A NOVEL AUTOMATIC CARDIAC AUSCULTATION WITH HYBRID ANT COLONY OPTIMIZATION-SVM CLASSIFICATION

Prasertsak  Charoen; Khamin  Subpinyo; Waree  Kongprawechnon

Authors

Prasertsak Charoen Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand.
Khamin Subpinyo Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand.
Waree Kongprawechnon Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand.

Keywords:

Support vector machine, Ccardiac auscultation, Aant colony optimization, Mmachine learning

Abstract

Cardiac auscultation is a method to examine the condition of a heart using a stethoscope. Since the method requires expertise, which is rare in suburban rural areas, to analyze the condition of a heart, an automatic cardiac auscultation system is introduced with the use of a machine learning technique to eliminate the need of for expertise. In this paper, we develop a classification model based on a support vector machine (SVM) and ant colony optimization (ACO) for an automatic cardiac auscultation system. The proposed method uses ACO to further select heart sound features, resulting from the initial feature selection by principleprincipal component analysis (PCA), and uses them to train the SVM for classification. Experimental results show that the proposed ACO/SVM technique is able to give higher classification accuracy on heart sound samples, compared to with a traditional SVM and a genetic algorithm (GA) -based SVM.

References

Aghdam, H.M., Ghasem-Adhaee, N., and Basiri, E.M. (2008). Text feature selection using ant colony optimization. Expert Syst.ems with Applications;., Vol. 36, Issue (3), Part 2,: p. 6,843–-6,853.

AhmedAl-Ani, A. (2007). Ant Ccolony Ooptimization for feature subset selection. International Journal of Computer, Electrical, Automation, Control, Quantum and Information Engineering;, Vol.1, No.(4).:999-1,002.

Banpavivhit, S., Kongprawechnon, W., and Tungpimolrut, K. (2013). Cardiac Aauscultation with Hhybrid GA/SVM. Proceedings of the 9th International Conference on Computing and Information Technology (IC2IT2013); May 9-10, 2013; Bangkok, Thailand, Vol. 209, p. 185-194.

Bunluechokchai, C. and, Ussawawongaraya, W. (2009). A wavelet-based factor for classification of heart sounds with mitral regurgitation. International Journal of Applied Biomedical Engineering, Vol.2, No.(1):44-48.

Burges, C. (1998). A tutorial on support vector machines for pattern recognition. Data Min.ing and Knowl. edge Discovery., vol. 2, no. (2):121-167.

Chatunapalak, I., Phatiwuttipat, P., Kongprawechnon, W., and Tungpimolrut, K. (2012). Childhood musical murmur classification with support vector machine technique. Proceedings of the 9th International Conference on Electrical Engineering/ Electronics, Computer, Telecommunications and Information Technology; May 16-18, 2012; Petchaburi, Thailand, p. 1-4.Sirindhorn Inter-national Institute of Technology, Thammasat University, Pathum Thani, Thailand.

Chebil, J., and Al-Nabulsi, J. (2007). Classification of heart sound signal using discrete wavelet analysis. International Journal of Soft Computing, 2(1),: p. 37-41.

Gupta, C.N., Palaniappan, R., Swaminathan, S., and Krishnan, S.M. (2007). Neural network classification of homomorphic segmented heart sounds. Appl. Soft Comput., 7(1):286-297. Biomedical Engineering Research Center, Nanyang Technological University, Singapore.

Kabir, M., Shahjahan, M., and Murase, K. (2013). Ant colony optimization toward feature selection. In: Ant Colony Optimization - Techniques and Ap plications. Barbosa, H., (Eed.). InTech, Rijeka, Croatia, DOI: 10.5772/51707.

Majdi, M., and Eleyan, D. (2013). Ant colony optimization based feature selection in rough set theory. International Journal of Computer Science and Electronics Engineering, (IJCSEE); Vol. 1, Issue (2):244-247.

Murase, K., Monirul, K., Shahjahan, M. (2013). Ant Colony Optimization toward Feature Selection. Ant Colony Optimization - Techniques and Applications, Dr. Helio Barbosa (Ed.), InTech, DOI: 10.5772/51707.

Phatiwuttipat, P., Kongprawechnon, W., and Tungpimolrut, K. (2011). Cardiac auscultation analysis system with neural network and SVM technique. Proceedings of the 8th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology Conference (ECTI-CON); May 17-19, 2011; Khonkaen, Thailand, p. 1,027-1,030.

Vapnik, V.N. N. (1998). Statistical Learning Theory, New York: Wiley, Hoboken, NJ, USA, 768p.