Data Labeling Using Unsupervised Cascaded Pre-training with Fused Multi-port Data for Optical Failure Management

被引：0

作者：

Yang, Weijie ^{[1
]}

Zhang, Chunyu ^{[1
]}

Wang, Danshi ^{[1
]}

Zhu, Hong ^{[2
]}

Xu, Xinxing ^{[2
]}

Shi, Degang ^{[3
]}

Zhang, Min ^{[1
]}

机构：

[1] BUPT, State Key Lab Informat Photon & Opt Commun, Beijing 100876, Peoples R China

[2] Intelligent Network Innovat Ctr Chinaunicom, Beijing, Peoples R China

[3] China United Network Commun Grp Co Ltd, Beijing, Peoples R China

来源：

2024 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXHIBITION, OFC | 2024年

基金：

中国国家自然科学基金;

关键词：

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

We propose an unsupervised cascaded pre-training data labeling method that considers the intrinsic correlation of multi-port data, and verifies the scheme validity in failure prediction using real multi-port data from optical networks. (C) 2023 The Author(s)

引用

页数：3

共 32 条

[31] Characterization of pre- and post-failure deformation and evolution of the Shanyang landslide using multi-temporal remote sensing data
Zhan, Jiewei
Sun, Yuemin
Yu, Zhaoyue
Meng, Huanyu
Zhu, Wu
Peng, Jianbing
LANDSLIDES, 2024, 21 (07) : 1659 - 1672
[32] Development of a data entry system using optical character recognition for a multi-center clinical trial: Cataract port-II study.
Lubomski, LH
Roman, PV
Katz, J
Tielsch, JM
Scheim, OD
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 1996, 37 (03) : 1403 - 1403

← 1 2 3 4 →