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

Abdelli, Khouloud; Griesser, Helmut; Tropschug, Carsten; Pachnicke, Stephan

doi:10.48550/arXiv.2202.08034

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

https://doi.org/10.48550/arXiv.2202.08034
Open external identifier URL

preprint

posted on 2023-01-12, 15:05 authored by Khouloud Abdelli, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke

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.

History

Related Materials

1.
URL - References https://doi.org/10.48550/arXiv.2202.08034
2.
DOI - Is supplement to A BiLSTM-CNN based Multitask Learning Approach for Fiber Fault Diagnosis

Disclaimer

This arXiv metadata record was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv.

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

History

Related Materials

Disclaimer

Usage metrics

Categories

Keywords

Licence

Exports