A hierarchical model-based system for discovering atypical behavior

Abstract

In this paper, we describe a model-based system for context discovery and behavior modeling for the purpose of monitoring well-being. In modeling behavior in a smart home, the system must detect atypical (anomalous) patterns of behavior resulting from failure of equipment as well as those deviations resulting from significant variations atypical of the human inhabitant. In the context of a smart home, both situations require human intervention although the response will differ. The home is embedded with sensors that unobtrusively record various environmental parameters. Models of behavior are generated from the sensor data. These models are employed to infer atypical behavior.