2016 International Conference on Frontiers of Information Technology (FIT) (2016)
Dec. 19, 2016 to Dec. 21, 2016
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/FIT.2016.064
An exponential increase has been observed in number of mobile game players in last five years. An increasing number of researches have been emerged that assesses the cognitive aspects of video game players. This creates a need to classify the expert-novice level of a player. A novel approach to classify players expert-novice level is to use machine learning algorithm by considering recorded electroencephalography (EEG) signals of player while playing mobile games. In this research work, EEG signals of ten mobile game players is recorded by commercially available 14 channel EMOTIV headset. After preprocessing stage, a feature vector is created in such a way that from each channel, thirteen morphological features are extracted. The extracted features are used to train three different classification algorithms. The Naive Bayes performed with an accuracy of 89:89%. From results, it is evident that EEG can be used to classify the expert-novice level of a player using machine algorithms. These results can be useful in the development of new and interesting entertainment and educational mobile games taking into account the player's cognition using EEG.
Games, Electroencephalography, Land mobile radio, Classification algorithms, Support vector machines, Feature extraction, Machine learning algorithms,Brain Computer Interface, Mobile Game, EEG, Wearable Sensors, Machine Learning
Syed Muhammad Anwar, Sanay Muhammad Umar Saeed, Muhammad Majid, "Classification of Expert-Novice Level of Mobile Game Players Using Electroencephalography", 2016 International Conference on Frontiers of Information Technology (FIT), vol. 00, no. , pp. 315-318, 2016, doi:10.1109/FIT.2016.064