EEG-based BCI: A novel improvement for EEG signals classification based on real-time preprocessing

• Published in: Computers in biology and medicine Vol. 148; p. 105931
• Main Authors: Abenna, Said, Nahid, Mohammed, Bouyghf, Hamid, Ouacha, Brahim
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.09.2022; Elsevier Limited
• Subjects: Accuracy; Algorithms; Bandpass filters; Brain–computer interface (BCI); Channels; Classification; Data acquisition; EEG; Electroencephalogram (EEG); Electroencephalography; Feature extraction; Feature selection; Internal Medicine; Machine learning; Optimization; Other; Prediction models; Preprocessing; Real time; Signal classification; Signal processing; Signal quality; Trigonometric functions; Feature selection; Machine learning; Signal processing; Feature extraction; Electroencephalogram (EEG); Optimization; Brain–computer interface (BCI); Brain-computer interface (BCI)
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105931

This work aims to improve EEG signal binary and multiclass classification for real-time BCI applications. Therefore, our paper discusses the results of a new real-time approach that was integrated into a complete prediction system, where we proposed a new trick to eliminate the effect of EEG’s non-stationarity nature. This improvement can increase the accuracy from 50% using raw EEG to the order of 90% after preprocessing step in the binary case and from 28% to 78% in the multiclass case. Then, we chose to filter all signals by the proposed bandpass filter automatically optimized using the sine cosine algorithm (SCA) to find the optimal bandwidth that contains the entire EEG characteristics in beta waves. Moreover, we used a common spatial pattern (CSP) filter to eliminate the correlation between all extracted features. Then, the light gradient boosting machine (LGBM) classifier is also combined with SCA algorithm to build better prediction models. As a result, the outcome system was applied on UCI and PhysioNet datasets to get excellent accuracy values of higher than 99% and 95%, respectively, using the data acquired only from three channels. On the other hand, the related works used all the data acquired from 14 channels to find an accuracy value between 70% and 98.5%, which shows the robustness of our method to improve EEG signal prediction quality. [Display omitted] •Removing the EEG’s non-stationary nature for every subject.•Auto-detection of important frequency bandwidths for EEG during each classification.•Auto-selecting important features for various subjects to study the system stability.•The use of different test-validation to show the stability of results.