Exact Fit Attention in Node-Holistic Graph Convolutional Network for Improved EEG-Based Driver Fatigue Detection

TL;DR

This paper introduces NHGNet, a graph convolutional network with exact fit attention, to improve EEG-based driver fatigue detection by capturing inter-channel correlations and enhancing interpretability.

Contribution

The paper proposes a novel node-holistic graph convolutional network with exact fit attention, improving EEG fatigue detection accuracy and interpretability over existing methods.

Findings

NHGNet outperforms state-of-the-art models in accuracy on two datasets.

The model highlights the importance of central parietal, frontal, and temporal brain regions.

Inter-channel correlation learning enhances fatigue detection performance.

Abstract

EEG-based fatigue monitoring can effectively reduce the incidence of related traffic accidents. In the past decade, with the advancement of deep learning, convolutional neural networks (CNN) have been increasingly used for EEG signal processing. However, due to the data's non-Euclidean characteristics, existing CNNs may lose important spatial information from EEG, specifically channel correlation. Thus, we propose the node-holistic graph convolutional network (NHGNet), a model that uses graphic convolution to dynamically learn each channel's features. With exact fit attention optimization, the network captures inter-channel correlations through a trainable adjacency matrix. The interpretability is enhanced by revealing critical areas of brain activity and their interrelations in various mental states. In validations on two public datasets, NHGNet outperforms the SOTAs. Specifically, in the intra-subject, NHGNet improved detection accuracy by at least 2.34% and 3.42%, and in the inter-subjects, it improved by at least 2.09% and 15.06%. Visualization research on the model revealed that the central parietal area plays an important role in detecting fatigue levels, whereas the frontal and temporal lobes are essential for maintaining vigilance.