Abstract
We propose a GAN based soft failure detection and identification algorithm. For the training, the detection and identification only need normal samples and very few soft failure samples, respectively. 95% accuracy is achieved in experiment.
© 2021 The Author(s)
PDF Article | Presentation VideoMore Like This
Kaixuan Sun, Zhenming Yu, Liang Shu, Zhiquan Wan, and Kun Xu
Th5D.6 Optical Fiber Communication Conference (OFC) 2021
Shahin Shahkarami, Francesco Musumeci, Filippo Cugini, and Massimo Tornatore
M3A.5 Optical Fiber Communication Conference (OFC) 2018
Liang Shu, Zhenming Yu, Zhiquan Wan, and Kun Xu
C2F_1 Conference on Lasers and Electro-Optics/Pacific Rim (CLEO/PR) 2020