Title: Combination of multi-component and single-component based electrocardiogram beat detection algorithms

Authors: T. Last, C.D. Nugent, F.J. Owens, D.D. Finlay

Addresses: Gold Coast, 111-08-01 Persiaran Bayan Indah, 11900 Bayan Lepas, Penang, Malaysia. ' School of Computing and Mathematics, University of Ulster, Room 16E18, Jordanstown campus, Shore Road, Newtownabbey, Co. Antrim, BT37 0QB, UK. ' School of Engineering, University of Ulster, Room 05B17, Jordanstown campus, Shore Road, Newtownabbey, Co. Antrim, BT37 0QB, UK. ' School of Computing and Mathematics, University of Ulster, Room 16E16, Jordanstown Campus, Shore Road, Newtownabbey, Co. Antrim, BT37 0QB, UK

Abstract: The accuracy of the beat detector is very important for the overall system performance in computerised processing of the Electrocardiogram (ECG). In the present study we introduce the concept of multi-component based beat detection using Cross Correlation (CC) and Neural Networks (NN) techniques. In addition, a new beat detection algorithm is proposed. A database containing 2966 cardiac cycles was used to validate the approaches. Results have shown the ability of achieving a 7% improvement in detecting individual waveform components. Furthermore, the new approach was able to reduce the number of incorrectly detected waveform components by a factor higher than 15.

Keywords: ECG; electrocardiograms; pattern recognition; PQRST complex detection; computerised electrocardiology; multi-component beat detection; cross correlation; neural networks; cardiac cycles; cardiac abnormalities; heart beat.

DOI: 10.1504/IJBET.2010.032693

International Journal of Biomedical Engineering and Technology, 2010 Vol.3 No.3/4, pp.212 - 232

Published online: 13 Apr 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article