Clustering Multivariate Time Series Data a via Multi-Nonnegative Matrix Factorization in Multi-Relational Networks

作     者：Zhou, Lihua Du, Guowang Tao, Dapeng Chen, Hongmei Cheng, Jun Gong, Libo 

作者机构：Yunnan Univ Sch Informat Kunming 650091 Yunnan Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Yunnan Rural Sci & Technol Serv Ctr Kunming 650051 Yunnan Peoples R China 

出 版 物：《IEEE ACCESS》 (IEEE Access)

年 卷 期：2018年第6卷

页      面：74747-74761页

核心收录：

基　　金：National Natural Science Foundation of China [61762090, 61262069, 61472346, 61662086, 61772455, 61572486, U1713213] Natural Science Foundation of Yunnan Province [2016FA026, 2015FB114] Project of Innovative Research Team of Yunnan Province [2018HC019] Program for Innovation Research Team (in Science and Technology) from the University of Yunnan Province under Grant IRTSTYN Yunnan Natural Science Funds [2016FB105, 2018FY001(-013)] Program for Excellent Young Talents of Yunnan University [WX069051] Program for Excellent Young Talents of National Natural Science Foundation of Yunnan University [2018YDJQ004] 

主　　题：Multivariate time series clustering multi-relational network nonnegative matrix factorization 

摘      要：In multivariate time series clustering, the inter-similarity across distinct variates and the intra-similarity within each variate pose analytical challenges. Here, we propose a novel multivariate time series clustering method using multi-nonnegative matrix factorization (MNMF) in multi-relational networks. Specifically, a set of multivariate time series is transformed from the time-space domain into a multi-relational network in the topological domain. Then, the multi-relational network is factorized to identify time series clusters. The transformation from the time-space domain to the topological domain benefits from the ability of networks to characterize both the local and global relationships between the nodes, and MNMF incorporates inter-similarity across distinct variates into clustering. Furthermore, to trace the evolutionary trends of clusters, time series is transformed into a dynamic multi-relational network, thereby extending MNMF to dynamic MNMF. Extensive experiments illustrate the superiority of our approach compared with the current state-of-the-art algorithms.