The Time Series Data Classification Method Based on Deep Spatial Transformer Network

被引：0

作者：

Hu, Demeng ^{[1
]}

Hu, Bo ^{[2
]}

Li, Zhao ^{[2
]}

Xv, Fangmin ^{[1
]}

机构：

[1] Beijing Univ Posts & Telecommun, Beijing, Peoples R China

[2] State Grid Liaoning Elect Power Supply Co Ltd, Shenyang, Liaoning, Peoples R China

来源：

COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, VOL. 1 | 2022年 / 878卷

基金：

中国国家自然科学基金;

关键词：

Multivariate time series; Prognostics health management; Spatial transformer network; Deep learning;

D O I：

10.1007/978-981-19-0390-8_82

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

In this paper, we propose a deep spatial transformer network (DSTN) to classify the time series data. This DSTN model can avoid the distortion thatmay be caused when the time series data is transformed to 2D-data, as it has an adaptive feature extractionmechanism profit and can carry out affine transformation on 2D-data. It can also avoid the influence of this distortion on the subsequent convolutional neural networks. Thus, Experimental results show that this framework can effectively classify and predict complex multivariable time series data.

引用

页码：667 / 671

页数：5

共 50 条

[41] A Transformer-Based Approach Combining Deep Learning Network and Spatial-Temporal Information for Raw EEG Classification
Xie, Jin
Zhang, Jie
Sun, Jiayao
Ma, Zheng
Qin, Liuni
Li, Guanglin
Zhou, Huihui
Zhan, Yang
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2022, 30 : 2126 - 2136
[42] A Novel Method of Hyperspectral Data Classification Based on Transfer Learning and Deep Belief Network
Li, Ke
Wang, Mingju
Liu, Yixin
Yu, Nan
Lan, Wei
APPLIED SCIENCES-BASEL, 2019, 9 (07):
[43] Prediction of Time Series Data Based on Transformer with Soft Dynamic Time Wrapping
Ho, Kuo-Hao
Huang, Pei-Shu
Wu, I-Chen
Wang, Feng-Jian
2020 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN (ICCE-TAIWAN), 2020,
[44] Multi-Channel Fusion Classification Method Based on Time-Series Data
Jin, Xue-Bo
Yang, Aiqiang
Su, Tingli
Kong, Jian-Lei
Bai, Yuting
SENSORS, 2021, 21 (13)
[45] Satellite time series data classification method based on trend symbolic aggregation approximation
Ruan H.
Liu L.
Hu X.
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2021, 47 (02): : 333 - 341
[46] Influence of Data Representations and Deep Architectures in Image Time Series Classification
Chelali, Mohamed
Kurtz, Camille
Puissant, Anne
Vincent, Nicole
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2021, 35 (12)
[47] CLR-based deep convolutional spiking neural network with validation based stopping for time series classification
Gautam, Anjali
Singh, Vrijendra
APPLIED INTELLIGENCE, 2020, 50 (03) : 830 - 848
[48] Robust IoT time series classification with data compression and deep learning
Azar, Joseph
Makhoul, Abdallah
Couturier, Raphael
Demerjian, Jacques
NEUROCOMPUTING, 2020, 398 : 222 - 234
[49] CLR-based deep convolutional spiking neural network with validation based stopping for time series classification
Anjali Gautam
Vrijendra Singh
Applied Intelligence, 2020, 50 : 830 - 848
[50] Spatial-temporal Attention Model Based on Transformer Architecture for Anomaly Detection in Multivariate Time Series Data
Zeng, Lai
Yang, Xiaomei
Journal of Computers (Taiwan), 2024, 35 (03) : 193 - 207

← 1 2 3 4 5 →