期刊
COMPUTER COMMUNICATIONS
卷 182, 期 -, 页码 52-59出版社
ELSEVIER
DOI: 10.1016/j.comcom.2021.10.036
关键词
Time series classification; Fully convolutional networks; LSTM; Multi-scale; Spatial-temporal features
资金
- National Natural Science Foundation of China [61906030]
- Natural Science Foundation of Liaoning Province [2020-BS-063]
- Fundamental Research Funds for the Central Universities [DUT20RC (4) 009, 80904010301]
Deep learning methods, especially CNN and FCN, show competitive performance in time series classification task. Variants of CNN, such as LSTM-FCN and GRU-FCN, achieve state of the art results by learning spatial and temporal features simultaneously, inspiring the proposal of multimodal network LSTM-MFCN.
Time series classification (TSC) task attracts huge interests, since they correspond to the real-world problems in a wide variety of fields, such as industry monitoring. Deep learning methods, especially CNN and FCN, shows competitive performance in TSC task by their virtue of good adaption for raw time series and self-adapting extraction of features. Then various variants of CNN are proposed so as to make further breakthrough by the better perception to characteristics of data. Among them, LSTM-FCN and GRU-FCN who learn spatial and temporal features simultaneously are the most remarkable ones, achieving state of the art results. Therefore, inspired by their success and in consideration of the discriminative features implied in time series are diverse in size, a multimodal network LSTM-MFCN composed of multi-scale FCN (MFCN) and LSTM are proposed in this work. The gate-based network LSTM naturally fits to various terms time dependencies, and FCN with multi scale sets of filters are capable to perceive spatial features of different range from time series curves. Besides, dilation convolution is deployed to build multi-scale receptive fields in larger level without increasing the parameters to be trained. The full perception of large multi-scale spatial-temporal features lead LSTM-MFCN to possess comprehensive and thorough grasp to time series, thus achieve even better accuracies. Finally, two representative architectures are presented specifically and their experiments on UCR datasets reveals the effectiveness and superiority of proposed LSTM-MFCN.
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