Applying Non Linear Approach for ECG Denoising and Waves Localization

In this paper, we develop and evaluate a robust single-lead electrocardiogram (ECG) delineation systemand waves localization method based on nonlinear filteringapproach. This system is built in two phases. In the firstphase, we proposed a mathematical model for detectingECG features like QRS complex peak, P and T-wavesonsets and ends from noise free of synthetic ECG signal. Later, we develop a theoretical model to obtain real approach for detecting these features from real noisy ECGsignals. To evaluate our method, it has been applied onelectrocardiogram signals of QT-MIT standard database, theQRS peak detection obtained sensitivity (Se) 98.88 and apositive productivity P+ =98.43. For P-onset, P-end, T-endevaluations, this approach provides Sensitivity (Se) of 75.16,71, and 90.7 respectively. Another test has been conducted toevaluate the performance of this approach against differentlevels of noise with the same synthetic ECG signal. Fordenoising test on electrocardiogram signals, our approachbased on nonlinear filtering scheme (NLFS) gives robustperformance against noise.