A fuzzy logic approach for learning daily human activities in an Ambient Intelligent Environment

This paper addresses the problem of learning human behavior models from sensor information in a smart home environment. Any smart home is provided with many devices that can determine the state of the environment at any moment, as well as the user interaction with the environment. This information is used by our approach to learn a flexible and reliable human behavior representation, extracting the relevant actions and the order constraints among them. In order to test our learning approach, we have performed experiments in the iSpace at the University of Essex which is an Ambient Intelligent Environment (AIE) testbed. We will present the results obtained by monitoring three participants' activities for three specific behaviors. The learned behavior model is compared with the behavior model provided by the participants. The results show that our proposed system effectively learns the behavior models for any behavior, acquiring not only the actions the user considers as basic, but also those unconsciously performed yet important ones done by the user. © 2012 IEEE.