Baseline Wandering Removal by Using Independent Component Analysis to Single-Channel ECG data

Removing baseline wandering from ECG records is one of the first steps for processing signals. Generally baseline wandering produces artifactual data when measuring ECG parameters. In this paper, we show the ability of independent component analysis (ICA) technique in removing baseline wandering from ECG by utilizing single-channel data. For applying ICA to single channel data, multi-channel signals are constructed by adding some delay to original data. For validation the effectiveness of proposed method, we applied ICA to constructed channels derived from each Frank lead in HRECG (high-resolution electrocardiogram) data as a preprocessing step in order to detect ventricular late potentials (VLPs) by Simson´s method. Results derived by our approach were compared with those obtained from traditional high-pass filtering for removing baseline wandering. We found perfect accordance between these two groups of results in detecting VLP positive patients from healthy control subjects.