基于脑电通道注意力机制的驾驶行为识别研究

doi:10.16097/j.cnki.1009-6744.2024.04.027

交通运输系统工程与信息 ›› 2024, Vol. 24 ›› Issue (4): 283-291.DOI: 10.16097/j.cnki.1009-6744.2024.04.027

基于脑电通道注意力机制的驾驶行为识别研究

赵朔，奇格奇，李培豪，关伟^*

北京交通大学，城市交通复杂系统理论与技术教育部重点实验室，北京100044

收稿日期:2024-03-11 修回日期:2024-04-08 接受日期:2024-04-22 出版日期:2024-08-25 发布日期:2024-08-22
作者简介:赵朔(1996- )，男，河南南阳人，博士生。
基金资助:
国家自然科学基金 (72271018, 72101014)。

Driving Behavior Recognition Based on EEG Channel Attention Mechanism

ZHAOShuo,QI Geqi,LI Peihao,GUAN Wei^*

State Key Laboratory of Theory and Technology of Urban Transportation Complex Systems, Beijing Jiaotong University, Beijing 100044, China

Received:2024-03-11 Revised:2024-04-08 Accepted:2024-04-22 Online:2024-08-25 Published:2024-08-22
Supported by:
NationalNaturalScienceFoundation of China (72271018, 72101014)。

摘要/Abstract

摘要： 脑电信号以其高时间分辨率等优点成为识别驾驶员认知状态和评估驾驶性能的重要工具。以往研究中，基于脑电识别驾驶行为往往局限于异常驾驶状态，例如，疲劳检测和分心驾驶等，忽略了常规驾驶场景。本文以常规驾驶行为作为研究对象，通过驾驶模拟实验同步采集驾驶员在执行加速、减速和转向行为时的驾驶数据和脑电数据，构建基于压缩—激励模块的通道注意力—可分离卷积神经网络，对驾驶员上述驾驶行为进行模式识别，并优化选择跨个体脑电信号通道。结果表明，本文模型在3类驾驶行为识别的准确率达到82%，且在保证预测精度的情况下，将通道数量降低了70%。通过消融实验以及与其他基准模型的对比证明了模型的有效性。对最优通道组合的头皮拓扑位置分析发现，大脑额区和枕区与常规驾驶行为最为相关。研究结果可为从认知角度理解驾驶行为及类脑驾驶决策提供方法依据。

关键词: 智能交通, 驾驶行为识别, 压缩—激励网络, 脑电通道优化

Abstract: Electroencephalogram (EGG) signals, with their high temporal resolution among other advantages, have become an essential tool for recognizing drivers' cognitive states and assessing driving performance. Previous research on brain electrical activity in the context of driving behavior has often been limited to abnormal driving states, such as fatigue detection and distracted driving, neglecting normal driving scenarios. This paper focuses on regular driving behaviors recognition. Through driving simulation experiments, this study synchronously collected driving and brain electrical activity data from drivers while they performed acceleration, deceleration, and turning maneuvers. A channel attention-separable convolutional neural network based on the squeeze-and-excitation module is constructed to recognize the driving behaviors and optimize channel selection across individuals' brain electrical signals. The results show that the proposed model achieved an accuracy of 82% in recognizing three types of driving behaviors while reducing the number of channels by 70% without compromising prediction accuracy. The effectiveness of the model was demonstrated through ablation experiments and comparisons with other baseline models. Analysis of the optimal channel combinations' scalp topography revealed that the frontal and occipital areas of the brain are most relevant to regular driving behaviors. The findings of this study provide a methodological basis to understand driving behavior from a cognitive perspective and for brain-like driving decision-making.

Key words: intelligent transportation, driving behavior recognition, squeeze-and-excitation network, electroencephalogram (EEG) channel selection

中图分类号:

U491.1

赵朔, 奇格奇, 李培豪, 关伟. 基于脑电通道注意力机制的驾驶行为识别研究[J]. 交通运输系统工程与信息, 2024, 24(4): 283-291.

ZHAOShuo, QI Geqi, LI Peihao, GUAN Wei. Driving Behavior Recognition Based on EEG Channel Attention Mechanism[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(4): 283-291.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.04.027

http://www.tseit.org.cn/CN/Y2024/V24/I4/283

参考文献

[1]沈钧贤.人类脑计划与神经信息学[J].生物物理学报, 2001, 17(4): 608-612. [SHEN J X. Human brain project and neural information[J]. Acta Biophysica Sinica, 2001, 17(4): 607-612.]

[2]关伟,杨柳,江世雄,等.脑电在交通驾驶行为中的应用研究综述[J]. 交通运输系统工程与信息,2016, 16(3): 35-44. [GUAN W, YANG L, JIANG S X, et al. Review on the application of EEG in traffic driving behavior study[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(3): 35-44.]

[3]陈骥驰,王宏,王翘秀,等.基于脑电信号的疲劳驾驶状态研究[J]. 汽车工程, 2018, 40(5): 515-520. [CHEN J C, WANG H, WANG Q X, et al. A study on drowsy driving state based on EEG signals[J]. Automotive Engineering, 2018, 40(5): 515-520.]

[4]POPESCU F, FAZLI S B, YAKOB B, et al. Single trial classification of motor imagination using 6 dry EEG electrodes[J]. PLoS ONE, 2007, 2: 1-5.

[5] ARVANEH M, GUAN C T, ANG K K, et al. Optimizing the channel selection and classification accuracy in eeg based BCI[J]. IEEE Transactions on Biomedical Engineering, 2022, 58: 1865-1873.

[6] JINDAL K, UPADHYAY R, SINGH H. A novel EEG channel selection and classification methodology for multi-class motor imagery-based BCI system design[J]. International Journal of Imaging Systems and Technology, 2022, 32: 1318-1337.

[7]郑赟,马玉良,孙明旭,等.一种疲劳驾驶检测中的脑电信号通道选择方法[J].中国生物医学工程学报, 2022, 41(4): 402-411. [ZHENG Y, MA Y L, SUN M X, et al. Method for selecting EEG signal channels in fatigue driving detection[J]. Chinese Journal of Biomedical Engineering, 2022, 41(4): 402-411.]

[8]许伦辉,罗强,吴建伟,等.基于最小安全距离的车辆跟驰模型研究[J]. 公路交通科技, 2010, 27(10): 95 100, 106. [XU L H, LUO Q, WU J W, et al. Research on vehicle following model based on minimum safe distance [J]. Highway Transportation Technology, 2010,27(10): 95-100, 106.]

[9] HU J, SHEN L, ALBANIE S, et al. Squeeze-and excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011- 2023.

[10] LAWHERN V J, SOLON A J, WAYTOWICH N, et al. EEGNet: A compact convolutional neural network for EEG-based brain-computer interfaces[J]. Journal of Neural Engineering, 2018, 15(5): 056013.1-056013.17.

[11] 杨巨成, 魏峰,林亮,等.驾驶员疲劳驾驶检测研究综述[J]. 山东大学学报(工学版), 2024, 54(2): 1-12. [YANG J C, WEI F, LIN L, et al. A review of research on driver fatigue driving detection[J]. Journal of Shandong University (Engineering Edition), 2024, 54(2): 1-12.]

[12] FARHANGI, F. Investigating the role of data preprocessing, hyperparameters tuning, and type of machine learning algorithm in the improvement of drowsy EEG signal modeling[J]. Intelligent Systems with Applications, 2022, 15: 200100.

[13] 李力.基于CNNs和LSTM的驾驶员疲劳和分心状态识别研究[D]. 长沙：南大学, 2018. [LI L. Research on driver fatigue and distraction state recognition based on CNNs and LSTM[D]. Changsha: Hunan University, 2018.]

[14] 张冰涛,常文文,李秀兰.基于时空脑电特征与并行神经网络的疲劳驾驶检测[J].交通运输系统工程与信息, 2023, 23(2): 315-325. [ZHANG B T, CHANG W W, LI X L. Fatigue driving detection based on spatial-temporal electroencephalogram features and parallel neural networks[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(2): 315-325.]

[15] YANG L, MA R, ZHANG H M, et al. Driving behavior recognition using EEG data from a simulated car following experiment[J]. Accident Analysis & Prevention. 2018, 116: 30-40.

[16] YAN F, LIU M, DING C, et al. Driving style recognition based on electroencephalography data from a simulated driving experiment[J]. Frontiers in Psychology, 2019, 10: 439121.

[17] 毛科俊, 刘小明,赵晓华,等.基于脑电信号的驾驶疲劳预报关键参数选取[J].北京工业大学学报,2010,36 (7): 966-970. [MAO K J, LIU X M, ZHAO X H, et al. The choice of driver fatigue prediction key parameters based on EEG recordings[J]. Journal of Beijing University of Technology, 2010, 36(7): 966-970.]

[18] HOUSHMAND S, KAZEMI R, SALMANZADEH H. A novel convolutional neural network method for subject independent driver drowsiness detection based on single channel data and EEG alpha spindles[J]. Proceedings of the Institution of Mechanical Engineers，Part H：Journal of Engineering in Medicine, 2021, 235(9): 1069-1078.

[19] ZHAO S, GUAN W, QI G, et al. Heterogeneous overtaking and learning styles with varied EEG patterns in a reinforced driving task[J]. Accident Analysis and Prevention, 2022, 171: 106665-106665.

基于脑电通道注意力机制的驾驶行为识别研究

Driving Behavior Recognition Based on EEG Channel Attention Mechanism

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李哲, 苟杨扬, 李震尧, 李敖, 岑威, 高建平. 车联网公交系统动态时空优先控制研究[J]. 交通运输系统工程与信息, 2024, 24(5): 56-64.
[2]	刘淼淼, 刘晓晨, 朱明月, 魏泽平, 邓辉, 姚民坤, 吴思霖, 李昂, 石赞, 龚筱萸. 基于动态轨迹规划的自动驾驶车辆协同换道方法[J]. 交通运输系统工程与信息, 2024, 24(5): 65-78.
[3]	胡正华, 周继彪, 毛新华, 张敏捷. 基于图像序列分析的城市道路交通事故预测[J]. 交通运输系统工程与信息, 2024, 24(5): 91-102.
[4]	刘东, 张大鹏, 万芸, 肖峰. 基于深度强化学习的单线路公交动态驻站控制策略研究[J]. 交通运输系统工程与信息, 2024, 24(5): 173-184.
[5]	刘美岐, 金楷然, 李雅澜, 郭戈. 城市道路智能网联车辆轨迹鲁棒控制方法[J]. 交通运输系统工程与信息, 2024, 24(4): 31-40.
[6]	温惠英, 张昕怡, 黄俊达, 许鹏鹏. 考虑动态交互作用的智能车辆轨迹预测[J]. 交通运输系统工程与信息, 2024, 24(4): 60-68.
[7]	马千里, 王通, 邵帅, 贾鹏. 路测环境下无人驾驶小巴复杂场景运行评价[J]. 交通运输系统工程与信息, 2024, 24(4): 300-310.
[8]	董红召, 杨嘉炜, 全程. 车联网下公交专用道复用的动态清空控制方法[J]. 交通运输系统工程与信息, 2024, 24(3): 12-20.
[9]	刘江, 张楚, 蔡伯根, 王剑, 陆德彪. 基于样本增强的列车卫星定位伪距欺骗检测方法[J]. 交通运输系统工程与信息, 2024, 24(3): 32-42.
[10]	李建市, 徐友春, 齐尧, 谢德胜, 李华. 起伏道路条件下无人车纵向速度控制方法研究[J]. 交通运输系统工程与信息, 2024, 24(3): 43-52.
[11]	张金雷, 杨健, 刘晓冰, 陈瑶, 杨立兴, 高自友. 基于计算机视觉的轨道交通站内火灾检测与定位[J]. 交通运输系统工程与信息, 2024, 24(3): 53-63.
[12]	陈喜群, 朱奕璋, 谢宁珂, 耿茂思, 吕朝锋. 基于异构多智能体自注意力网络的路网信号协调顺序优化方法[J]. 交通运输系统工程与信息, 2024, 24(3): 114-126.
[13]	辛琪, 王嘉琪, 杨文科, 徐猛, 袁伟. 信控路段混行交通生态驾驶深度强化学习模型[J]. 交通运输系统工程与信息, 2024, 24(3): 127-139.
[14]	倪浩原, 余贵珍, 李涵, 陈鹏, 刘喜, 王文达. 露天矿作业区无人矿车协同通行决策方法研究[J]. 交通运输系统工程与信息, 2024, 24(3): 277-289.
[15]	张磊, 彭金栓, 陈晓利. 接管场景驱动下非驾驶任务对驾驶人视觉与生理特征的影响[J]. 交通运输系统工程与信息, 2024, 24(3): 290-298.