Litcius/Paper detail

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

Manling Tian, Hui Dong, Xiaomin Cao, Kuanglu Yu

2022Applied Optics19 citationsDOI

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.

Topics & Concepts

Computer scienceOptical time-domain reflectometerPattern recognition (psychology)Convolution (computer science)Artificial intelligenceTime domainFalse alarmFeature extractionAlgorithmArtificial neural networkTelecommunicationsComputer visionFiber optic sensorOptical fiberGraded-index fiberAdvanced Fiber Optic SensorsOptical Coherence Tomography ApplicationsAdvanced Photonic Communication Systems
Temporal convolution network with a dual attention mechanism for φ-OTDR event classification | Litcius