Behavior Pattern Extraction Based on Growing Neural Networks for Informationally Structured Space

In this paper, we focus on behavior pattern extraction using sensor networks and portable sensing system. Behavior analysis is one of the most important tasks, which provides suitable information service to users. This paper proposes a pattern extraction method based on growing neural networks. The learning system is composed of two modules for feature extraction and contextual relation modeling using Growing Neural Gas (GNG) and Spiking Neural Network (SNN). GNG is applied to the feature extraction of human behavior, and SNN is used to associate the features with event information labels. We show several experimental results, and discuss the effectiveness of our proposed method.