A Framework for Detecting and Analyzing Behavior Changes of Elderly People over Time Using Learning Techniques

Sensors (Basel). 2020 Dec 11;20(24):7112. doi: 10.3390/s20247112.

Abstract

A sensor-rich environment can be exploited for elder healthcare applications. In this work, our objective was to conduct a continuous and long-term analysis of elderly's behavior for detecting changes. We indeed did not study snapshots of the behavior but, rather, analyzed the overall behavior evolution over long periods of time in order to detect anomalies. Therefore, we proposed a learning method and formalize a normal behavior pattern for elderly people related to her/his Activities of Daily Living (ADL). We also defined a temporal similarity score between activities that allows detecting behavior changes over time. During the periods of time when behavior changes occurred, we then focused on each activity to identify anomalies. Finally, when a behavior change occurred, it was also necessary to help caregivers and/or family members understand the possible pathology detected in order for them to react accordingly. Therefore, the framework presented in this article includes a fuzzy logic-based decision support system that provides information about the suspected disease and its severity.

Keywords: activities of daily living; behavior change observation; decision support system; elderly people; fuzzy logic system; smart home.

MeSH terms

  • Activities of Daily Living*
  • Aged
  • Caregivers*
  • Decision Support Systems, Clinical*
  • Female
  • Fuzzy Logic
  • Geriatric Assessment / methods*
  • Humans