基于小波变换和ICA的房颤信号分离  

Atrial fibrillation signal separation based on wavelet transform and ICA

作　　者：林土胜[1] 陈国豪[1] 

机构地区：[1]华南理工大学电子与信息学院,广东广州510640

出　　处：《西北师范大学学报（自然科学版）》2010年第5期34-39,共6页Journal of Northwest Normal University(Natural Science)

基　　金：国家自然科学基金资助项目(60673191)

摘　　要：提出了一种基于小波变换和独立成分分析(ICA)的心房颤动(房颤)信号分离方法.首先通过小波变换将2个导联的Holter心电信号分解成一组信号,然后取其中几个尺度的单支重构信号进行ICA,分离出房颤信号.2个导联Holter系统无法满足ICA对信号通路数的要求,小波分解及单支重构解决了这一问题.ICA技术充分利用2个导联的信息,消除了单导联房颤信号分离方法易受伪迹和异位心搏等因素影响的缺点.实验证明了本方法的可行性和有效性,并且与常用的单导联分离方法的效果进行了对比.A method based on wavelet transform and ICA（independent component analysis） is proposed to separate atrial fibrillation（AF） signal.The first step is decomposing the two leads Holter electrocardiogram（ECG） signals into a set of signals.The second step is selecting some single branch reconstruction signals of certain scales to separate AF signal according to ICA.The proposed method solve the Holter system＇s problem of the number of leads can not meet the requirement of ICA by wavelet decomposition and single branch reconstruction.ICA technology fully use the information of two leads,and eliminate the drawbacks of single lead AF separation methods which is easy to be disturbed by artifacts ectopic,heart beat and so on.Experiment shows the feasibility and validity of this method,and the effort of this method is made contrast with the common single lead separation methods.

关 键 词：房颤 心电 独立成分分析 小波变换 

分 类 号：TN911.7[电子电信—通信与信息系统] TP391.4[电子电信—信息与通信工程]