Electrocardiogram Reconstruction Based on Compressed Sensing

Abstract

Compressed Sensing (CS) attempts to acquire and reconstruct a sparse signal from a sampling much below the Nyquist rate. In this paper, we proposed novel CS algorithms for reconstructing under-sampled and compressed electrocardiogram (ECG) signal. In the proposed CS-ECG scheme, the ECG signal was first sub-sampled randomly and mapped onto a two-dimensional (2D) space by using Cut and Align (CAB), for the purpose of promoting sparsity. A nonlinear optimization model was then used to reconstruct the 2D signal. In the compression scheme, the ECG signal was mapped into the frequency domain, and the compression was achieved by a series of multiplying and accumulating between the original ECG and a Gaussian random matrix. For the reconstruction, two matching pursuits (MP) methods and two blocks sparse Bayesian learning (BSBL) methods were implemented and evaluated by the percentage rootmean-square difference (PRD). Based on the test with real ECG data, it was found that the proposed CS scheme was capable of faithfully reconstructing ECG signals with only 30% acquisition.INDEX TERMS Compressed sensing (CS), compression, electrocardiogram (ECG), reconstruction, subsampling.

Comparative Study of Compressed Sensing for Heart Sound Acquisition in Wireless Body Sensor Networks

“…4can be roughly divided into convex optimization, greedy pursuit, and iterative thresholding. In specific, the widelyused reconstruction algorithms include Orthogonal Matching Pursuit (OMP), Basis Pursuit (BP), Compressive Sampling Matching Pursuit (CoSaMP), iteratively reweighted least squares (Irls), and subspace pursuit (SP) [12], [22], [30]. The performance of these reconstruction algorithms for ECG acquisition has been investigated in [8].…”

“…The benchmarks in various aspects require more numerical support. For example, the BSBL is originally developed for ECG acquisition [22] yet it is introduced in [27] as a compared algorithm. If we can use open accessible HS data sets, and find the most suitable sparsifying basis and reconstruction algorithm from the common candidates, then they can be referred as benchmarks in the future academic research.…”

“…It has been proposed by Zhang et al [20] and Polania and Barner [21] that using CS for electrocardiograph (ECG) signals had good reconstruction quality and can be well applied to the design of WBSN. In [22], Zhang et al proposed the block sparse bayesian learning (BSBL) algorithm for reconstructing ECG signals from the CS measurements, and demonstrated that BSBL had remarkable advantages over traditional solutions in terms of accuracy and efficiency. On the other hand, Pant and Krishnan [23] analyzed the reconstruction performance of CS for different QRS complexes, and concluded that the reconstruction performance of CS is related to specific QRS.…”

A Survey on Compressive Sensing: Classical Results and Recent Advancements

“…This problem has demonstrated to revolutionize several real-world applications in both science and engineering disciplines, including but not limited to signal processing, imaging, video processing, remote sensing, communication systems, electronics, machine learning, data fusion, manifold processing, natural language and speech processing, and processing biological signals [70,90,92,96,140].…”

Constrained Backtracking Matching Pursuit Algorithm for Image Reconstruction in Compressed Sensing

“…Compressed sensing (CS) is a technique that reconstructs sparse, compressible signals from under-determined random linear measurements. Over the past few decades, CS has been widely applied to image processing, including image reconstruction [1][2][3][4][5] and acquisition [6][7][8].…”