Abstract: Electroencephalography（EEG） signals of control subjects and epileptic subjects are identified by combination of wavelet packet decomposition and genetic neural network.Signal features are identified through the EEG data analysis.The frequency bands of EEG signals including identified features are extracted by 1-D wavelet packet decomposition.The relative energy of different frequency bands in EEG is remained as signals features.Then BP neural network optimized by genetic algorithm is built for the identification of epileptic signals.The experiment results demonstrate that this method can extract signal features effectively and identify signal exactly.

摘要： 基于小波包分解和遗传神经网络对正常脑电和癫痫脑电进行识别。通过分析脑电数据找出信号特征；利用一维离散小波包分解提取含有识别特征的脑电信号频率段，并以脑电各频段的相对能量作为信号特征；然后建立基于遗传算法优化的BP网络，用于对癫痫脑电识别。实验结果表明，该方法可以有效提取信号特征，并且对信号进行准确的识别。