Detection of motor imagery EEG signals employing Naïve Bayes based learning process

• An optimum allocation based approach is proposed for detecting mental EEG signals.
• The mechanism considers variability of observations within a time-window.
• Naive Bayes learning based process is employed to classify the OA based features.
• The proposed approach outperforms the most recently reported five methods.
• This method achieves 0.64–20.90% improvement on overall accuracy.

The objective of this study is to develop a reliable and robust analysis system that can automatically detect motor imagery (MI) based electroencephalogram (EEG) signals for the development of brain–computer interface (BCI) systems. The detection of MI tasks provides an important basis for designing a communication way between brain and computer in creating devices for people with motor disabilities. This paper presents a synthesis approach based on optimum allocation system and Naive Bayes (NB) algorithm for detecting mental states based on EEG signals. In this study, an optimal allocation (OA) is introduced to discover the most effective representatives with minimal variability from a large number of MI based EEG data and the NB classifier is employed on the extracted features for discriminating the MI signals. The feasibility and effectiveness of the proposed method is demonstrated by analyzing the results and its success on two public benchmark datasets. The results indicate that the proposed approach outperforms the most recently reported five methods and achieves 0.64–20.90% improvement on average accuracy. The performances of this proposed approach implies that it can be reliably used to detect EEG based MI activity and can be a promising avenue for EEG based BCI applications.