Online Kernel AMGLVQ for Arrhythmia Hearbeats Classification

Elly Matul Imah, R. Sulaiman


This study proposes Online Kernel Adaptive Multilayer Generalized Learning Vector Quantization (KAMGLVQ) for handling imbalanced data sets. KAMGLVQ is extended version of AMGLVQ that used kernel function to handling non-linear classification problems. Basically AMGLVQ is vector quantization based learning. The vector quantization based learning is very simple algorithm that can be applied to the multiclass problem and the complexity of LVQ can be controlled during training process. KAMGLVQ works at online kernel learning system that integrating feature extraction and classification. The architecture network of KAMGLVQ consists of three layers, input layer, hidden layer, and an output layer. The hidden layer of KAMGLVQ is adaptive; this algorithm will generate a number of hidden layer nodes. The algorithm implement on real ECG signals from the MIT-BIH arrhythmias database and synthetic data. The experiments showed that KAMGLVQ able improve the accuracy of classification better than SVM or back-propagation NN; also able to reduce the time computational cost.


KAMGLVQ, SVM, Backpropagation, arrhythmia, ECG, imbalanced data set

Full Text:



S. García and F. Herrera, “Evolutionary undersampling for classification with imbalanced datasets: proposals and taxonomy.,” Evolutionary computation, vol. 17, no. 3, pp. 275-306, Jan. 2009.

B. X. Wang and N. Japkowicz, “Boosting support vector machines for imbalanced data sets,” Knowledge and Information Systems, vol. 25, no. 1, pp. 1-20, 2009.

N. Japkowicz, “Learning from Imbalanced Data Sets : A Comparison of Various Strategies,” in Proc. Am. Assoc. for Artificial Intelligence (AAAI) Workshop, 2000, vol. 68.

C. Vivaracho-pascual and A. Simon-hurtado, “Improving ANN performance for imbalanced data sets by means of the NTIL technique,” IEEE International Join Conference on Neural Networks (IJCNN), 2010.

E. M. Imah, W. Jatmiko, and T. Basaruddin, “Adaptive multilayer generalized learning vector quantization (amglvq) as a new algorithm with integrating feature extraction and classification for arrhythmia heartbeats classification,” in IEEE international Conference on System Man and Cybernetics, Seoul 2012, 2012.

A. Sato and K. Yamada, “Generalized Learning Vector Quantization,” in Advances in Neural Information Processing Systems 8 Proceedings of the 1995 Conference, 1996, vol. 7, pp. 423-429.

T. Kohonen, “Learning-Vector Quantization and the Self-Organizing Map,” in Theory and Applications of Neural Networks, 1992, pp. 235-242.

F.-michael Schleif, T. Villmann, B. Hammer, P. Schneider, and M. Biehl, “Generalized derivative based kernelized Learning Vector Quantization,” Springer, Intelligent Data Engineering and Automated Learning – IDEAL 2010 Lecture Notes in Computer Science, vol. 6283, pp. pp 21-28, 2010.

K. Marika, B. Hammer, M. Biehl, and T. Villmann, “Neurocomputing Functional relevance learning in generalized learning vector quantization,” vol. 90, pp. 85-95, 2012.

E. Matul I., I. M. A. Setiawan, a. Febrian, and W. Jatmiko, “Arrhythmia heart beats classification using mahalanobis Generalized Learning Vector Quantization (Mahalanobis GLVQ),” 2011 International Symposium on Micro-NanoMechatronics and Human Science, pp. 355-360, Nov. 2011.

E. M. Imah, F. Al Afif, M. Ivan Fanany, W. Jatmiko, and T. Basaruddin, “A comparative study on Daubechies Wavelet Transformation, Kernel PCA and PCA as feature extractors for arrhythmia detection using SVM,” in TENCON 2011-2011 IEEE Region 10 Conference, 2011, pp. 5–9.

W. Jatmiko, W. P. Nulad, E. M. I, and I. M. A. Setiawan, “Heart Beat Classification Using Wavelet Feature Based on Neural Network,” vol. 10, no. 1, pp. 17-26, 2011.

F. Sufi and I. Khalil, “Diagnosis of cardiovascular abnormalities from compressed ECG: a data mining-based approach.,” IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society, vol. 15, no. 1, pp. 33-9, Jan. 2011.

P. Tadejko and W. Rakowski, “Mathematical morphology based ECG feature extraction for the purpose of heartbeat classification Faculty of Computer Science,” 6th International Conference on Computer Information System and Industrial Management Application (CISIM’07), 2007.

E. Sadat, H. Rooteh, Y. Zhang, and Z. Tian, “Comparison of Parallel and Single Neural Networks in Heart Arrhythmia Detection by Using ECG Signal Analysis,” in PHM, 2011, pp. 1-9.

G. de L. D. Francois, J. Delbeke and and M. Verleysen, “Weighted SVMs and Feature Relevance Assessment in Supervised Heart Beat Classification,” Commun. Comput. Inf. Sci., vol. vol. 127, pp. 212–225, 2011.

G. de Lannoy, D. Francois, J. Delbeke, and M. Verleysen, “Weighted conditional random fields for supervised interpatient heartbeat classification,” IEEE Transactions on Biomedical Engineering, vol. 59, no. 1, pp. 241-7, Jan. 2012.

A. L. Goldberger et al., “PhysioBank, PhysioToolkit, and PhysioNet,” Circulation, vol. 101, no. 23, p. 215, 2000.

Luz, E., et all.," ECG-based heartbeat classification for arrhythmia detection: A survey", Computer Methods and Programs in Biomedicine, Vol 127, Pages: 144–164, 2016.

J. Weng, Cheng G, Poon, “A New Evaluation Measure for Imbalanced Datasets,” in Seventh Austraasian Data Mining Conference (AusDM 2008), 2008.



  • There are currently no refbacks.

    Informatika - UTM