作者: Tingzhi Zhao , Hongbo Ni , Xingshe Zhou , Lin Qiang , Daqing Zhang
DOI: 10.1007/978-3-319-06269-3_11
关键词: Markov chain 、 Physical medicine and rehabilitation 、 Cognitively impaired 、 Activities of daily living 、 Computer science 、 Automated method
摘要: In order to reduce the potential risks associated with physically and cognitively impaired ability of elderly living alone, in this work, we develop an automated method that is able detect abnormal patterns elderly’s entering exiting behaviors collected from simple sensors equipped home-based setting. With spatiotemporal data left by when they carrying out daily activities, a Markov Chains Model (MCM) based proposed classify sequences via analyzing probability distribution activity data. The experimental evaluation conducted on 128-day user shows high detection ratio 92.80% for individual 92.539% sequence consisting series activities.