基于ICA和小波变换的房颤F波提取算法.pdfVIP

学兔兔 第32卷 第8期 仪 器 仪 表 学 报 Vo1．32 No．8 2011年8月 Chinese Journal of Scientific Instrument 基于ICA和小波变换的房颤F波提取算法冰 戴呼合，姜守达 (哈尔滨工业大学电气工程及自动化学院 哈尔滨 150080) 摘 要：应用独立成分分析(independent component analysis，ICA)提取的房颤F波在QRST数据段有明显“扰动”失真， 为减少 这种失真，提出了一种ICA与小波变换相结合的F波提取算法。首先对原始信号进行ICA分解，获得初始F波及其分离向量； 然后对初始F波进行多层小波分解，在小波域内构造反映F波失真的目标函数；最后利用最速下降法优化目标函数， 获得准确 的F波分离向量，从而实现对F波的准确提取。对仿真信号和真实信号的F波提取实验表明，该算法明显减少了F波的“扰 动”失真。 关键词：房颤；独立成分分析；小波变换；最速下降法 中图分类号：TN911．7 文献标识码：A 国家标准学科分类代码：460．4030 Atrial fibrillation wave extraction algorithm based on ICA and wavelet transform Dai Huhe，Jiang Shouda (School of Electrical Engineering and Automation，Harbin Institute of Technology，Harbin 150080，China) Abstract：When independent component analysis(ICA)algorithms are used to extract atrial fibrillation(F)wave from electrocardiogram signal(ECGs)of persistent atrial fibrillation，serious distortion exists in F wave QRST seg— ment．To reduce this distortion，a new algorithm based on ICA and wavelet transform is proposed．Firstly，ICA algo— rithm is applied to get initial F wave and its separation vector．Then wavelet transform is used to decompose initial F wave，and the objective function that reflects F wave distortion is constructed in wavelet domain．Finally，steepest descent method is used to optimize the objective function and get more accurate separation vector．The proposed algo— rithm is validated with both simulated signal and real ECGs of atrial fibrillation，and distortion in the extracted F wave is considerately reduced． Key words：atrial fibrillation；independent component analysis(ICA)；wavelet transform；steepest descent method