Research Article
BibTex RIS Cite

Independent Component Analysis Applied Marks EEG diagnosis of migraine Success Rate Effect

Year 2013, Volume: 16 Issue: 1, 30 - 33, 17.08.2013

Abstract

In this study, effect of Independent Component Analysis (ICA) was investigated in EEG based migraine diagnosis. Migraine diagnosis method used for this purpose is determined in previous studies as the magnitude variation at the beta band of EEG signals of migraine patients. Power spectral densities of the both raw EEG and BBA applied EEG signals were obtained by using Burg-AR method. Obtained Power Spectral Density (PSD) values are classified by using support vector machine (SVM) classifier and performances are compared. According to the results of this study we can conclude that usage of ICA method as a preprocessing technique, gave a %5 extra classification accuracy performance.

References

  • Waters WE, O'Connor PJ (1975). Prevalence of migraine. Journal of Neurology, Neurosurgery, and Psychiatry, 38, 613-616.
  • Akben, SB, Subasi A, Tuncel D (2011). Analysis of EEG Signals Under Flash Stimulation for Migraine and Epileptic Patients. Journal of Medical Systems. 35(3):437-43.
  • Akben, SB, Subasi A, Tuncel D (2012). Analysis of Repetitive Flash Stimulation Frequencies and Record Periods to Detect Migraine Using Artificial Neural Network. Journal of Medical Systems. 36(2):925-931.
  • De Marinis M, Rinalduzzi S, Accornero N (2007) Impairment in color perception in migraine with and without aura. Headache. 47(6):895–904. Ozkul Y, Gurler B, Bozlar S, Uckardes A, Karadede S (2001) Flash visual evoked potentials and electroretinograms in migraine. NeuroOphthalmology. 25(3):143–150.
  • De Tommaso M, Marinazzo D, Guido M, Libro G, Stramaglia S, Nitti L, Lattanzi G, Angelini L, Pellicoro M (2005). Visually evoked phase synchronization changes of alpha rhythm in migraine: correlations with clinical features. Int. J. Psychophysiol. 57(3):203–210.
  • Benna P, Bianco C, Costa P, Piazza D, Bergamasco B (1985). Visual evoked potentials and brainstem auditory evoked potentials in migraine and transient ischemic attacks. Cephalalgia. 2, 53–58.
  • Spreafico C, Frigerio R, Santoro P, Ferrarese C, Agostoni E (2004). Visual evoked potentials in migraine. Neurol. Sci. 25, 288–290.
  • Adeli H, Zhou Z, Dadmehr N (2003) Analysis of EEG records in an epileptic patient using wavelet transform. J. Neurosci. Methods. 123, 69–87.
  • Cao LJ, Chua KS, Chong WK, Lee HP, Gu QM (2003). A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machines. Neurocomputing. 55, 321–336.
  • Duda RO, Hart PE, Strok DG (2001). Pattern Classification Second Edition, John Wiley & Sons.
  • Widodo A, Yang B (2007). Application of nonlinear feature extraction and support vector machiness for fault diagnosis of induction motors. Expert Systems with Applications. 33, 241–250.
  • Cortes C, Vapnik V (1995). Support vector networks. Machines Learning. 20(3):273-297.
  • Cristianini N, Shawe-Taylor J (2000). An Introduction to Support Vector Machines and other kernel-based learning methods. Cambridge University Press.
  • Vapnik VN (1998). Statistical Learning Theory, Wiley-Interscience

EEG İşaretlerine Uygulanan Bağımsız Bileşen Analizinin Migren Teşhisindeki Başarı Oranına Etkisi

Year 2013, Volume: 16 Issue: 1, 30 - 33, 17.08.2013

Abstract

Bu çalışmada Bağımsız Bileşen Analizinin (BBA) EEG tabanlı migren teşhisindeki etkisi araştırılmıştır. Bu amaç için kullanılan migren teşhis yöntemi ise önceki çalışmalarda kullanılan ışık uyartısı altındaki migren hastalarının EEG işaretlerinin beta bandında görülen genlik değişimidir. Çalışmada kullanılan güç spektral yoğunlukları, hem ham EEG işaretlerinden hem de BBA ile azaltılmış EEG işaretlerinden Burg-AR yöntemi ile elde edilmiştir. Elde edilen güç spektral yoğunluğu değerleri destek vektör makineleri (DVM) sınıflandırıcısı ile sınıflandırılarak başarımlar karşılaştırılmıştır. Çalışmanın sonucu olarak önceki migren teşhis metoduna BBA’nın ön işleme yöntemi olarak kullanımı eklenirse, sınıflama performansını %5 civarında arttırdığı görülmüştür.

References

  • Waters WE, O'Connor PJ (1975). Prevalence of migraine. Journal of Neurology, Neurosurgery, and Psychiatry, 38, 613-616.
  • Akben, SB, Subasi A, Tuncel D (2011). Analysis of EEG Signals Under Flash Stimulation for Migraine and Epileptic Patients. Journal of Medical Systems. 35(3):437-43.
  • Akben, SB, Subasi A, Tuncel D (2012). Analysis of Repetitive Flash Stimulation Frequencies and Record Periods to Detect Migraine Using Artificial Neural Network. Journal of Medical Systems. 36(2):925-931.
  • De Marinis M, Rinalduzzi S, Accornero N (2007) Impairment in color perception in migraine with and without aura. Headache. 47(6):895–904. Ozkul Y, Gurler B, Bozlar S, Uckardes A, Karadede S (2001) Flash visual evoked potentials and electroretinograms in migraine. NeuroOphthalmology. 25(3):143–150.
  • De Tommaso M, Marinazzo D, Guido M, Libro G, Stramaglia S, Nitti L, Lattanzi G, Angelini L, Pellicoro M (2005). Visually evoked phase synchronization changes of alpha rhythm in migraine: correlations with clinical features. Int. J. Psychophysiol. 57(3):203–210.
  • Benna P, Bianco C, Costa P, Piazza D, Bergamasco B (1985). Visual evoked potentials and brainstem auditory evoked potentials in migraine and transient ischemic attacks. Cephalalgia. 2, 53–58.
  • Spreafico C, Frigerio R, Santoro P, Ferrarese C, Agostoni E (2004). Visual evoked potentials in migraine. Neurol. Sci. 25, 288–290.
  • Adeli H, Zhou Z, Dadmehr N (2003) Analysis of EEG records in an epileptic patient using wavelet transform. J. Neurosci. Methods. 123, 69–87.
  • Cao LJ, Chua KS, Chong WK, Lee HP, Gu QM (2003). A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machines. Neurocomputing. 55, 321–336.
  • Duda RO, Hart PE, Strok DG (2001). Pattern Classification Second Edition, John Wiley & Sons.
  • Widodo A, Yang B (2007). Application of nonlinear feature extraction and support vector machiness for fault diagnosis of induction motors. Expert Systems with Applications. 33, 241–250.
  • Cortes C, Vapnik V (1995). Support vector networks. Machines Learning. 20(3):273-297.
  • Cristianini N, Shawe-Taylor J (2000). An Introduction to Support Vector Machines and other kernel-based learning methods. Cambridge University Press.
  • Vapnik VN (1998). Statistical Learning Theory, Wiley-Interscience
There are 14 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Research Articles
Authors

S. Batuhan Akben

Ahmet Alkan

Publication Date August 17, 2013
Submission Date April 23, 2012
Published in Issue Year 2013Volume: 16 Issue: 1

Cite

APA Akben, S. B., & Alkan, A. (2013). EEG İşaretlerine Uygulanan Bağımsız Bileşen Analizinin Migren Teşhisindeki Başarı Oranına Etkisi. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 16(1), 30-33.