Data Anomaly Detection Method of Sensor Nodes in Internet of Things
Huang Hua · Jisuanji fangzhen · 2012
Research the abnormality detection of the network nodes to improve the testing accuracy.Data collected from sensor nodes of network are random and different in format and storage form,thus it is hard for the nodes to fit each other.The traditional detection method cannot accurately suggest the uniform features to be detected according to different information,which leads to the low accuracy of the detection.To solve this problem,this paper proposed an algorithm based on the characteristics of the fuzzy clustering probability searching.By caculating the probability of the fuzzy characteristics between node data and abnormal data,we can determine the illegal node data with the application of the fuzzy probability factors.