会议专题

Fault Diagnosis of Wireless Sensor Network Based On aiNet-KNN Classifier

In the application of WSN, the reliability of the output data of Network nodes is judged to monitor the operational status of the entire network. To make use of the advantage of artificial immune network and KNN algorithm in data processing, aiNet-KNN classifier algorithm is proposed in this paper. According to the outstanding capacity of aiNet, all training samples are compressed by clustering, and generate a memory set that is fully representative of the characteristics of the original training samples. And then the tested samples were classified based on the memory antibody set according to the accurate classification of KNN and determine which fault types they belonged to. The simulation result shows that this method can reduced complexity of KNN algorithm and more accurate and reliable in fault diagnosis.

aiNet immune network KNN algorithm dynamic clustering wireless sensor network fault diagnosis

LEI Lin YAN Dan

School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 610054

国际会议

第八届国际测试技术研讨会(8th International Symposium on Test and Measurement)

重庆

英文

3162-3165

2009-08-01(万方平台首次上网日期,不代表论文的发表时间)