SVM-Based Multi-Modal Classification of Activities of Daily Living in Health Smart Homes: Sensors, Algorithms and First Experimental Results

By 2050, about a third of the French population will be over 65. Our laboratory’s current research focuses on the monitoring of elderly people at home, to detect a loss of autonomy as early as possible. Our aim is to quantify criteri a such as the international ADL or the French AGGIR scales, by automatically classifying the different Activities of Daily Living performed by the subject during the day. A Health Smart Home is used for this. Our Health Smart Home includes, in a real flat , Infra-Red Presence Sensors (location), door contacts (to c ontrol the use of some facilities), temperature and hygrometry sen sor in the bathroom, and microphones (sound classification and speech recognition). A wearable kinematic sensor also info rms on postural transitions (using pattern recognition) and walk periods (frequency analysis). This data collected from thevarious sensors, is then used to classify each temporal frame into on e of the activities of daily living that was previously acquired (seven activities: hygiene, toilet use, eating, resting, sleepin g, communication, and dressing/undressing). This is done using Sup port Vector Machines. We performed a one-hour experimentation with 13 young and healthy subjects to determine the models of the different activities and then we tested the classification a lgorithm (cross-validation) with real data.