DocumentCode :
2112161
Title :
Epileptic seizure prediction based on a bivariate spectral power methodology
Author :
Bandarabadi, Mojtaba ; Teixeira, C.A. ; Direito, Bruno ; Dourado, Antonio
Author_Institution :
Centre for Inf. & Syst. (CISUC), Univ. of Coimbra, Coimbra, Portugal
fYear :
2012
fDate :
Aug. 28 2012-Sept. 1 2012
Firstpage :
5943
Lastpage :
5946
Abstract :
The spectral power of 5 frequently considered frequency bands (Alpha, Beta, Gamma, Theta and Delta) for 6 EEG channels is computed and then all the possible pairwise combinations among the 30 features set, are used to create a 435 dimensional feature space. Two new feature selection methods are introduced to choose the best candidate features among those and to reduce the dimensionality of this feature space. The selected features are then fed to Support Vector Machines (SVMs) that classify the cerebral state in preictal and non-preictal classes. The outputs of the SVM are regularized using a method that accounts for the classification dynamics of the preictal class, also known as “Firing Power” method. The results obtained using our feature selection approaches are compared with the ones obtained using minimum Redundancy Maximum Relevance (mRMR) feature selection method. The results in a group of 12 patients of the EPILEPSIAE database, containing 46 seizures and 787 hours multichannel recording for out-of-sample data, indicate the efficiency of the bivariate approach as well as the two new feature selection methods. The best results presented sensitivity of 76.09% (35 of 46 seizures predicted) and a false prediction rate of 0.15-1.
Keywords :
data reduction; diseases; electroencephalography; feature extraction; medical signal processing; neurophysiology; signal classification; support vector machines; EEG; EPILEPSIAE database; SVM classifier; alpha band spectral power; beta band spectral power; bivariate spectral power methodology; cerebral state classification; classification dynamics; delta band spectral power; epileptic seizure prediction; feature selection methods; feature space dimensionality reduction; firing power method; gamma band spectral power; mRMR feature selection method; minimum redundancy maximum relevance feature selection method; pairwise feature combinations; preictal class; support vector machines; theta band spectral power; Electroencephalography; Feature extraction; Kernel; Scalp; Sensitivity; Support vector machines; Training; Algorithms; Electroencephalography; Epilepsy; Humans; Multivariate Analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE
Conference_Location :
San Diego, CA
ISSN :
1557-170X
Print_ISBN :
978-1-4244-4119-8
Electronic_ISBN :
1557-170X
Type :
conf
DOI :
10.1109/EMBC.2012.6347347
Filename :
6347347
Link To Document :
بازگشت