Abstract

This paper presents a computer-based sound recognition system for diagnosis of pulmonary disorders based on the interpretation of the lung sound signals (LSS). We propose a novel method of analysis of LSS using the Mel-frequency cepstral coefficients, the spectral and temporal parameters estimated from the frequency subbands of the discrete wavelet transform. A Linde Buzo Gray (LBG) clustering neural network model is developed for classifying the LSS to one of the six categories: normal, wheeze, crackle, squawk, stridor, or rhonchus. Experimental results demonstrate the effectiveness of the proposed system in detecting pulmonary disorders.

References

• Sovijarvi, A. R. A. , Vanderschoot, J. , and Earis, J. E. 2000. Standardization of computerised respiratory sound analysis. European Respiratory Review, 10 (77), 585.
• Bahoura, M. 2009. Pattern recognition methods applied to respiratory sounds classification to normal and wheeze classes. Computers in Biology and Medicine, 39 (9). 824–843.
• Kandaswamy, A. , Kumar C. S. , Ramanathan, Rm. Pl. , Jayaraman, S. , and Malmurugan, N. 2004. Neural classification of lung sounds using wavelet coefficients. Computers in Biology and Medicine, 34 (6), 523–537.
• Sovijärvi, A. R. A, Dalmasso, F. , Vanderschoot, J. , Malmberg, L. P. , Righini, G. , and Stoneman, S. A. T. 2000. Definition of terms for applications of respiratory sounds. Eur Respir Rev, 10 (77), 597–610.
• Sovijarvi, A. R. A. , Malmberg, L. P. , Charbonneau, G. , and Vanderschoot, J. 2000. Characteristics of breath sounds and adventitious respiratory sounds. European Respiratory Review, 10 (77), 591–596.
• Mehta, A. C. , Gat, M. , Mann, S. , and Madison, J. M. 2010. Accuracy of gray-scale coding in lung sound mapping. Computerized Medical Imaging and Graphics, 34 (5), 362–369.
• Dalmay, F. , Antonini, M. T. , Marquet, P. , and Menier, R. 1995. Acoustic properties of the normal chest. European Respiratory Journal, 8 (10), 1761–1769.
• Sankur, B. , Kahya, Y. P. , Guler, E. C. , and Engin, T. 1994. Comparison of AR-based algorithms for respiratory sound classification. Computers in Biology and Medicine, 24 (1), 67–76.
• Guler, E. , Sankur, B. , Kahya, Y. , and Raudys, S. 2005. Two-stage classification of respiratory sound patterns. Computers in Biology and Medicine, 35 (1), 67–83.
• Bahoura, M. , and Pelletier, C. 2004. Respiratory sounds classification using cepstral analysis and Gaussian mixture models. In 26th Annual Conference of the IEEE EMBS, San Francisco, CA, September 1–5, pp. 9–12.
• Taplidou, S. A. , Hadjileontiadis, L. J. , Kittsas, I. K. , and Panoulas, K. I. 2004. On applying continuous wavelet transform in wheeze nalysis. In Proceedings of the 26th International Conference of the IEEE EMBS, San Francisco, CA, USA, pp. 3832–3835.
• Polat, H. , and Guler, I. 2004. A simple computer-based measurement and analysis system of pulmonary auscultation sounds. J. Med. Syst. 28 (6), 665–672.
• Taplidou, S. A. , and Hadjileontiadis, L. J. 2007. Nonlinear analysis of wheezes using wavelet bicoherence. Computers in Biology and Medicine, 37 (4), 563–570.
• Waitman, L. R. , Clarkson, K. P. , Barwise, J. A. , and King, P. H. 2000. Representation and classification of breath sounds recorded in an intensive care setting using neural networks. Journal of Clinical Monitoring and Computing, 16 (2), 95–105.
• Lin, B. S. , Wu, H. D. , Chong, F. C. , and Chen, S. J. 2006. Wheeze recognition based on 2D bilateral filtering of spectrogram. Biomedical Engineering Applications, Basis & Communications, 18 (3), 128–137.
• Donoho, D. L. , and Johnstone, I. M. 1995. Adapting to unknown smoothness via wavelet shrinkage, J. Am. Stat. Assoc. , 90 (432), 1200–1224.
• Calvo de Lara, J. R. 2005. A method of automatic speaker recognition using cepstral features and vectorial quantization. Springer-Verlag Berlin Heidelberg, 3773, 146-153.
• Jung, S. , and Ghaboussi, J. 2006. Characterizing rate-dependent material behaviors in self-learning simulation. Computer Methods in Applied Mechanics and Engineering, 196 (1–3), 608–619.
• Riedmiller, M. , and Braun, H. , 1993. A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In Proceedings of the IEEE International Conference on Neural Networks, San Francisco, CA.
• The R. A. L. E. lung sound 3. 0. www. rale. ca, 2003.