A new model for ECG signal filtering and feature extraction

This work proposes a simplified approach for filtering electrocardiogram (ECG) signal by means of Gaussian Mean Variant Filtering technique and feature extraction procedure using Integrated Peak Analyzer method. The preprocessing stage is confined to signal filtering and smoothening the waveform with the conventional filters like low pass filter, Butterworth filter, Finite impulse (FIR) filter, least mean squares (LMS) filter and the proposed filter. The next stage includes feature extraction procedure using peak estimations of QRS complexes and their pulse transit time (PTT) estimations. For this purpose, a novel model, Integrated Peak Analyzer is used. Finally the obtained results from the proposed methods are compared with the adaptive filters.