An electrocardiogram (ECG) pattern recognition technique is presented based on identification of significant points (SPs) in the waveform and classifications of beats by relational matching between beats and stored templates. The SPs in the waveforms are determined by calculating curvatures and by seeking SPs with maximum local curvature. The pattern matching is carried out by calculating a correlation function between the SPs of each beat under consideration and stored templates. Studies with actual ECG signals show that this method is suitable for automatic classification of complex beat patterns.
|Original language||English (US)|
|Number of pages||4|
|State||Published - Dec 1 1986|
ASJC Scopus subject areas