/ecg-segmented-beat-modulation-noise-removal

Implementation of the ECG noise removal algorithm using segmented-beat modulation proposed by Agostinelli et al., (2014)

Primary LanguagePythonMIT LicenseMIT

ECG Noise Removal Using Segmented-beat Modulation

This is the Python and MATLAB implementation of the algorithm proposed in the paper:

Agostinelli, Angela, Corrado Giuliani, and Laura Burattini. "Extracting a clean ECG from a noisy recording: a new method based on segmented-beat modulation.". Computing in Cardiology Conference (CinC), 2014. IEEE, 2014.

Full credit goes to the authors.

This technique computes a template based on the median of several cardiac cycles:

Median-based template of a cardiac cycle

Then, it uses this template to reconstruct cardiac cycles of a clean ECG. The duration of these cycles matches that of the corresponding beats in the original (noisy) recording:

ECG comparison

An example ECG signal is included (as a .mat file) for quick testing of the algorithm, which was obtained from the MIT-BIH Polysomnographic Database.