Related Experiment Video
Updated: Jul 7, 2026
08:10
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Model-based fiducial points extraction for baseline wandered electrocardiograms
Omid Sayadi1, Mohammad B Shamsollahi
1Biomedical Signal and Image Processing Laboratory (BiSIPL), Electrical Engineering Department, Sharif University of Technology, Tehran, Iran. osayadi@ee.sharif.edu
IEEE Transactions on Bio-Medical Engineering
|February 1, 2008
Summary
This study introduces a fast algorithm for precise electrocardiogram (ECG) characteristic point extraction, effectively removing baseline drift using adaptive bionic wavelet transform for improved accuracy.
Area of Science:
- Biomedical Signal Processing
- Cardiovascular Technology
- Computational Physiology
Background:
- Electrocardiogram (ECG) signal analysis is crucial for diagnosing cardiac conditions.
- Baseline wander and waveform variations complicate accurate ECG feature extraction.
- Existing methods struggle with precise fiducial point detection in noisy ECG signals.
Purpose of the Study:
- To develop a fast, model-based algorithm for precise ECG characteristic point extraction.
- To effectively remove baseline drift from ECG signals.
- To improve the accuracy of fiducial point detection in complex ECG signals.
Main Methods:
- A nonlinear dynamical model for ECG signal analysis was employed.
- Adaptive bionic wavelet transform was utilized for efficient baseline wander removal.
- A model-based approach with Gaussian functions determined fiducial points by minimizing least square error.
Main Results:
- The proposed method achieved high performance in simulations.
- Average sensitivity reached 99.58%.
- Average detection accuracy was 99.64%, with 100% specificity.
Conclusions:
- The developed algorithm accurately extracts ECG characteristic points even with baseline drift.
- Adaptive bionic wavelet transform enhances baseline wander cancellation.
- The model-based approach provides a robust solution for precise ECG fiducial point detection.
