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. watched videos containing a pure and 25th frame effect and recorded EEG signals from participants. 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.