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 The Author(s)
PDF Article | Presentation VideoMore Like This
Khouloud Abdelli, Helmut Grießer, and Stephan Pachnicke
S3D.3 Optoelectronics and Communications Conference (OECC) 2021
Khouloud Abdelli, Carsten Tropschug, Helmut Grießer, Sander Jansen, and Stephan Pachnicke
M2G.4 Optical Fiber Communication Conference (OFC) 2023
Luis Velasco and Danish Rafique
W3G.3 Optical Fiber Communication Conference (OFC) 2019