A clustering-based improved Grey-Markov target tracking algorithm in wireless sensor networks

Target position prediction in wireless sensor networks (WSN) has long been an important but difficult problem to be addressed. Owing to the dynamic motion of the target, the accuracy of prediction results is still far from what we expect in real applications. In order to solve this problem, this paper presents a clustering-based improved Grey-Markov target tracking (CIGMTT for short) algorithm to combine Markov process with a segmentation Grey model to adapt to the changes of target motion. The algorithm can greatly improve prediction accuracy by introducing new initial value and background value into the segmentation Grey model. After getting the predicted position, a clustering routing mechanism is used to transmit the tracking information. Our clustering routing mechanism is based on node distance to the predicted target position and node residual energy to dynamically construct the tracking cluster. In this way, sensor nodes can wake up in advance so that we can complete the target tracking with as few nodes as possible and maximise the network lifetime. The performance analysis and simulation results show that the proposed algorithm is energy-efficient and achieves a superior performance in tracking accuracy and tracking probability.