噪声环境下起搏心电信号的压缩感知重构算法

发布时间：2018-06-20 04:49

  本文选题：压缩感知 + 起搏心电信号　； 参考：《计算机工程与应用》2017年18期

【摘要】：针对传统压缩感知重构算法在起搏心电信号远程监测过程中易受噪声干扰的问题,提出在利用正交匹配追踪进行残差更新的迭代过程中引入岭回归正则化参数K,降低噪声对重构结果的影响。利用岭迹法证明了最佳K值与信噪比呈负相关,为选取K值以获得更接近真实解的重构信号提供了理论依据。对基于岭回归的重构算法与分块稀疏贝叶斯学习算法、正交匹配追踪算法进行了对比分析,实验结果表明,在低信噪比环境下,引入了岭回归思想的算法在保留高重构效率的同时提高了重构精度。
[Abstract]:In view of the problem that the traditional compression sensing reconstruction algorithm is prone to noise interference in the remote monitoring of the pacemaker signal, the ridge regression regularization parameter K is introduced in the iterative process of residual updating using orthogonal matching tracking to reduce the effect of noise on the reconstruction results. The ridge trace method is used to prove that the best K value and the signal to noise ratio are negative phase In order to select the K value to obtain the refactoring signal which is closer to the real solution, the reconstruction algorithm based on ridge regression and the block sparse Bayesian learning algorithm and the orthogonal matching tracking algorithm are compared. The experimental results show that the algorithm of ridge regression thinking is reserved for high reconstruction efficiency under the environment of low signal to noise ratio. At the same time, the precision of reconstruction is improved.
【作者单位】： 重庆理工大学计算机科学与工程学院;
【基金】：国家自然科学基金(No.61502064) 重庆市自然科学基金(No.cstc2011jj A40002) 重庆市教委科学技术研究项目(A类)(No.KJ110813)
【分类号】：R540.4;TN911.7
，

本文编号：2043026