基于Mel频率倒谱系数的心音识别技术研究  

Study of Biometric Identification of Heart Sound Based on Mel-Frequency Cepstrum Coefficient

作　　者：陈玮[1] 赵屹华[1] 雷声[1] 赵子恺[1] 潘敏[1] 

机构地区：[1]浙江大学生仪学院生物传感器国家专业实验室,杭州310027

出　　处：《生物医学工程学杂志》2012年第6期1015-1020,共6页Journal of Biomedical Engineering

基　　金：十二五国家科技支撑计划项目资助(2012BAD35B03)

摘　　要：心音是人体心脏搏动产生的具有个体特征的生理参数。实验利用小波变换实现对心音信号的去噪处理,选择Mel频率倒谱系数(MFCC)作为特征参量,并经过主成分分析(PCA)降维处理后用于个体分类识别中。旨在对心音作为生物识别特征参数可行性和识别方法做一个初步研究。实验结果显示,在选定的实验条件下,系统可以达到90%以上的识别率。可以为心音识别技术的进一步研究提供参考。Heart sound is a physiological parameter with individual characteristics generated by heart beat. To do the individual classification and recognition, in this paper, we present our study of using wavelet transform in the signal denoising, with the MelFrequency cepstrum coefficients （MFCC） as the feature parameters, and propose a research of reducing the dimensionality through principal components analysis （PCA）. We have done the preliminary study to test the feasibility of biometric identification method using heart sound. The results showed that under the selected experimental conditions, the system could reach a 90% recognition rate. This study can provide a reference for fur ther research.

关 键 词：生物识别 心音 小波去噪 MEL频率倒谱系数 主成分分析 

分 类 号：TN911.7[电子电信—通信与信息系统]