Abstract
This paper proposes a way to detect human behavior at home and to costruct human behavior model. The life behavior is related to the operating state of electric apliance in this paper because we usually use many kind of electric appliances in our daily life. Therefore we describe human behavior at home by a binary matrix and neural network is used to express subject's state. A experiment to observe an operating state of electric apliance has been carried out for a year. And computer simulations are carried out using the observed data. The simulation results show that the proposed method has good performance to detect human non-habitual behavior at home.
