Department of Electronics and Computer Education, Selcuk University, Konya, Turkey.
J Med Syst. 2012 Feb;36(1):1-13. doi: 10.1007/s10916-010-9440-0. Epub 2010 Feb 23.
In this study, it has been intended to perform an automatic classification of Electroencephalography (EEG) signals via Artificial Neural Networks (ANN) and to investigate these signals using Wavelet Transform (WT) for diagnosing epilepsy syndrome. EEG signals have been decomposed into frequency sub-bands using WT and a set of feature vectors which were extracted from the sub-bands. Dimensions of these feature vectors have been reduced via Principal Component Analysis (PCA) method and then classified as epileptic or healthy using Multilayer Perceptron (MLP) and ELMAN ANN. Performance evaluation of the used ANN models have been carried out by performing Receiver Operation Characteristic (ROC) analysis.
在这项研究中，旨在通过人工神经网络 (ANN) 对脑电图 (EEG) 信号进行自动分类，并使用小波变换 (WT) 对这些信号进行分析，以诊断癫痫综合征。通过 WT 将 EEG 信号分解为频带子带，并从子带中提取一组特征向量。使用主成分分析 (PCA) 方法降低这些特征向量的维度，然后使用多层感知器 (MLP) 和 ELMAN ANN 将其分类为癫痫或健康。通过执行接收者操作特征 (ROC) 分析来评估所使用的 ANN 模型的性能。
