In Search of an SVD and QRcp Based Optimization Technique of ANN for Automatic Classification of Abnormal Heart Sounds

Artificial Neural Network (ANN) has been extensively used for classification of heart sounds for its discriminative training ability and easy implementation. However, it suffers from overparameterization if the number of nodes is not chosen properly. In such cases, when the dataset has redundancy within it, ANN is trained along with this redundant information that results in poor validation. Also a larger network means more computational expense resulting more hardware and time related cost. Therefore, an optimum design of neural network is needed towards real-time detection of pathological patterns, if any from heart sound signal. The aims of this work are to (i) select a set of input features that are effective for identification of heart sound signals and (ii) make certain optimum selection of nodes in the hidden layer for a more effective ANN structure. Here, we present an optimization technique that involves Singular Value Decomposition (SVD) and QR factorization with column pivoting (QRcp) methodology to optimize empirically chosen over-parameterized ANN structure. Input nodes present in ANN structure is optimized by SVD followed by QRcp while only SVD is required to prune undesirable hidden nodes. The result is presented for classifying 12 common pathological cases and normal heart sound.




References:
[1] Ibrahim R. Hanna, Mark E. Silverman, "A history of cardiac
auscultation and some of its contributors", The American
Journal of Cardiology, vol. 90, pp. 259-267, Aug. 1, 2002
[2] J. R. Bender, "Yale University School of Medicine Heart Book", New
York: William Morrow and Company, Inc., 1992, ch. 13, pp. 167-175.
[3] S. Mangione, L. Nieman, "Cardiac auscultatory skills of internal
medicine and family practice trainees", Journal of the American Medical
Association, vol. 278, pp. 717-722, 1997.
[4] L. G. Durand, P. Pibarot, "Digital signal processing of the
phonocardiogram: review of the most recent advancements", Critical
Reviews in Biomedical Engineering, vol. 22, no. (3/4), pp. 163-219,
1995.
[5] S. Lukkarinen, A. Nopanen, K. Sikio, A. Angerla, "A new
phonocardiographic recording system", Computers in Cardiology, vol.
27, pp. 117-120, 1997.
[6] Leslie Cromwell, Fred J. Weibell, Erich A. Pfeiffer, "Biomedical
Instrumentation and Measurements", 2nd ed, June, 2002, PHI
Publication, Ch. 6: 169-172.
[7] Rangaraj M. Rangayyan, "Biomedical Signal Analysis", 2002, IEEE
Press, John Willy & Sons Inc., Ch. 1:34-38.
[8] Z. Sharif, M. S. Zainal, A. Z. Sha-ameri, S. H. S. Salleh, "Analysis and
classification of heart sounds and murmurs based on the instantaneous
energy and frequency estimations", in Proceedings TENCON 2000, vol.
2, pp. 130-134, Sept., 2000.
[9] Ian Cathers, "Neural network assisted cardiac auscultation", Artificial
Intelligence in Medicine, vol. 7, pp. 53-66, 1995.
[10] T. Ölmez, Z. Dokur, "Classification of heart sounds using an artificial
neural network", Pattern Recognition Letters,vol. 24, pp. 617-629, Jan.,
2003.
[11] T. R. Reed, N. E. Reed, P. Fritzson, "Heart sound analysis for symptom
detection and computer-aided diagnosis", Simulation Modelling Practice
and Theory, vol. 12, pp. 129-146, 2004.
[12] C. N. Gupta, R. Palaniappan, S. Swaninathan, S. M. Krishnan, "Neural
Netork classification of homo-morphic segmented heart sounds",
Applied Soft Computing, vol. 7, pp. 286-297, 2007.
[13] S. Omran, M. Tayel, "A heart sound segmentation and feature extraction
algorithm using wavelets", in First international symposium on control,
communication and signal processing, pp. 235-238, 2004.
[14] B. El-Asir, L. Khadra, A. H. Al-Abbasi, M. M. J. Mohammed, "Timefrequency
analysis of heart sounds", TENCON -96 Proceedings on
Digital Signal Processing Applications, vol. 2, pp. 26-29, Nov., 1996.
[15] J. C. Wood, D. T. Barry, "Time-frequency analysis of the first heart
sound", Engineering in Medicine and Biology Magazine, IEEE, vol. 14,
no. (2), pp. 144-151, March- April, 1995.
[16] Jung Jun Lee, S. M. Lee, I. Y. Kim, H. K. Min, and S. H. Hong,
"Comparison between the short time Fourier and wavelet transform for
feature extraction of heart sounds", in Proceedings of IEEE Tencon-99,
pp. 1547-1550, 1999.
[17] S. M. Debbal, F. Bereksi-Reguig, "Time-frequency analysis of
the first and the second heartbeat sounds", Applied Mathematics
and Computation (2006), doi: 10.1016/j.amc.2006.07.005.
[18] P. P. Kanjilal, G. Saha, T. J. Koickal "On Robust Nonlinear Modelling
of a Complex Process with Large Number of Inputs Using m-Qrcp
Factorization and Cp Statistics", IEEE transaction on systems,Man and
Cybernatics, vol. 29, pp. 1-12, 1999.
[19] S. Ari, P. Kumar, G. Saha, "A Robust Heart Sound Segmentation
Algorithm for Commonly occurring Heart Valve Diseases ", Journal of
Medical Engineering & Technology(2006), doi: 10.1080 /
03091900601015162.
[20] S. Ari, K. Sensharma, G. Saha, "A DSP implementation of heart valve
disorder detection system from phonocardiogram signal", Journal of
Medical Engineering & Technology(2006), doi: 10.1080 /
03091900600861574.
[21] P. P. Kanjilal, "Adaptive Prediction and Predictive Control", Peter
Peregrinus Ltd., 1995, ch. 10, Appendix 3B.
[22] H. Liang, S. Lukkarinen, I. Hartimo, "Heart Sound Segmentation
Algorithm based on Heart Sound Envelogram", Computers in
Cardiology, vol. 24, pp. 105-108, 1997.
[23] H. Liang, S. Lukkarinen, I. Hartimo, "A heart sound segmentation
algorithm using wavelet decomposition and reconstruction", in
Proceedings of the 19th Annual International Conference of the
Engineering in Medicine and Biology society, IEEE, vol. 4, pp. 1630-
1633, 30 Oct.-2 Nov., 1997.
[24] N. P. Archer and S. Wang, "fuzzy set representation of Neural network
classification boundaries", IEEE transaction on systems,Man and
Cybernatics, pp. 735-742, 1991.
[25] Symon Haykin, "Neural Networks", Pearson education Asia, 2002, ch.
4: 156-256.