基于功能性脑网络和图卷积网络的驾驶疲劳检测

打开文本图片集

Driver fatigue detection based on functional brain networks and graph convolutional networks

XU Junli

（JiangxiUniversityofTechnology，InnovationCenter，Nanchang3oo98，China）

Abstract：Toaddress the issue of ambiguous threshold criteria inconstructing functional brain networks（FBN） forfatiguedetection，thispaper proposed tosetafixed thresholdand employing graph convolutional networks （GCN）tooptimize the learning of brain network graph features.Athresholdof O.5 was setfor building the FBN， and the degree and clustering coeficientfeatures ofthe network were extracted.These features were then input into the GCN，which learned and optimized the graph features for detection classification.Theresults show that the preposed model's detectionaccuracy has reached 88.90% .Furthermore，degree centrality identifies 14 significant electrodes within thebrain network.Among them，the GCN modelbuilton7key electrodesachieves an 87.2% detection accuracy，with faster detection speed and superior overall performance compared to the detectionmodel based on 30 leads.

Keywords：graph convolutional networks （GCN）；functional brain networks （FBN）；simplified channels；driver fatigue

目前疲劳驾驶已经成为引发交通事故的重要原因，研究者已经采用了很多方法来检测驾驶员的疲劳，其中脑电信号是疲劳检测中常用的疲劳特征。（剩余11768字）