Heart sound signal classification using fast independent component analysis
Heart sound signal classification using fast independent component analysis
The analysis of heart sound signals is a basic method for heart examination. It may indicate the presence of heart disorders and provide clinical information in the diagnostic process. In this study, a novel feature dimension reduction method based on independent component analysis (ICA) has been proposed for the classification of fourteen different heart sound types; the method was compared with principal component analysis. The feature vectors are classified by support vector machines, linear discriminant analysis, and naive Bayes (NB) classifiers using 10-fold cross validation. The ICA combined with NB achieves the highest average performance with a sensitivity of 98.53%, specificity of 99.89%, g-means of 99.21%, and accuracy of 99.79%.
___
- [1] Liang H, Hartimo I. A heart sound feature extraction algorithm based on wavelet decomposition and reconstruction. In: IEEE EMBS 1998 the 20th Annual International Conference; 29 October1 November 1998; Hong Kong, China: IEEE. pp. 1539-1542.
- [2] Olmez T, Dokur Z. Classification of heart sounds using an artificial neural network. Pattern Recogn Lett 2003; 24: ¨ 617-629.
- [3] Andrisevic N, Ejaz K, Gutierrez FR, Flores RA. Detection of heart murmurs using wavelet analysis and artificial neural networks. J Biomech Eng-T ASME 2005; 127: 899-904.
- [4] Gupta CN, Palaniappan R, Swaminathan S, Krishnan SM. Neural network classification of homomorphic segmented heart sounds. Appl Soft Comput 2007; 7: 286-297.
- [5] Uguz H, Arslan A, Turkoglu I. A biomedical system based on hidden Markov model for diagnosis of the heart valve diseases. Pattern Recogn Lett 2007; 28: 395-404.
- [6] Dokur Z, Olmez T. Heart sound classification using wavelet transform and incremental self-organizing map. Digit ¨ Signal Process 2008; 18: 951-959.
- [7] Saraco˘glu R. Hidden Markov model-based classification of heart valve disease with PCA for dimension reduction. Eng Appl Artif Intel 2012; 25: 1523-1528.
- [8] U˘guz H. Adaptive neuro-fuzzy inference system for diagnosis of the heart valve diseases using wavelet transform with entropy. Neural Comput Appl 2012; 21: 1617-1628.
- [9] Safara F, Doraisamy S, Azman A, Jantan A, Ranga S. Wavelet packet entropy for heart murmurs classification. Adv Bioinformatics 2012; 1-6.
- [10] Patidar S, Pachori RB. Classification of cardiac sound signals using constrained tunable-Q wavelet transform. Expert Syst Appl 2014; 41: 7161-7170.
- [11] Karlık B, Ko¸cyi˘git Y, Kor¨urek M. Differentiating types of muscle movements using wavelet based fuzzy clustering neural network. Expert Syst 2009; 26: 49-59.
- [12] Duda RO, Hart PE, Stork DG. Pattern classification. 2nd ed. New York, NY, USA: Wiley, 2001.
- [13] Kocyigit Y, Alkan A, Erol H. Classification of EEG recordings by using fast independent component analysis and artificial neural network. J Med Syst 2008; 32: 17-20.
- [14] Subasi A, Gursoy MI. EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst Appl 2010; 37: 8659-8666.
- [15] Hyv¨arinen A, Oja E. Independent component analysis: algorithms and applications. Neural Networks 2000; 13: 411-430.
- [16] Martis RJ, Acharya UR, Min LC. ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform. Biomed Signal Proces 2013; 8: 437-448.
- [17] Hyv¨arinen A. Fast and robust fixed-point algorithms for independent component analysis. IEEE T Neural Networ 1999; 10: 626-634.
- [18] Vapnik V. The Nature of Statistical Learning. Berlin, Germany: Springer-Verlag, 1995.
- [19] Kocyigit Y, Seker H. Imbalanced data classifier by using ensemble fuzzy c-means clustering. In: IEEE-EMBS 2012 International Conference on Biomedical and Health Informatics; 57 January 2012; Shenzhen, China: IEEE. pp. 952-955.
- [20] Mathew J, Sahoo L, Saha G. A system for behavior prediction based on neural signals. Neurocomputing 2012; 97: 214-222.
- [21] Novey DW, Pencak M, Stang JM. The guide to heart sounds: normal and abnormal. Boca Raton, FL, USA: CRC Press, 1988.
- [22] Say O. Analysis of heart sounds and classification by using artificial neural networks. MSc, Istanbul Technical University, Istanbul, Turkey, 2002.
- [23] Giri D, Acharya UR, Martis RJ, Sree SV, Ahamed T, Suri JS, Lim TC. Automated diagnosis of coronary artery disease affected patients using LDA, PCA, ICA and discrete wavelet transform. Knowl-Based Syst 2013; 37: 274-282.
- [24] Jia L, Song D, Tao L, Lu Y. Heart sounds classification with a fuzzy neural network method with structure learning. Lect Notes Comput SC 2012; 7368: 130-140.
- [25] Liwei F, Kim LP. A comparative study of PCA, ICA and class-conditional ICA for naive Bayes classifier. Lect Notes Comput SC 2007; 4507:16-22.
- [26] Bressan M, Vitria J. Improving naive Bayes using class-conditional ICA. Lect Notes Comput SC 2002; 2527:1-10.