一种基于S变换及样本熵组合特征的癫痫脑电信号分类方法

癫痫脑电信号的自动检测对癫痫的临床诊断与治疗具有重要意义。为了解决脑电信号采用单一特征识别率不高的问题,提出了一种基于S变换与样本熵组合的癫痫脑电信号自动识别方法。首先对原始信号进行S变换;然后对变换后脑电信号各节律的幅值分别求其波动指数,将其与原始信号计算得到的样本熵组合为特征向量;最后采用支持向量机进行癫痫脑电信号自动识别。实验结果表明:方法的分类准确率明显提高,准确率可达到98.94%。

An Epileptic EEG Signal Classification Based on Combination of S Transform and Sample Entropy

Automatic detection and classification of epileptic EEG(electroencephalogram) signals have been a significance method for the clinical diagnosis and treatment of epilepsy. In order to solve the problem that the recognition accuracy is not high by using the single feature of EEG signals, a method of automatic discrimination of epileptic EEG signals based on Combination of S transform and sample entropy is proposed. Firstly, the original signals were decomposed by S transform, and then the fluctuation index of amplitude of each rhythm was calculated and combined the sample entropy of EEG signals into feature vectors. Finally, put the feature vectors into a support vector machine (SVM) to automatically detected the epileptic EEG from EEG recordings.Experimental results shows that the proposed methods could achieve a great classification accuracy of 98.94%.