Applied Optics · 2022 · 19 citations · 17 references
ComputingData ScienceComputer VisionFeature EngineeringTime Series AnalysisAttention NetworksDeep LearningNeural Signal ProcessingPattern RecognitionTemporal AttentionTime Series ClassificationAttentionAttention-based ClassificationCausalityLong Short-term Memory NetworksSpatial Attention NetworksTemporal Convolutional NetworksTemporal Feature ExtractionTime-domain Features
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.
17
Squeeze-and-Excitation Networks
Jie Hu, Li Shen, Samuel Albanie et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2019 · 12.5K citations
Distributed fiber-optic intrusion sensor system
Julio César Montenegro Juárez, Eric Maier, Kyoo Nam Choi et al. · Journal of Lightwave Technology · 2005 · 758 citations
Distributed Vibration Sensor Based on Coherent Detection of Phase-OTDR
Yuelan Lu, Tao Zhu, Liang Chen et al. · Journal of Lightwave Technology · 2010 · 725 citations
Ultra-long high-sensitivity Φ-OTDR for high spatial resolution intrusion detection of pipelines
Fei Peng, Han Wu, Xin-Hong Jia et al. · Optics Express · 2014 · 404 citations · Full text