Rachid Kadouche

Personalization in Smart Homes for Disabled People

Dependent people have a great variability in their needs and levels of motor and/or cognitive handicap. Hence they call for personalized services, especially when interacting with their environment. In smart homes, the semantic matching framework (SMF) provides an appropriate middleware for delivering personalized assistive services in line with the disabilities of a user. SMF is a system based on the Web Ontology Language (OWL) as a modeling language to define ontologies for modeling and reasoning on the user environment and its profile. This paper first, details the adopted approach to personalize a smart home to people with special needs. Then shows how SMF support and manage multiple-users.

Support vector machines for inhabitant identification in smart houses

Authentication is the process by which a user establishes his identification when accessing a service. The use of password to identify the user has been a successful technique in conventional computers. However, in pervasive computing where computing resources exist everywhere, it is necessary to perform user identification through various means. This paper addresses the inhabitant identification issue in smart houses. It studies the optimum time and sensor set required to unobtrusively detect the house occupant. We use a supervised learning approach to address this issue by learning Support Vector Machines classifier (SVM), which predict the users by their daily life habits. We have analyzed the early morning routine with six users. From the very first minute, users can be recognized with an accuracy of more than 85%. Then we have applied an SVM feature selection algorithm to remove noisy and outlier features. Thus, this increases the accuracy to 88% using less then 10 sensors.

Semantic approach for modelling an assistive environment using description logic

Smart living spaces provide autonomy and assistance to people with disabilities and elderly people in order to increase their independence. In this paper we present our approach to personalize a complex living environment for users with special needs. It provides an appropriate middleware for supporting assistive services in dynamic environments. It is built upon formalisms based on Description logic (DL) named Semantic Matching Framework (SMF) and designed on the matching of two models: an environment model, and a user model. SMF was implemented and integrated into a demonstrator, which is validated under laboratory conditions. Performance results are presented to highlight the time response of SMF.

User's behavior study for smart houses occupant prediction

This paper deals with the smart house occupant prediction issue based on daily life activities. Based on data provided by nonintrusive sensors and devices, our approach use supervised learning technics to predict the house occupant. We applied support vector machines classifier to build a behavior classification model and learn the users’ habits when they perform activities for predicting and identifying the house occupant among a group of inhabitants. We analyzed the publicly available dataset from the Washington State University smart apartment tesbed. We particulary studied the grooming, having breakfast and bed to toilet activities. The results showed a hight prediction precision and demonstrated that each user has his own manner to perform his daily activities and can be easily identified by just learning his habit.

Modeling of the residual capability for people with severe motor disabilities: analysis of hand posture

People with severe motor disabilities use mainly their residual motor capability for the use of technical aids, and for the control of input devices to technical aids. This paper describes our work on characterizing the motor capability of the upper arm for patients with severe motor disabilities. This work is a continuation of a project aimed at modeling the arm posture of quadriplegic patients using STS (Spatial Tracking System) and at analyzing the compensatory strategies developed by hemiplegic patients while accessing physical interfaces for technical aids [5]. Here we report work undertaken for analyzing the posture of the hand: we have developed two calibration methods for the Cyberglove and compare their utility and ergonomics in applications on patients with motor disabilities. The first type of calibration proceeds sequentially and takes into account one joint after the other (of the hand and each digit), whereas the second procedure is based on a few key postures calibrating several joints at once. To compare the precision of both methods, four healthy subjects participated in experiments using the Cyberglove. We show that the first type of calibration is more accurate but takes longer, whereas the second is less accurate but shorter. This trade-off might be acceptable for assessing the manual workspace in patients with motor disabilities. In particular, excessive muscular fatigue and limited dexterity are decisive factors for choosing the calibration by key postures in patients. We applied the calibration by key postures to three myopathic patients and individually quantified their restricted manual working space.

Designing an Evaluation Method for Computer Accessibility for People with Severe Disabilities

This paper presents our research work on the accessibility of assistive technologies dedicated to peoples having severe disabilities. The objective is to provide quantitative and qualitative evaluations methodologies on human-machine interaction while getting access to a computer. We aim to design compensation strategies developed by people having sever motor disabilities in order to use physical input devices to control a computer. The study developed in this paper is based on a quantitative evaluation method when using pointing devices such as mouse, Trackballs, Joysticks, etc. The preliminary results presented corresponds to one month of evaluation with 8 patients mainly having spinal cord injuries and muscular dystrophies from the rehabilitation hospital of Garches and from French Muscular dystrophies Association (AFM).

User’s Behavior Classification Model for Smart Houses Occupant Prediction

This paper deals with the smart house occupant prediction issue based on daily life activities. Based on data provided by non intrusive sensors and devices, our approach uses supervised learning technics to predict the house occupant. We applied Support Vector Machines (SVM) classifier to build a Behavior Classification Model (BCM) and learn the users’ habits when they perform activities for predicting and identifying the house occupant. To test the model, we have analyzed the early morning routine activity of six users at the DOMUS apartment and two users of the publicly available dataset of the Washington State University smart apartment tesbed. The results showed a high prediction precision and demonstrate that each user has his own manner to perform his morning activity, and can be easily identified by just learning his habits.

From Smart Home to Smart Space in Independent Living: A Framework for Multiple Contexts Management

During this last decade we have seen that the most suitable application of smart homes targeted independent living of people with disabilities and elderly people. We have seen the emergence of different smart homes prototype developed by several research projects in Europe, North America and Asia. This concept of smart home in a box, which is mainly technology push driven, have two weak points: at first end-users were generally not involved, not user pull driven, and secondly, the smartness of the living environment was limited to the indoor box, even if some remote access functionalities where designed, as soon as the user leaves the box he loose all of the available smartness. In this paper, we describe our research strategy on how to provide a suitable living environment for dependent people based on a push-pull approach. The idea is to focus on the user and provide him the mean to bring part of the home smartness outside in order to interact with unknown environments, as such the bus/train station, the shopping mall, the hospital, and so on. The goal of this research work is not to develop a product, but mainly to focus on a generic framework for service continuity taking into account the user, the environments, and the mobility aspects within known and unknown environments. The ultimate goal is not only to ensure of a coherent matching between the user requirements and the available services, but also the way to interact that we described as human-environment interaction (HEI).

Semantic Matching Framework for handicap situation detection in smart environments

In this paper we present a novel approach to detect the handicap situation on a complex living environment for users with special needs. It is built upon formalisms based on Description Logic (DL) named Semantic Matching Framework (SMF). SMF provides an appropriate middleware for supporting assistive services in dynamic environments. This framework is based on the matching of two models: an environment model, describing the environment related services (actuators, devices, etc.) and a user model, containing the description of the users characteristics (behaviors, preferences, etc.). This Framework was implemented and integrated into a demonstrator (a smart home for dependent people), which is used to validate the smart home concept under laboratory conditions dedicated to dependant people. Performance results are presented to highlight the time response of SMF.

Semantic Matching Framework for Personalizing ubiquitous Environment dedicated to people with special needs

User adaptability and acceptability in heterogeneous environments are very important issues, mainly for people with disabilities. Traditional technology-push approaches fail in overcoming the needs. It becomes crucial to adopt a user-centric approach, both from methodological and technological points of views. In this paper we present a semantic matching framework for personalized service delivery in assistive environments. This framework is based on matching two models: (1) environment model, describing environment factors and (2) user model, describing the human factors. The Framework was implemented using semantic web technologies and integrated into a demonstrator, which has been used to validate the concept in laboratory conditions. Our contribution is three folded: first, the formalization of the user model and the environment model, second, the matching between these two models combining the human factors and the environmental factors, and third the description of these models and their association with ontology based languages.