Time-frequency optimization for discrimination between imagination of right and left hand movements based on two bipolar electroencephalography channels

Abstract

To enforce a widespread use of efficient and easy to use brain-computer interfaces (BCIs), the inter-subject robustness should be increased and the number of electrodes should be reduced. These two key issues are addressed in this contribution, proposing a novel method to identify subject-specific time-frequency characteristics with a minimal number of electrodes. In this method, two alternative criteria, time-frequency discrimination factor (TFDF) and F score, are proposed to evaluate the discriminative power of time-frequency regions. Distinct from classical measures (e.g., Fisher criterion, r 2 coefficient), the TFDF is based on the neurophysiologic phenomena, on which the motor imagery BCI paradigm relies, rather than only from statistics. F score is based on the popular Fisher's discriminant and purely data driven; however, it differs from traditional measures since it provides a simple and effective measure for quantifying the discriminative power of a multi-dimensional feature vector. The proposed method is tested on BCI competition IV datasets IIa and IIb for discriminating right and left hand motor imagery. Compared to state-of-the-art methods, our method based on both criteria led to comparable or even better classification results, while using fewer electrodes (i.e., only two bipolar channels, C3 and C4). This work indicates that time-frequency optimization can not only improve the classification performance but also contribute to reducing the number of electrodes required in motor imagery BCIs.

Subject-specific time-frequency selection for multi-class motor imagery-based BCIs using few Laplacian EEG channels

“…For each Laplacian channel, 5th order Butterworth filters were employed to obtain 15 tic and a steep boundary. Shown in previous studies [29,[48][49][50], the 5th order Butterworth filters work well with different feature extraction methods for various frequency bands including the frequency bands we used in this study.…”

“…Instead of using machine learning techniques to select the optimal subset of channels, we simply used a few EEG channels located around the sensorimotor cortex. By selecting optimal time-frequency areas to extract subject-specific band power (BP) features, our preliminary study yielded better classification performances using fewer channels than the state-of-art methods in decoding hand MI [29,30]. Similar strategies have also been used in some other recent studies.…”

“…Additionally, the delay between the cue onset and the starting of motor imagery varies with individuals [21]. Previous studies have demonstrated that estimating optimal time-frequency areas for each individual can greatly improve the classification performance [52,29]. Due to the volume conduction effect, spatial filtering is also needed to reduce the correlation of EEG signals and eliminate the artefacts [18].…”

“…To address this challenge, we have proposed an alternative solution to increase inter-subject robustness of MI-based BCI using few EEG channels [29,30]. Instead of using machine learning techniques to select the optimal subset of channels, we simply used a few EEG channels located around the sensorimotor cortex.…”

Information Theoretic Approaches for Motor-Imagery BCI Systems: Review and Experimental Comparison

“…An extension to the multiclass problem can be found in [67]. Since the optimal frequency bands can vary from subject to subject, several alternative approaches have been proposed that combine the time-frequency characteristics of the EEG data [68,69] for improving the classification accuracy and reducing the number of electrodes [70]. …”