Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization
Wei Song1Lu Liu2Minghao Liu1,3Wenxiang Wang1,3Xiao Wang1Yu Song4
1. Henan Academy of Big Data, Zhengzhou University2. Department of Computational Linguistics, University of Washington3. School of Information Engineering, Zhengzhou University4. Network Management Center, Zhengzhou University
摘要：We propose a new model based on the convolutional networks and SAX（Symbolic Aggregate Approximation） discretization to learn the representation for multivariate time series. The deep neural networks has excellent expressiveness, which is fully exploited by the convolutional networks with means of unsupervised learning. We design a network structure to obtain the cross-channel correlation with means of convolution and deconvolution, the pooling operation is utilized to perform the dimension reduction along each position of the channels. Discretization which based on the Symbolic Aggregate Approximation is applied on the feature vectors to extract the bag of features.We collect two different representations from the convolutional networks, the compression from bottle neck and the last convolutional layers. We show how these representations and bag of features can be useful for classification. We provide a full comparison with the sequence distance based approach on the standard datasets to demonstrate the effectiveness of our method. We further build the Markov matrix according to the discretized representation abstracted from the deconvolution, time series is visualized to complex networks through Markov matrix visualization, which show more class-specific statistical properties and clear structures with respect to different labels.
关键词：
Multivariate time-series; Deconvolution; Symbolic aggregate approximation; Deep learning; Markov matrix; Visualization;
会议名称：
2020国际计算机前沿大会
会议时间：
2020-09-18
会议地点：
中国山西太原
- 专辑：
信息科技
- 专题：
自动化技术
- DOI：
10.26914/c.cnkihy.2020.030344
- 分类号：
TP181
引文网络
相关推荐
- 相似文献
- 读者推荐
- 相关基金文献
- 关联作者
- 相关视频
