DST_VI: An efficient DST-based vehicle identification algorithm in WSN

Wireless Sensor Networks (WSN) with small, densely distributed wireless sensor nodes are being envisioned and developed for a variety of applications. The advantages of WSN enable its significant prospects in target identification. Vehicle identification is the basic issue in Intelligent Traffic System (ITS) which is the typical application of WSN. Due to the diversity of road condition, the variety of vehicle and the complexity of on-road environment, readings or information obtained from sensor may be inaccurate. In this paper, to deal with the inaccuracy, we propose the Dempster-Shafer Theory of Evidence (DST) based vehicle identification algorithm (DSTVI) under the ITS background and put forward a novel basic belief mass construction model which is the crucial issue in DST theory. The experimental results sufficiently show the flexibility of the basic belief mass construction model and the efficiency of DSTVI algorithm.