Study on modeling and recognition of human behaviors by If-Then-Rules with HMM

Conventional intelligent systems require humans to acquire knowledge and technique about the systems in order that humans receive their benefits. This means that humans must adapt to the systems. For this problem, it is necessary to realize such systems that can support humans, in other words, the systems that adapt to humans by considering human behaviors. In order to realize this idea, we propose a modeling and recognition method of human behaviors in this paper. In this method, we suppose that a human changes his behavior according to the change of the situation around him, and this concept is expressed by if-then-rules. In the rules, the change of the situation around a human is described by HMM (hidden Markov model) in order to consider its temporal and spatial redundancy. To recognize the change of human behaviors, the optimal if-then-rule is chosen based on the current human behavior and similarity to the time series data of the situation obtained by sensors. In this paper, human driving behaviors are considered as an example of human behaviors, and a recognition system of human driving behaviors is constructed. The usefulness of the proposed method is examined through some experimental results with the constructed system.