期刊名称：International Journal of Electronics and Computer Science Engineering
电子版ISSN：2277-1956
出版年度：2014
卷号：3
期号：1
页码：44-50
出版社：Buldanshahr : IJECSE
摘要：The adaptive filtering techniques for various noises removal on Electrocardiogram signals (ECGs) have shown best performances with significant Mean Squared Error (MSE) results in comparison to the non adaptive filters. We present in this paper a comparative performance analysis of MATLAB simulations on a set of nonlinear adaptive filters applied on a sample ECG signal from the MIT database. The nonlinear filters are a class of mixed average – median filters able to switch between several modes of operation according to the random and/or the impulse nature of the noise that interferes with the ECG signal. As results, sequences of the statistical characteristics of the mixed noise where the minimum MSE of one of the mixed filter of the set is better than the others and the average and the median filters taken separately are presented, optimal adaptive parameters of the mixed filters are also given
关键词：Nonlinear Adaptive Filter; Mixed Average-Median Filter; MSE; ECG signal
