Detecting Abnormal Behavior by Real-Time Monitoring of Patients

Contents

The paper deals with a follow-up system that passively observes elderly people moving about in a hospital setting and records automatically various patterns of activity. The aim is to propose a support tool to help the medical staff make decisions. The system is based on a sensor network connected to a processing unit. The software developed automatically follows the patient’s behaviour and plots statistical curves related to a number of characteristics such as getting up, going to bed, going to the bathroom, etc, ... Thus real-time monitoring can be displayed on a graphical interface for the medical staff. Experimental platform using this system is presented along with examples of behaviour monitored during the night.