A Data Processing Method for Human Motion Estimation to Reduce Network and Sensor Node Loads
Shintaro Imai, Mariko Miyamoto, Mingrui Cai, Yoshikazu Arai, Toshimitsu Inomata · International Journal of Cognitive Informatics and Natural Intelligence · 2013
Systems for estimating human motion using acceleration sensors present the following two problems: 1) advanced analysis and processing of sensor data are difficult because of resource limitations of sensor nodes; and 2) such analyses and processes burden the network because numerous sensor data are sent to the network. The authors’ proposed method described herein for sensor data analysis and processing uses a host computer located near sensor nodes (neighborhood host). This method is intended to achieve a good balance between reduction of the network load and advanced sensor data analysis and processing. Moreover, this method incorporates reduction of the load to sensor nodes. To evaluate their method, the authors implement two prototype systems that use different machine learning methods. The authors conduct some experiments using these prototype systems. The experimentally obtained results demonstrate that the proposed method can resolve two problems.