IEFS-GMB: Gradient Memory Bank-Guided Feature Selection Based on Information Entropy for EEG Classification of Neurological Disorders

2025-09-18

AI Summary

Existing EEG feature selection methods suffer from poor domain adaptability, limited interpretability, and insufficient robustness due to reliance on single-iteration optimization. To address these limitations, this paper proposes a novel feature selection method integrating information entropy with a gradient memory bank. The gradient memory bank continuously accumulates historical gradient information across training iterations, while information entropy dynamically quantifies feature importance, enabling iterative optimization and adaptive feature weighting. Integrated end-to-end with a deep learning encoder, the method jointly learns task-relevant EEG features and model parameters. Experiments on four public neurological disorder datasets demonstrate that our approach improves classification accuracy by 0.64%–6.45% over baseline models and significantly outperforms four state-of-the-art feature selection methods. Moreover, it enhances model interpretability and clinical applicability without compromising performance.

Technology Category

• Machine Learning: Dimensionality Reduction/Feature Selection
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Deep learning-based EEG classification is crucial for the automated detection of neurological disorders, improving diagnostic accuracy and enabling early intervention. However, the low signal-to-noise ratio of EEG signals limits model performance, making feature selection (FS) vital for optimizing representations learned by neural network encoders. Existing FS methods are seldom designed specifically for EEG diagnosis; many are architecture-dependent and lack interpretability, limiting their applicability. Moreover, most rely on single-iteration data, resulting in limited robustness to variability. To address these issues, we propose IEFS-GMB, an Information Entropy-based Feature Selection method guided by a Gradient Memory Bank. This approach constructs a dynamic memory bank storing historical gradients, computes feature importance via information entropy, and applies entropy-based weighting to select informative EEG features. Experiments on four public neurological disease datasets show that encoders enhanced with IEFS-GMB achieve accuracy improvements of 0.64% to 6.45% over baseline models. The method also outperforms four competing FS techniques and improves model interpretability, supporting its practical use in clinical settings.

Problem

• Improving EEG classification for neurological disorder detection
• Addressing low signal-to-noise ratio in EEG signals
• Overcoming limitations of existing feature selection methods

Innovation

• Dynamic memory bank storing historical gradients
• Feature importance computed via information entropy
• Entropy-based weighting selects informative EEG features