论文部分内容阅读
在非线性时间序列预测研究的基础上,提出了基于非线性预测效果的癫痫脑电信号特征提取方法,从脑电信号中自动检测出癫痫脑电信号.采用基于可预测性的选取嵌入维数的方法确定脑电信号序列的嵌入维数,进行相空间重构.实验结果表明:基于非线性预测效果的特征提取方法提取的特征能明显地区分癫痫脑电信号与正常脑电信号,该非线性特征提取方法适合小数据量的情况且对噪声的稳定性好.
Based on the nonlinear time series prediction, a new feature extraction method of epileptic EEG based on nonlinear prediction is proposed, and the epileptic EEG signals are automatically detected from the EEG signals. The predictive embedding dimension Method to determine the embedding dimension of EEG signal sequence and reconstruct the phase space.The experimental results show that the features extracted by the feature extraction method based on nonlinear prediction can obviously distinguish the epileptic EEG signals from the normal EEG signals, The linear feature extraction method is suitable for a small amount of data and has good noise stability.