چاپ صفحه |  صفحه نخست سامانه |  نویسندگان |  اطلاعات تفضیلی |  دانلود مقاله | دانشگاه علوم پزشکی تبریز |
| نویسنده | نفر چندم مقاله |
|---|---|
| امین بشارت | اول |
| ناصر صمدزاده اقدم | دوم |
| عنوان | متن |
|---|---|
| خلاصه مقاله | Background and aims: Following spinal cord damage from trauma or disease, there is a great need for a method that can substitute for voluntary control in order to regain self-mobility, environmental control, and computer access. One of the potential solutions is brain-computer interface (BCI) that records brain activity in the form of electroencephalography (EEG) signals and extracts the movement intention or imagination by artificial intelligence methods and finally provides the possibility of communicating with the surrounding. High density EEG acquisition systems include many recording electrodes. However, selecting the optimum EEG channels and the appropriate classifier is crucial for accurate detection of the intended movement in BCI systems. Method: In the current paper, we used the motor imagery EEG dataset 1 provided by BCI competition IV. It consisted of EEG signals recorded from seven subjects. The subjects had to imagine the movements of the left (class 1) and right (class 2) hands during a cue-based BCI experiment. This dataset includes 200 trials for each subject. In the preprocessing step, first, EEG signals are band-pass filtered in the frequency range of 8-30 Hz using a 3rd order Butterworth filter. Then, a low Laplacian filter is applied for source localization. To select the optimal channels containing the most useful information of the imagined movement, the wrapper-based method called sequential forward feature selection (SFFS) is used. After applying the regularized common spatio-spectral pattern (RCSSP) filter for better separability of the features, the variance of the channels and their logarithm are extracted as time domain features. Finally, the support vector machine (SVM) and weighted extreme learning machine (WELM) were used for the classification of the performed motor imagery tasks. Results: The K-fold cross validation (K = 15) was used to evaluate the performance of the proposed method. The quantitative criteria include accuracy, precision, and recall. The average (±standard deviation) classification accuracy, precision, and recall obtained for all subjects by SVM classifier were approximately 84.20±9.28%, 87.17.76±9.37%, and 81.50±9%, respectively. On the other hand, using the WELM classifier, the average accuracy, precision, and recall were equal to 83.80±8.40%, 84.81±8.52%, and 83.17±7.27%, respectively. Therefore, based on the precision criterion, the SVM classifier applied to the EEG channels selected by the SFFS method has approximately three percent higher precision compared to WELM. Compared to one of the recent papers in the field of motor imagery classification (Mohammad Norizadeh Cherloo, 2021), our purposed method has approximately two percent more accuracy value. Conclusion: In this paper, we classified two motor imagery tasks by two classifiers using EEG signals. Although different studies have been conducted to classify motor imagery tasks, our results show that the proposed method outperforms the previous studies. |
| کلمات کلیدی | Brain-Computer Interfaces; motor imagery; Common spatial patterns; Channel selection; support vector machines |
| نام فایل | تاریخ درج فایل | اندازه فایل | دانلود |
|---|---|---|---|
| certificate.pdf | 1402/06/14 | 101559 | دانلود |
| ketabche.pdf | 1402/05/08 | 3260939 | دانلود |
| AIMS_nssr.docx | 1402/05/08 | 159398 | دانلود |
