Improved target tracking using regression tree in wireless sensor networks

Abstract

Positioning and tracking of wireless devices in indoor environment is a challenging research problem. Accurate localization of a moving target is a fundamental requirement in Wireless Sensor Networks monitoring applications. In this paper, a novel location tracking algorithm which combines learning methods is proposed. In previous work, regression tree using received signal strength method is proposed to localize a static sensor node. This approach is employed in this paper to solve the complex relation between the received signal strength and the target position. Then, an ensemble of trees are applied leading to more accurate position of the moving target. The proposed algorithm has been experimentally evaluated using real measurement of a moving target in an office room. The performance results have been analyzed through a comparison with the standard regression tree and ordinary Kalman filter.