基于连续小波变换和人工神经网络的癫痫棘波检测.pdfVIP

International Journal of Wavelets, Multiresolution and Information Processing Vol. 8, No. 1 (2010) 33–48 c World Scientific Publishing Company DOI: 10.1142/S0219691310003341 EPILEPTIC SPIKE DETECTION USING CONTINUOUS WAVELET TRANSFORMS AND ARTIFICIAL NEURAL NETWORKS BERDAKH ABIBULLAEV Department of Electronic Engineering, Yeungnam University Gyeongbuk Gyeongsan, Dae-Dong 214-1/712-749, South Korea berdakho@ynu.ac.kr HEE DON SEO∗ Microsystem Laboratory, Yeungnam University Gyeongbuk Gyeongsan, Dae-Dong 214-1/712-749, South Korea hdseo@ynu.ac.kr MIN SOO KIM Integrated Energy Research Institute, Dongguk University Gyeongbuk Gyeongju, Seokjang-dong 707, 780-714, South Korea Received 18 October 2008 Revised 17 February 2009 We propose a new method for detection and classification of noisy recorded epilep- tic transients in Electroencephalograms (EEG) using the continuous wavelet transform (CWT) and artificial neural networks (ANN). The proposed method consists of a seg- mentation, feature extraction and classification stage. For the feature extraction stage, we use best basis mother wavelet functions and wavelet thresholding technique. For the classification stage, multilayer perceptron neural networks were implemented according to standard backpropagation learning formulations. We demonstrate the efficiency of our feature extraction method on data to