RTFN: A robust temporal feature network for time series classification

Impact Factor:8.233

DOI number:10.1016/j.ins.2021.04.053

Affiliation of Author(s):Southwest Jiaotong Univ, Sch Comp & Artificial Intelligence

Journal:Information Sciences

Key Words:Attention mechanism,Convolutional neural network,Data mining,LSTM,Time series classification

Abstract:Time series data usually contains local and global patterns. Most of the existing feature networks focus on local features rather than the relationships among them. The latter is also essential, yet more difficult to explore because it is challenging to obtain sufficient rep-resentations using a feature network. To this end, we propose a novel robust temporal fea-ture network (RTFN) for feature extraction in time series classification, containing a temporal feature network (TFN) and a long short-term memory (LSTM)-based attention network (LSTMaN). TFN is a residual structure with multiple convolutional layers, and functions as a local-feature extraction network to mine sufficient local features from data. LSTMaN is composed of two identical layers, where attention and LSTM networks are hybridized. This network acts as a relation extraction network to discover the intrinsic rela-tionships among the features extracted from different data positions. In experiments, we embed the RTFN into supervised and unsupervised structures as a feature extractor and encoder, respectively. The results show that the RTFN-based structures achieve excellent supervised and unsupervised performances on a large number of UCR2018 and UEA2018 datasets. (c) 2021 Elsevier Inc. All rights reserved.

Co-author:Zhiwen Xiao,Xin Xu,Huanlai Xing*,Shouxi Luo,Penglin Dai,Dawei Zhan

Document Code:10.1016/j.ins.2021.04.053

Volume:571

Page Number:65-86

ISSN No.:0020-0255

Translation or Not:no

Date of Publication:2021-08-24

Included Journals:SCI