摘要
介绍了将短时傅立叶变换(STFT)和连续小波变换(CWT)用于先天性心脏病(房间隔缺损、室间隔缺损、动静导管未闭)心音信号进行时频分析、特征提取的研究.两种方法都能较好的识别先天性心脏病人,总有效率为85%.论文对两种方法的优缺点进行了比较.小波变换比短时傅里叶变换能更有效的识别正常人与病人的心音信号的特征,可分性更好.但是短时傅里叶变换能量范围更集中,动态范围变化也更小一些.
Short-time Fourier Transform(STFT) and Continuous Wavelet Transform(CWT) were used in the time-frequency analyses of heart sounds of congenital heart disease.Three types of congenital heart diseases,atrial septal defect(ASD), ventricular septal defect(VSD),and patent ductus arteriosus(PDA) were studied.Some characteristics were extracted from phonocardiogram(PCG) by the time-frequency representation.The result shows that the congenital heart disease can be identified effectively by differentiating the chara...
出处
《云南大学学报（自然科学版）》
CAS
CSCD
北大核心
2006年第S1期89-93,共5页
Journal of Yunnan University(Natural Sciences Edition)
基金
国家自然科学基金资助项目(60561002)
关键词
先天性心脏病
心音
PCG(心音图)
短时傅立叶变换
小波变换
congenital heart disease（CHD）
heart sound
phonocardiogram（PCG）
Short-time Fourier Transform（STFT）
Continuous Wavelet Transform
