Abnormal network data mining model based on deep training learning. Issue 4 (12th October 2020)

• Record Type: Journal Article
• Authors: Jiang, Xiaoling; Zhang, Hui; Xu, Jiaming; Wu, Weicheng; Xie, Xingyong
• Is Part Of: International journal of internet protocol technology. Volume 13:Issue 4(2020)
• Page Start: 228
• Page End: 236
• Publication Date: 2020-10-12
• Subjects: local linear embedding algorithm -- target network data characteristics -- k-means algorithm -- improved particle swarm optimisation algorithm; File Transfer Protocol (Computer network protocol) -- Periodicals; Multicasting (Computer networks) -- Periodicals; 004.678
• Languages: English
• ISSNs: 1743-8209

Abstract

Aiming at the problems of low detection efficiency and poor clustering effect in traditional abnormal network data mining process, an abnormal data mining model based on kernel extreme learning machine and particle swarm optimisation is proposed. The enhanced local linear embedding algorithm is used to extract the features of abnormal network data, and the required feature dimensions are extracted repeatedly to obtain the corresponding features of target network data. K-means algorithm is introduced to cluster the target network data to increase the identification of data mining. By improving the particle swarm optimisation algorithm to optimise the parameters of the kernel limit learning machine, the final abnormal data mining results are the best. The experimental results show that the proposed method has high detection efficiency and good clustering effect, which fully proves the superiority of the proposed method and lays a foundation for the progress of abnormal network data mining technology.