基于小波包法与CSSD的P300特征提取方法  

P300 Feature Extraction With Wavelet Packet Transform and CSSD

作　　者：李明爱[1] 李骧[1] 杨金福[1] 郝冬梅[2] 

机构地区：[1]北京工业大学电子信息与控制工程学院,北京100124 [2]北京工业大学生命科学与生物工程学院,北京100124

出　　处：《北京工业大学学报》2014年第4期521-527,共7页Journal of Beijing University of Technology

基　　金：国家自然科学基金资助项目(61201362);北京市自然科学基金资助项目(7132021);北京市教育委员会资助项目(KM201110005005)

摘　　要：针对P300电位信号微弱、抗干扰能力差、识别率低等问题,提出一种小波包变换(wavelet packet transform,WPT)与共空域子空间分解法(spatial subspace decomposition,CSSD)相结合的特征提取方法,即WPCSSD法.首先,对脑电信号进行叠加平均以提高信号的信噪比;其次,使用小波包法对脑电信号进行滤波,并依据P300电位的有效时频信息重构脑电信号;然后,求取其AR模型功率谱,并基于CSSD法构造空间滤波器,获得能体现P300电位时-频-空特征的特征向量;最后,以支持向量机为分类器进行分类.实验结果表明:本方法具有较强的抗干扰能力和自适应能力,在国际BCI竞赛数据集上获得了95.22%的分类正确率,证明了本方法的正确性和有效性.P300 potential is weak and has poor anti-interference ability and low recognition rate. Based on wavelet packet transform （WPT） and common spatial subspaee decomposition （CSSD）, a feature extraction method, denoted as WPCSSD, was proposed in this paper. First, the EEG was preprocessed by the overlapping average algorithm to improve its signal-to-noise ratio. Second, the EEG was filtered and reconstructed by WPT according to the time-frequency information of P300. Third, the power spectrum based on AR model was computed, and a spatial filter with CSSD was applied to extract the spatial feature of P300. The feature vector can therefore reflect the time-frequency-space information of P300 generally. Finally, the support vector machine was used for classification. Results show that WPCSSD has better anti-interference and adaptive ability, and the recognition accuracy is 95.22% in data sets of BCI competition. The correctness and validity of the method are proven.

关 键 词：P300电位 特征提取 小波包 AR模型功率谱 共空域子空间 

分 类 号：R318[医药卫生—生物医学工程]