摘要
通过船舶驾驶模拟实验,采集船舶驾驶人员脑电信号,对正常航行和突发事件处理两种场景下的100组脑电信号数据进行了预处理,提取特征指标,使用方差分析研究了特征指标与场景的相关性,借助SVM理论方法构建了基于脑电信号的船舶驾驶人员工作负荷识别模型,并对该模型进行了验证.结果表明:船舶驾驶人员在不同的航行场景的脑电信号有显著差异,提出的模型对船舶驾驶人员工作负荷识别的准确率达到92%.
Through the simulation experiment of ship driving, the EEG signals of ship drivers were collected, and 100 groups of EEG data in normal navigation and emergency treatment scenarios were preprocessed. After extracting feature indexes, the correlation between feature indexes and scenes was studied by variance analysis. With the help of SVM theory, the workload identification model of ship drivers based on EEG signals was constructed and verified. The results show that there are significant differences in EEG signals of ship drivers in different navigation scenarios, and the accuracy of the proposed model in identifying the workload of ship drivers reaches 92%.
作者
刘清
万志远
杨柳
何萌
陈俊华
杨锬
LIU Qing;WAN Zhiyuan;YANG Liu;HE Meng;CHEN Junhua;YANG Xian(School of Transportation and Logistics Engineering,Wuhan University of Technology,Wuhan 430063,China;National Water Transportation Safety Engineering Technical Research Center,Wuhan 430063,China)
出处
《武汉理工大学学报（交通科学与工程版）》
2022年第5期759-763,共5页
Journal of Wuhan University of Technology（Transportation Science & Engineering）
基金
国家自然科学基金(51979214)
国家自然科学基金青年科学基金(72001163)。
