Detecting Elderly Behavior Shift via Smart Devices and Stigmergic Receptive Fields.

Smart devices are increasingly used for health monitoring. We present a novel connectionist architecture to detect elderly behavior shift from data gathered by wearable or ambient sensing technology. Behavior shift is a pattern used in many applications: it may indicate initial signs of disease or deviations in performance. In the proposed architecture, the input samples are aggregated by functional structures called trails. The trailing process is inspired by stigmergy, an insects’ coordination mechanism, and is managed by computational units called Stigmergic Receptive Fields (SRFs), which provide a (dis-)similarity measure between sample streams. This paper presents the architectural view, and summarizes the achievements related to three application case studies, i.e., indoor mobility behavior, sleep behavior, and physical activity behavior.