Wearable Sensor System for Human Behavior Recognition (First Report: Basic Architecture and Behavior Prediction Method)

Abstract

We developed a wearable sensor system for human behavior recognition. It can distinguish users' behaviors such as walking, running, standing, eating, talking, and desk working. The system consists of foot pressure sensing shoes, motion sensing watch, Sound sensing glasses, pen-shaped ceiling sensor and Indoor/outdoor positioning mobile phones. These sensors are all connected by wireless communication.