基于脑电功率谱密度的作业人员脑力负荷评估方法

张洁; 庞丽萍; 完颜笑如; 陈浩; 王鑫; 梁晋

doi:10.7527/S1000-6893.2019.23618

航空学报 >

2020 , Vol. 41 >Issue 10: 123618 - 123618

DOI: https://doi.org/10.7527/S1000-6893.2019.23618

流体力学与飞行力学

基于脑电功率谱密度的作业人员脑力负荷评估方法

张洁 ,
庞丽萍 ,
完颜笑如 ,
陈浩 ,
王鑫 ,
梁晋

展开

1. 北京航空航天大学航空科学与工程学院, 北京 100083;
2. 中国船舶工业综合技术经济研究院船舶人因工程实验室, 北京 100081

收稿日期: 2019-10-31

修回日期: 2020-01-03

网络出版日期: 2020-01-02

基金资助

国家自然科学基金委员会与中国民用航空局联合资助项目（U1733118）；辽宁省"兴辽英才计划"（XLYC1802092）

收起

Method for operator mental workload assessment based on power spectral density of EEG

ZHANG Jie ,
PANG Liping ,
WANYAN Xiaoru ,
CHEN Hao ,
WANG Xin ,
LIANG Jin

Expand

1. School of Aeronautic Science and Engineering, Beihang University, Beijing 100083, China;
2. Marine Human Factors Engineering Lab, China Institute of Marine Technology & Economy, Beijing 100081, China

Received date: 2019-10-31

Revised date: 2020-01-03

Online published: 2020-01-02

Supported by

The Jointly Program of National Natural Science Foundation of China and Civil Aviation Administration of China (U1733118);The Liao Ning Revitalization Talents Program (XLYC1802092)

Fold

摘要

脑力负荷状态的准确识别对减少因作业人员无效脑力负荷导致的人因事故具有重要意义。针对人-机系统中作业人员脑力负荷客观评估问题开展了基于MATB-Ⅱ平台的3种不同脑力负荷水平下的航空情境实验，记录16名被试的NASA任务负荷指数（NASA-TLX）量表数据和脑电（EEG）信号，提出了一种基于脑电功率谱密度（PSD）和支持向量机（SVM）的个体脑力负荷评估方法。结果表明：随着实验设计脑力负荷水平增加，被试的主观脑力负荷得分显著提高（p<0.001），这表明该实验任务设计较好地诱发了低负荷、中负荷和高负荷情境。在此基础上，通过网格搜索法确定个体脑力负荷评估模型的统一优化参数，惩罚系数取3 000，核函数参数取0.000 1，模型测试正确率达到0.966 5±0.029 8，宏平均的受试者工作特征曲线下的面积（Macro-AUC）达到0.991 0±0.011 4。本文为作业人员脑力负荷状态的客观和准确评估提供了一种新的办法，为后期作业人员脑力负荷状态的实时判别提供模型基础。

关键词： 脑力负荷; NASA任务负荷指数; 功率谱密度; 支持向量机; 个体评估模型

本文引用格式

张洁 , 庞丽萍 , 完颜笑如 , 陈浩 , 王鑫 , 梁晋 . 基于脑电功率谱密度的作业人员脑力负荷评估方法[J]. 航空学报, 2020 , 41(10) : 123618 -123618 . DOI: 10.7527/S1000-6893.2019.23618

Abstract

The accurate recognition of mental workload levels is of great significance to reduce human accidents caused by operators with invalid mental workload. This paper focuses on the objective mental workload assessment of operators in human-machine system. An aviation situational experiment based on MATB-Ⅱ was carried out at three levels of mental workload. Sixteen subjects were asked to fill in the NASA-Task Load Index (NASA-TLX) scale and the Electroencephalogram (EEG) results during the experiment were recorded. By analyzing the collected subjective and physiological data, a subject-specified mental workload assessment method was proposed using the Power Spectral Density (PSD) of EEG and the Support Vector Machine (SVM). The results show that the subjective mental workload scores increase significantly (p<0.001) with the increase of designed mental workload levels, indicating that the experimental design successfully induces different mental workload scenarios. Based on the rationality of the experimental design, the subject-specified mental workload assessment models are established, and the parameters of these models are optimized by grid search and then unified as the penalty parameter of 3 000 and the kernel function parameter of 0.000 1. The test accuracy reaches 0.966 5±0.029 8, and the area under Macro-Averaging receiver operating Characteristic curve (Macro-AUC) reaches 0.991 0±0.011 4. Thus, the models provide a new approach for the objective and accurate assessment of mental workload, providing a basis for the real-time discrimination of mental workload.

Key words： mental workload; NASA-task load index; power spectral density; support vector machine; subject-specified discrimination model

参考文献

[1] WILSON G F, CALDWELL J A, WESENSTEN N J. Operator functional state assessment for adaptive automation implementation[J].Proceedings of SPIE-The International Society for Optical Engineering, 2005, 5797:100-104.
[2] 完颜笑如, 庄达民. 飞行员脑力负荷测量与应用[M]. 北京:科学出版社, 2014:15, 49-52. WANYAN X R, ZHUANG D M. Measurement and application of mental workload in pilots[M]. Beijing:Science Press, 2014:15, 49-52(in Chinese).
[3] RADUNTZ T. Dual frequency head maps:A new method for indexing mental workload continuously during execution of cognitive tasks[J].Frontiers in Physiology, 2017, 8:1019.
[4] 郭孜政, 潘雨帆, 潘毅润, 等. 驾驶员脑力负荷的SVM识别模型[J].哈尔滨工业大学学报, 2016, 48(3):154-158. GUO Z Z, PAN Y F, PAN Y R, et al. SVM recognition model of driver's mental workload[J].Journal of Harbin Institute of Technology, 2016, 48(3):154-158(in Chinese).
[5] AYAZ H, SHEWOKIS P A, BUNCE S, et al. Optical brain monitoring for operator training and mental workload assessment[J].NeuroImage, 2012, 59(1):36-47.
[6] WANYAN X R, ZHUANG D M, LIN Y, et al. Influence of mental workload on detecting information varieties revealed by mismatch negativity during flight simulation[J].International Journal of Industrial Ergonomics, 2018, 64:1-7.
[7] RYU K, MYUNG R, ERGON J. Evaluation of mental workload with a combined measure based on physiological indices during a dual task of tracking and mental arithmetic[J].International Journal of Industrial Ergonomics, 2005, 35(11):991-1009.
[8] 白杰, 冯传宴, 杨坤. 飞行员脑力负荷生理测量方法研究进展[J].航天医学与医学工程, 2016, 29(2):150-156. BAI J, FENG C Y, YANG K. Research progress of physiological measurement of mental workload in pilots[J].Space Medicine & Medical Engineering, 2016, 29(2):150-156(in Chinese).
[9] 明东, 柯余峰, 何峰, 等. 基于生理信号的脑力负荷检测及自适应自动化系统研究:40年回顾与最新进展[J].电子测量与仪器学报, 2015, 29(1):1-13. MING D, KE Y F, HE F, et al. Psychophysiological measurement based studies on mental workload assessment and adaptive automation:Review of the last 40 years and the latest developments[J].Journal of Electronic Measurement and Instrumentation, 2015, 29(1):1-13(in Chinese).
[10] STEVEN L, BENJAMIN B, THORSTEN D, et al. Introduction to machine learning for brain imaging[J].NeuroImage, 2011, 56(2):387-399.
[11] GARRETT L D, ANDERSON B W, THAUT M H, et al. Comparison of linear, nonlinear, and feature selection methods for EEG signal classification[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013, 11(2):141-144.
[12] SUN Z, QIAO Y, LELIEVELDT B P F, et al. Integrating spatial-anatomical regularization and structure sparsity into SVM:Improving interpretation of Alzheimer's disease classification[J].NeuroImage, 2018, 178:445-460.
[13] SWIDERSKI B, OSOWSKI S, CICHOCKI A, et al. Single-class SVM and directed transfer function approach to the localization of the region containing epileptic focus[J].Neurocomputing, 2009, 72(7-9):1575-1583.
[14] BARJINDER K, DINESH S, PARTHA P R. EEG based emotion classification mechanism in BCI[J].Procedia Computer Science, 2018, 132:752-758.
[15] MIRANDA P B C, PRUDENCIO R B C, CARVALHO A P L F D, et al. A hybrid meta-learning architecture for multi-objective optimization of SVM parameters[J].Neurocomputing, 2014, 143:27-43.
[16] 冯传宴, 完颜笑如, 刘双, 等. 负荷条件下注意力分配策略对情境意识的影响[J].航空学报, 2019, 41(3):123307. FENG C Y, WANYAN X R, LIU S, et al. Influence of different attention allocation strategies under workloads on situation awareness[J].Acta Aeronautica et Astronautica Sinica, 2020, 41(3):123307(in Chinese).
[17] WILSON G F, RUSSELL C A. Operator functional state classification using multiple psychophysiological features in an air traffic control task[J].Human Factors:The Journal of the Human Factors and Ergonomics Society, 2003, 45(3):381-389.
[18] 赵仑. ERPs实验教程[M]. 南京:东南大学出版社, 2010:137-140. ZHAO L. ERPs experimental tutorial[M]. Nanjing:Southeast University Press, 2010:137-140(in Chinese).
[19] 范晓丽, 牛海燕, 周前祥, 等. 基于EEG的脑力疲劳特征研究[J].北京航空航天大学学报, 2016, 42(7):1406-1413. FAN X L, NIU H Y, ZHOU Q X, et al. Mental fatigue characteristics based on EEG analysis[J].Journal of Beijing University of Aeronautics and Astronautics, 2016, 42(7):1406-1413(in Chinese).
[20] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016:33-35, 121-129. ZHOU Z H. Machine learning[M]. Beijing:Tsinghua University Press, 2016:33-35, 121-129(in Chinese).
[21] BURGES C J C. A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery, 1998, 2(2):121-167.
[22] 奉国和. SVM分类核函数及参数选择比较[J].计算机工程与应用, 2011, 47(3):123-124. FENG G H. Parameter optimizing for support vector machines classification[J].Computer Engineering and Application, 2011, 47(3):123-124(in Chinese).
[23] BRAGA I, DO CARMO L P, BENATTI C C, et al. A note on parameter selection for support vector machines[C]//Mexican International Conference on Artificial Intelligence-Advances in Soft Computing and Its Applications. Berlin:Springer, 2013:233-244.
[24] 李颖洁, 邱意弘, 朱贻盛. 脑电信号分析方法与应用[M]. 北京:科学出版社, 2009:13-14. LI Y J, QIU Y H, ZHU Y S. Analysis method and application of EEG signal[M]. Beijing:Science Press, 2009:13-14(in Chinese).
[25] WILSON G F, RUSSELL C A. Real-time assessment of mental workload using psychophysiological measures and artificial neural networks[J].Human Factors:The Journal of the Human Factors and Ergonomics Society, 2003, 45(4):635-643.
[26] WILSON G F, RUSSELL C A. Operator functional state classification using multiple psychophysiological features in an air traffic control task[J].Human Factors:The Journal of the Human Factors and Ergonomics Society, 2003, 45(3):381-389.
[27] LIU N H, CHIANG C Y, CHU H C. Recognizing the degree of human attention using EEG signals from mobile sensors[J].Sensors, 2013, 13(8):10273-10286.
[28] YOUNGWORTH R N, GALLAGHER B B, STAMPER B L. An overview of power spectral density (PSD) calculations[C]//Proceeding of SPIE-The International Society for Optical Engineering. Bellingham:Society of Photo-optical Instrumentation Engineers, 2005:206-216.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献