Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Snoring Sound Classification using Efficient Spectral Features and SVM for Smart Pillow

스마트 베개를 위한 효율적인 스펙트럼 특징과 SVM을 이용한 코골이 판별 방법

  • 김병만 (금오공과대학교 컴퓨터소프트웨어공학과) ;
  • 문창배 (금오공과대학교 ICT융합특성화연구센터)
  • Received : 2018.01.10
  • Accepted : 2018.04.09
  • Published : 2018.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Severe snoring can lead to OSA(Obstructive Sleep Apnea), which can lead to life-threatening cases, and snoring can lead to serious pernicious relationships. In order to solve these snoring problems, several types of smart pillows have recently been released. The core technology is snoring discrimination technology, ie, a technique for determining whether snoring is included in the input sound. In this paper, we propose a snoring detection method to apply to a smart pillow. After extracting the features of the snoring sound from the input signal, we discriminate the snoring using these features and SVM. In order to measure the performance of the proposed method, comparative experiments with the existing methods are performed. The experimental results show about 6% better discrimination performance than the existing method.

코골이가 심한경우 무호흡증(OSA : Obstructive Sleep Apnea)으로 연결되어 생명을 위협하는 경우도 발생할 수 있고, 코골이로 인하여 주변인과의 관계가 심각해지는 경우도 발생할 수 있다. 이런 코골이 문제를 해결하기 위해 최근 여러 형태의 스마트 베개들을 출시하고 있는데, 핵심 기술은 코골이 판별 기술, 즉 입력 사운드에 코골이 소리가 포함되어 있는지를 판별하는 기술이다. 본 논문에서는 스마트 베개에 적용하기 위한 코골이 판별 방법을 제안하였는데, 입력 신호로부터 코골이 소리의 특징을 추출 후 SVM을 이용하여 코골이를 판별하는 방법을 사용하였다. 제안한 방법의 성능을 측정하기 위해 기존 방법과 비교 실험을 실시하였고, 실험결과 기존방법 코골이 판별성능보다 약 6% 좋은 판별성능을 보였다.

Keywords

References

  1. T Young, L Finn, PE Peppard, et al, "Sleep Disordered Breathing and Mortality: Eighteen-Year Follow-up of the Wisconsin Sleep Cohort," Sleep, Vol. 31 No. 8, pp. 1071-1078, 2008.
  2. C Zamarron, F Gude, YO Otero, JR Rodriguez-Suarez, "Snoring and Myocardial Infarction: a 4-Year Follow-up Study," Respir, Med, 93, pp. 108-12, 1999. https://doi.org/10.1016/S0954-6111(99)90299-8
  3. J. Zhang, Q. Zhang, Y. Wang, and C. Qiu, "A Real-time Autoadjustable Smart Pillow System for Sleep Apnea Detection and Treatment," in Proc. 12th Int. Conf. Inf. Process. Sens. Netw., pp. 179-190, 2013.
  4. W. Gu, L. Shangguan, Z. Yang, and Y. Liu, "Sleep Hunter: Towards Fine Grained Sleep Stage Tracking with Smartphones," IEEE Transactions on Mobile Computing, Vol. 15, No. 6, pp. 1514-1527, 2016. https://doi.org/10.1109/TMC.2015.2462812
  5. R. Wei, Kim, H.S. X. Li, Im, J.J. and Kim, H.J., "A Development of Pillow for Detection and Restraining of Snoring," In Biomedical Engineering and Informatics(BMEI), IEEE, 2010 3rd International Conference on, Vol. 4, pp. 1381-1385, 2010.
  6. Sun, X., Kim, J.Y. Won, Y., et al, "Efficient Snoring and Breathing Detection Based on Sub-Band Spectral Statistics," Bio-Medical Materials and Engineering, 26(s1), pp. 787-793, 2015. https://doi.org/10.3233/BME-151370
  7. Chang, C.C. Lin, C.J., "LIBSVM: A Library for Support Vector Machines," ACM Transactions on Intelligent Systems and Technology, Vol. 2, No. 27, 2011.
  8. M, Frigo., Johnson, S.G., "FFTW: An Adaptive Software Architecture for the FFT," Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. Vol. 3, pp. 1381-1384, 1998.
  9. Moon, C.B. Kim, H.S. Kim, B.M., "Audio Recorder Identification using Reduced Noise Features," Ubiquitous Information Technologies and Applications, Springer, pp. 35-42, 2014.
  10. Sun, X., Kim, J.Y. and Won, Y.G., "Simple and Efficient Spectral Features for Breathing and Snoring Sound Classification," Journal of Korean Institute of Information Technology Vol. 12, No. 12, pp. 69-75, 2014.
  11. Beck, R., Odeh, M., Oliven, A., and Gavriely, N., "The Acoustic Properties of Snores," European Respiratory Journal, Vol. 8, No. 12, pp. 2120-2128, 1995. https://doi.org/10.1183/09031936.95.08122120