Removal of Low Frequency Noise from ECG signal using Genetic Algorithm

The Electrocardiogram is commonly used technique for non-invasive analysis of the electrical activity of the heart in real-time. Electrocardiographic signals can be degraded by different types of noises like power-line interference, electrode contact, motion artifacts, muscle contraction, baseline drift, instrumental noise and electrosurgical noise. Baseline noise is low frequency signal caused by the loose connection of electrode and skin. Genetic algorithm is applied to remove this type of noise to get better diagnosis of the signal and observe the results in term of mean square error of the error signal for baseline wander noise. In this paper, the comparison of the results obtained from genetic algorithm and the results obtained from the digital FIR filters are done. To validate this method, the recording of signals from MIT-BIH is used. The examining of the purposed algorithm was conducted in MATLAB environment. Index Terms ECG, Baseline Wander, Genetic Algorithm, Digital Filters, Mean square error. ________________________________________________________________________________________________________