Feature Reweighting for EEG-based Motor Imagery Classification

2023-07-29

arXiv.org

AI Summary

Low signal-to-noise ratio and non-stationarity in EEG-based motor imagery (MI) classification hinder convolutional neural networks (CNNs) by causing sensitivity to irrelevant features. To address this, we propose a learnable feature reweighting mechanism that dynamically suppresses noise-correlated feature maps along both temporal and channel dimensions, thereby enhancing the discriminability of task-relevant neural patterns. Integrated into an end-to-end CNN architecture, this mechanism enables adaptive spatiotemporal feature selection, overcoming the limited feature robustness of conventional CNNs in MI-EEG decoding. Evaluated on PhysioNet EEG-MMIDB and BCI Competition IV 2a datasets, our method achieves absolute accuracy improvements of 9.34% and 3.82%, respectively, surpassing state-of-the-art approaches. This work introduces, for the first time, learnable reweighting for MI-EEG feature optimization, establishing a novel paradigm for noise-robust brain–computer interface decoding.

Abstract

Classification of motor imagery (MI) using non-invasive electroencephalographic (EEG) signals is a critical objective as it is used to predict the intention of limb movements of a subject. In recent research, convolutional neural network (CNN) based methods have been widely utilized for MI-EEG classification. The challenges of training neural networks for MI-EEG signals classification include low signal-to-noise ratio, non-stationarity, non-linearity, and high complexity of EEG signals. The features computed by CNN-based networks on the highly noisy MI-EEG signals contain irrelevant information. Subsequently, the feature maps of the CNN-based network computed from the noisy and irrelevant features contain irrelevant information. Thus, many non-contributing features often mislead the neural network training and degrade the classification performance. Hence, a novel feature reweighting approach is proposed to address this issue. The proposed method gives a noise reduction mechanism named feature reweighting module that suppresses irrelevant temporal and channel feature maps. The feature reweighting module of the proposed method generates scores that reweight the feature maps to reduce the impact of irrelevant information. Experimental results show that the proposed method significantly improved the classification of MI-EEG signals of Physionet EEG-MMIDB and BCI Competition IV 2a datasets by a margin of 9.34% and 3.82%, respectively, compared to the state-of-the-art methods.

Problem

• Improving EEG-based motor imagery classification accuracy
• Reducing irrelevant features in noisy EEG signals
• Enhancing CNN performance with feature reweighting

Innovation

• Feature reweighting module for noise reduction
• Suppresses irrelevant temporal and channel features
• Improves EEG classification accuracy significantly