[1]张伟,顾旋,梁富娥,等.基于改进变步长最小均方算法的心电图信号去噪[J].中国医学物理学杂志,2023,40(9):1135-1142.[doi:DOI:10.3969/j.issn.1005-202X.2023.09.013]
　ZHANG Wei,GU Xuan,LIANG Fue,et al.ECG signal denoising using improved variable step size least mean square algorithm[J].Chinese Journal of Medical Physics,2023,40(9):1135-1142.[doi:DOI:10.3969/j.issn.1005-202X.2023.09.013]
点击复制

基于改进变步长最小均方算法的心电图信号去噪()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
40卷
期数:
2023年第9期
页码:
1135-1142
栏目:
医学信号处理与医学仪器
出版日期:
2023-09-26

文章信息/Info

Title:
ECG signal denoising using improved variable step size least mean square algorithm
文章编号:
1005-202X（2023）09-1057-08
作者:
张伟; 顾旋; 梁富娥; 吕珊珊; 刘东华
甘肃中医药大学信息工程学院， 甘肃 兰州 730100
Author(s):
ZHANG Wei;  GU Xuan;  LIANG Fue;  L?Shanshan;  LIU Donghua
College of Information Engineering, Gansu University of Chinese Medicine, Lanzhou 730100, China
关键词:
心电图信号; 噪声; 最小均方算法; 收敛速度; 稳态误差
Keywords:
Keywords: electrocardiogram signal noise least mean square algorithm convergence speed steady-state error
分类号:
R318；TN911.7
DOI:
DOI:10.3969/j.issn.1005-202X.2023.09.013
文献标志码:
A
摘要:
针对定步长和现有变步长最小均方（LMS）自适应滤波算法对心电图（ECG）信号去噪效果较差的问题，提出一种基于分式函数改进的变步长LMS算法。首先利用分式函数构造出改进的变步长LMS算法的步长函数式，通过理论和仿真分析得到该算法参数的最佳取值，并在相同条件下与定步长和其他变步长LMS算法进行性能对比，验证了该算法具有更快的收敛速度、更低的稳态误差和更小的计算复杂度。然后将该算法与定步长和其他变步长LMS算法在相同条件下对含多种真实噪声的ECG信号进行去噪效果对比。实验结果表明，相比于其他算法，该算法能更好地去除ECG信号的噪声，且去噪后ECG信号的信噪比最大，均方误差最小，Pearson相关系数最接近于1。
Abstract:
An improved variable step size least mean square (LMS) algorithm based on fractional function is proposed to solve the problem of the poor denoising performances of the fixed step size and the existing variable step size LMS adaptive filtering algorithms on electrocardiogram (ECG) signals. The fractional function is used to construct the step function of the improved variable step size LMS algorithm, and the optimal parameter values of the algorithm are obtained through theoretical and simulation analyses. The performance comparison with the fixed step size and other variable step size LMS algorithms under the same conditions verifies that the proposed algorithm has faster convergence speed, lower steady-state error and less computational complexity. Moreover, the proposed algorithm is compared with the fixed step size and other variable step size LMS algorithms on ECG signals containing multiple real noises under the same conditions. The experimental results show that compared with the other algorithms, the proposed algorithm can better remove the noise in ECG signals, and that the denoised ECG signals have the largest signal-to-noise ratio and the minimum mean square error, with a Pearson correlation coefficient closest to 1.

相似文献/References:

[1]郑庆增,鞠忠建,邵莹,等. 模拟定位CT的机型及扫描参数对CT值和噪声的影响[J].中国医学物理学杂志,2017,34(5):439.[doi:DOI:10.3969/j.issn.1005-202X.2017.05.002]
[2]李倩,王飞,刘芊,等.心冲击图信号的采集和特征分析及其应用[J].中国医学物理学杂志,2020,37(1):83.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.017]
　LI Qian,WANG Fei,LIU Qian,et al.Acquisition, feature analysis and application of ballistocardiogram signals[J].Chinese Journal of Medical Physics,2020,37(9):83.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.017]
[3]顾旋,张伟,吕珊珊,等.基于改进小波阈值算法的ECG肌电信号去噪研究[J].中国医学物理学杂志,2023,40(2):212.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.015]
　GU Xuan,ZHANG Wei,L?Shanshan,et al.An improved wavelet threshold algorithm for cancelling EMG signal from ECG signal[J].Chinese Journal of Medical Physics,2023,40(9):212.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.015]
[4]洪启帆,玄祖兴,李雅馨.基于全卷积神经网络的低剂量CT去噪算法[J].中国医学物理学杂志,2023,40(6):695.[doi:DOI:10.3969/j.issn.1005-202X.2023.06.005]
　HONG Qifan,XUAN Zuxing,LI Yaxin.Fully convolutional neural network based algorithm for low-dose CT image denoising[J].Chinese Journal of Medical Physics,2023,40(9):695.[doi:DOI:10.3969/j.issn.1005-202X.2023.06.005]

备注/Memo

备注/Memo:
【收稿日期】2023-03-11 【基金项目】甘肃省教育厅创新基金（2022B-113）；甘肃中医药大学研究生创新基金（2022CX81） 【作者简介】张伟，副教授，研究方向：医学信号处理、医学图像处理， E-mail: 27670934@qq.com；顾旋，硕士，研究方向：生物医学信号处理，E-mail: guxuan_2020@163.com
更新日期/Last Update: 2023-09-26