A Wavelet Analysis-Based Big Data Spectral Clustering Algorithm for Electric Internet of Things. (August 2020)

• Record Type: Journal Article
• Authors: Zhang, Hao; Liu, Xin; Liu, Donglan; Yu, Hao
• Is Part Of: Journal of physics. Volume 1627(2020)
• Publication Date: 2020-08
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1627/1/012007
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: As traditional spectral clustering algorithm is not ideal in big data scenarios, this paper proposes a wavelet analysis-based big data spectral clustering algorithm for Electric Internet of Things. Firstly, using wavelet analysis to measure the dissimilarity of the network communication data, and then the similarity relationship between EIoT data is established to obtain the similarity matrix. Finally the spectral clustering algorithm is used to cluster the data based on similarity matrix obtained above. The experimental results show that the accuracy and purity of the proposed spectral clustering algorithm based on wavelet analysis are respectively 36.2 percent and 19.6 percent higher than traditional algorithms, indicating that the proposed spectral clustering algorithm based on wavelet analysis is effective for EIoT data clustering.