主催: 一般社団法人 日本機械学会
会議名: ロボティクス・メカトロニクス 講演会2017
開催日: 2017/05/10 - 2017/05/13
In recent years, the increase in accidents and lonely death in the home has become a social problem due to the increase of the elderly living alone. Therefore this paper proposes an elderly people's abnormal behavior detection system by the floor laying pressure sensor. The system consists of more than 30 belt-like sensors and the sensing data provides many important information such as the subject position and the amount of movement.The feature patterns appeared in daily samples such as housework and sleeping are modeled by fuzzy inference and then the abnormal patterns can be detected as non-existent feature patterns using the possibility distribution estimation. Some experiments are provided to verify the effectiveness of the proposed system.