[1]张奇良,杨坤华,曲行达,等.基于多模态生理信号的驾驶人脑力负荷评估[J].深圳大学学报理工版,2022,39(3):278-286.[doi:10.3724/SP.J.1249.2022.03278]
 ZHANG Qiliang,YANG Kunhua,QU Xingda,et al.Evaluation of drivers’ mental workload based on multi-modal physiological signals[J].Journal of Shenzhen University Science and Engineering,2022,39(3):278-286.[doi:10.3724/SP.J.1249.2022.03278]
点击复制

基于多模态生理信号的驾驶人脑力负荷评估()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第39卷
期数:
2022年第3期
页码:
278-286
栏目:
交通物流
出版日期:
2022-05-16

文章信息/Info

Title:
Evaluation of drivers’ mental workload based on multi-modal physiological signals
文章编号:
202203006
作者:
张奇良杨坤华曲行达陶达
深圳大学人因工程研究所,广东深圳 518060
Author(s):
ZHANG Qiliang YANG Kunhua QU Xingda and TAO Da
Institute of Human Factors and Ergonomics, Shenzhen University, Shenzhen 518060, Guangdong Province, P. R. China
关键词:
交通信息工程及控制脑力负荷机器学习多模态脑电信号心电信号皮电信号
Keywords:
traffic information engineering and control mental workload machine learning multi-modal electroencephalogram electrocardiogram electrodermal activity
分类号:
U491;TN911.72
DOI:
10.3724/SP.J.1249.2022.03278
文献标志码:
A
摘要:
准确评估驾驶人脑力负荷状态对降低因驾驶人脑力负荷过载导致的交通事故具有重要意义.基于典型驾驶场景,结合N-back认知负荷次任务,设计不同难度的驾驶任务实验,以研究驾驶人脑力负荷.实验收集驾驶人在任务完成过程中的多种模态生理信号(包括脑电、心电和皮电信号)及美国航空航天局任务负荷指数量表主观脑力负荷数据,提出基于多模态生理信号特征分析和模式识别的驾驶人脑力负荷分类模型,并比较了不同模态生理信号及其组合在三种典型机器学习算法(随机森林、决策树和K最近邻模型)中的脑力负荷分类识别效果.研究表明,基于不同模态生理信号组合的脑力负荷分类模型具有不同的分类准确率.单一模态生理信号的分类模型中,基于皮电、心电和脑电信号的分类模型准确率依次增加.基于多模态生理信号的分类模型准确率普遍优于单一模态分类模型.基于脑电、心电及皮电三模态生理信号的随机森林分类模型具有最高的分类准确率.
Abstract:
It is of great significance to accurately assess drivers’ mental workload in order to reduce traffic accidents induced by mental overload. This study aims to evaluate drivers’ mental workload in simulated typical driving scenarios, with N-back memory tasks used to manipulate varied levels of task difficulty. We collect data on multi-modal physiological signals (including electroencephalogram, electrocardiogram, and electrodermal signals) and National Aeronautics and Space Administration task load index (NASA_TLX) subjective mental workload scores in the experiment, and propose a series of mental workload classification models based on feature analysis and pattern recognition of the multi-modal physiological signals. These classification models are verified by machine learning algorithms of random forest, decision tree and K-nearest neighbor models. The results show that the accuracy of classification models varies with different modalities of physiological signals. EEG-based classification models yield the highest accuracy among single-modal classification models, followed by EDA- and ECG-based models. Multi-modal-based classification models generally perform better than single-modal classification models. The three-modal-based classification model based on EEG, ECG and EDA signals has the highest classification accuracy with random forest classification algorithm.
更新日期/Last Update: 2022-05-30