Adaptive cost-sensitive learning: Improving the convergence of intelligent diagnosis models under imbalanced data

Zhijun REN, Yongsheng ZHU, Wei KANG, Hong FU, Qingbo NIU, Dawei GAO, Ke YAN, Jun HONG

Research output: Contribution to journalArticlespeer-review

Abstract

The natural distribution of industrial data is imbalanced, which deteriorates the performance of intelligent fault diagnostic models. Although cost-sensitive learning is an effective method for solving the data imbalance problem, it suffers from the difficulty of setting optimal costs. Therefore, this paper proposes a strategy that considers the number distribution of samples, the convergence trend of classes, and the convergence trend of samples to calculate sample costs adaptively. Using costs to weigh the sample losses and applying them to different models and different loss functions, the diagnostic results under different sample sets show that the weighted losses can significantly improve the model's performance when using imbalanced data. By further analysing the training loss of the modified model, the angles between deep features, and the angles between deep features and classification weight vectors, it can be found that the dominance of majority classes in imbalanced data is suppressed in training, which is attributed to the loss of each class being coordinated by the proposed strategy. The comparison with various imbalanced learning methods demonstrates the advantages of the proposed method under conditions of large imbalance ratios and complex tasks. Copyright © 2022 Elsevier B.V. All rights reserved.

Original languageEnglish
Article number108296
JournalKnowledge-Based Systems
Volume241
Early online dateFeb 2022
DOIs
Publication statusPublished - Apr 2022

Citation

Ren, Z., Zhu, Y., Kang, W., Fu, H., Niu, Q., Gao, D., . . . Hong, J. (2022). Adaptive cost-sensitive learning: Improving the convergence of intelligent diagnosis models under imbalanced data. Knowledge-Based Systems, 241. Retrieved from https://doi.org/10.1016/j.knosys.2022.108296

Keywords

  • Intelligent fault diagnosis
  • Imbalanced data
  • Imbalanced learning
  • Cost-sensitive learning
  • Adaptive cost

Fingerprint

Dive into the research topics of 'Adaptive cost-sensitive learning: Improving the convergence of intelligent diagnosis models under imbalanced data'. Together they form a unique fingerprint.