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

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. (C) 2022 Optica Publishing Group

Automated summary

We propose a hybrid model named ATCN-SA-BiLSTM for phase sensitive optical time domain reflectometry signal recognition. The model combines channel attention based temporal convolutional network, spatial attention, and bidirectional long short-term memory network. Experimental results show that our method achieves better classification performance.