Ventricular and Atrial Activity Estimation Through Sparse Ecg Signal Decompositions

Abstract

This paper explores a novel approach for ventricular and atrial activities estimation in electrocardiogram (ECG) signals, based on sparse source separation. Sparse decompositions of ECG over signal-adapted multi-component dictionaries can lead to natural separation of its components. In this work, dictionaries of functions adapted to ventricular and atrial activities are respectively defined. Then, the weighted orthogonal matching pursuit algorithm is used to unmix the two components of ECG signals. Despite the simplicity of the approach, results are very promising, showing the capacity of the algorithm to generate realistic estimations of atrial and ventricular activities.

Atrial Activity Detection through a Sparse Decomposition Technique

“…Once determined the atoms some approaches have been proposed in order to find the respective coefficients [4][10]. Given their properties, the Orthogonal Matching Pursuit Algorithm [12] has been used in this work.…”

Dictionary learning for the sparse modelling of atrial fibrillation in ECG signals

“…Escoda et al applied this to separate AA and VA components [3]. They used a Gabor dictionary for the AA and Gaussian waveforms for the VA. We propose to use the same separation approach with learnt dictionaries to better match the sources.…”

“…In present ICA based approaches, a major gap is that only statistical priors are considered without taking into account the structural nature of signals. A sparsity-based source separation method has also been explored in [3], which used a simple analytical model to represent both the QRST complexes and the fibrillatory waves.…”

Extraction of Desired Signal Based on AR Model with Its Application to Atrial Activity Estimation in Atrial Fibrillation

“…In recent years, there has been considerable interest in the electrical and physiological mechanisms associated with atrial fibrillation (AF) [1][2][3][4]. AF is a relatively common arrhythmia, which occurs when the atria depolarize repeatedly in an irregular uncontrolled manner.…”

“…This approach uses an average of the ventricular QRST complexes which is then subtracted from the wave to determine AA [5]. However, this approach is limited by the small number of VA average templates available for general VA approximation [3]. Recently, methods which utilize blind source separation (BSS) have been developed for extracting AA signals from ECG plots [6][7][8][9][10].…”