A Study on Robust Pattern Classification of Lung Sounds for Diagnosis of Pulmonary Dysfunction in Noise Environment

폐질환 진단을 위한 잡음환경에 강건한 폐음 패턴 분류법에 관한 연구

  • 여송필 (한국방송광고공사 광고연구소) ;
  • 전창익 (서울시립대학교 전자전기공학부) ;
  • 유세근 (서울시립대학교 전자전기공학부) ;
  • 김덕영 (부천대학 전자과) ;
  • 김성환 (서울시립대학교 전자전기공학부)
  • Published : 2002.03.01

Abstract

In this paper, a robust pattern classification of breath sounds for the diagnosis of pulmonary dysfunction in noise environment is proposed. The feature parameter extraction method by highpass lifter algorithm and PM(projection measure) algorithm are used. 17 different groups of breath sounds are experimentally classified and investigated. The classification has been performed by 6 different types of combinations with proposed methods to evaluate the performances, such as ARC with EDM and LCC with EDM, WLCC with EDM, ARC with PM, LCC with PM, WLCC with PM. Furthermore, all feature parameters are extracted to 80th orders by 5th orders step, and all experiments are evaluated in increasing noise environments by degrees SNR 24dB to 0dB. As a results, WLCC which is derived from highpass lifter algorithm, is selected for the feature parameter extraction method. Pm is more robust than EDM in noisy environments to test and compare experimental results. WLCC with PM method(WLCC/PM) has a better performance in an increasing noise environment for diagnosis of pulmonary dysfunction.

Keywords

References

  1. Jingping Xu, Jingzhi Cheng, Yanjun Wu, 'A Cepstral Method for Analysis of Acoustic Transmission Characteristics of Respiratory System,' IEEE Trans. Biomedical Eng., Vol. 45, pp. 660-664, May, 1998 https://doi.org/10.1109/10.668757
  2. Kevin E. Forkheim, David Scuse, Hans Pasterkamp, 'A Comparison of Neural Network Models for Wheeze Detection,' IEEE ESCANEX '95 Proceedings, Vol. 1, pp. 214-219, vol. 1, 1995 https://doi.org/10.1109/WESCAN.1995.493973
  3. Modegi T, Iisaku S, 'Application of MIDI Technique for Medical Audio Signal Coding,' IEEE 19th Annual International Conferences, Eng. Medicine and Biology Soc., Vol. 4, pp. 1417-1420, vol. 4, 1997 https://doi.org/10.1109/IEMBS.1997.756970
  4. Schuttler F, Penzel T, von Wichert, 'Digital Recording and Computer Based Analysis of Lung Sounds,' IEEE 18th Annual International Conferences, Eng. Medicine and Biology Soc., Vol. 5, pp. 2301-2302, vol. 5, 1997 https://doi.org/10.1109/IEMBS.1996.646544
  5. P. Forgas, 'Lung Sounds,' Brit. J. Dis. Chest, vol. 63, pp. 1-12, 1969 https://doi.org/10.1016/S0007-0971(69)80039-2
  6. Banaszak E. F., R. C. Kory and G. L. Snider, Phonopneumography, Am. Rev. Resp. Dis., 107, pp. 449-455, 1973
  7. R.M. Nachman and L. Vinaru, 'Recording and Analysis of Sounds Produced by Human Lungs during Respiration,' Experienta 25, pp. 1040-1041, 1969 https://doi.org/10.1007/BF01901414
  8. Murphy R. L. H. and K. Sarensen, 'Chest Auscultation and Diagnosis of Pulmonary Asbestosis,' J. Occup. Med. 15, pp. 272-276, 1973
  9. Arnon Cohen, Dorota Landsberg, 'Analysis and Automatic Classification of Breath Sounds,' IEEE Trans. Vol. BME-31, No. 9, pp. 585-590, september, 1984 https://doi.org/10.1109/TBME.1984.325301
  10. Peyton Z. Peebles JR, Probability Random Variables and Random signal Principles, McGraw-Hill, 1993
  11. Lawrence Rabiner, Biing-Hwang Juang, Fundamentals of Speech recognition, Prentice-Hall Inc., pp. 163-166, 1993
  12. Steven Leherer, Understanding Lung Sounds, W. B. Sounder West Washington, 1984