Detecting and predicting of abnormal behavior using hierarchical Markov model in smart home network

In this paper, we present an application of the hierarchical hidden Markov model (HHMM) for the problem of predicting the state of human behavior in a smart home network. We argue that to robustly model and recognize sequential human activities, it is crucial to exploit both the natural hierarchical decomposition and shared semantics embedded in a ubiquitous environment. To this end, we propose the use of the HHMM, a rich stochastic model that has recently been extended to handle shared structures, for representing and recognizing a set of complex indoor activities. The main contributions of this paper lie in the application of the shared structure HHMM, the estimation of the state of a user's behavior, and the detection of abnormal behavior. The user behavior data from an experiment show that directly modeling shared structures improves the recognition efficiency and prediction accuracy for the state of a human's behavior when compared with a flat HMM.