Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 20, 2026Energy Conversion and EconomicsOpen Access

HSL‐CFS: Hybrid stacked learning with cooperative feature selection for cyberattack detection in smart grids

View Full Paper
Ask AI
Bookmark
Share

Authors

QGQize GaoQLQiuyu LuJLJune Li

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved cyberattack detection accuracy in smart grids, indicating enhanced security measures are necessary.

Key Points

  • To develop an effective method for detecting cyberattacks in smart grids by utilizing multi-source data.
  • Proposed a cooperative feature selection approach for extracting key features from heterogeneous data.
  • Developed a hybrid stacked model integrating Extreme Random Trees and an improved Convolutional Neural Network.
  • Implemented enhancements like Euclidean-norm regularization and attention mechanisms to reduce overfitting.
  • HSL-CFS selected fewer features while improving stability and generalization.
  • The model achieved higher accuracy compared to existing methods on the dataset.
  • Probability alignment enhanced the complementary pattern recognition in cyber-physical data.

Cite This Study

Gao et al. (2026) studied this question.

synapsesocial.com/papers/6a362fbcdb0793dc1a53716ahttps://doi.org/10.1049/enc2.70042
View Full Paper
Ask AI
Bookmark
Share