Determination of the 25th Frame with the Eeg Signals Stored in the Videos

Abstract

Nowadays, the videos that appear in every part of our lives are a set of images resulting from the sequential addition of a series of image files. One second of the video is the result of the merging of 24 picture frames. The visual subliminal perceives 24 frames per second. It is difficult to see pictures hidden in the frames of videos and called the 25th frame effect. In this study, electroencephalogram (EEG) signals are analyzed and it is aimed to determine whether or not the 25th frame effect is perceived by the brain. In the study, 50 participants were shown 6 different videos. Participants watched videos containing a pure and 25th frame effect and recorded EEG signals. Statistical feature extraction algorithms were applied to EEG signals. In this study, k-nearest neighbor (knn) classifier and Naive Bayes(NB) classifier, are used Training was performed by applying the k-fold cross validation method. The knn classifiers achievement performance is as follows; accuracy %96.60, recall %98.00, F1 score %96.50 precision %95.29. The NB classifiers achievement performance is as follows; accuracy %92.00, recall %92.00, F1 score %92.20 precision %92.00. It is aimed to develop the study by using different classification methods and signal processing methods.