Denoising ECG Signals Using Unbiased FIR Smoother and Harmonic State-Space Model

The electrocardiogram (ECG) signals provide information for making decisions about different kinds of heart diseases. During decades various approaches have been developed to denoise ECG data and extract useful features, although further increase in the accuracy is required. In this paper, we view the ECG signal as a quasi periodic process and employ the unbiased finite impulse response (UFIR) smoother on optimal horizons. It is shown that the UFIR smoother applied to a harmonic ECG model performs better than that recently developed for polynomial ECG models. Extensive investigation are provided for diverse ECG data. The results are compared in terms of the mean square error and signal-to-noise ratio.