Classification of daily physical activities from a single kinematic sensor

This work was conducted in TIMC laboratory to develop methods able to monitor physical activities. In the framework of Health Smart Home, the purpose is to maintain and supervise elderly or fragile people at home. Activity and autonomy levels are important criteria to evaluate the health of the patient. The time spent in each postural state (lying, sitting, standing), the periods of walking and the number of postural transitions: sit-to-stand (StS), back-to-sit (BtS) give information about the patient's activity. The purpose of the current study is to detect these activities using an unique sensor made of three accelerometers, attached to the chest. First, this paper describes how each algorithm (posture, walk, postural transitions) works. Secondly, the results on real data are shown. An experiment with elderly subjects was carried out. Each subject performed daily activities (walking, sitting, lying down, ...) while wearing the sensor.