Title: Motor Imaginary Task Classification using Statistically Significant Time Domain and Frequency Domain EEG features

Abstract: Motor Imaginary (MI) electroencephalography (EEG) signals are obtained when a subject imagines a task without essentially applying it. The accurate decoding of MI EEG signals plays an important role in the design of brain-computer interface (BCI) systems due to the use of these signals in the rehabilitation process of paralyzed patients in recent studies. In this study, two different MI tasks were tried to be differentiated by extracting time-domain and frequency-domain features from 22 channel EEG signals and determining best combination of important and distinctive features based on statistical significance. MI EEG signals were supplied from BCI Competition IV Dataset-IIa. These features were differentiated using 25 different classification algorithms and 5-fold cross-validation method. The repeatability of the results was examined testing each algorithm 10 times. As a result, the highest average accuracy rate of 60.69% was calculated in the Quadratic Support Vector Machine (SVM) using all features and 62.52% in the Ensemble Subspace Discriminant (ESD) algorithm using only the selected features by the independent t-test. The results showed that the independent t-test based feature selection increased the performance in 20 classifiers, and decreased the performance in 5 classifiers. Also, the effectiveness of the feature selection method examined using the paired-sample t-test which is known as repeated measures t-test. The significance value, p-value was found as 0.04. Therefore, the independent t-test based feature selection method is an effective feature selection method and is providing the significant improvement in classifier performance.

Keywords: EEG signals; Feature selection; Frequency-domain features; Motor imaginary task classification; Time-domain features

Başlık: İstatistiksel olarak Anlamlı EEG Zaman Alanı ve Frekans Alanı Öznitelikleri ile Motor Hayali Görev Sınıflandırılması

Özet: Motor Hayali (MH) elektroensefalografi (EEG) sinyalleri, bir özne, aslında uygulamadan bir görevi hayal ettiğinde elde edilir. Son yıllarda yapılan çalışmalarda bu sinyallerin felçli hastaların rehabilitasyon sürecinde kullanılmasından dolayı MH EEG sinyallerinin doğru olarak çözülmesi beyin-bilgisayar arayüzü (BBA) sistemlerinin tasarımında önemli bir rol oynamaktadır. Bu çalışmada, 22 kanallı EEG sinyallerinden zaman alanı ve frekans alanı öznitelikleri çıkarılarak ve istatistiksel anlamlılığa dayalı olarak önemli ve ayırt edici özelliklerin en iyi kombinasyonu belirlenerek iki farklı MI görevi ayırt edilmeye çalışılmıştır. MI EEG sinyalleri, BCI Competition IV Dataset-IIa'dan sağlandı. Bu öznitelikler, 25 farklı sınıflandırma algoritması ve 5-kat çapraz doğrulama yöntemi kullanılarak ayrıştırılmıştır. Sonuçların tekrarlanabilirliği, her bir algoritma 10 defa test edilerek incelenmiştir. Sonuç olarak, en yüksek ortalama doğruluk oranı tüm öznitelikler kullanılarak Kuadratik Destek Vektör Makinesinde (DVM) 60,69% ve sadece bağımsız t-testi ile seçilen öznitelikler kullanılarak Topluluk Altuzay Ayırım (TAA) algoritmasında 62,52% olarak hesaplanmıştır. Sonuçlar, bağımsız t-testine dayalı öznitelik seçiminin 20 sınıflandırıcıda performansı artırdığını, 5 sınıflandırıcıda ise performansı azalttığını göstermiştir. Ayrıca, yinelenen ölçümler t-testi olarak bilinen bağımlı örneklem t-testi kullanılarak öznitelik seçme yönteminin etkinliği incelenmiştir. Anlamlılık değeri olan p-değeri 0.04 olarak bulunmuştur. Bu nedenle, bağımsız t-testine dayalı öznitelik seçim yöntemi, etkili bir öznitelik seçme yöntemidir ve sınıflandırıcı performansında önemli iyileştirmeler sağlamaktadır.

Anahtar kelimeler: EEG sinyalleri; Öznitelik seçimi; Frekans alanı öznitelikleri; Motor hayali görev sınıflandırma; Zaman alanı öznitelikleri

• Musallam YK, AlFassam NI, Muhammad G, Amin SU, Alsulaiman M, Abdul W, Altaheri H, Bencherif MA, Algabri M. Electroencephalography-based motor imagery classification using temporal convolutional network fusion. Biomedical Signal Processing and Control 2021; 69: 102826.
• Panicker RC, Puthusserypady S, Sun Y. An asynchronous p300 bci with ssvep-based control state detection. IEEE Trans Biomed Eng 2011; 58(6): 1781–1788.
• Degirmenci M, Sayilgan E, Isler Y. Evaluation of wigner-ville distribution features to estimate steady-state visual evoked potentials' stimulation frequency. Journal of Intelligent Systems with Applications 2021; 4(2): 133-136.
• Pawar D, Dhage S. Feature Extraction Methods for Electroencephalography based Brain-Computer Interface: A Review. International Journal of Computer Science (IAENG) 2020; 47(3).
• Djamal EC, Abdullah MY, Renaldi F. Brain computer interface game controlling using fast fourier transform and learning vector quantization. Journal of Telecommunication, Electronic and Computer Engineering (JTEC) 2017; 9(2-5): 71-74.
• Xu B, Zhang L, Song A, Wu C, Li W, Zhang D, Xu G, Li H, Zeng H. Wavelet transform time-frequency image and convolutional network-based motor imagery EEG classification. IEEE Access 2018; 7: 6084-6093.
• Luo J, Gao X, Zhu X, Wang B, Lu N, Wang J. Motor imagery EEG classification based on ensemble support vector learning. Computer Methods and Programs in Biomedicine 2020; 193: 105464.
• Wang J, Feng Z, Lu N, Sun L, Luo J. An information fusion scheme based common spatial pattern method for classification of motor imagery tasks. Biomedical Signal Processing and Control 2018; 46: 10-17.
• Ang KK, Chin ZY, Wang C, Guan C, Zhang H. Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Frontiers in Neuroscience 2012; 6: 39.
• Luo J, Feng Z, Zhang J, Lu N. Dynamic frequency feature selection based approach for classification of motor imageries. Computers in Biology and Medicine 2016; 75: 45-53.
• Isler Y. A Detailed Analysis of the Effects of Various Combinations of Heart Rate Variability Indices in Congestive Heart Failure, PhD Thesis, Dokuz Eylul University, 2009.
• Narin A, Isler Y, Ozer M. Investigating the performance improvement of HRV Indices in CHF using feature selection methods based on backward elimination and statistical significance. Computers in Biology and Medicine 2014; 45: 72-79.
• Mousa MA, El-Khoribi RA, Shoman ME. A novel brain computer interface based on principle component analysis. Procedia Computer Science 2016; 82: 49-56.
• Selek MB, Yesilkaya B, Egeli SS, Isler Y. The effect of principal component analysis in the diagnosis of congestive heart failure via heart rate variability analysis. Proceedings of the IMechE Part H: Journal of Engineering in Medicine 2021; 235(12): 1479-1488.
• Gaur P, Pachori RB, Wang H, Prasad G. A multi-class EEG-based BCI classification using multivariate empirical mode decomposition based filtering and Riemannian geometry. Expert Systems with Applications 2018; 95: 201-211.
• Dong E, Li C, Li L, Du S, Belkacem AN, Chen C. Classification of multi-class motor imagery with a novel hierarchical SVM algorithm for brain–computer interfaces. Medical & Biological Engineering & Computing 2017; 55(10): 1809-1818.
• Kato M, Kanoga S, Hoshino T, Fukami T. Motor imagery classification of finger motions using multiclass CSP. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), July 20-24, 2020, Montreal, QC, Canada, pp. 2991-2994.
• Brunner C, Leeb R, Muller-Putz G, Schlogl A, Pfurtscheller G. BCI Competition 2008–Graz data set A. Institute for Knowledge Discovery (Laboratory of Brain-Computer Interfaces), Graz University of Technology 2008; 16: 1-6.
• Sayilgan E, Yuce YK, Isler Y. Frequency recognition from temporal and frequency depth of the brain-computer interface based on steady-state visual evoked potentials. Journal of Intelligent Systems with Applications 2021; 4(1): 68-73.
• Sayilgan E, Yuce YK, Isler Y. Evaluation of mother wavelets on steady-state visually-evoked potentials for triple-command brain-computer interfaces. Turkish Journal of Electrical Engineering & Computer Sciences 2021; 29(5): 2263-2279.
• Sayilgan E, Yuce YK, Isler Y. Investigating the effect of flickering frequency pair and mother wavelet selection in steady-state visually-evoked potentials on two-command brain-computer interfaces, Innovation and Research in BioMedical Engineering 2022; IN PRESS.
• Sayilgan E, Yuce YK, Isler Y. Evaluation of wavelet features selected via statistical evidence from steady-state visually-evoked potentials to predict the stimulating frequency. Journal of the Faculty of Engineering and Architecture of Gazi University 2021; 36(2): 593-605.
• Sayilgan E, Yuce YK, Isler Y. Determining gaze information from steady-state visually-evoked potentials. Karaelmas Science and Engineering Journal 2020; 10(2): 151-157.
• Sayilgan E, Yuce YK, Isler Y. Estimation of three distinct commands using Fourier transform of steady-state visual-evoked potentials. Duzce Universitesi Bilim ve Teknoloji Dergisi 2020; 8(4): 2337-2343.
• Hart PE, Stork DG, Duda RO. Pattern Classification, A Wiley-Interscience Publication, 2001.
• Degirmenci M, Yuce YK, Isler Y. Motor imaginary task classification using statistically significant time-domain EEG features. In 2022 30th Signal Processing and Communications Applications Conference (SIU), May 16-18, 2022, Safranbolu, Turkey, ACCEPTED.