振动与冲击
振動與遲擊
진동여충격
JOURNAL OF VIBRATION AND SHOCK
2014年
6期
29-34
,共6页
心音%特征参数%改进高斯混合模型%加权可选择模糊C均值
心音%特徵參數%改進高斯混閤模型%加權可選擇模糊C均值
심음%특정삼수%개진고사혼합모형%가권가선택모호C균치
heart sound%feature parameter%improved Gaussian Mixture Model (GMM)%Weighted Optional Fuzzy C-Means (WOFCM)
为提高心音信号特征提取的准确性及分类识别的高效性,将小波包变换的Mel频率倒谱系数与改进的高斯混合模型结合用于心音信号分类识别。在Mel频率倒谱系数提取方法基础上,用小波包变换代替傅里叶变换与Mel滤波器组,获得新特征参数DWPTMFCC;针对传统GMM参数初始化K-means算法缺点,用加权可选择模糊C均值算法进行改进;将提取的特征参数分别输入到改进后GMM进行分类识别。对临床采集的心音数据测试结果表明,该方法能有效提取心音特征,优于传统GMM识别性能。
為提高心音信號特徵提取的準確性及分類識彆的高效性,將小波包變換的Mel頻率倒譜繫數與改進的高斯混閤模型結閤用于心音信號分類識彆。在Mel頻率倒譜繫數提取方法基礎上,用小波包變換代替傅裏葉變換與Mel濾波器組,穫得新特徵參數DWPTMFCC;針對傳統GMM參數初始化K-means算法缺點,用加權可選擇模糊C均值算法進行改進;將提取的特徵參數分彆輸入到改進後GMM進行分類識彆。對臨床採集的心音數據測試結果錶明,該方法能有效提取心音特徵,優于傳統GMM識彆性能。
위제고심음신호특정제취적준학성급분류식별적고효성,장소파포변환적Mel빈솔도보계수여개진적고사혼합모형결합용우심음신호분류식별。재Mel빈솔도보계수제취방법기출상,용소파포변환대체부리협변환여Mel려파기조,획득신특정삼수DWPTMFCC;침대전통GMM삼수초시화K-means산법결점,용가권가선택모호C균치산법진행개진;장제취적특정삼수분별수입도개진후GMM진행분류식별。대림상채집적심음수거측시결과표명,해방법능유효제취심음특정,우우전통GMM식별성능。
To improve the precision of feature extraction and efficiency of classification and recognition of heart sound,the method of Discrete Wavelet Transform Mel Frequency Cepstrum Coefficients (DWPTMFCC)combined with an improved Gaussian Mixture Model (GMM)was used for the classification and recognition of heart sound.A new feature parameter was formed by using wavelet packet transform instead of Fourier transform and Mel filter group on the basis of the extraction method of MFCC.To overcome the shortcoming of K-means algorithm which is used in the parameters initialization process of traditional GMM,Weighted Optional Fuzzy C-Means (WOFCM)algorithm was proposed.The feature parameters were then input into the improved GMMfor recognition.The clinical diagnosis and test results show that the method not only can effectively extract heart sound feature,but also have better recognition performance comparing with the traditional GMM.