摘要
提出了一种应用离散小波变换(DWT)结合主分量分析(PCA)进行特征提取,然后用支持向量机(SVM)对P300进行分类的算法。该算法首先在一定预处理基础上使用离散小波变换对P300脑电信号分解,然后选取蕴含P300大多数信息的特征尺度进行小波重构,从而达到去噪增强的效果。然后使用PCA进行特征的提取和集中。最后使用支持向量机对提取到的特征分量进行分类。该算法将小波分解和主分量分析结合起来进行特征增强与提取,实验结果表明,该算法能够达到令人满意的正确分类率。
A P300 classification method based on discrete wavelet transform（DWT）,principal component analysis（PCA） and support vector machine（SVM） is proposed. First, P300 signals which have been preprocessed are decomposed by discrete wavelet transform, choose feature scales which contain much P300 information to do wavelet reconstruction to wipe off noise and strengthen the useful signals. After that, PCA is used to extract the feature, at the same time the feature is focused. Support vector machine（SVM） is used to the P300 classification at last. This method connect the DWT with PCA to enhance the feature and extraction. The experiment results show that the classification rate can be gained satisfactorily .
出处
《电子技术（上海）》
2007年第11期192-194,共3页
Electronic Technology
关键词
P300
脑-机接口
离散小波变换
支持
向量机
P300, Brain-Computer Interface, discrete wavelet transform（DWT）, support vector machine（SVM）
