VR motion sickness recognition by using EEG rhythm energy ratio based on wavelet packet transform

• Published in: Computer methods and programs in biomedicine Vol. 188; p. 105266
• Main Authors: Li, Xiaolu, Zhu, Changrong, Xu, Cangsu, Zhu, Junjiang, Li, Yuntang, Wu, Shanqiang
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.05.2020
• Subjects: Algorithms; Diagnosis, Computer-Assisted; Electroencephalogram (EEG); Electroencephalography; Humans; k-Nearest neighbor classifier (k-NN); Models, Statistical; Motion Sickness - diagnosis; Motion Sickness - physiopathology; Reproducibility of Results; Rhythm energy ratio; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Support Vector Machine; Support vector machine (SVM); Virtual Reality; VR motion sickness (VRMS); Wavelet Analysis; Wavelet packet transform (WPT); VR motion sickness (VRMS); Rhythm energy ratio; Support vector machine (SVM); Electroencephalogram (EEG); k-Nearest neighbor classifier (k-NN); Wavelet packet transform (WPT)
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2019.105266

•A feature extraction method based on wavelet packet transform for EEG rhythm energy ratios of delta, theta, alpha and beta is proposed.•The VR motion sickness is recognized by combining with k-NN, polynomial-SVM and RBF-SVM, respectively.•The average VRMS recognition accuracy for single subject reaches 92.85%, and the VRMS recognition accuracy to 18 subjects is also up to 79.25%.•The results are compared with those of other methods, and the limitations of this study are also pointed out. Virtual reality motion sickness (VRMS) is one of the main factors hindering the development of VR technology. At present, the VRMS recognition methods using electroencephalogram (EEG) signals have poor applicability to multiple subjects. Aiming at this dilemma, the wavelet packet transform (WPT), was used to propose a feature extraction method for EEG rhythm energy ratios of delta (δ), theta (θ), alpha (α), and beta (β) in this research. Moreover, VRMS was recognized by combining k-Nearest Neighbor classifier (k-NN), support vector machine (SVM) with polynomial kernel (polynomial-SVM) and radial basis function kernel (RBF-SVM), respectively. The method is that the raw EEG signals were de-noised by an elliptical band-pass filter and segmented by a fixed window, 7-level db4 WPT was performed on each EEG segment, and the wavelet packet energy ratios of delta, theta, alpha and beta rhythms from FP1, FP2, C3, C4, P3, P4, O1 and O2 channels were calculated and combined to form feature vectors for recognizing VRMS. Under the condition of 4-s window size, the average VRMS recognition accuracy of polynomial-SVM for the single subject was 92.85%, and the VRMS recognition accuracy of 18 subjects was about 79.25%. Compared with other VRMS recognition methods, this method does not only have a higher recognition accuracy to a single subject, but also have better applicability to multiple subjects. Meanwhile, when using the EEG four rhythm energy ratios of FP1, FP2, C3, C4, P3, P4, O1 and O2 channels as feature vectors, the polynomial-SVM achieved better VRMS recognition performance than the k-NN and RBF-SVM.