Authors: Mao Yingying; Yuan Hao
Addresses: Department of Information Engineering, HeNan Polytechnic, ZhengZhou, 450000, China ' School of Electronics and Information Engineering, ZhengZhou University SIAS International College, ZhengZhou, 451150, China
Abstract: The current method obtains the frequency of occurrence of abnormal data detected in the adjacent regions through reading between the sensor and the adjacent conversion data, and uses the frequency of occurrence of abnormal data to describe the spatial correlation, according to readings of sensor data using the Bayesian analysis method of sensor to determine whether the sensor is abnormal. But this method has the problem of low detection accuracy. For this reason, this paper proposes a method to detect the fuzzy breakpoint of data in the massive dynamic data flow. Firstly, this method used the amplitude difference method to determine the abnormal data amplitude and the discrete point difference of data fuzzy breakpoint, and then used the wavelet transform to extract the features of inflection point of the data fuzzy breakpoint. Combined with the features of inflection point of the extracted data fuzzy breakpoint, we carried out the support vector machine classification, and detected the data fuzzy breakpoints in the massive dynamic data flow. Experimental results show that the proposed method can effectively improve the accuracy of fuzzy breakpoint detection.
Keywords: massive dynamic; data flow; data fuzzy breakpoint; support vector machine.
International Journal of Information and Computer Security, 2019 Vol.11 No.6, pp.604 - 620
Received: 14 Jul 2017
Accepted: 28 Dec 2017
Published online: 09 Oct 2019 *