Sleeping activity recognition for an intelligent tele-monitoring system

Abstract

People that need assistance, as for instance elderly or disabled people, may be affected by a decline in daily functioning that usually involves the reduction and discontinuity in daily routines, as well as, a worsening in the overall quality of life. Thus, there is the need to intelligent systems able to monitor indoor activities of users to detect emergencies, recognise activities, send notifications, and provide a summary of all the relevant information. In this TFG, a machine learning system is presented, it is aimed at improving the ruled-based system accuracy in detecting whether the user is performing their sleeping activity or not. It has been integrated in a sensor-based tele-monitoring and home support system. The data used to build and evaluate the system was obtained from a real-world environment with real end-users, thus ensuring the data reflect the complexities of the real-world.