Baseline Wander Correction in ECG by the Empirical Mode Decomposition

The electrocardiogram (ECG) has been widely used for diagnosis purposes of heart diseases. A good quality ECG may help the physicians to easily interpret any physiological or pathological phenomena. However, in real situations, ECG recordings are often affected by several factors that result in the baseline wander. Baseline wander is a low frequency artifact that may be due to respiration or the motion of the patients or the electrodes. A large baseline wander severely limits the utility of the recorded ECG and thus need to be corrected to enable better clinical evaluation. In this paper, we propose a new baseline wander correction method based on the recently developed tool-Empirical Mode Decomposition (EMD). We validate our method by experiments from the MIT-BIH databases and also compare our method with the highpass filtering method. Both qualitative and quantitative results show that the proposed EMD-based method provides very good results.