Efficient Adaptive Method for ECG Noise Elimination

Electrocardiogram (ECG) signals play an essential role in cardiovascular disease diagnosis. However, ECG signals frequently encounter contamination from various noises, such as additive white Gaussian noise, muscle artifact, and baseline wander, which alters the ECG signal and can result in misdiagnosis. This paper introduces a robust method for efficiently removing noise from ECG signals utilizing an adaptive noise canceller (ANC) based on the gases Brownian motion optimization (GBMO) algorithm. The suggested approach dynamically modifies the filter coefficients according to the input signal and noise characteristics, making it more effective and efficient than traditional methods. The results show that the suggested ANC surpasses other state-of-the-art noise removal techniques in terms of standard performance metrics.