Optimal Time Window Selection in the Wavelet Signal Domain for Brain–Computer Interfaces in Wheelchair Steering Control

Background and objective: Principally, the procedure of pattern recognition in terms of segmentation plays a significant role in a BCI-based wheelchair control system for avoiding recognition errors, which can lead to the initiation of the wrong command that will put the user in unsafe situations. Arguably, each subject might have different motor-imagery signal powers at different times in the trial because he or she could start (or end) performing the motor-imagery task at slightly different time intervals due to differences in the complexities his or her brain. Therefore, the primary goal of this research is to develop a generic pattern recognition model (GPRM)-based EEG-MI brain-computer interface for wheelchair steering control. Additionally, having a simplified and well generalized pattern recognition model is essential for EEG-MI based BCI applications. Methods: Initially, bandpass filtering and segmentation using multiple time windows were used for denoising the EEG-MI signal and finding the best duration that contains the MI feature components. Then, feature extraction was performed using five statistical features, namely the minimum, maximum, mean, median, and standard deviation, were used for extracting the MI feature components from the wavelet coefficient. Then, seven machine learning methods were adopted and evaluated to find the best classifiers. Results: The results of the study showed that, the best durations in the time-frequency domain were in the range of (4-7 s). Interestingly, the GPRM model based on the LR classifier was highly accurate, and achieved an impressive classification accuracy of 85.7%.