Wavelet-based variational Bayesian ECG denoising
Hamidreza R. Amindavar, Fateme Naraghi · 2017
Electrocardiogram is an important biomedical signal for analysing the electrical activity of the heart during its contraction and expansion. The analysis of Electrocardiogram becomes difficult if noise is augmented to the signal during acquisition. In this paper, the wavelet-based variational Bayesian estimation theory for signal denoising is used. Non-stationary signals such as Electrocardiogram can be represented as a model through their wavelet coefficients. In this method, we assume the mixture of normal matrix distribution over the noisy wavelet coefficients and the variational Bayesian Expectation Maximization algorithm is implemented on the wavelet coefficient distribution. The experimental results show that the proposed technique successfully denoised the noisy Electrocardiogram signals. Finally, the signal-to-noise ratio and mean square error were also evaluated.