基于小波变换和SVD的心电身份识别

基于心电信号的身份识别技术是生物身份识别领域研究的热点问题.该文利用小波变换将经过预处理之后的心电信号进行多尺度分解,组成一个初始特征矩阵;随后对该矩阵进行奇异值分解,分解后的奇异值包含了心电信号的重要信息,将其作为特征参数并最终采用支持向量机对心电信号进行匹配识别.通过对26个正常测试者的心电信号进行识别,识别率可达97.80％.

ECG Identification Based on Wavelet Transform and SVD

Analysis of the electrocardiogram（ECG） signal has been in spotlight of study in the biological i- dentification field. In this paper, we use the multi-seale wavelet transform decomposition to deal with the pre- process ECG to form an initial feature matrix; singular value decomposition（SVD） is used to process the ma- trix and get the singular value feature parameters which contain the important information of the ECG; finally, support vector machine（SVM） is as the classifier to classify the signal. Experimental results show that the per- formance of the system over 26 subjects is 97.80%.