Personalized real-time anomaly detection and health feedback for older adults

Rapid population aging and the availability of sensors and intelligent objects motivate the development of healthcare systems; these systems, in turn, meet the needs of older adults by supporting them to accomplish their day-to-day activities. Collecting information regarding older adults daily activity potentially helps to detect abnormal behavior. Anomaly detection can subsequently be combined with real-time, continuous and personalized interventions to help older adults actively enjoy a healthy lifestyle. This paper introduces a system that uses a novel approach to generate personalized health feedback. The proposed system models user's daily behavior in order to detect anomalous behaviors and strategically generates interventions to encourage behaviors conducive to a healthier lifestyle. The system uses a Mamdani-type fuzzy rule-based component to predict the level of intervention needed for each detected anomaly and a sequential decision-making algorithm, Contextual Multi-armed Bandit, to generate suggestions to minimize anomalous behavior. We describe the system's architecture in detail and we provide example implementations for the anomaly detection and corresponding health feedback.