Top > JACIII > Spectral Classification of Oral and Nasal Snoring Sounds Using ...

single-jc.php

JACIII Vol.17 No.4 pp. 611-621
doi: 10.20965/jaciii.2013.p0611
(2013)

Paper:

Views over last 60 days: 868

Spectral Classification of Oral and Nasal Snoring Sounds Using a Support Vector Machine

Tsuyoshi Mikami*, Yohichiro Kojima*, Kazuya Yonezawa**,
Masahito Yamamoto***, and Masashi Furukawa***

*Tomakomai National College of Technology, 443 Nishikioka, Tomakomai 059-1275, Japan

**Department of Clinical Research, National Hospital Organization Hakodate Hospital, 18-16 Kawaharacho, Hakodate 041-8512, Japan

***Graduate School of Information Science & Technology, Hokkaido University, Kita 14, Nishi 9, Kita-ku, Sapporo 060-0814, Japan

Received:
July 17, 2012
Accepted:
May 6, 2013
Published:
July 20, 2013
Creative Commons License
Keywords:
support vector machine, snoring sound, sleep apnea syndrome, pattern classification
Abstract
Since oral breathing during sleep tends to make the upper airway more collapsible, loud snoring caused by oral breathing is found in many sleep apnea/hypopnea patients and should be detected in the earlier stage. But unfortunately we cannot know our own sleep condition or snoring. Thus, a simple method that can detect oral snoring makes it possible to become a useful technique to develop a home medical device. For such purpose, we adopt a Support Vector Machine (SVM) classifier so as to classify oral and nasal snoring sounds based on the spectral properties. Fifteen subjects are asked to simulate snoring with oral and nasal breath respectively and the sounds are recorded with a linear sound recorder. We adopted seven kernel functions (linear, polynomial, sigmoid, Gaussian, Laplacian, chisquare, and Kullback-Leibler) for SVM-based spectral classification. As a result, over 95% of snoring sounds are successfully classified under the various cross validation test.
Cite this article as:
T. Mikami, Y. Kojima, K. Yonezawa, M. Yamamoto, and M. Furukawa, “Spectral Classification of Oral and Nasal Snoring Sounds Using a Support Vector Machine,” J. Adv. Comput. Intell. Intell. Inform., Vol.17 No.4, pp. 611-621, 2013.
Data files:
References
  1. [1] H. A. McLean, A. M. Urton, H. S.Driver, A. K. W. Tan, A. G. Day, P. W. Munt, and M. F. Fitzpatrick, “Effect of treating severe nasal obstruction on the severity of obstructive sleep apnoea,” European Respiratory J., Vol.25, pp. 521-527, 2005.
  2. [2] C. W. Zwillich et al., “Disturbed sleep and prolonged apnea during nasal obstruction in normal men,” Am. Rev. Respir. Dis., Vol.124, pp. 158-160, 1981.
  3. [3] J. E. Cillo Jr, R. Finn, and R. M. Dasheiff, “Combined Open Rhinoplasty With Spreader Grafts and Laser-Assisted Uvuloplasty for Sleep-Disordered Breathing: Long-Term Subjective Outcomes,” J. of Oral and Maxillofacial Surgery, Vol.64, No.8, pp. 1241-1247, 2006.
  4. [4] H. Hara et al., “Morphological Change of the Upper Airway in OSAS Patients with Open Mouth,” Stomatopharyngol., Vol.20, No.1, p. 45, 2007.
  5. [5] J. A. Fiz, J. Abad, R. Jane, M. Riera, M. A. Mananas, and P. Caminal, “Acoustic analysis of snoring sound in patients with simple snoring and obstructive sleep apnoea,” European Respiratory J., Vol.9, No.11, pp. 2365-2370, 1996.
  6. [6] H. Hara, N. Murakami, Y. Miyauchi, and H. Yamashita, “Acoustic analysis of snoring sounds by a multidimensional voice program,” Laryngoscope, Vol.116, No.3, pp. 379-381, 2006.
  7. [7] J. Sola-Soler, R. Jane, J. A. Fiz, and J. Morera, “Spectral envelope analysis in snoring signals from simple snorers and patients with obstructive sleep apnea,” Engineering in Medicine and Biology Society, 2003 Proc. of the 25th Annual Int. Conf. of the IEEE, Vol.3, pp. 2527-2530, 2003.
  8. [8] S. J Quinn, L. Huang, P. D.M. Ellis, and J. E. F.Williams, “The differentiation of snoring mechanisms using sound analysis,” Clinical Otolaryngology, Vol.21, pp. 119-123, 1996.
  9. [9] J. E. Osborne, E. Z. Osman, P. D. Hill, B. V. Lee, and C. Sparkes, “A new acoustic method of differentiating palatal from non-palatal snoring,” Clinical Otolaryngology, Vol.24, No.2, pp. 130-133, 1999.
  10. [10] U. R. Abeyratne, A. S.Wakwella, and C. Hukins, “Pitch jump probability measures for the analysis of snoring sounds in apnea,” Physiological Measurement, Vol.26, No.5, pp. 779-798, 2005.
  11. [11] M. Cavusoglu, M. Kamasak, O. Erogul, T. Ciloglu, Y. Serinagaoglu, and T. Akcam, “An efficient method for snore/nonsnore classification of sleep sounds,” Physiological Measurement, Vol.28, No.8, pp. 841-854, 2007.
  12. [12] F. Dalmasso and R. Prota, “Snoring: analysis, measurement, clinical implications and applications,” European Respiratory J., Vol.9, pp. 146-159, 1996.
  13. [13] G. Liistro, D. Stanescu, and C. Veriter, “Pattern of simulated snoring is different through mouth and nose,” J. of Applied Physiology, Vol.70, No.6, pp. 2746-2741, 1991.
  14. [14] T. Mikami, Y. Kojima, K. Yonezawa, M. Yamamoto, and M. Furukawa, “Automatic Classification of Oral/Nasal Snoring Soundsbased on the Acoustic Properties,” Proc. of the IEEE 37th Int. Conf. Acoustics, Speech, and Signal Proc. (ICASSP), pp. 609-612, 2012.
  15. [15] T. Mikami, Y. Kojima, K. Yonezawa, M. Yamamoto, and M. Furukawa, “Classification of Oral/Nasal Simulated Snores based onthe Acoustic Properties,” J. of Biomechanical Science and Engineering, Vol.7, No.4, pp. 433-448, 2012.
  16. [16] O. Chapelle, P. Haffner, and V. N. Vapnik, “Support Vector Machines for Histogram-Based Image Classification,” IEEE Trans. on Neural Networks, Vol.10, No.5, pp. 1055-1064, 1999.
  17. [17] P. J. Moreno et al., “A Kullback-Leibler divergence based kernel for SVM classification in multimedia applications,” Proc. of Neural Information Processing Systems, 2004.
  18. [18] T. Ishigaki, T. Higuchi, and K. Watanabe, “Deterioration Diagnosis of Pressure Regulator for High Pressure Gas by Spectrum Classification with the Kullback-Leibler Kernel,” IEICE Trans. on Information and Systems, Vol.J90-D, No.10, pp. 2787-2797, 2007.
  19. [19] S. Agrawal, P. Stone, K. McGuinness, J. Morris, and A. E. Camilleri, “Sound frequency analysis and the site of snoring in natural and induced sleep,” Clinical Otolaryngology, Vol.27, pp. 162-166, 2002.
  20. [20] A. K. Bieger-Farhan, N. K. Chadha, A. E. Camileri, P. Stone, and K. McGuinness, “Portable method for the determination of snoring site by sound analysis,” J. of Laryngology and Otology, Vol.118, No.2, pp. 135-138, 2004.
  21. [21] M. Herzog, T. Metz, A. Schmidt, T. Bremert, B. Venohr, W. Hosemann, and H. Kaftan, “The Prognostic Value of Simulated Snoring in Awake Patients With Suspected Sleep-Disordered Breathing: Introduction of a New Technique of Examination,” Sleep, Vol.29, No.11, pp. 1456-1462, 2006.
  22. [22] M. Herzog et al., “Frequency analysis of snoring sounds during simulated and nocturnal snoring,” European Archives on Oto-Rhino-Laryngology, Vol.265, No.12, pp. 1553-1562, 2008.
  23. [23] J. R. Perez-Padilla, E. Slawinski, L. M. Difrancesco, R. R. Feige, J. E. Remmers, and W. Whitelaw, “Characteristics of the snoring noise in patients with and without occlusive sleep apnea,” American Review of Respiratory Disorders,” Vol.147, No.3, pp. 635-644, 1993.
  24. [24] R. Beck, M. Odeh, A. Oliven, and N. Gavriely, “The acoustic properties of snores,” European Respiratory J., Vol.8, pp. 2120-2128, 1995.
  25. [25] T. Emoto, U. R. Abeyratne, T. Kusumoto,M. Akutagawa, E. Kondo, I. Kawata, T. Azuma, S. Konaka, and Y. Konouchi, “Discriminating Apneic Snorers and Benign Snorers Based on Snoring Formant Extracted Via a Noise-robust Linear Prediction Technique,” J. of Japanese Society for Medical and Biological Engineering, Vol.48, No.1, pp. 115-121, 2010.
  26. [26] E. J. Olson, W. R. Moore, and T. A. Staats, “Obstructive Sleep Apnea-Hypopnea,” Mayo Clinic Proceedings, Vol.78, No.12, pp. 1545-1552, 2003.
  27. [27] Y. Inoue and Y. Yamashiro, “Sleep Disordered Breathing: update 2006,” Nippon Hyoronsha, Inc., 2007 (in Japanese).
  28. [28] M. Ichioka, “Respiratory organs and sleep disorders,” Folia Pharmacolia Japonica, Vol.129, pp. 432-435, 2007.
  29. [29] N. Cristianini et al., “An Introduction to Support Vector Machines and Other Kernel-based Learning Methods,” Cambridge University Press, 2004.
  30. [30] H. Murata, T. Onoda, K. Yoshimoto, Y. Nakano, and S. Kondo, “Non-Intrusive Electric Appliances Load Monitoring System – Experiment for Real Household –,” IEEJ Trans. on Electronics, Information, and Systems, Vol.124, No.9, pp. 1874-1880, 2004.
  31. [31] T. Horiuchi, T. Beppu, Y. Eujioka, and M. Hara, “Comparison of Pattern Classification Methods in Discrimination of Inferior Shijimi Clams Based on Acoustic Signals,” J. of Japanese Society of Fuzzy Theory and Intelligent Informatics, Vol.20, No.5, pp. 817-822, 2008 (in Japanese).
  32. [32] A. Karatzoglou et al., “kernlab – An S4 Package for Kernel Methods in R,” J. of Statistical Software, Vol.11, No.9, pp. 1-20, 2004.
  33. [33] H.-T. Lin and C.-J. Lin, “A Study on Sigmoid Kernels for SVM and the Training of non-PSD Kernels by SMO-type Methods,” Technical report, Department of Computer Science, National Taiwan University, March, 2003.
  34. [34] K. Ishii, E. Maeda, N. Ueda, and H. Murase, “Pattern Recognition,” Ohmsha, 1998.

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Nov. 04, 2024