Abstract
This paper presents the comparison between two electrocardiogram (ECG) classification systems which are based on the Dynamic Time Warping (DTW) and K-means algorithms. The DTW has been chosen due to this capacity to align beats of different lengths by a non linear time warping. K-means is a classical self-organizing algorithm very popular in ECG applications because it can cluster efficiently signals by making comparisons among them. The two systems are based on a non supervised approach which divides the heart beats of an ECG recording in two different classes. Experiments were carried out using 34 two-channel recordings of the MIT-BIH Arrhythmia Database. Both systems have shown a very good performance in terms of sensitivity and positive predictivity measures. However, the system based on the DTW has presented some important advantages, since it carries out a full automatic classification, without requiring the manual labeling, and operates on-line, allowing patient monitoring with alarms for cases of arrhythmia.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Referências
Chazal, P. (2004) “Automatic Classification of the Heartbeats Using ECG Morphology and Heartbeat Interval Features”, IEEE Transactions on Biomedical Engineering, v. 18, i. 3, p. 1996–1206, July.
Osowski, S.; Linh, T. H. (2001). ECG Beat Recognition Using Fuzzy Hybrid Neural Network, IEEE Transactions on Biomedical Engineering, v. 48, n. 11, p. 1265–1271.
Andreão, R.; Dorizzi B.; Boudy, J. (2006). ECG Signal Analysis Through Hidden Makiov Models, IEEE Transactions on Biomedical Engineering, v. 53, no. 8, p. 1541–1549.
Wang, K.; Gasser, T. “Synchronizing Sample Curves Non-Parametrically”, The Annals of Statistics, 27, pp. 439–460, 1999.
Huang, B.; Kinser, W. (2002) “ECG Frame Classification Using Dynamic Time Warping”, In: Canadian Conference on Electrical & Computer Engineering of the IEEE, Canada, p. 1105–1110, May.
Aguiar, R; Andreão, R.; Bastos, T.: Classificação Automática e Não Supervisionada de Sinais de Eletrocardiograma, CBEB, XX Congresso Brasileiro de Engenharia Biomédica, São Paulo, Brasil, 2006, pp 375–378
Moody, G., Mark, R., Goldberger, A. (2001) “PhysioNet: A Web-Based Resource for the Study of Physiologic Signal”, In: IEEE Engineering in Medicine and Biology, Istanbul, p. 70–75, 25–28 Oct.
ANSI/ AAMI (1998) “Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms”, ANSI/AANI EC 57-293, Arlington, p. 37.
Coast, D., Stern, R. (1990) “An Approach to Cardiac Arrhythmia Analysis Using Hidden Markov Models”, IEEE Transactions on Biomedical Engineering, v. 37, i. 9, p. 826–836, Sep.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
de Aguiar, R.O., Andreão, R.V., Bastos Filho, T.F. (2007). Análise de Diferentes Técnicas de Classificação Não-Supervisionada de Batimentos Cardíacos. In: Müller-Karger, C., Wong, S., La Cruz, A. (eds) IV Latin American Congress on Biomedical Engineering 2007, Bioengineering Solutions for Latin America Health. IFMBE Proceedings, vol 18. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74471-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-74471-9_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74470-2
Online ISBN: 978-3-540-74471-9
eBook Packages: EngineeringEngineering (R0)