Abstract
We proposed an autoencoder-based anomaly-detection for optical failure detection with imbalanced data (<3%), which identifies implicit failure and achieves detection accuracy of 96.8% and F1 value of 0.9224.
© 2021 The Author(s)
PDF ArticleMore Like This
Yu Wan, Hui Yang, Qiuyan Yao, Bowen Bao, Chao Li, and Jie Zhang
T2A.7 Optoelectronics and Communications Conference (OECC) 2021
Francesco Musumeci
Th4J.1 Optical Fiber Communication Conference (OFC) 2021
Danshi Wang, Dongdong Wang, Chunyu Zhang, Lingling Wang, Songlin Liu, and Min Zhang
T3A.3 Optoelectronics and Communications Conference (OECC) 2021