基于脑功能网络的虚拟现实晕动症检测OA

An effective detection scheme based on decoding electroencephalogram(EEG)signals under different sickness states can aid in the research of approaches to alleviate symptoms of Virtual Reality Motion Sickness(VRMS).This article uses Multivariate Variational Mode Decomposition(MVMD)to categorize EEG into five fre-quency bands and divides the data into different sickness groups based on motion sickness scale results.The Phase-Locking Value(PLV)method is used to calculate the functional connectivity within and between EEG frequency bands to construct super-adjacency matrices,and classification recognition is performed based on models such as Support Vector Machine(SVM)and Convolutional Neural Network(CNN).The research results show that,after the fusion of three topological features with significant differences including clustering coefficient,local efficiency,and weighted node degree,the highest average classification accuracies achieved in tasks of sickness vs.non-sick-ness,high sickness vs.low sickness are 91.70%and 96.00%,respectively.In addition,this article also directly in-puts the super-adjacency matrices into the CNN model,achieving average classification accuracies of 93.40%and 98.50%in the two tasks,respectively.These results indicate that the proposed method can be applied to the detec-tion of VRMS and provide reference for further research into the impact of motion sickness on functional coupling among various brain regions.