An energy saving strategy for object tracking in sensor networks by mining seamless temporal moving patterns

Abstract

Energy saving in sensor networks has received extensive attentions for researches in recent years due to the wide applications. One important research issue is energy efficient object tracking in sensor networks (OTSNs) in considering the limited power of sensor nodes. The past studies on energy saving in OTSNs usually considered the movement behavior of objects as randomness. However, in some real applications, the object movement behavior often carries certain patterns instead of randomness completely. In this paper, we propose a seamless data mining algorithm named STMP-Mine for efficiently discovering the seamless temporal movement patterns of objects in sensor networks. Moreover, we propose novel location prediction strategies that employ the discovered seamless temporal movement patterns to reduce the prediction errors for energy saving. Through empirical evaluation on simulated, STMP-Mine and the proposed prediction strategies are shown to deliver excellent performance in terms of scalability and energy efficiency.