AUTHOR=Zhang Yue , Zhang Lulu , Hua Haoqiang , Jin Jianxiu , Zhu Lingqing , Shu Lin , Xu Xiangmin , Kuang Feng , Liu Yunhe 

TITLE=Relaxation Degree Analysis Using Frontal Electroencephalogram Under Virtual Reality Relaxation Scenes

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2021.719869

DOI=10.3389/fnins.2021.719869

ISSN=1662-453X

ABSTRACT=The increasing social pressure makes psychological burden of people much heavier, and the severity of depression could no longer be ignored. The characteristics of high immersion and interactivity make virtual reality applied more in the psychological therapy. Many studies have verified the effectiveness of VR relaxation therapy, few of which have done a quantitative study on relaxation state, though. In order to confirm the effectiveness of VR relaxation and make a quantitative study on relaxation, this paper confirmed the effectiveness of the VR sightseeing relaxation scenes by subjective emotion scale and objective EEG data from college students. And some EEG features with significant consistent differences after watching the VR scenes were found including energy ratio of alpha wave, gamma wave, DASM, and so on. R-state regression model was then built using model stacking method for optimization, of which RFR, Adaboost, GB and LGBM were adopted as the first level, LR and SVM were applied at the second level. Leave-one-subject-out method for cross validation was used to evaluate the results, where the mean accuracy of the framework achieved 81.46%. The significantly changed features and the R-State (relaxation state) Model with over 80% accuracy have laid a foundation for further research on relaxation interaction systems.