Reinforcement Learning for assistance of Alzheimer's disease patients

Abstract

Alzheimer's disease is a chronic brain disease with multi-factorial causes that begins in the middle of life. It affects the patient in many ways, like the ability to perform daily life activities. In this paper, we proposed an assistance system for Alzheimer's patients to assist them in performing their activities of daily living autonomously. The developed system is based on a human activity recognition system and a prompt system to provide alerts to the patient in case of need. To detect the anomalies in the patient's behavior and provide assistance, we used a reinforcement learning (RL) module as a decision-making system. This module may be responsible for identifying and prompting the patient's wanted assistance based on his or her behavior. The efficiency of the proposed system was proven after testing using the Dem Care dataset.