IJMTES – EFFECTIVE VENTRICULAR FIBRILLATION DETECTION USING FEATURE EXTRACTION AND NEURAL NETWORKS

Journal Title : International Journal of Modern Trends in Engineering and Science

Author’s Name : Karthika V S | Aswathy Madhu

Volume 02 Issue 12  Year 2015 

ISSN no: 2348-3121

Page no: 13-17

Abstract Early detection of cardiac pathologies is crucial for the success of the defibrillation therapy. A wide variety of detection algorithms have been proposed based on temporal, spectral or complexity parameters extracted from the ECG. However, these algorithms are mostly constructed by considering each parameter individually. This study presents a novel life-threatening cardiac pathology detection algorithm that combines ECG parameters to a single feature vector and classifies using machine learning techniques. A total of 16 ECG parameters were computed accounting for morphological, spectral, complexity features and statistical measures of the ECG signal. A wavelet based feature extraction for statistical parameters was proposed to analyze, how they affect the detection performance. The proposed methodology was evaluated in the scenario, VF versus non-VF rhythms using the information contained in the medical imaging technology database. The combination of ECG parameters using statistical learning algorithms may improve the detection efficiency of life-threatening cardiac pathologies.

Keywords— Feature extraction; Ventricular fibrillation(VF) detection; Wavelet; Neural Networks

Reference

[1] Felipe Alonso-Atienza,Eduardo Morgado, Lorena Fernandez-Martinez, Arcadi Garcia-Alberola, and Jose Luis Rojo-Alvarez, ”Detection of Life-Threatening Arrhythmias Using Feature Selection and Support Vector Machines,” IEEE Trans.Biomed. Eng., Vol. 61 PP, No.3, Mar.(2014).
[2] M. Harris, ”A shocking truth” IEEE Spectr., Vol. 49, No. 3, pp. 30-58, Mar. (2012).
[3] F. Alonso-Atienza, J. L. Rojo-Alvarez, A. Rosado-Mun, J. J. Vinagre, and A. Garcia-Alberola, G. CampsValls,”Feature selection using sup-port vector machines and bootstrap methods for ventricular fibrillation detection,” Expert Syst. Appl., Vol. 39, No. 2, pp. 1956- 1967, (2012).
[4] F. Alonso-Atienza, E. Morgado, L. Fernandez-Martinez, A. Garcia-Alberola, and J. Rojo-Alvarez, ” Combination of ECG parameters with support vector machines for the detection of life-threatening arrhythmias,” in Proc. Comput. Cardiol., pp. 385-388,(2012).
[5] U. Irusta, J. Ruiz, E. Aramendi, S. R. de Gauna, U. Ayala, and E. Alonso, ”A high-temporal resolution algorithm to discriminate shockable from nonshockable rhythms in adults and children,”Resuscitation, Vol. 83, No. 9, pp. 1090-1097, (2012).
[6] Y. Li, J. Bisera, M.Weil, and W. Tang, ”An algorithm used for ventric-ular fibrillation detection without interrupting chest compression,” IEEE Trans.Biomed. Eng., Vol. 59, No. 1, pp. 78-86, Jan. (2012).
[7] M. Arafat, A. Chowdhury, and M. Hasan, ”A simple time domain algo-rithm for the detection of ventricular fibrillation in electrocardiogram,” Signal, Image Video Process., Vol. 5, pp. 1-10, (2011).
[8] J. L. Rojo Alvarez, G.Camps Valls, and A.J.Caamano Fernandez, J.F.Guerrero Martinez, ”A review of kernel methods in ECG signal clas-sification, in ECG Signal Processing”, ”Classification and Interpretation: A Comprehensive Framework of Computational Intelligence” A.Gacek and W.Pedrycz,Eds. Berlin, Germany:Springer-Verlag, (2011).
[9] E. Anas, S. Lee, and M. Hasan, ”Sequential algorithm for life threatening cardiac pathologies detection based on mean signal strength and emd functions,” BioMed. Eng. OnLine, Vol. 9, No. 1, (2010).

Full Pdf Paper: Click Here

 

Scroll Up