Human Stress Recognition by Correlating Vision and EEG Data

作     者：S.Praveenkumar T.Karthick 

作者机构：SRM Institute of Science and TechnologyDepartment of Data Science and Business SystemsSchool of ComputingKattankulathur603203TamilnaduIndia 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2023年第45卷第6期

页      面：2417-2433页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors sincerely thank the colleagues who participated in the work in the authors' laboratory. Martin Katz provided advice on the manuscript  and helped guide it to its final form. We also thank Lynette Feeney-Burns  K.C. Hayes  Melanie Mayer  Wemer Noell  W. Gerald Robison  and Richard Young for constructive comments on the manuscript. Work in the authors' laboratory was supported by Hoffman-La Roche  the Children's Brain Disease Foundation  and the U.S. Public Health Service (EY-01521) 

主　　题：Mental stress physiological data XGBoost feature fusion DEAP video data EEG CNN HAR 

摘      要：Because stress has such a powerful impact on human health,we must be able to identify it automatically in our everyday *** human activity recognition(HAR)system use data from several kinds of sensors to try to recognize and evaluate human actions automatically recognize and evaluate human *** the multimodal dataset DEAP(Database for Emotion Analysis using Physiological Signals),this paper presents deep learning(DL)technique for effectively detecting human *** combination of vision-based and sensor-based approaches for recognizing human stress will help us achieve the increased efficiency of current stress recognition systems and predict probable actions in advance of when *** on visual and EEG(Electroencephalogram)data,this research aims to enhance the performance and extract the dominating characteristics of stress *** the stress identification test,we utilized the DEAP dataset,which included video and EEG *** also demonstrate that combining video and EEG characteristics may increase overall performance,with the suggested stochastic features providing the most accurate *** the first step,CNN(Convolutional Neural Network)extracts feature vectors from video frames and EEG *** Level(FL)fusion that combines the features extracted from video and EEG *** use XGBoost as our classifier model to predict stress,and we put it into *** stress recognition accuracy of the proposed method is compared to existing methods of Decision Tree(DT),Random Forest(RF),AdaBoost,Linear Discriminant Analysis(LDA),and KNearest Neighborhood(KNN).When we compared our technique to existing state-of-the-art approaches,we found that the suggested DL methodology combining multimodal and heterogeneous inputs may improve stress identification.