Robust condition identification against label noise in industrial processes based on trusted connection dictionary learning

Keke Huang, Shijun Tao, Dehao Wu, Chunhua Yang, Weihua Gui

Abstract

Highlights•This paper proposes a robust condition identification method against label noise.•A dynamic graph is constructed to label noise correction and label propagation.•Experiments demonstrate the superiority and trustworthy of the proposed method.
BibTeX
@article{huang2024robust,
  author = {Keke Huang and Shijun Tao and Dehao Wu and Chunhua Yang and Weihua Gui},
  title = {{Robust condition identification against label noise in industrial processes based on trusted connection dictionary learning}},
  journal = {Reliab. Eng. Syst. saf},
  year = {2024},
  doi = {10.1016/j.ress.2024.110133},
}

Loading related content...

Figure