CSF-GTNet: A Novel Multi-Dimensional Feature Fusion Network Based on Convnext-GeLU- BiLSTM for EEG-Signals-Enabled Fatigue Driving Detection

• Published in: IEEE journal of biomedical and health informatics 2024-05, Vol.28 (5), p.2558-2568
• Main Authors: Gao, Dongrui, Li, Pengrui, Wang, Manqing, Liang, Yujie, Liu, Shihong, Zhou, Jiliu, Wang, Lutao, Zhang, Yongqing
• Format: Article
• Language: English
• Subjects: Adult; Algorithms; Automobile Driving; Band-pass filters; Brain; Brain - physiology; brain fatigue detection; Brain mapping; Brain modeling; Brain research; Cerebrospinal fluid; Convolution; cross-subject difference; Deep Learning; EEG; Electroencephalography; Electroencephalography - methods; Fatigue; Fatigue - diagnosis; Fatigue - physiopathology; Feature extraction; Female; Frequencies; Frequency dependence; Frequency domain analysis; Gaussian time domain network; Humans; Low-pass filters; Male; Multi-dimensional; Neural Networks, Computer; pure convolutional spatial-frequency domain network; Signal Processing, Computer-Assisted; Topology; Young Adult
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2023.3240891

Electroencephalography (EEG) signal has been recognized as an effective fatigue detection method, which can intuitively reflect the drivers' mental state. However, the research on multi-dimensional features in existing work could be much better. The instability and complexity of EEG signals will increase the difficulty of extracting data features. More importantly, most current work only treats deep learning models as classifiers. They ignored the features of different subjects learned by the model. Aiming at the above problems, this paper proposes a novel multi-dimensional feature fusion network, CSF-GTNet, based on time and space-frequency domains for fatigue detection. Specifically, it comprises Gaussian Time Domain Network (GTNet) and Pure Convolutional Spatial Frequency Domain Network (CSFNet). The experimental results show that the proposed method effectively distinguishes between alert and fatigue states. The accuracy rates are 85.16% and 81.48% on the self-made and SEED-VIG datasets, respectively, which are higher than the state-of-the-art methods. Moreover, we analyze the contribution of each brain region for fatigue detection through the brain topology map. In addition, we explore the changing trend of each frequency band and the significance between different subjects in the alert state and fatigue state through the heat map. Our research can provide new ideas in brain fatigue research and play a specific role in promoting the development of this field.