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

被引:8
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 45 条
[11]   Relative Wavelet Entropy Complex Network for Improving EEG-Based Fatigue Driving Classification [J].
Gao, Zhongke ;
Li, Shan ;
Cai, Qing ;
Dang, Weidong ;
Yang, Yuxuan ;
Mu, Chaoxu ;
Hui, Pan .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2019, 68 (07) :2491-2497
[12]  
Gregor K, 2015, PR MACH LEARN RES, V37, P1462
[13]   Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach [J].
He, He ;
Wu, Dongrui .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2020, 28 (05) :1091-1108
[14]   An adversarial discriminative temporal convolutional network for EEG-based cross-domain emotion recognition [J].
He, Zhipeng ;
Zhong, Yongshi ;
Pan, Jiahui .
COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 141
[15]   Driver drowsiness detection with eyelid related parameters by Support Vector Machine [J].
Hu Shuyan ;
Zheng Gangtie .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (04) :7651-7658
[16]   An EEG-Based Fatigue Detection and Mitigation System [J].
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)
[17]   CNN and LSTM based ensemble learning for human emotion recognition using EEG recordings [J].
Iyer, Abhishek ;
Das, Srimit Sritik ;
Teotia, Reva ;
Maheshwari, Shishir ;
Sharma, Rishi Raj .
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (04) :4883-4896
[18]   PERSONAL IDENTIFICATION BASED ON BRAIN NETWORKS OF EEG SIGNALS [J].
Kong, Wanzeng ;
Jiang, Bei ;
Fan, Qiaonan ;
Zhu, Li ;
Wei, Xuehui .
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE, 2018, 28 (04) :745-757
[19]   BENDR: Using Transformers and a Contrastive Self-Supervised Learning Task to Learn From Massive Amounts of EEG Data [J].
Kostas, Demetres ;
Aroca-Ouellette, Stephane ;
Rudzicz, Frank .
FRONTIERS IN HUMAN NEUROSCIENCE, 2021, 15
[20]   Using Muse: Rapid Mobile Assessment of Brain Performance [J].
Krigolson, Olave E. ;
Hammerstrom, Mathew R. ;
Abimbola, Wande ;
Trska, Robert ;
Wright, Bruce W. ;
Hecker, Kent G. ;
Binsted, Gordon .
FRONTIERS IN NEUROSCIENCE, 2021, 15