An Improved ECG Segmentation Method Based on Adaptive Hermite Functions

Electrocardiograms (ECGs), which are recordings of the electrical activity of the heart with electrodes placed on the body, have many clinical applications. Each phase of the heart's mechanical function is represented by one of the P, QRS, and T waves in the ECG. The change in the morphological characteristics of these waves compared to the normal state can be used to diagnose cardiac functional abnormalities. Therefore, developing algorithms that can automatically extract these waves from the ECG signal with high accuracy is of high diagnostic importance. In this paper, an adaptive method is presented to estimate the shape of each heartbeat individually. The proposed algorithm is based on the improvement of previous studies. It tries to get a more accurate estimate of ECG waves by including the ST segment model in the ECG signal model. Simulation results on experimental data show that the proposed method outperforms previous similar algorithms.