Compression and analysis of ECG features using optimal polynomial approximations
Résumé
The electrocardiogram (ECG) is a signal reflecting the electrical activity of the heart muscles. Computer processing
of ECG signals has been a very active area of research for decades. All modern recording systems of ECG incorporate compression software, automatic analysis and a guide for interpretation of the signal. The ECG signal is usually modeled
by descriptors to facilitate the automatic analysis. We have proposed in this work, the modeling of the characteristic waves
of ECG signal by the low degree polynomials, prior to compression and automatic analysis. To this end, we have implemented a complex QRS detection algorithm, and the extraction of the characteristics wave or intervals is carried out semi-automatically. Each segment of the extracted signal is then approximated by polynomials of low degrees, so that the error
between the original signal and the approximation polynomial is minimum. Compression consists in keeping a small number of polynomial coefficients to store or transmit the signal, instead of the large amount of samples values. We have obtained very
satisfactory results as regards the compression with very high compression ratio and low values of PRD (Percent Difference
square root). We have also shown that the coefficients from the polynomial approximations can be used for the automatic
analysis of the signal, especially in the estimation of peak values of the waves and determining their concavities. It is possible to
establish correlations between the coefficients of the polynomial approximation and the energy of the signal, and also the spectral congestion of the signal. Similarly, tools of intelligent systems such as artificial neural networks and fuzzy logic may be
associated with the polynomial coefficients for the automatic interpretation of the ECG signal.