medigraphic.com

2016, Number 1

<< Back

Rev Mex Ing Biomed 2016; 37 (1)

Determining optimal size of HMM-GMM models to classify bio-acoustic signals

Mayorga-Ortiz P, Druzgalski C, Miranda VJE, Zeljkovic V

Language: Spanish
References: 41
Page: 63-79
PDF size: 1628.37 Kb.


ABSTRACT

This paper demonstrates the analysis and proposed HMM-GMM models architecture to classify heart and lung sounds (HS and LS) signals emphasizing the model size optimization. Respiratory and cardiovascular diseases continue to represent one of the major worldwide healthcare problems associated with a high mortality rate, which can be reduced by an early and effective diagnosis; in this context, the use of digital tools utilizing signal pattern recognition allows efficient screening for abnormalities and their quantitative assessment. In particular, the HMM-GMM models demonstrated their efficiency in normal and traditionally noisy environments in light of very low intensities of these auscultation signals used as diagnostic indicators. Furthermore, applied MFCC and Quantiles feature extractors improve overall classification. While characterization with silhouettes, dendrograms and algorithms such as BIC was inconclusive when GMM was applied, however they were useful as a starting point in the determination of a size of the model as it allowed a reduction in the number of iterations considering different model size. In addition one can note that application of MFCC or Quantiles allowed differentiating the characteristics of normal HS and LS from those associated with pathological conditions. Furthermore, it was observed that a large amount of data leads to more robust and adapted models, but does not limit the calculation demand. Overall, this approach may enhance efficiency and precision of the diagnostic screening for abnormal auscultation indicators.


REFERENCES

  1. J. Earis, “Lung sounds,” Thorax, vol. 47, pp. 671-2, Sep 1992.

  2. P. Forgacs, “Lung sounds,” Br J Dis Chest, vol. 63, pp. 1-12, Jan 1969.

  3. H. S. Hira, “Lung sounds,” J Assoc Physicians India, vol. 41, pp. 33-7, Jan 1993.

  4. R. Loudon and R. L. Murphy, Jr., “Lung sounds,” Am Rev Respir Dis, vol. 130, pp. 663-73, Oct 1984.

  5. M. Mori, “[Origin of normal breath sounds and abnormal lung sounds (crackles and wheezes)],” Kokyu To Junkan, vol. 31, pp. 493-501, May 1983.

  6. P. Roudebush, “Lung sounds,” J Am Vet Med Assoc, vol. 181, pp. 122-6, Jul 15 1982.

  7. I. Sen, M. Saraclar, and Y. P. Kahya, “A Comparison of SVM and GMMBased Classifier Configurations for Diagnostic Classification of Pulmonary Sounds,” Biomedical Engineering, IEEE Transactions on, vol. 62, pp. 1768-1776, 2015.

  8. K. Kosasih, U. R. Abeyratne, V. Swarnkar, and R. Triasih, “Wavelet Augmented Cough Analysis for Rapid Childhood Pneumonia Diagnosis,” Biomedical Engineering, IEEE Transactions on, vol. 62, pp. 1185-1194, 2015.

  9. J. Herzig, A. Bickel, A. Eitan, and N. Intrator, “Monitoring Cardiac Stress Using Features Extracted From S1 Heart Sounds,” Biomedical Engineering, IEEE Transactions on, vol. 62, pp. 1169-1178, 2015.

  10. D. Emmanouilidou, E. D. McCollum, D. E. Park, and M. Elhilali, “Adaptive Noise Suppression of Pediatric Lung Auscultations With Real Applications to Noisy Clinical Settings in Developing Countries,” Biomedical Engineering, IEEE Transactions on, vol. 62, pp. 2279-2288, 2015.

  11. S. Barma, C. Bo-Wei, J. Wen, J. Feng, and W. Jhing-Fa, “Measurement of Duration, Energy of Instantaneous Frequencies, and Splits of Subcomponents of the Second Heart Sound,” Instrumentation and Measurement, IEEE Transactions on, vol. 64, pp. 1958-1967, 2015.

  12. S. Barma, C. Bo-Wei, M. Ka Lok, and W. Jhing-Fa, “Quantitative Measurement of Split of the Second Heart Sound (S2),” Computational Biology and Bioinformatics, IEEE/ACM Transactions on, vol. 12, pp. 851-860, 2015.

  13. C. D. Papadaniil and L. J. Hadjileontiadis, “Efficient Heart Sound Segmentation and Extraction Using Ensemble Empirical Mode Decomposition and Kurtosis Features,” Biomedical and Health Informatics, IEEE Journal of, vol. 18, pp. 1138- 1152, 2014.

  14. D. Ferreira da Ponte, C. A. Faria da Rocha, D. C. Hizume, and R. Moraes, “Equalization of Crackle Sounds to Compensate Thorax Attenuation,” Instrumentation and Measurement, IEEE Transactions on, vol. 63, pp. 1983-1990, 2014.

  15. A. Abushakra and M. Faezipour, “Acoustic Signal Classification of Breathing Movements to Virtually Aid Breath Regulation,” Biomedical and Health Informatics, IEEE Journal of, vol. 17, pp. 493-500, 2013.

  16. F. Ghaderi, H. R. Mohseni, and S. Sanei, “Localizing Heart Sounds in Respiratory Signals Using Singular Spectrum Analysis,” Biomedical Engineering, IEEE Transactions on, vol. 58, pp. 3360-3367, 2011.

  17. L. Besacier, A. Ariyaeeinia, J. S. Mason, J. F. Bonastre, P. Mayorga, C. Fredouille, et al., “Voice Biometrics over the Internet in the Framework of COST Action 275,” EURASIP Journal on Advances in Signal Processing, vol. 2004, pp. 466-479, Apr 2004 2004.

  18. P. Mayorga, L. Besacier, R. Lamy, and J.-F. Serignat, “Audio packet loss over IP and speech recognition,” Automatic Speech Recognition and Understanding, 2003. ASRU ’03. 2003 IEEE Workshop on, 2003, pp. 607-612.

  19. L. Besacier, P. Mayorga, J.-F. Bonastre, C. Fredouille, and S. Meignier, “Overview of compression and packet loss effects in speech biometrics,” Vision, Image and Signal Processing, IEE Proceedings, vol. 150, pp. 372-376, 2003.

  20. D. M. Istrate, “Detection et Reconnaissance des Sons pour la Surveillance Médicale, These Doctorale, France,” PhD, ENSERG, INPG, Grenoble, France 2003.

  21. P. Mayorga, C. Druzgalski, and J. Vidales, “Quantitative models for assessment of respiratory diseases," in Health Care Exchange (PAHCE), 2010 Pan American, pp. 25-30, 2010.

  22. B. Milner and S. Semnani, “Robust Speech Recognition over IP Networks,” in IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, ICASSP2000, Istambul, Turkey, Jun 2000.

  23. D. Pearce, “Developing the ETSI Aurora advanced distributed speech recognition front-end and what next?,” in Automatic Speech Recognition and Understanding, 2001. ASRU ’01. IEEE Workshop on, pp. 131-134, 2001.

  24. J. S. Yoon, G. H. Lee, and H. K. Kim, “A MFCC-based CELP speech coder for server-based speech recognition in network environments," Ieice Transactions on Fundamentals of Electronics Communications and Computer Sciences, vol. E90a, pp. 626- 632, Mar 2007.

  25. P. Mayorga, M. Olguín, O. H. González, N. Flores, and V. Luis, “Quantile Acoustic Vectors vs. MFCC Applied to Speaker Verification,” in International Journal of Advanced Robotic Systems, 2013.

  26. P. Mayorga, C. Druzgalski, O. H. Gonzalez, and H. Lopez, “Modified classification of normal Lung Sounds applying Quantile Vectors,” presented at the Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE, San Diego, California USA„ 2012.

  27. A. F. L. Julian David Echeverry, Juan Fernando López. (2007, 28 / octubre / 2015) “Reconocimiento de valvulopatías cardíacas en señales de fonocardiografía empleando la transformada Gabor,” Scientia Et Technica. 139-144. Available: http://www.redalyc.org/articulo.oa? id=84934024

  28. K. Benabdeslem and Y. Bennani, “Dendogram based SVM for multi-class classification.,” in Journal of Computing and Information Technology-CIT 14, 2006.

  29. Xue Mei Lu; Sung Jong Eun; Taeg Keun Whangbo, "Vector Silhouette Extraction for Generating Blueprint.," in Automation and Logistics, 2007 IEEE International Conference on, 18-21 Aug. 2007, pp. 2946-2951.

  30. Xuejun Li; Jiaguang Sun; Changgui Yang, “Extracting silhouette curves of NURBS sufaces by tracing silhouette points,” in Tsinghua Science and Technology, June 1998, pp. 1005-1008.

  31. J. Zhao, “Efficient Model Selection for Mixtures of Probabilistic PCA Via Hierarchical BIC,” IEEE Transactions on, vol. vol.44, pp. 1871-1883, Oct. 2014.

  32. Pearce D., “An Overview of ETSI Standards Activities for Distributed Speech Recognition Front-Ends,” in AVIOS 2000: The Speech Applications Conference, San Jose, CA, USA, May 22-24, 2000.

  33. Reynolds D. A., “Gaussian Mixture Modeling Approach to Text- Independent speaker Identification,” Thesis from Georgia Institute of Tecnology, Georgia Institute of Tecnology, Georgia, 1992.

  34. Webb Andrew R., Statistical Pattern Recognition, John Wiley & Sons Ltd„ 2002.

  35. L. R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, N.J.: PTR Prentice Hall, 1993.

  36. P. Mayorga Ortiz, C. Druzgalski, J. E. Miranda Vega, and D. O. Calderas Ochoa. (2014) “Modelos Acústicos HMM Multimodales para Sonidos Cardiacos y Pulmonares,”’ Revista Mexicana de Ingeniería Biomédica. 197- 210.

  37. B. C. s. Hospital. Boston Children’s Hospital http://www.childrenshospital.org/. Available: http://www.childrenshospital.org/

  38. T. H. Institute. Texas Heart Institute http://www.texasheartinstitute.org/ AboutUs/index.cfm.

  39. J. Cerda L and L. Cifuentes A, “Uso de tests diagnósticos en la práctica clínica (Parte 1): Análisis de las propiedades de un test diagnóstico,” Revista Chilena de Infectología, vol. 27, pp. 205-208, 2010.

  40. L. R. Rabiner and B. Gold, Theory and Application of Digital Signal Processing. Englewood Cliffs, N.J.: Prentice-Hall, 1975.

  41. L. R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, N.J.: PTR Prentice Hall, 1993.




2020     |     www.medigraphic.com