A BiLSTM-CNN based Multitask Learning Approach for Fiber Fault Diagnosis

Abstract

A novel multitask learning approach based on stacked bidirectional long short-term memory (BiLSTM) networks and convolutional neural networks (CNN) for detecting, locating, characterizing, and identifying fiber faults is proposed. It outperforms conventionally employed techniques.

2021 Optical Fiber Communications Conference and Exhibition (OFC)

References in corpus (1)

• Machine Learning based Data Driven Diagnostic and Prognostic Approach for Laser Reliability Enhancement

Cited by in corpus (3)

• Machine Learning-based Anomaly Detection in Optical Fiber Monitoring
• Optical Fiber Fault Detection and Localization in a Noisy OTDR Trace Based on Denoising Convolutional Autoencoder and Bidirectional Long Short-Term Memory
• Gated Recurrent Unit based Autoencoder for Optical Link Fault Diagnosis in Passive Optical Networks