{"title":"Wavelet Feature Selection Approach for Heart Murmur Classification","authors":"G. Venkata Hari Prasad, P. Rajesh Kumar","volume":99,"journal":"International Journal of Biomedical and Biological Engineering","pagesStart":315,"pagesEnd":323,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10002123","abstract":"Phonocardiography is important in appraisal of\r\ncongenital heart disease and pulmonary hypertension as it reflects the\r\nduration of right ventricular systoles. The systolic murmur in patients\r\nwith intra-cardiac shunt decreases as pulmonary hypertension\r\ndevelops and may eventually disappear completely as the pulmonary\r\npressure reaches systemic level. Phonocardiography and auscultation\r\nare non-invasive, low-cost, and accurate methods to assess heart\r\ndisease. In this work an objective signal processing tool to extract\r\ninformation from phonocardiography signal using Wavelet is\r\nproposed to classify the murmur as normal or abnormal. Since the\r\nfeature vector is large, a Binary Particle Swarm Optimization (PSO)\r\nwith mutation for feature selection is proposed. The extracted\r\nfeatures improve the classification accuracy and were tested across\r\nvarious classifiers including Na\u00efve Bayes, kNN, C4.5, and SVM.","references":"[1] Roy, D. L. (2003). The paediatrician and cardiac auscultation.\r\nPaediatrics& child health, 8(9), 561.\r\n[2] Donnerstein, R. L., & Thomsen, V. S. (1994). Hemodynamic and\r\nanatomic factors affecting the frequency content of Still's innocent\r\nmurmur. The American journal of cardiology, 74(5), 508-510.\r\n[3] Barschdorff, D., Femmer, U., &Trowitzsch, E. (1995, September).\r\nAutomatic phonocardiogram signal analysis in infants based on wavelet\r\ntransforms and artificial neural networks. In Computers in Cardiology\r\n1995 (pp. 753-756). IEEE.\r\n[4] Shino, H., Yoshida, H., Yana, K., Harada, K., Sudoh, J., &Harasewa, E.\r\n(1996). Detection and classification of systolic murmur for\r\nphonocardiogram screening. In Engineering in Medicine and Biology\r\nSociety, 1996. Bridging Disciplines for Biomedicine. Proceedings of the\r\n18th Annual International Conference of the IEEE (Vol. 1, pp. 123-124).\r\nIEEE.\r\n[5] Durand, L. G., &Pibarot, P. (1995). Digital signal processing of the\r\nphonocardiogram: review of the most recent advancements. Critical\r\nReviews\u2122 in Biomedical Engineering, 23(3-4).\r\n[6] Bogdanovi\u0107, V., Bo\u017ei\u0107, I., Gavrovska, A., Stoji\u0107, V., &Jakovljevi\u0107, V.\r\n(2013). Phonocardiography-based mitral valve prolapse detection using\r\nan artificial neural network. Serbian Journal of Experimental and\r\nClinical Research, 14(3), 113-120.\r\n[7] Rangayyan, R. M., &Lehner, R. J. (1986). Phonocardiogram signal\r\nanalysis: a review. Critical reviews in biomedical engineering, 15(3),\r\n211-236.\r\n[8] Reynolds, D. A., & Rose, R. C. (1995). Robust text-independent speaker\r\nidentification using Gaussian mixture speaker models. Speech and\r\nAudio Processing, IEEE Transactions on, 3(1), 72-83.\r\n[9] Lung, S. Y. (2007). Efficient text independent speaker recognition with\r\nwavelet feature selection based multilayered neural network using\r\nsupervised learning algorithm. Pattern Recognition, 40(12), 3616-3620.\r\n[10] Guyon, I., &Elisseeff, A. (2003). An introduction to variable and feature\r\nselection. The Journal of Machine Learning Research, 3, 1157-1182.\r\n[11] D. B., Brennan, T., Zuhlke, L. J., Abdelrahman, H. Y., Ntusi, N.,\r\nClifford, G. D. & Tarassenko, L. (2014, May). Signal quality\r\nclassification of mobile phone-recorded phonocardiogram signals. IEEE\r\nInternational Conference on Acoustics, Speech and Signal Processing\r\n(ICASSP), 2014 (pp. 1335-1339).\r\n[12] Gavrovska, A., Zaji\u0107, G., Reljin, I., & Reljin, B. (2013). Classification of\r\nprolapsed mitral valve versus healthy heart from phonocardiograms by\r\nmultifractal analysis. Computational and mathematical methods in\r\nmedicine, 2013.\r\n[13] Singh, M., & Cheema, A. (2013). Heart Sounds Classification using\r\nFeature Extraction of Phonocardiography Signal. International Journal\r\nof Computer Applications, 77(4).\r\n[14] Sinha, Rakesh Kumar, et al. \"K-Nearest Neighborhood Approach to\r\nIdentify Level of Left Ventricular Ejection Fraction From\r\nPhonocardiogram.\" Journal of Clinical Engineering 38.2 (2013): 75-78.\r\n[15] Ramos, J. P., Carvalho, P., & Coimbra, M. (2013, July). Towards a timefeature\r\nindependent phonocardiogram segmentation. Annual\r\nInternational Conference of the IEEE in Engineering in Medicine and\r\nBiology Society (EMBC), 2013 35th (pp. 2116-2119).\r\n[16] Dixit, A., &Majumdar, S. (2013). Comparative Analysis Of Coiflet And\r\nDaubechies Wavelets Using Global Threshold For Image De-Noising.\r\nInternational Journal of Advances in Engineering & Technology,6(5).\r\n[17] Kumar, V. S., & Reddy, M. I. S. (2012). Image Compression\r\nTechniques by using Wavelet Transform. Journal of information\r\nengineering and applications, 2(5), 35-39.\r\n[18] Kaur, E. R., & Singh, J. Comparative Study Of DWT Based Image\r\nCompression Using Haar, Daub & Coif Wavelets.\r\n[19] Zhao, F., Liu, J., Liu, J., Guibas, L., & Reich, J. (2003). Collaborative\r\nsignal and information processing: an information-directed approach.\r\nProceedings of the IEEE, 91(8), 1199-1209.\r\n[20] Weiss, L. E., Sanderson, A. C., & Neuman, C. P. (1987). Dynamic\r\nsensor-based control of robots with visual feedback. Robotics and\r\nAutomation, IEEE Journal of, 3(5), 404-417.\r\n[21] Sugumaran, V., V. Muralidharan, and K. I. Ramachandran. \"Feature\r\nselection using decision tree and classification through proximal support\r\nvector machine for fault diagnostics of roller bearing.\" Mechanical\r\nsystems and signal processing 21.2 (2007): 930-942.\r\n[22] Kennedy, J. (2010). Particle swarm optimization. In Encyclopedia of\r\nMachine Learning (pp. 760-766). Springer US.\r\n[23] Ding, S., & Chen, L. (2010). Intelligent Optimization Methods for High-\r\nDimensional Data Classification for Support Vector Machines.\r\nIntelligent Information Management, 2, 354.\r\n[24] Sharma, L., Pathak, B. K., & Sharma, N. (2012). Breaking of simplified\r\ndata encryption standard using binary particle swarm optimization.\r\nIJCSI International Journal of Computer Science Issues, 9(3), 1694-\r\n0814.\r\n[25] Das, S., Abraham, A., & Konar, A. (2008). Particle swarm optimization\r\nand differential evolution algorithms: technical analysis, applications and hybridization perspectives. In Advances of Computational\r\nIntelligence in Industrial Systems (pp. 1-38). Springer Berlin\r\nHeidelberg.\r\n[26] Ting, S. L., Ip, W. H., & Tsang, A. H. (2011). Is Naive Bayes a good\r\nclassifier for document classification?. International Journal of Software\r\nEngineering and Its Applications, 5(3), 37.\r\n[27] Kataria, A., & Singh, M. D. A Review of Data Classification Using KNearest\r\nNeighbour Algorithm.\r\n[28] Adhatrao, K., Gaykar, A., Dhawan, A., Jha, R., & Honrao, V. (2013).\r\nPredicting Students' Performance Using ID3 and C4. 5 Classification\r\nAlgorithms. arXiv preprint arXiv:1310.2071.\r\n[29] Srivastava, D. K., & Bhambhu, L. (2010). Data classification using\r\nsupport vector machine.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 99, 2015"}