Title :
QRS detection based on hidden Markov modeling
Author :
Cost, A.A. ; Cano, Gerald G.
Author_Institution :
Allegheny Singer Res. Inst., Pittsburgh, PA, USA
Abstract :
An experiment is described to investigate the application of hidden Markov modeling (HMM) to QRS detection. Previously reported detection algorithms employ decision rule stages which require specification and adjustment of numerous parameters for adequate detection accuracy. The hidden Markov modeling approach provides automatic estimation of all parameters in the decision rule stage from each ECG file undergoing analysis. Preliminary results using a simple HMM detector show performance comparable to that of a multiparameter threshold based decision rule scheme
Keywords :
Markov processes; electrocardiography; physiological models; QRS detection; detection accuracy; detection algorithms; hidden Markov modeling; multiparameter threshold based decision rule scheme; Algorithm design and analysis; Band pass filters; Cardiology; Detection algorithms; Detectors; Electrocardiography; Hidden Markov models; Parameter estimation; Signal analysis; Speech analysis;
Conference_Titel :
Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century., Proceedings of the Annual International Conference of the IEEE Engineering in
Conference_Location :
Seattle, WA
DOI :
10.1109/IEMBS.1989.95558
