Classification of Magnetoencephalography Signals by Multilayer and Radial Based Artificial Neural Networks
Öz
Magnetoencephalography (MEG) is a neuroimaging technique for recording brain activity, using very sensitive magnetometers. MEG signals are obtained from neuronal electrical activity and are capable of providing important information for decoding brain activity. In the case of visual stimulation, the relationship between the stimuli and the signal due to the generated mental activity is important for the development of machine learning algorithms. MEG signals have a complex structure due to environmental factors and functional differences arising from brain structures of individuals. It is difficult to get meaningful information from these complex signals. For this reason it is necessary to utilize advanced signal processing techniques. In this study, the successes of multilayer neural network (MLNN) and radial basis neural network (RBNN) have been demonstrated by classifying magnetoencephalography signals through MLNN and RBNN. The performances of proposed classifiers are compared with the results of the previous studies using same dataset.
Anahtar Kelimeler
Magnetoencephalography Multilayer Neural Network Radial Basis Neural Network
Kaynakça
- [1] Olivetti E, Kia SM, Avesani P. MEG decoding across subjects. International Workshop on Pattern Recognition in Neuroimaging 2014; doi: 10.1109/PRNI.2014.6858538.[2] Cetin O, Temurtas F. Öğrenmeli Vektör Kuantalama ile Beyin Bilgisayar Arayüzü Üzerine Bir Çalışma. Sakarya University Journal of Computer and Information Sciences 2018;1(2):1 7.[3] Gulbag A, Temurtas F. A study on quantitative classification of binary gas mixture using neural networks and adaptive neuro-fuzzy inference systems. Sensors and Actuators B 2006;115(1):252-62.[4] Caliskan A, Yuksel ME, Badem H, Basturk A. A Deep Neural Network Classifier for Decoding Human Brain Activity Based on Magnetoencephalography. Elektronika ir Elektrotechnika 2017;23(2):63-67.[5] Henson RN, Wakeman DG, Litvak V, Friston KJ. A parametric empirical Bayesian framework for the EEG/MEG inverse problem: generative models for multi-subject and multi-modal integration. Frontiers in Human Neuroscience 2011;5:76.[6] Barachant A, Bonnet S, Congedo M, Jutten C. Multiclass brain–computer interface classification by Riemannian geometry. IEEE Trans. Biomedical Engineering 2012;59(4):920 28.[7] Yger F, Berar M, Lotte F. Riemannian approaches in brain computer interfaces: a review. IEEE Trans. Neural Systems and Rehabilitation Engineering 2017;25(10):1753-62.[8] Cetin O, Temurtas F, Gulgonul S. An application of multilayer neural network on hepatitis disease diagnosis using approximations of sigmoid activation function. Dicle Medical Journal 2015;42(2):150 7.[9] DecMeg2014-Decoding the Human Brain. Ulaşılabileceği adres: https://www.kaggle.com/c/decoding-the-human-brain[10] Bascil MS, Cetin O, Er O, Temurtas F. Olasılıksal Sinir Ağının (PNN) Parkinson Hastalığının Teşhisinde Kullanılması. Electronic Letters on Science&Engineering 2012; 8(1):1 10.[11] Gorur K, Bozkurt MR, Bascil MS, Temurtas F. Glossokinetic potential based tongue-machine interface for 1-D extraction. Australas Phys Eng Sci Med 2018. doi: 10.1007/s13246-018-0635-x.[12] Moakher M. A differential geometric approach to the geometric mean of symmetric positive-definite matrices. SIAM Journal on Matrix Analysis and Applications 2005;26(3):735 47.[13] Barachant A. Covariance toolbox. Ulaşılabileceği adres: https://github.com/alexandrebarachant/covariancetoolbox[14] Pennec X, Fillard P, Ayache N. A Riemannian framework for tensor computing. International Journal of Computer Vision 2006;66(1):41-66.[15] Temurtas H, Temurtas F. An application of neural networks for harmonic coefficients and relative phase shifts detection. Expert Systems with Applications 2011;38(4):3446-3450.[16] Moller, M. F. (1993). A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks, 6, 525–533.[17] Gulbag A, Temurtas F, Tasaltin C, Öztürk ZZ. A study on radial basis function neural network size reduction for quantitative identification of individual gas concentrations in their gas mixtures. Sensors and Actuators B: Chemical 2007;124(2):383-392.[18] R. Segal, M.L. Kothari, S. Madnani, Radial basis function (RBF) network adaptive power system stabilizer, IEEE Trans. Power Syst. 15(2000):722-727.
Çok Katmanlı ve Radyal Tabanlı Yapay Sinir Ağları ile Manyetoensefalografi Sinyallerinin Sınıflandırılması
Öz
Manyetoensefalografi (MEG) çok hassas
manyetometreler kullanarak beyin aktivitesini kaydetmek için bir
nörogörüntüleme tekniğidir. MEG sinyalleri nöronal elektriksel aktiviteden elde
edilir ve beyin aktivitesinin kodunu çözmek için önemli bilgiler sağlayabilir.
Görsel uyarım durumunda, uyarıcı ile üretilen zihinsel aktiviteye bağlı sinyal
arasındaki ilişki, makine öğrenimi algoritmalarının geliştirilmesi için
önemlidir. MEG sinyalleri, çevresel faktörler ve bireylerin beyin yapılarından
kaynaklanan fonksiyonel farklılıklar nedeniyle karmaşık bir yapıya sahiptir. Bu
karmaşık sinyallerden anlamlı bilgi edinmek zordur. Bu nedenle gelişmiş sinyal
işleme tekniklerini kullanmak gereklidir. Bu çalışmada, çok katmanlı sinir ağı
(MLNN) ve radyal tabanlı sinir ağının (RBNN) başarıları, MLNN ve RBNN
aracılığıyla magnetoensefalografi sinyalleri sınıflandırılarak gösterilmiştir.
Önerilen sınıflandırıcıların performansları, aynı veri kümesini kullanan önceki
çalışmaların sonuçlarıyla karşılaştırılmıştır.
Anahtar Kelimeler
Manyetoensefalografi Çok Katmanlı Sinir Ağı Radyal Tabanlı Sinir Ağı
Kaynakça
- [1] Olivetti E, Kia SM, Avesani P. MEG decoding across subjects. International Workshop on Pattern Recognition in Neuroimaging 2014; doi: 10.1109/PRNI.2014.6858538.[2] Cetin O, Temurtas F. Öğrenmeli Vektör Kuantalama ile Beyin Bilgisayar Arayüzü Üzerine Bir Çalışma. Sakarya University Journal of Computer and Information Sciences 2018;1(2):1 7.[3] Gulbag A, Temurtas F. A study on quantitative classification of binary gas mixture using neural networks and adaptive neuro-fuzzy inference systems. Sensors and Actuators B 2006;115(1):252-62.[4] Caliskan A, Yuksel ME, Badem H, Basturk A. A Deep Neural Network Classifier for Decoding Human Brain Activity Based on Magnetoencephalography. Elektronika ir Elektrotechnika 2017;23(2):63-67.[5] Henson RN, Wakeman DG, Litvak V, Friston KJ. A parametric empirical Bayesian framework for the EEG/MEG inverse problem: generative models for multi-subject and multi-modal integration. Frontiers in Human Neuroscience 2011;5:76.[6] Barachant A, Bonnet S, Congedo M, Jutten C. Multiclass brain–computer interface classification by Riemannian geometry. IEEE Trans. Biomedical Engineering 2012;59(4):920 28.[7] Yger F, Berar M, Lotte F. Riemannian approaches in brain computer interfaces: a review. IEEE Trans. Neural Systems and Rehabilitation Engineering 2017;25(10):1753-62.[8] Cetin O, Temurtas F, Gulgonul S. An application of multilayer neural network on hepatitis disease diagnosis using approximations of sigmoid activation function. Dicle Medical Journal 2015;42(2):150 7.[9] DecMeg2014-Decoding the Human Brain. Ulaşılabileceği adres: https://www.kaggle.com/c/decoding-the-human-brain[10] Bascil MS, Cetin O, Er O, Temurtas F. Olasılıksal Sinir Ağının (PNN) Parkinson Hastalığının Teşhisinde Kullanılması. Electronic Letters on Science&Engineering 2012; 8(1):1 10.[11] Gorur K, Bozkurt MR, Bascil MS, Temurtas F. Glossokinetic potential based tongue-machine interface for 1-D extraction. Australas Phys Eng Sci Med 2018. doi: 10.1007/s13246-018-0635-x.[12] Moakher M. A differential geometric approach to the geometric mean of symmetric positive-definite matrices. SIAM Journal on Matrix Analysis and Applications 2005;26(3):735 47.[13] Barachant A. Covariance toolbox. Ulaşılabileceği adres: https://github.com/alexandrebarachant/covariancetoolbox[14] Pennec X, Fillard P, Ayache N. A Riemannian framework for tensor computing. International Journal of Computer Vision 2006;66(1):41-66.[15] Temurtas H, Temurtas F. An application of neural networks for harmonic coefficients and relative phase shifts detection. Expert Systems with Applications 2011;38(4):3446-3450.[16] Moller, M. F. (1993). A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks, 6, 525–533.[17] Gulbag A, Temurtas F, Tasaltin C, Öztürk ZZ. A study on radial basis function neural network size reduction for quantitative identification of individual gas concentrations in their gas mixtures. Sensors and Actuators B: Chemical 2007;124(2):383-392.[18] R. Segal, M.L. Kothari, S. Madnani, Radial basis function (RBF) network adaptive power system stabilizer, IEEE Trans. Power Syst. 15(2000):722-727.
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Konular | Mühendislik |
| Bölüm | Makaleler |
| Yazarlar | |
| Yayımlanma Tarihi | 16 Ağustos 2018 |
| Gönderilme Tarihi | 7 Ağustos 2018 |
| Yayımlandığı Sayı | Yıl 2018 Cilt: 14 Sayı: 1 |
