A regression method for EEG-based cross-dataset fatigue detection

被引:5
|
作者
Yuan, Duanyang [1 ]
Yue, Jingwei [2 ]
Xiong, Xuefeng [1 ]
Jiang, Yibi [1 ]
Zan, Peng [1 ]
Li, Chunyong [2 ]
机构
[1] Shanghai Univ, Sch Mechatron Engn & Automat, Shanghai Key Lab Power Stn Automat, Shanghai, Peoples R China
[2] Beijing Inst Radiat Med, Acad Mil Med Sci AMMS, Beijing, Peoples R China
关键词
fatigue detection; cross-dataset; EEG; regression method; self-supervised learning;
D O I
10.3389/fphys.2023.1196919
中图分类号
Q4 [生理学];
学科分类号
071003 ;
摘要
Introduction: Fatigue is dangerous for certain jobs requiring continuous concentration. When faced with new datasets, the existing fatigue detection model needs a large amount of electroencephalogram (EEG) data for training, which is resource-consuming and impractical. Although the cross-dataset fatigue detection model does not need to be retrained, no one has studied this problem previously. Therefore, this study will focus on the design of the cross-dataset fatigue detection model.Methods: This study proposes a regression method for EEG-based cross-dataset fatigue detection. This method is similar to self-supervised learning and can be divided into two steps: pre-training and the domain-specific adaptive step. To extract specific features for different datasets, a pretext task is proposed to distinguish data on different datasets in the pre-training step. Then, in the domain-specific adaptation stage, these specific features are projected into a shared subspace. Moreover, the maximum mean discrepancy (MMD) is exploited to continuously narrow the differences in the subspace so that an inherent connection can be built between datasets. In addition, the attention mechanism is introduced to extract continuous information on spatial features, and the gated recurrent unit (GRU) is used to capture time series information.Results: The accuracy and root mean square error (RMSE) achieved by the proposed method are 59.10% and 0.27, respectively, which significantly outperforms state-of-the-art domain adaptation methods.Discussion: In addition, this study discusses the effect of labeled samples. When the number of labeled samples is 10% of the total number, the accuracy of the proposed model can reach 66.21%. This study fills a vacancy in the field of fatigue detection. In addition, the EEG-based cross-dataset fatigue detection method can be used for reference by other EEG-based deep learning research practices.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] EEG-Based Cross-Dataset Driver Drowsiness Recognition With an Entropy Optimization Network
    Yuan, Liqiang
    Zhang, Shasha
    Li, Ruilin
    Zheng, Zhong
    Cui, Jian
    Siyal, Mohammed Yakoob
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2025, 29 (03) : 1970 - 1981
  • [2] Benchmarking EEG-based Cross-dataset Driver Drowsiness Recognition with Deep Transfer Learning
    Cui, Jian
    Yuan, Liqiang
    Li, Ruilin
    Wang, Zhaoxiang
    Yang, Dongping
    Jiang, Tianzi
    2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC, 2023,
  • [3] TFTL: A Task-Free Transfer Learning Strategy for EEG-Based Cross-Subject and Cross-Dataset Motor Imagery BCI
    Wang, Yihan
    Wang, Jiaxing
    Wang, Weiqun
    Su, Jianqiang
    Bunterngchit, Chayut
    Hou, Zeng-Guang
    IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2025, 72 (02) : 810 - 821
  • [4] An EEG-based Cognitive Fatigue Detection System
    Karim, Enamul
    Pavel, Hamza Reza
    Jaiswal, Ashish
    Zadeh, Mohammad Zaki
    Theofanidis, Michail
    Wylie, Glenn
    Makedon, Fillia
    PROCEEDINGS OF THE 16TH ACM INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS, PETRA 2023, 2023, : 131 - 136
  • [5] An EEG-Based Fatigue Detection and Mitigation System
    Huang, Kuan-Chih
    Huang, Teng-Yi
    Chuang, Chun-Hsiang
    King, Jung-Tai
    Wang, Yu-Kai
    Lin, Chin-Teng
    Jung, Tzyy-Ping
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2016, 26 (04)
  • [6] Amplifying pathological detection in EEG signaling pathways through cross-dataset transfer learning
    Darvishi-Bayazi, Mohammad-Javad
    Ghaemi, Mohammad Sajjad
    Lesort, Timothee
    Arefin, Md. Rifat
    Faubert, Jocelyn
    Rish, Irina
    COMPUTERS IN BIOLOGY AND MEDICINE, 2024, 169
  • [7] Joint domain symmetry and predictive balance for cross-dataset EEG emotion recognition
    Jiang, Haiting
    Shen, Fangyao
    Chen, Lina
    Peng, Yong
    Guo, Hongjie
    Gao, Hong
    JOURNAL OF NEUROSCIENCE METHODS, 2023, 400
  • [8] EEG-based neural networks approaches for fatigue and drowsiness detection: A survey
    Othmani, Alice
    Sabri, Aznul Qalid Md
    Aslan, Sinem
    Chaieb, Faten
    Rameh, Hala
    Alfred, Romain
    Cohen, Dayron
    NEUROCOMPUTING, 2023, 557
  • [9] Detection of Cross-Dataset Fake Audio Based on Prosodic and Pronunciation Features
    Wang, Chenglong
    Yi, Jiangyan
    Tao, Jianhua
    Zhang, Chu Yuan
    Zhang, Shuai
    Chen, Xun
    INTERSPEECH 2023, 2023, : 3844 - 3848
  • [10] Cross-Dataset Variability Problem in EEG Decoding With Deep Learning
    Xu, Lichao
    Xu, Minpeng
    Ke, Yufeng
    An, Xingwei
    Liu, Shuang
    Ming, Dong
    FRONTIERS IN HUMAN NEUROSCIENCE, 2020, 14