Node Fault Diagnosis in WSN Based on RS and SVM

Abstract

In the wireless sensor network (WSN), the operation reliability is usually evaluated by processing measured datas at network nodes. As the traditional algorithms exist the problems of the complex calculation and large energy consumption, a method for fault diagnosis of nodes in WSN based on rough set theory (RS) and support vector machine (SVM) is proposed in this paper. In this paper, we collect various kinds of fault symptoms and integrate them first and then diagnose the fault nodes through rough set theory (RS) and support vector machine (SVM). Firstly, the rough set theory is used to reduce the attributes of sampling data in order to select the decision-making attributes for constituting a new simple dataset. Then we use the new simple dataset to train the SVM. And finally classify failure modes of WSN through the trained SVM model. The result shows with RS-SVM the diagnosis time is only 0.16s and the diagnosis accuracy is up to 95%. The algorithm in this paper makes full use of the RS and the SVM and the result shows the effectiveness of the algorithm in fault diagnosis of WSN, and also shows it can improve the efficiency and accuracy of fault diagnosis.