天津大学学报（英文版）
天津大學學報（英文版）
천진대학학보（영문판）
TRANSACTIONS OF TIANJIN UNIVERSITY
2004年
4期
247-251
,共5页
万柏坤%毕卡诗%綦宏志%赵丽
萬柏坤%畢卡詩%綦宏誌%趙麗
만백곤%필잡시%기굉지%조려
epileptic EEG wave%wavelet transformation(WT)%artificial neural network(ANN)%expert rule(ER)
In order to sufficiently exploit the advantages of different signal processing methods, such as wavelet transformation (WT), artificial neural networks (ANN) and expert rules (ER),a synthesized multi-method was introduced to detect and classify the epileptic waves in the EEG data. Using this method, at first, the epileptic waves were detected from pre-processed EEG data at different scales by WT, then the characteristic parameters of the chosen candidates of epileptic waves were extracted and sent into the well-trained ANN to identify and classify the true epileptic waves,and at last, the detected epileptic waves were certificated by ER. The statistic results of detection and classification show that, the synthesized multi-method has a good capacity to extract signal features and to shield the signals from the random noise. This method is especially fit for the analysis of the biomedical signals in biomedical engineering which are usually non-placid and nonlinear.
