Today, the monitoring of dependent people is a real challenge. This is mainly due to the increase in the number of elderly and reduction of medical staff. However, works done in recent years in France are faced with obstacle of clinical and industrial validation. In this paper, we propose a monitoring system for dependent persons living alone at home or in an institution 24h/24. This system is based on a presence multisensor network deployed in the living environment of the monitored person coupled with a wireless identification system. A learning algorithm is implemented in order to define a personalized behavioural model (motions deviation, nocturnal activity, falls, mobility). This model allows the nursing staff monitoring the behaviour through a web application accessed remotely, and also intervention in case of dangerous situations thanks to an alert system. In further, we describe the experiments conducted at the Caussade Local Hospital in France with Alzheimer patients and we present the results of data obtained. Finally, we propose the way for an economic model that would allow to industrialize the system with prospects of clinical validation on a larger cohort of patients.