Classification of Human Vision Discrepancy during Watching 2D and 3D Movies Based on EEG Signals

• Published in: International journal of computer science and information security Vol. 15; no. 2; p. 430
• Main Authors: Manshouri, Negin, Maleki, Masoud, Kayikçioglu, Temel
• Format: Journal Article
• Language: English
• Published: Pittsburgh L J S Publishing 01.02.2017
• Subjects: 3-D films; Accuracy; Brain; Brain research; Classification; Classifiers; Deltas; Electroencephalography; Feature extraction; Human-computer interface; Methods; Noise; Pattern recognition systems; Radio communications; Support vector machines; Visual perception
• ISSN: 1947-5500

besides the important applications of Electroencephalogram (EEG) signals, like recognizing different mental diseases other aspects of EEG utilization such as biometrics, music, entertainment, etc., are striking nowadays. To make a good interface between human brains and the surrounding environment, brain-computer interface (BCI) has created a strange evolution in this field. In this paper, achieved EEG signals, during watching 2D and 3D movie has been investigated. A sample of nine healthy volunteers (age range 18-30) contributed in the experiments, these experiments consist of two parts: first, subjects watched 2D movie and then watched the same movie in 3D mode. After data acquisition, to predict states of brain, signals are sent to the feature extraction stage. Fast Fourier Transformation (FFT) is used to extract features and then classified by "Classification Learner App". Two kinds of Support Vector Machine (SVM) classifier, and fine kind of k nearest neighbors (kNN) were used as classifiers in this study. To understanding that which frequency bands are more effective in the EEG signals during watching 2D and 3D Movies, these combinations of EEG bands are used as the features: delta, theta, alfa, beta and gamma bands abbreviated as "all bands", delta, theta and alfa bands as "low frequency bands", theta, alfa and beta as "middle bands" and alfa, beta and gamma bands as "high frequency bands". Finally, in comparing the results, the classification accuracy of "all bands" in channel T5 for Quadratic SVM was attained as the highest.