Color Histogram Features for the Classification of Brain Signals using 2D and 3D Educational Content

In this paper, a novel classification method has been proposed for brain signals by extracting features using RGB color histogram to classify images (topomaps) created from the electroencephalogram (EEG) signals. The signals are recorded during the answering of 2D and 3D questions. The system is used to classify the correct and incorrect answers for both 2D and 3D questions. Using the classification, we compared the impact of 3D and 2D educational contents on recall, learning and memory retention. Same 3D and 2D contents are presented to subjects for learning purpose. After learning, twenty multiple-choice questions (MCQs) are asked from the subjects related to the learned contents after two stages: two months (Long-Term Memory (LTM)) and 30 minutes (Short-Term Memory (STM)). Next, discriminative features from color histogram are extracted from topomap images. Support Vector Machine (SVM) is used as a classifier to predict brain states related to incorrect / correct answers. Results show the superiority of the proposed system.