期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 32, 期 9, 页码 3942-3955出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2020.3016291
关键词
Time series analysis; Feature extraction; Task analysis; Hidden Markov models; Clustering algorithms; Predictive models; Heuristic algorithms; Model-based dynamics; recurrent neural networks (RNNs); self-supervised learning; time series clustering; unsupervised learning
类别
资金
- National Natural Science Foundation of China [61502174, 61872148, 61571005]
- Natural Science Foundation of Guangdong Province [2017A030313355, 2017A030313358, 2019A1515010768]
- Guangzhou Science and Technology Planning Project [201704030051, 201902010020]
- Key Research and Development Program of Guangdong Province [2018B010107002]
This article introduces a self-supervised time series clustering network framework named STCN, aiming to optimize feature extraction and clustering simultaneously. By using RNN for time series prediction, capturing temporal dynamics and maintaining local structures, the output is then fed into a self-supervised clustering module. Experimental results show that STCN has state-of-the-art performance, and visualization analysis further demonstrates the effectiveness of the proposed model.
Time series clustering is usually an essential unsupervised task in cases when category information is not available and has a wide range of applications. However, existing time series clustering methods usually either ignore temporal dynamics of time series or isolate the feature extraction from clustering tasks without considering the interaction between them. In this article, a time series clustering framework named self-supervised time series clustering network (STCN) is proposed to optimize the feature extraction and clustering simultaneously. In the feature extraction module, a recurrent neural network (RNN) conducts a one-step time series prediction that acts as the reconstruction of the input data, capturing the temporal dynamics and maintaining the local structures of the time series. The parameters of the output layer of the RNN are regarded as model-based dynamic features and then fed into a self-supervised clustering module to obtain the predicted labels. To bridge the gap between these two modules, we employ spectral analysis to constrain the similar features to have the same pseudoclass labels and align the predicted labels with pseudolabels as well. STCN is trained by iteratively updating the model parameters and the pseudoclass labels. Experiments conducted on extensive time series data sets show that STCN has state-of-the-art performance, and the visualization analysis also demonstrates the effectiveness of the proposed model.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据