A BiLSTM-CNN based Multitask Learning Approach for Fiber Fault Diagnosis
2022-02-16Unverified0· sign in to hype
Khouloud Abdelli, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
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.