Temporal convolution network with a dual attention mechanism for φ-OTDR event classification

Page view(s)
108
Checked on Sep 10, 2025
Temporal convolution network with a dual attention mechanism for φ-OTDR event classification
Title:
Temporal convolution network with a dual attention mechanism for φ-OTDR event classification
Journal Title:
Applied Optics
Publication Date:
10 June 2022
Citation:
Tian, M., Dong, H., Cao, X., & Yu, K. (2022). Temporal convolution network with a dual attention mechanism for φ-OTDR event classification. Applied Optics, 61(20), 5951. https://doi.org/10.1364/ao.458736
Abstract:
We propose a hybrid model named channel attention based temporal convolutional network combined with spatial attention and bidirectional long short-term memory network (ATCN-SA-BiLSTM) for phase sensitive optical time domain reflectometry signal recognition. This hybrid model consists of three parts: ATCN, which extracts temporal features and preserves causality of time domain signals, the SA mechanism, which re-weights spatial sequences for better feature extraction, and BiLSTM, which extracts spatial relationships considering the bidirectional propagation characteristics of disturbances in space domain signals. Experimental results show that our method achieves better classification performance with an accuracy of 93.4% and zero nuisance alarm rate.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation Singapore - Central GAP Fund
Grant Reference no. : NRF2020NRF-CG001-040

Fundamental Research Funds for the Central Universities (2020JBM024); National Natural Science Foundation of China (61805008); Outstanding Chinese and Foreign Youth Exchange Program of China Association of Science and Technology.
Description:
© 2022 Optica Publishing Group. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modifications of the content of this paper are prohibited.
ISSN:
2155-3165
1559-128X
Files uploaded: