Automatic detection of ECG wave boundaries using empirical mode decomposition

Automatic detection of the boundaries of ECG characteristic waves with a reasonable accuracy has been a difficult task. This paper presents an algorithm based on empirical mode decomposition (EMD) for automatically locating the waveform boundaries (the onsets and offsets of P, QRS, and T waves) in generalized single lead ECG signals. First, the R peak of each beat is detected from the first three intrinsic mode functions (IMFs) of the EMD analysis of the filtered ECG signal. Next, the onset and offset of each QRS complex are located. The P wave and T wave, relative to each QRS complex, are then identified using a set of higher order IMFs. Our algorithm is tested using the QT database (reference annotated database) and the MIT-BIH arrhythmia database. Examples of detection of the fiducial points and a comparison with the threshold-based detector are presented for the assessment of performance of the algorithm.