Abstract
We propose a fault prediction scheme using interpretable XGBoost based on actual datasets, which not only achieves high accuracy (99.72%) and low positive rate (0.18%), but also reveals the five most remarkable features that caused the fault.
© 2020 The Author(s)
PDF ArticleMore Like This
Ameni Mezni, Douglas W. Charlton, Christine Tremblay, and Christian Desrosiers
STh4M.1 CLEO: Science and Innovations (CLEO:S&I) 2020
Qunzhi Lin, Xiaokang Chen, Zhenlin Ouyang, Hanyu Gao, Xiaoliang Chen, and Zhaohui Li
Th3I.2 Optical Fiber Communication Conference (OFC) 2024
Bing Zhang, Yongli Zhao, Yajie Li, and Jie Zhang
M4A.197 Asia Communications and Photonics Conference (ACP) 2020