Clasification Of Arrhythmic ECG Data Using Machine Learning Techniques
DOI:
https://doi.org/10.9781/ijimai.2011.1411Keywords:
ECG arrhythmia, Sensitivity, Specificity, Accuracy, Artificial Neural NetworksAbstract
In this paper we proposed a automated Artificial Neural Network (ANN) based classification system for cardiac arrhythmia using multi-channel ECG recordings. In this study, we are mainly interested in producing high confident arrhythmia classification results to be applicable in diagnostic decision support systems. Neural network model with back propagation algorithm is used to classify arrhythmia cases into normal and abnormal classes. Networks models are trained and tested for MIT-BIH arrhythmia. The differen structures of ANN have been trained by mixture of arrhythmic and non arrhythmic data patient. The classification performance is evaluated using measures; sensitivity, specificity, classification accuracy, mean squared error (MSE), receiver operating characteristics (ROC) and area under curve (AUC). Our experimental results gives 96.77% accuracy on MIT-BIH database and 96.21% on database prepared by including NSR database also.Downloads
References
[1] E Rumelhart, G. E Hinton, and Williams R. J. Hinton, “Learning internal representations by error propagation. In Parallel distributed Processing: explorations in the microstructure of cognition,” MIT Press
[2] MIT-BIH ECG Arrhythmia Datahase, Availahle Beth Israel Hospital,Biomedical Engineering Division Room, KB-26, 330 Brookline Ave.,Boston MA 022 1.5
[3] T. H. Yap, F, Johnson, and M. Rachniowski, “ECG beat classification by a neural networks,” In Pedmn PC, OnaralB (eds): Proc. of the Annual International Conference of the IEEE Eng. of Med. and Biology Society, 12, pp.1457, 1990.
[4] Y. S. Tsai, B. N. Hung, and S. F. Tung, “An experiment on ECG classification using back-propagation neural networks,” In Pederson PC, Onaral B(eds): Proceedings of the Annual International Conference of the IEEE Eng. of Med. and Biology Society, 12, pp. 1463, 1990.
[5] D. E Rumelhart, G. E Hinton, and Williams R. J. Hinton, “Learning internal representations by error propagation. In Parallel distributed Processing: explorations in the microstructure of cognition,” MIT Press Camhridge, Massachusetts, J. L., 1, pp. 3 18462,1986.
[6] Y. Ozhay, “Fast Recognition of ECG Arrhythmias,” Ph.D. Paper, University of Selcuk, Konya, Turkey, 1999.
[7] Bortolan, G. Jekova, I. Christov, “Comparison of four methods for premature ventricular contraction and normal beat clustering,” Computers in Cardiology, September 2005 pp. 921 – 924
[8] Dayong Gao, Michael Madden, “Bayesian ANN Classifier for ECG Arrhythmias Diagnostic System,” Proceeding of IEEE International Joint Conference on Neural Network 2003 pp. 2454-2459.
[9] T. J. Downey, D. J. Meyer, and R. K. Price, “Using the receiver operating characteristic to assess the performance of neural classifiers,” in IEEE, 1999, pp. 3642 – 3 646 103.
[10] T. Fawcett, “ROC graphs: Note and practical considerations for data mining,” in Researchers, HP Labs Technical Report (HPL-2003- 4),2003.
[11] J. C. Principe, V. Euliano, and W. C. Lefebvre, Neural and Adaptive Systems: Fundamentals Through Simulations. John Wiley & Sons, Inc., 2000.
[12] D. Gao and M. Madden, “Bayesian ANN classifier for ECG arrhythmias diagnostic system,” in Proceeding of IEEE International Joint Conference on Neural Network, 2003, pp. 2454–2459.
[13] N. V. Thakor and Y. S. Zhu, “Applications of adaptive filtering to ECG analysis: Noise cancellation and arrhythmia detection,” in Biomedical Engineering, 1991, pp. 785–794.
[14] B. Anuradha and V. C. Veera Reddy , “ANN FOR CLASSIFICATION OF CARDIAC ARRHYTHMIAS” in ARPN Journal of Engineering and Applied Sciences, vol. 3, no. 3, june 2008.
Downloads
Published
-
Abstract52
-
PDF23
Submit Article
Information
