Destek Vektör Makinaları ile EEG Sinyallerinden Epileptik Nöbet Sınıflandırması

Epileptik aktivitelerin saptanması Elektroensflogram (EEG) verilerinin ayrıntılı analizini gerektirir. El ile epileptik aktiviteleri skorlaması hem zor hem de tutarsızdır. Makine öğrenme teknikleri ise el ile skorlamaya göre daha hızlı ve tutarlıdır. Bu nedenle, EEG verilerini sınıflandırmak için etkili bir makine öğrenmesi tekniğine ihtiyaç vardır. Doğrusal olmayan verileri modelleme başarısından dolayı gözetimli öğrenme algoritmalarından Destek Vektör Makineleri(SVM) tercih edilmiştir. Bu başarı ancak uygun çekirdek fonksiyonu seçildiğinde gerçekleşmektedir. Sıklıkla kullanılan çekirdek fonksiyonları linear, polinom ve radyal tabanlı(RBF)’dır. Verilerin doğası önceden bilinmediğinden çekirdek fonksiyonları arasından uygun seçim yapmak zordur. Bu nedenle modeli oluştururken birden fazla çekirdek fonksiyonu kullanılarak aralarından en iyi performansı veren seçilmelidir. Bu çalışmada Bonn üniversitesinden alınan EEG verileri ile 9 farklı sınıflandırma problemi ele alınmıştır. EEG sinyalleri farklı 5 frekans bandında incelenmiş, her frekans bandının standart sapma değerlerinden öznitelik vektörü oluşturulmuştur. Linear, polinom, radyal tabanlı ve Pearson VII(PUK) çekirdek fonksiyonlarının genelleme yetenekleri karşılaştırılmıştır. PUK çekirdek fonksiyonları parametre değerlerinin başarı oranları üzerindeki etkisi de ayrıca incelenmiştir. Çalışmada önerilen model ile öznitelik hesap yükü azaltılmış, boyut azaltım algoritmaları kullanım ihtiyacı ortadan kaldırılmış, daha az işlem yükü oluşturmuştur. PUK çekirdek fonksiyonunun diğer fonksiyonlara göre daha iyi genelleme performansına sahip olduğu sonucuna varılmıştır. İki sınıflı problemlerde %100 başarı oranına ulaşılmıştır.

Epileptic Seizure Classification from EEG Signals with Support Vector Machines

Detection of epileptic activities requires detailed analysis of the electroencephalogram (EEG) data. Scoring manual epileptic activities is both difficult and inconsistent. Machine learning techniques are faster and more consistent than manual scoring. Therefore, there is a need for an effective machine learning technique to classify EEG data. Because of the success of modeling nonlinear data, Support Vector Machines (SVM), which is a supervised learning algorithm, is preferred. This success is achieved only when the appropriate kernel function is selected. Commonly used kernel functions are linear, polynomial and radial based (RBF). Since the nature of the data is not known in advance, it is difficult to make appropriate selection from the kernel functions. For this reason, when creating the model, it should be selected using multiple kernel functions to give the best performance among them. In this study, EEG data from Bonn University and 9 different classification problems are discussed. EEG signals were analyzed in 5 different frequency bands and feature vectors were generated from the standard deviation values of each frequency band. The generalization capabilities of linear, polynomial, radial based and Pearson VII(PUK) kernel functions are compared. The effect of PUK kernel functions parameter values on success rates is also investigated. With the model proposed in the study, processing load was reduced, dimensionality reduction algorithms were eliminated, and less processing load was created. It was concluded that PUK kernel function has better generalization performance than other functions. 100% success rate was achieved in two-class problems.

___

  • [1] Chu H., Chung C.K., Jeong W., Cho K.H., “Predicting epileptic seizures from scalp EEG based on attractor state analysis”, Computer Methods and Programs in Biomedicine, 143: 75-87, (2017).
  • [2] Li M., Chen W., Zhang T., “Automatic epilepsy detection using wavelet-based nonlinear analysis and optimized SVM”, Biocybernetics and Biomedical Engineering, 36: 708–718, (2016).
  • [3] Wang G., Deng Z., Choi K.Z., “Detection of epilepsy with electroencephalogram using rule-based Classifiers”, Neurocomputing, 228: 283–290, (2017).
  • [4] Li M., Chen W., Zhang T., “Classification of epilepsy EEG signals using DWT based envelope analysis and neural network ensemble”, Biomedical Signal Processing and Control, 31: 357–365, (2017).
  • [5] Yalçın N., Tezel G., Karakuzu C., “Epilepsy diagnosis using artificial neural network learned by PSO”, Turkish Journal of Electrical Engineering & Computer Sciences, 23: 421-432, (2015).
  • [6] Yuan Q., Zhou W., Liu Y., Wang J., “Epileptic seizure detection with linear and nonlinear features”, Epilepsy & Behavior, 24: 415–421, (2012).
  • [7] Fergus P., Hussain A., Hignett D.,, Al-Jumeily D., Abdel-Aziz K., Hamdan H., “A machine learning system for automated whole-brain seizure detection”, Applied Computing and Informatics, 12: 70–89, (2016).
  • [8] Tzimourta K.D., Astrakas L.G., Tsipouras M.G., Giannakeas N., Tzallas A.T., “Wavelet based classification of epileptic seizures in EEG signals”, IEEE 30th International Symposium on Computer-Based Medical Systems, 35-39, (2017).
  • [9] Qin Y-M., Han C-X., Che Y-Q., Li H-Y., “Efficient Epileptic Seizure Detection Based on Electroencephalography Signal”, Proceedings of the 36th Chinese Control Conference, 5324-5327, (2017).
  • [10] Sharmila A., Mahalakshmi P., “Wavelet-based feature extraction for classification of epileptic seizure EEG signal”, Journal of Medical Engineering & Technology, 41(8): 670-680, (2017).
  • [11] Cılasun M.H., Yalçın H., “A deep learning approach to eeg based epilepsy seizure determination”, Signal Processing And Communication Application Conference, (2016).
  • [12] Dash D., “Advanced Signal Processing Techniqes to Study Normal and Epileptic EEG”, Computational Engineering Finance and Science, (2014).
  • [13] Yavuz E., Kasapbaşı M.C., Eyüpoğlu C., Yazıcı R., “An epileptic seizure detection system based on cepstral analysis and generalized regression neural network”, Biocybernetics and Biomedical Engineering, (2017).
  • [14] Subaşı A., “EEG signal classification using wavelet feature extraction and a mixture of expert model”, Expert Systems with Applications, 32: 1084-1093, (2007).
  • [15] Güler İ., Übeyli E.D., “Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients”, Journal of Neuroscience Methods, 148: 113–121, (2005).
  • [16] Tzallas T.A., Tsipouras M.G., Fotiadis D.I., “Epileptic Seizure Detection in EEGs Using Time–Frequency Analysis”, IEEE Transactions on Information Technology in Biomedicine, 13(5): 703-710, (2009).
  • [17] Stanimirova I., Ustun B., Cajka T., Riddelova K., Hajslova J., Buydens L.M.C., Walczak B., “Tracing the geographical origin of honeys based on volatile compounds profiles assessment using pattern recognition techniques”, Food Chemistry, 171–176, (2010).
  • [18] Üstün B., Melssen W.J., “Buydens L.M.C., Facilitating the application of Support Vector Regression by using a universal Pearson VII function based kernel”, Chemometrics and Intelligent Laboratory Systems, 29-40, (2006).
  • [19] Zhang G., Huihua G., “Support vector machine with a Pearson VII function kernel for discriminating halophilic and non-halophilic proteins”, Computational Biology and Chemistry, 16-22, (2013).
  • [20] Amin H.U., Yusoff M.Z., Ahmad R.F., “A novel approach based on wavelet analysis and arithmetic coding for automated detection and diagnosis of epileptic seizure in EEG signals using machine learning techniques”, Biomedical Signal Processing and Control, 56: 1-10, (2020).
  • [21] ZhangT., Chen W., Li M., “Generalized Stockwell transform and SVD-based epileptic seizure detection in EEG using random forest”, Biocybernetics and Biomedical Engineering, 38: 519-534, (2018).
  • [22] Gupta V., Pachori R.B., “Epileptic seizure identification using entropy of FBSE based EEG rhythms”, Biomedical Signal Processing and Control, 53: 1-11, (2019).
  • [23] Mahapatra A.G., Horio K., “Classification of ictal and interictal EEG using RMS frequency,dominant frequency, root mean instantaneous frequency square and their parameters ratio”, Biomedical Signal Processing and Control, 44: 168–180, (2018).
  • [24] Ullah I., Hussain M., Qazi E.H., Aboalsamh H., “An automated system for epilepsy detection using EEG brain signals based on deep learning approach”, Expert Systems With Applications, 107: 61–71, (2018).
  • [25] Hussein R., Palangi H., Ward R.K., Wang Z.J., “Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals”, Clinical Neurophysiology, 130: 25–37, (2019).
  • [26] Raghu S., Sriraam N., Hegde A.S., Kubben P.L., “A novel approach for classification of epileptic seizures using matrix determinant”, Expert Systems With Applications, 127: 323–341, (2019).
  • [27] Li Y., Cui W.G., Huang H., Guo Y., Li K., Tan T., “Epileptic seizure detection in EEG signals using sparse multiscale radial basis function networks and the Fisher vector approach”, Knowledge-Based Systems, 164: 96–106, (2019).
  • [28] Ghayab H.R.A., Lia Y., Siulyc S., Abdullad S., “A feature extraction technique based on tunable Q- factor wavelet transform for brain signal classification”, Journal of Neuroscience Methods, 312: 43–52, (2019).
  • [29] Andrzejak R.G., Lehnertz K., Normann F., Rieke C., David P., Elger C.E., “Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state”, Physical Review E., 64: 1-8, (2001).
  • [30] Tuncer E., Bolat E.D., “EEG Signal based sleep stage classification using discrete wavelet transform, International Conference on Chemistry”, Biomedical and Environment Engineering, 57-61, (2014).
  • [31] Faust O., Acharya U.R., Adeli H., Adeli A., “Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis”, Seizure, 26: 56–64, (2015).
  • [32] Martinez-del-Rincon J., Santofimia M.J., Toro X.D., Barba J., Romero F., Navas P. ,Lopez J.C., “Non-linear classifiers applied to EEG analysis for epilepsy seizure detection”, Expert Systems with Applications, 86: 99-112, (2017).
  • [33] Subaşı A., Gürsoy M.I., “EEG Signal classification using PCA, ICA, LDA and support vector machines”, Expert Systems with Applications, 37: 8659-8666, (2010).
  • [34] Abakar K.A., Yu C., “Performance of SVM based on PUK kernel in comparison to SVM based on RBF kernel in prediction of yarn tenacity”, Indian Journal of Fibre &tectile Research, 39: 55-59, (2014).
  • [35] Kavzoğlu T., Çölkesen İ., “Destek Vektör Makineleri ile Uydu Görüntülerinin Sınıflandırılmasında Kernel Fonksiyonlarının Etkilerinin İncelenmesi”, Harita Dergisi, 144: 73-82, (2010).
  • [36] Shanthini D.,Shanthi M., Bhuvaneswari M.C., “Comparative Study of SVM Kernel Functions Based on Polynomial Coefficients and V-Transform Coefficients”, International Journal of Engineering and Computer Science, 6: 20765-20769, (2017).
  • [37] Zhang G., Ge H., “Support vector machine with a Pearson VII function kernel for discriminating halophilic and non-halophilic proteins”, Computational Biology and Chemistry, 46: 16-22, (2013).
  • [38] Thara D.K., PremaSudha B.G., Xiong F., “Auto-detection of epileptic seizure events using deep neural network with different feature scaling techniques”, Pattern Recognition Letters, 128: 544-550, (2019).
Politeknik Dergisi-Cover
  • ISSN: 1302-0900
  • Yayın Aralığı: Yılda 4 Sayı
  • Başlangıç: 1998
  • Yayıncı: GAZİ ÜNİVERSİTESİ