变压器
计算机科学
人工智能
异常检测
光谱图
计算机视觉
模式识别(心理学)
工程类
电压
电气工程
作者
Khouloud Abdelli,Matteo Lonardi,J. Gripp,Daniela Gallon Corrêa,Samuel L. I. Olsson,Fabien Boitier,Patricia Layec
标识
DOI:10.1364/ofc.2024.tu2j.4
摘要
We introduce an innovative vision transformer approach to identify and precisely locate high-risk events, including fiber cut precursors, in state-of-polarization derived spectrograms. Our method achieves impressive 97% diagnostic accuracy and precise temporal localization (6-ms- RMSE).
科研通智能强力驱动
Strongly Powered by AbleSci AI