计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (6): 200-210.doi: 10.11896/jsjkx.240300124

• 计算机图形学&多媒体 • 上一篇    下一篇

基于局部与全局特征集成网络的跨被试驾驶疲劳检测

龚子安, 顾正晖, 陈迪   

  1. 华南理工大学自动化科学与工程学院 广州 510000
  • 收稿日期:2024-03-18 修回日期:2024-07-18 出版日期:2025-06-15 发布日期:2025-06-11
  • 通讯作者: 陈迪(202010102835@mail.scut.edu.cn)
  • 作者简介:(202121018369@mail.scut.edu.cn)
  • 基金资助:
    国家自然科学基金(62276102);广东省自然科学基金(2021A1515012630)

Cross-subject Driver Fatigue Detection Based on Local and Global Feature Integrated Network

GONG Zian, GU Zhenghui, CHEN Di   

  1. School of Automation Science and Engineering,South China University of Technology,Guangzhou 510000,China
  • Received:2024-03-18 Revised:2024-07-18 Online:2025-06-15 Published:2025-06-11
  • About author:GONG Zian,born in 1999,postgraguate.His main research interests include fatigue detection based on EEG and cross-subject transfer learning of EEG.
    CHEN Di,born in 1999,doctoral student.Her main research interests include attention detection based on EEG and cross-subject transfer learning of EEG.
  • Supported by:
    National Natural Science Foundation of China(62276102) and Natural Science Foundation of Guangdong(2021A1515012630).

PDF (PC)

112

摘要： 驾驶员疲劳检测在减少交通事故中发挥着重要作用。脑电信号作为能够直接反映驾驶员精神状态的指标,被公认为驾驶疲劳检测的有效工具。然而,脑电信号本身的高噪声特性以及在不同个体间的明显差异性,给基于脑电信号的跨被试驾驶疲劳检测带来了诸多挑战。对此,提出了一种基于局部特征处理和全局特征处理的集成网络来提取脑电信号中的特征,用于解决跨被试驾驶疲劳检测中面临的问题。在SEED-VIG数据集上进行跨被试三分类检测任务时,该模型取得了61.34%的准确率,显著优于基线方法。为了增强模型的性能,使用并改良了迁移学习方法,在跨被试三分类检测任务中,模型准确率提高了13.35%。综上,所提模型在基于脑电信号的跨被试驾驶疲劳检测上取得了良好效果,有望为该方向的研究提供新的策略。

关键词: 疲劳检测, 脑电信号, 跨被试, 局部特征处理, 全局特征处理, 集成网络, 迁移学习

Abstract: Driver fatigue detection plays a crucial role in reducing traffic accidents.Electroencephalogram(EEG) signals,recognized as effective indicators that directly reflect a driver's mental state,are widely acknowledged as valuable tools for fatigue detection.However,the inherent high noise characteristics of EEG signals and their significant variability across individuals pose considerable challenges for cross-subject driver fatigue detection.To address these challenges,this paper proposes an integrated network based on local feature processing and global feature processing to extract features from EEG signals,aiming at overcoming the issues in cross-subject fatigue detection.When applied to the SEED-VIG dataset for a cross-subject three-class detection task,this model achieves an accuracy of 61.34%,significantly surpassing baseline methods.To enhance the performance of the model further,it employs and refines transfer learning methods,resulting in a 13.35% increase in model accuracy for the cross-subject three-class detection task.Overall,this study has demonstrated promising results in EEG-based cross-subject driver fatigue detection,offering new strategies for future studies in this direction.

Key words: Fatigue detection, Electroencephalogram, Cross-subject, Local feature processing, Global feature processing, Integra-ted network, Transfer learning

中图分类号: 

  • TP391.4
[1]World Health Organization.Global status report on road safety:time for action[M].World Health Organization,2009.
[2]FERNANDES R,HATFIELD J,JOB R F S.A systematic investigation of the differential predictors for speeding,drink-driving,driving while fatigued,and not wearing a seat belt,among young drivers[J].Transportation Research Part F:Traffic Psychology and Behaviour,2010,13(3):179-196.
[3]GAO Y,FU X,OUYANG T,et al.Emotion Recognition from EEG Signals Based on Spatio-Temporal Adaptive Graph Convolutional Neural Network[J].Computer Science,2022,49(4):30-36.
[4]SIKANDER G,ANWAR S.Driver fatigue detection systems:A review[J].IEEE Transactions on Intelligent Transportation Systems,2018,20(6):2339-2352.
[5]FOONG R,ANG K K,QUEK C.Correlation of reaction timeand EEG log bandpower from dry frontal electrodes in a passive fatigue driving simulation experiment[C]//2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC).IEEE,2017:2482-2485.
[6]WANG B,WU X,HU X,et al.Fatigue Detection System Based on Single-Channel EEG Signal[J].Computer Science,2020,47(5):225-229.
[7]WANG H,DRAGOMIR A,ABBASI N I,et al.A novel real-time driving fatigue detection system based on wireless dry EEG[J].Cognitive Neurodynamics,2018,12(4):365-376.
[8]ABIDI A,BEN KHALIFA K,BEN CHEIKH R,et al.Automa-tic detection of drowsiness in EEG records based on machine learning approaches[J].Neural Processing Letters,2022,54(6):5225-5249.
[9]SUBASI A,SAIKIA A,BAGEDO K,et al.EEG-based driver fatigue detection using FAWT and multiboosting approaches[J].IEEE Transactions on Industrial Informatics,2022,18(10):6602-6609.
[10]JANIESCH C,ZSCHECH P,HEINRICH K.Machine learning and deep learning[J].Electronic Markets,2021,31(3):685-695.
[11]RUNDO F,RINELLA S,MASSIMINO S,et al.An innovative deep learning algorithm for drowsiness detection from EEG signal[J].Computation,2019,7(1):13.
[12]KO W,OH K,JEON E,et al.Vignet:A deep convolutional neural network for eeg-baseddriver vigilance estimation[C]//2020 8th International Winter Conference on Brain-Computer Interface(BCI).IEEE,2020:1-3.
[13]GAO D,LI P,WANG M,et al.CSF-GTNet:A novel multi-dimensional feature fusion network based on Convnext-GeLU-BiLSTM for EEG-signals-enabled fatigue driving detection[J/OL].https://ieeexplore.ieee.org/abstract/document/10032797.
[14]SONG X W,YAN D D,ZHAO L L,et al.LSDD-EEGNet:An efficient end-to-end framework for EEG-based depression detection[J].Biomedical Signal Processing and Control,2022,75:103612.
[15]JIA H,XIAO Z,JI P.End-to-end fatigue driving EEG signal detection model based on improved temporal-graph convolution network[J].Computers in Biology and Medicine,2023,152:106431.
[16]PAN S J,YANG Q.A survey on transfer learning[J].IEEE Transactions on Knowledge and Data Engineering,2009,22(10):1345-1359.
[17]ZENG H,ZHANG J,ZAKARIA W,et al.InstanceEasyTL:An improved transfer-learning method for EEG-based cross-subject fatigue detection[J].Sensors,2020,20(24):7251.
[18]WEI C S,LIN Y P,WANG Y T,et al.Selective transfer learning for EEG-based drowsiness detection[C]//2015 IEEE International Conference on Systems,Man,and Cybernetics.IEEE,2015:3229-3232.
[19]SHALASH W M.Driver fatigue detection with single EEGchannel using transferlearning[C]//2019 IEEE International Conference on Imaging Systems and Techniques(IST).IEEE,2019:1-6.
[20]LIU Y,LAN Z,CUI J,et al.Inter-subject transfer learning for EEG-based mental fatigue recognition[J].Advanced Enginee-ring Informatics,2020,46:101157.
[21]BOSER B E,GUYON I M,VAPNIK V N.A training algorithm for optimal margin classifiers[C]//Proceedings of the Fifth Annual Workshop on Computational Learning Theory.1992:144-152.
[22]LAWHERN V J,SOLON A J,WAYTOWICH N R,et al.EEGNet:a compact convolutional neural network for EEG-based brain-computer interfaces[J].Journal of Neural Engineering,2018,15(5):056013.
[23]GAO Z,WANG X,YANG Y,et al.EEG-based spatio-temporal convolutional neural network for driver fatigue evaluation[J].IEEETransactions on Neural Networks and Learning Systems,2019,30(9):2755-2763.
[24]PENG B,ZHANG Y,WANG M,et al.TA-MFFNet:Multi-feature fusion network for EEG analysis and driving fatigue detection based on time domain network and attention network[J].Computational Biology and Chemistry,2023,104:107863.
[25]ZHENG W L,LU B L.A multimodal approach to estimating vigilance using EEG and forehead EOG[J].Journal ofNeural Engineering,2017,14(2):026017.
[26]DINGES D F,GRACE R.PERCLOS:A valid psychophysiological measure of alertness asassessed by psychomotor vigilance[J/OL].https://www.researchgate.net/publication/247130704_PERCLOS_A_Valid_Psychophysiological_Measure_of_Alertness_as_Assessed_by_Psychomotor_Vigilance.
[27]WU W,SUN W,WU Q M J,et al.Multimodal vigilance estimation using deep learning[J].IEEE Transactions on Cybernetics,2020,52(5):3097-3110.
[28]SHI L C,JIAO Y Y,LU B L.Differential entropy feature for EEG-based vigilance estimation[C]//2013 35th Annual International Conference of the IEEE Engineering in Medicine and Bio-logy Society(EMBC).IEEE,2013:6627-6630.
[29]LIANG M.Research on Emotion Recognition Based on Multi-modal Physiological Signals [D].Taiyuan:Taiyuan University of Technology,2022.
[30]HUANG G,MENG J,ZHANG D,et al.Window function for EEG power density estimation and its application in SSVEP based BCIs[C]//Intelligent Robotics and Applications:4th International Conference(ICIRA 2011).Aachen,Germany,Part II 4.Springer Berlin Heidelberg,2011:135-144.
[31]SHI L C,LU B L.Off-line and on-line vigilance estimation based on linear dynamical system and manifold learning[C]//2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.IEEE,2010:6587-6590.
[32]ZHAO Y,CHU D,HE J,et al.Interactive local and global feature coupling for EEG-based epileptic seizure detection[J].Biomedical Signal Processing and Control,2023,81:104441.
[33]WANG Z,YAN W,OATES T.Time series classification from scratch with deep neural networks:A strong baseline[C]//2017 International Joint Conference on Neural Networks(IJCNN).IEEE,2017:1578-1585.
[34]CUI F,WANG R,DING W,et al.A novel DE-CNN-BiLSTM multi-fusion model for EEG emotion recognition[J].Mathema-tics,2022,10(4):582.
[35]LI Y,ZHENG W,WANG L,et al.From regional to globalbrain:A novel hierarchical spatial-temporal neural network model for EEG emotion recognition[J].IEEE Transactions on Affective Computing,2019,13(2):568-578.
[36]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[37]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[38]BAHDANAU D,CHO K,BENGIO Y.Neural machine translation by jointly learning to align and translate[J].arXiv:1409.0473,2014.
[39]KIRANYAZ S,INCE T,GABBOUJ M.Real-time patient-spe-cific ECG classification by 1-D convolutional neural networks[J].IEEETransactions on Biomedical Engineering,2015,63(3):664-675.
[40]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[41]PAN J,FENG Y,ZOU X.A Single-Channel EEG Signal Based Sleep Staging with Global-Context-Modeling Feature Fusion[C]//2023 China Automation Congress(CAC).IEEE,2023:3268-3273.
[42]HANSEN L K,SALAMON P.Neural network ensembles[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(10):993-1001.
[43]CHENG J,CHEN L.A weighted regional voting based ensemble of multiple classifiers for face recognition[C]//International Symposium on Visual Computing.Cham:Springer International Publishing,2014:482-491.
[44]UGONI A,WALKER B F.The Chi square test:an introduction[J].COMSIG Review,1995,4(3):61.
[45]CHEN F,QING Z,ZHANG Y,et al.Lara:A light and anti-overfitting retraining approach for unsupervised anomaly detection[J].arXiv:2310.05668,2023.
[46]DZIUGAITE G K,ROY D M,GHAHRAMANI Z.Traininggenerative neural networks via maximum mean discrepancy optimization[J].arXiv:1505.03906,2015.
[47]LI X,ZHANG Z,GAO L,et al.A new semi-supervised faultdiagnosis method via deep CORAL and transfer component analysis[J].IEEE Transactions on Emerging Topics in Computa-tional Intelligence,2021,6(3):690-699.
[48]THIMM G,FIESLER E.Neural network initialization[C]//From Natural to Artificial Neural Computation:International Workshop on Artificial Neural Networks Malaga-Torremolinos.Spain:Springer,1995:535-542.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发