability. This paper focuses on reliability for healthcare applications. Reliable WSN-based monitoring services can prevent accidents, improve the quality of life, and even help with early health diagnosis and treatments. However, because patients/the elderly may have cognitive or other health problems, the reliability is the dominant factor of quality of services of WSN. This paper presents an approach to analyze the reliability of a WSN with the most popular tree structures. The analysis is based on two distribution models, exponential distribution and Weibull distribution. The simulation results also give options to users on the cost vs. reliability issue.
Keywords: assistive system, fault tolerance, network, quality of service, risk management, sensor node management, system lifetime, wireless sensor network

Workshop on Affect and Behaviour Related Assistance for the Elderly

Affect- and behaviour-related assistance for families in the home environment BIBAKFull-Text 47
  Christian Peter; Gerald Bieber; Bodo Urban
The ABRA System for affect- and behaviour-related assistance for families in the home environment is a modular system, comprising components for assessing a person's state, for communicating and displaying relevant information, and for social togetherness. The technology platform is being developed to study novel approaches to social inclusion, particularly for elderly, and new, senior-friendly interaction and display techniques. This paper describes a first implementation of a bimodal sensing module for assessing a person's wellbeing, combined with an assistance and communication module for enhanced social inclusion and sense of safety.
Keywords: AAL, activity monitoring, affect, cognition, pervasive assistance, sensor fusion, social inclusion, social network, user state detection, wellness technologies
Assessing accelerometer based gait features to support gait analysis for people with complex regional pain syndrome BIBAKFull-Text 48
  Mingjing Yang; Huiru Zheng; Haiying Wang; Sally McClean; Jane Hall; Nigel Harris
In this paper, we explored the feasibility of analysing gait patterns during the Short Physical Performance Battery test by using an accelerometer to record the movement of the subject. 12 subjects with Complex Regional Pain Syndrome (CRPS) and 10 control subjects were recruited in this study. 21 gait features including temporal, frequency, regularity and symmetric information were extracted from each recording. The differences of each feature value on control subjects and patient subjects were assessed and compared. Features were selected based on the signal to noise ratio (SNR) ranking. Multilayer perceptron neural-networks were employed to differentiate between the normal and abnormal gait patterns. The result shows when using five features the best classification accuracy (97.5%) was achieved. It is feasible to discriminate the patients with CRPS from the control subjects using a small set of gait features extracted from walking acceleration data recorded during the SPPB test.
Keywords: accelerometer, complex regional pain syndrome, feature extraction, gait analysis
Human-computer interaction and the older adult: an example using user research and personas BIBAKFull-Text 49
  Francisco Nunes; Paula Alexandra Silva; Filipe Abrantes
This paper reports on the outcomes of the first phase of the eCAALYX project -- an European project which aim is to develop a complete solution that improves the quality of life of the older adult with chronic conditions by monitoring his health and by improving the communication with his caretakers. Specifically, the authors are responsible for creating a TV user interface for older adults with chronic conditions.
   The work described followed a multi-disciplinary approach strongly influenced by Human-Computer Interaction (HCI) methodologies. The main contributions of this paper are two-fold and materialize into i) a user research study that covers aspects such as perception, cognition, mental and psychosocial changes that occur with age and ii) an example-based description of the process of creating personas. John, the diabetic persona, is the example provided that abstracts the process followed to generate the remaining personas in the project.
Keywords: human-computer interaction, personas, user research
Mobile physical activity recognition of stand-up and sit-down transitions for user behavior analysis BIBAKFull-Text 50
  Gerald Bieber; Philipp Koldrack; Christopher Sablowski; Christian Peter; Bodo Urban
Sufficient physical activity is required for everybody, especially for elderly people. Monitoring of physical activity is possible in daily life by using mobile sensors such as acceleration sensors. The recognition of periodic activity types like walking, cycling, car driving etc. is easy to perform. However, the identification of transitions between physical activities is difficult, because those events are nonrecurring and unique. The estimation about the share of standing or sitting during work is interesting for the design of the modern workplace. Human ergonomics demand for a limitation of standing work; this may even be enforced by the legal protection of working mothers to improve the working condition. The recognition of standing and sitting is furthermore useful within the home living area design. Hereby a detection of staying, sitting and walking supports the assessment of the activities of daily life. This paper addresses the methodology of mobile physical activity recognition of transitions between sitting and standing by using only one three-dimensional acceleration sensor. The recognition is performed by using a synthetic kernel signal and a correlation of the measurement signal. For the evaluation, a detection application has been developed which uses the build-in sensors of a standard mobile phone. The evaluation included 12 subjects and the result shows that mobile recognition of activity transitions is possible.
Keywords: DiaTrace, acceleration sensor, activity monitoring, assistive technologies, physical activity transitions, user state detection
A deterministic large-scale device-free passive localization system for wireless environments BIBAKFull-Text 51
  Moustafa Seifeldin; Moustafa Youssef
The widespread usage of wireless local area networks and mobile devices has fostered the interest in localization systems for wireless environments. The majority of research in the context of wireless-based localization systems has focused on device-based active localization, in which a device is attached to tracked entities. Recently, device-free passive localization (DfP) has been proposed where the tracked entity is neither required to carry devices nor participate actively in the localization process. DfP systems are based on the fact that RF signals are affected by the presence of people and objects in the environment.
   Previous studies have focused on small areas with direct line of sight (LOS) and/or controlled environments. In this paper, we present the design, implementation and analysis of Nuzzer, a large-scale non-LOS DfP localization system, which tracks a single entity in real environments, rich in multipath. Without any additional hardware, Nuzzer makes use of the already-installed wireless data networks to monitor and process changes in the received signal strength (RSS) at one or more monitoring points transmitted from access points. The Nuzzer system enables many applications which support the elderly, including smart homes automation which can be used to assist the elderly, and intrusion detection which is used to protect the elderly's homes.
   We present deterministic techniques for DfP localization and evaluate their performance in a building, rich in multipath, with an area of 750 square meters. Our results show that the Nuzzer system gives device-free location estimates with less than 7 meters median distance error using only two monitoring laptops and three access points. This indicates the suitability of Nuzzer to a number of application domains.
Keywords: device-free localization, passive radio map
Analysis of requirements and specifications for a monitoring system to support the self-management of dementia patients at home BIBAKFull-Text 52
  Stefanos Xefteris; Maria Haritou; Konstantinos Tserpes; Alessandro Serretti; Josep Ramon Llopart; Raffaella Calati; Theodora Varvarigou
Telemedicine systems are nowadays making significant advances in healthcare by decentralising it, offering innovative services to patients and doctors worldwide, and making medical practice more efficient and cost-effective in a plethora of its subfields. There is although a field that has not yet been successfully coped with, even though it induces a significant burden, both socially and financially. This field includes patients suffering from dementia, as well as their carers, who run the risk of developing depression symptoms themselves and often face social withdrawal and heavy additional private costs. ALADDIN is a technology platform that intends to progress "state-of-the-art" in integration of existing technological solutions. In order to develop and validate an innovative monitoring system for health promotion, risk assessment, prevention and sustainable impact of self management tools and education for patients suffering from dementia and their care-givers. In this paper the authors present the envisaged services of the ALADDIN platform, the user requirements and ALADDIN's functional specifications.
Keywords: Dementia, assisted living, cognitive states, e-health and assistive infrastructures, non-obtrusive monitoring, quality of life, risk analysis

Workshop on Light-Weight Signal Processing for Computationally Intensive BSN Applications

Applications of sensing platforms with wearable computers BIBAKFull-Text 53
  Vitali Loseu; Hassan Ghasemzadeh; Sarah Ostadabbas; Nikhil Raveendranathan; Jacques Malan; Roozbeh Jafari
Use of mobile sensor-based platforms for human monitoring is an ever-growing area of research. These system are able to provide objective, quantitative measurements over a time period without being restricted to a clinical settings. However, these platforms also face some challenges in terms of wearability. Wearability concerns force sensor nodes to decrease in size and employ wireless communication. Both of these constraints pose a serious design challenge for realistic applications. In this paper, we present a variety of sensing platforms from inertial tracking with an accelerometer system to emotion recognition with a large set of physiological sensors. We aim to show that body sensor network's properties and design patterns can be useful not only in a traditional accelerometer based system applications, but also in applications that are better suited with other sensor modalities.
Keywords: EEG, EMG, body sensor networks, haptics, inertial tracking, physiological sensors
Linear frequency estimation technique for reducing frequency based signals BIBAKFull-Text 54
  Jonathan Woodbridge; Alex Bui; Majid Sarrafzadeh
This paper presents a linear frequency estimation (LFE) technique for data reduction of frequency-based signals. LFE converts a signal to the frequency domain by utilizing the Fourier transform and estimates both the real and imaginary parts with a series of vectors much smaller than the original signal size. The estimation is accomplished by selecting optimal points from the frequency domain and interpolating data between these points with a first order approximation. The difficulty of such a problem lies in determining which points are most significant. LFE is unique in the fact that it is generic to a wide variety of frequency-based signals such as electromyography (EMG), voice, and electrocardiography (ECG). The only requirement is that spectral coefficients are spatially correlated. This paper presents the algorithm and results from both EMG and voice data. We complete the paper with a description of how this method can be applied to pattern types of recognition, signal indexing, and compression.
Keywords: compression, data reduction, pattern recognition, signal indexing
Low complexity sensors for body area networks BIBAKFull-Text 55
  Harinath Garudadri; Pawan K. Baheti; Somdeb Majumdar
In this work, we present signal processing approaches to offload complexity from resource constrained sensor nodes to gateway/receiver nodes with better power, memory and CPU budgets. We consider the resources in commercially available cell phone platforms to fill the role of both gateway and receiver nodes in emerging Body Sensor Networks, with applications in healthcare. We leverage Compressed Sensing (CS), wherein signals can be reconstructed fairly accurately with high probability from significantly fewer measurements than that suggested by the Nyquist-Shannon sampling rate, albeit with additional complexity at the receiver. This enables receiver nodes with better resource budgets to leverage computationally intensive signal processing algorithms in lieu of on-board processing at the sensor node. We show that aliasing can be avoided at the sensor by trading analog domain complexity for a modest increase in digital domain complexity with synthetic examples and real-time pulse oximeter implementation. We describe ways to leverage receiver resources for mitigating packet losses and sensing artifacts and present experimental results with ECG. Finally, we motivate multi-sensor fusion at the receiver and show that CS paradigm can be used to reduce sensor complexity with sloppy clock management schemes.
Keywords: aliasing, body area networks, compressed sensing, low power sensor nodes
Opportunistic strategies for lightweight signal processing for body sensor networks BIBAKFull-Text 56
  Edmund Seto; Eladio Martin; Allen Yang; Posu Yan; Raffaele Gravina; Irving Lin; Curtis Wang; Michael Roy; Victor Shia; Ruzena Bajcsy
We present a mobile platform for body sensor networking based on a smartphone for lightweight signal processing of sensor mote data. The platform allows for local processing of data at both the sensor mote and smartphone levels, reducing the overhead of data transmission to remote services. We discuss how the smartphone platform not only provides the ability for wearable signal processing, but it allows for opportunistic sensing strategies, in which many of the onboard sensors and capabilities of modern smartphones may be collected and fused with body sensor data to provide environmental and social context. We propose that this can help refine data reduction at the local level. We describe three examples related to health and wellness, to which our system has been applied.
Keywords: body area networks, energy expenditure, health monitoring, opportunistic sensing, physical activity, wearable computing, wireless sensors
Time-domain heart rate variability analysis with the SPINE-HRV toolkit BIBAKFull-Text 57
  Alessandro Andreoli; Raffaele Gravina; Roberta Giannantonio; Paola Pierleoni; Giancarlo Fortino
We present a toolkit for the time-domain Heart Rate Variability (HRV) analysis, namely SPINE-HRV (Signal Processing In Node Environment-HRV). The HRV is based on the analysis (time and frequency domain) of the R-peak to R-peak intervals (RR-interval). The toolkit is composed of a wearable Heart Activity Monitoring System (HAMS) to acquire the RR-interval (RRi), and a processing application developed using the SPINE framework. The HAMS system consists of a wireless chest band, a wireless wearable sensor node and a base station. The RRi signal is processed using the SPINE framework at the base station side through a time-domain analysis of HRV. The analysis provides seven common parameters known in medical literature to help cardiologists in the diagnosis related to several heart diseases.
Keywords: HRV, SPINE, body sensor networks, domain specific frameworks, health care
Tracking your steps on the track: body sensor recordings of a controlled walking experiment BIBAKFull-Text 58
  Jefrey Lijffijt; Panagiotis Papapetrou; Jaakko Hollmén
Monitoring human motion has recently received great attention and can be used in many applications, such as human motion prediction. We present the collected data set from a body sensor network attached to the human body. The set of sensors consists of accelerometers measuring acceleration in three directions that are attached to the upper and lower back as well as the knees and ankles. In addition, pressures on the insoles are measured with four pressure sensors inside each shoe. Two types of motion are considered: walking backwards on a straight line and walking forwards on a figure-8 path. Finally, we study and present basic statistics of the data.
Keywords: acceleration, body sensor network, time series

Workshop on Workflow and Event Analysis for Assistive Environments

Benchmarking dynamic time warping for music retrieval BIBAKFull-Text 59
  Jefrey Lijffijt; Panagiotis Papapetrou; Jaakko Hollmén; Vassilis Athitsos
We study the performance of three dynamic programming methods on music retrieval. The methods are designed for time series matching but can be directly applied to retrieval of music. Dynamic Time Warping (DTW) identifies an optimal alignment between two time series, and computes the matching cost corresponding to that alignment. Significant speed-ups can be achieved by constrained Dynamic Time Warping (cDTW), which narrows down the set of positions in one time series that can be matched with specific positions in the other time series. Both methods are designed for full sequence matching but can also be applied for subsequence matching, by using a sliding window over each database sequence to compute a matching score for each database subsequence. In addition, SPRING is a dynamic programming approach designed for subsequence matching, where the query is matched with a database subsequence without requiring the match length to be equal to the query length. SPRING has a lower computational cost than DTW and cDTW. Our database consists of a set of MIDI files taken from the web. Each MIDI file has been converted to a 2-dimensional time series, taking into account both note pitches and durations. We have used synthetic queries of fixed size and different noise levels. Surprisingly, when looking for the top-K best matches, all three approaches show similar behavior in terms of retrieval accuracy for small values of K. This suggests that for the specific application area, a computationally cheaper method, such as SPRING, is sufficient to retrieve the best top-K matches.
Keywords: dynamic time warping, query-by-humming, time series
Dynamic background modeling for a safe road design BIBAKFull-Text 60
  Anastasios Doulamis
In this paper we propose a new dynamic algorithm able to automatically identify the background from images under severe changes of the environmental conditions. The algorithm exploits motion estimation techniques and background subtraction methods. The proposed scheme is implemented in road construction application scenarios under outdoor environments in which the camera vision is dramatically varied with respect to the weather conditions. Despite such variations, the background can be automatically detected improving the tracking performance for the vehicles and just assisting survey engineers in defining possible errors in the design yielding as deviations between the actual and the ideal trajectory of the vehicle over a turn. Experimental results in real-life road surveillance systems reveal the efficiency of the proposed scheme regardless of significant background changes. In addition, the proposed algorithm requires low computational complexity.
Keywords: dynamic background updating, motion estimation, road design, tracking, vehicles
Integrating RFID on event-based hemispheric imaging for internet of things assistive applications BIBAKFull-Text 61
  V. Kolias; I. Giannoukos; C. Anagnostopoulos; I. Anagnostopoulos; V. Loumos; E. Kayafas
Automatic surveillance of a scene in a broad sense comprises one of the core modules of pervasive applications. Typically, multiple cameras are installed in an area to identify events through image processing techniques, which however present limitations in terms of object occlusion, noise, lighting conditions, image resolution and computational cost. To overcome such limitations and increase recognition accuracy, the video sensor output can be complemented by Radio Frequency Identification technology, which is ideal for the unique identification of objects. In this paper we examine the feasibility of integrating RFID with hemispheric imaging video cameras. After a brief description and discussion of related research regarding RFID location, video surveillance and their integration, we examine the factors that would render such a system feasible in terms of hardware, software and their environments. The advantages and limitations of each technology and their integration are also presented to conclude that their combination could lead to a robust detection of objects and their interactions within an environment. Finally, this work ends with the presentation of some possible applications of such integration.
Keywords: RFID, hemispheric imaging, internet of things (IoT), pervasive systems, surveillance
Iterative motion estimation constrained by time and shape for detecting persons' falls BIBAKFull-Text 62
  Nikolaos Doulamis
The quality of life for the ageing population is associated with the ability of the elderly people living independently. Fall is a major health hazard for the elders when they live independently. How to effectively assess, response and assist those elderly patients in trouble becomes an important research topic in medical elderly care services. This paper presents the visual fall detection subsystem developing the framework of ISISEMD project. The system is able to detect person falls by taking into consideration only camera information. The system is able to perform tracking of the person using advanced image processing and computer vision algorithms event in complex and dynamic background situations. The traditional approaches for detecting a human fall is based on the use of specialized devices, e.g., accelerometers, which is not a convenient framework, especially for persons with mild Dementia. Methods for automatic defection of person fall from camera cues uses motion information of the human object. However, using only motion information, we are not able to accurately detect a fall event. This is mainly due to the fact that a fall is encountered at different directions with respect to the camera position. In addition, motion information is a noise sensitive process. For this reason, accurate foreground object detection is required. However, foreground detection using the traditional background subtraction methods suffers from the dynamic changes of the background. To address these obstacles, we proposed in this paper a combined framework for fall alert based on joint estimation of foreground object and motion scene activity. In particular, motion information is estimated over a set of "good image pixels" to eliminate the noise sensitivity. Additionally, foreground object are extracted using frame differencing and a set of rules that express shape constraints, time continuity and the detection motion information in the scene. Experimental results on lad conditions indicate a accurate detection of a person fall.
Keywords: event driven video analysis, foreground detection, motion estimation
Multi-modal sensing smart spaces embedded with WSN based image camera BIBAKFull-Text 63
  Sun-Min Hwang; Kyu-Jin Kim; Md. Motaharul Islam; Eui-Nam Huh; W. Huang; V. Foo; A. Tolstikov; Aung Aung; M. Jayachandran; J. Biswas
In this paper we discuss the use of low frame rate image cameras on a WSN in order to gather micro-context information in the context of smart homes and smart living spaces for the elderly. These simple devices are an attractive alternative to their more heavy duty counterparts since they can gather ambient image data at a rate that is amenable to the ambient space that they are in without much infrastructural support or modification. We propose their use in a multi-modal sensing environment where information from other ambient sensors may be mixed and matched in order to provide intelligence about the space and the activities of the subjects within the space. Their compelling use case, which includes their light weight and ease of mobility makes them a good candidate for a multi-modal sensing smart space. In this paper we introduce our work on architecture of the smart space and the implementation of the feature extraction using the image camera.
Keywords: feature extraction, multi-modal, recognition, sensor image camera

Poster session

Video-surveillance and context aware system for activity recognition BIBAKFull-Text 64
  Xanthi Kolovou; Ilias Maglogiannis
Fall detection is the main issue in design an AAL system for elderly. This paper describes an algorithm for vision and audio fall detection. The main problem with video surveillance is the distinction of a fall from similar daily activities such as lying down, kneeling, standing up, walking or falling. The goal of this research is to design a reliable fall detection system which not only relies on video analysis, but also uses the information from environment of the patient to create context information.
Keywords: fall detection, sound analysis, video processing
Computer aided sensor placement and automatic state definition BIBAKFull-Text 65
  Alexandros Papangelis; Georgios Galatas; Shahina Ferdous; Sarantos Kapidakis; Fillia Makedon
The design of an Finite State Machine for human activity recognition heavily depends on the type, number and deployment of the sensors used. In this work we propose a tool that automatically creates the FSM, independently of the type and number of sensors or the environment where these are deployed in. This tool allows the users to define the areas of interest in an assistive living environment.
Keywords: assistive environment, decision support, graphical tool, information fusion, sensor placement
An industrial video surveillance system for quality assurance of a manufactory assembly BIBAKFull-Text 66
  Emmanouel Sardis; Athanasios Voulodimos; Vasilios Anagnostopoulos; Constantinos Lalos; Anastasios Doulamis; Dimitrios Kosmopoulos
In this paper, we present the research achievements of a computer vision system that surveys the behavior of workers in an industrial environment. The proposed system applies weakly supervised learning algorithms able to detect objects, then to extract the behaviors of workers with respect to the predefined assembly construction for a task and adopts adaptation mechanisms able to dynamically modified the performance of a system with respect to the environmental changes. The proposed architecture has been tested on real-life applications.
Keywords: behavior recognition, object tracking and detection, relevance feedback, surveillance
EEG: pattern classification during emotional picture processing BIBAKFull-Text 67
  Timo Schuster; Sascha Gruss; Henrik Kessler; Andreas Scheck; Holger Hoffmann; Harald Traue
In this work we describe the processing and classifying of EEG-data that was acquired under emotional conditions. In the context of assistive environment technology it is one of the most important challenges to get information about a persons emotional state. To get this information, psychophysiological data was recorded while stimulating subjects with emotional pictures. Afterwards a classifier was trained to differentiate between physiological patterns of negative, positive and neutral conditions. The classification results show an accuracy of about 72%.
Keywords: EEG, brain-computer-interaction, classification, emotion recognition
Individual emotional profiles in Wizard-of-Oz-experiments BIBAKFull-Text 68
  Steffen Walter; David Hrabal; Andreas Scheck; Henrik Kessler; Gregor Bertrand; Florian Nothdurft; Wolfgang Minker; Harald Traue
One of the most important and difficult fields in research of assistive environment technology is the recognition of emotional and motivational user's states. Emotion studies in the past show, that there are only a few universal interindividual valid psychobiological profiles states, which are stable associated with a user's emotional state. In this approach we look for intraindividual valid psychobiological patterns of emotions and motivations. In order to predict such states separate for different subjects we introduced a calibration procedure for each of the 20 subjects. We expect higher emotion recognition rates than preceding studies focusing on universal patterns on sample data. First results will be presented at the conference.
Keywords: Wizard-of-Oz-experiments, emotional calibration, individual emotional states
INDIGO project: personality and dialogue enabled cognitive robots BIBAKFull-Text 69
  Vangelis Karkaletsis; Stasinos Konstantopoulos; Dimitris Bilidas; Dimitrios Vogiatzis
This demonstration aims to show specific technological advancements that enable cognitive based robots to perceive and understand natural human behavior as well as to act in ways that are familiar to humans. The demonstration is built around a museum guide use-case, where a simulated robotic guide is operating in a virtual environment. During the demonstration visitors are able to interact with the simulated robot using natural language. At the same time, videos of a real robot operating in a real museum are also demonstrated.
Keywords: cognitive architecture, dialogue systems, natural language processing, reasoning systems and machine learning for assistive environments, signal and image processing for ambient intelligence and pervasive computing, usability and HCI interfaces
Reinforcement learning of interface mapping for interactivity enhancement of robot control in assistive environments BIBAKFull-Text 70
  Jartuwat Rajruangrabin; Dan O. Popa
The supervisory control of robots is a very demanding application. In the context of robots control in assistive environments, it is important that the robot user is able to give commands to robots in a way that is easy and intuitive. There are several tasks that can be achieved using robots under assistive environments. It is challenging to efficiently control multiple robots / robots with degrees of freedom with a simple/intuitive interface by a single operator. In this proposal, we propose the use of Reinforcement Learning for intuitive interface mapping. Based on interaction with the environments, we can determine the optimal interface mapping through the process of Reinforcement Learning. The novelty of this paper is the use of changing reward functions based on qualitative performance evaluation for the Reinforcement Learning algorithm. In this paper, we show that the use of proposed reward functions can result in optimal/intuitive interface mapping for multiple robots / robots with degrees of freedom control applications.
Keywords: human-robot interface, reinforcement learning
Breach of internet privacy through the use of cookies BIBAKFull-Text 71
  Anderson A. L. Queiroz; Ruy J. G. B. de Queiroz
This paper describes the issue of invasion of privacy on the Internet using the techniques of cookies, as subtle means to commit such a crime. The issue of data privacy and information of millions of internet users becomes increasingly critical in terms of maintaining social order, for large corporations that dominate the World Wide Web is one of the main beneficiaries of these illegal practices that are happening daily.
Keywords: cookies, crime, internet, invasion, privacy