2P1-J08 On-line Learning Structure based on Spiking Neural Networks for Recognizing Human Behaviors(Integrating Ambient Intelligence)
Takenori Obo, Naoyuki Kubota · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · 2011
Human behavior recognition is one of the most important approaches in ubiquitous society. With the development of information technology and network technology, we can get various data from environments. However, it is very difficult to extract the required information from the huge data in real time. Almost previous method is based on off-line statistic approaches for modeling human behaviors. In this paper, we discuss on-line learning methods for human behavior recognition using sensor network. First of all, we apply a spiking neural network as a learning architecture based on the time series of measured data. Furthermore, we propose hierarchical learning structure using spiking neural network. Finally, we discuss the effectiveness of the proposed method through experimental results in a living room.