Journal of Sasang Constitutional Medicine (사상체질의학회지)

The Society Of Sasang Constitutional Medicine (사상체질의학회)
권호 표지

Voice Classification Algorithm for Sasang Constitution Using Support Vector Machine

SVM을 이용한 음성 사상체질 분류 알고리즘

  • Received : 2009.10.22
  • Accepted : 2009.12.02
  • Published : 2010.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

1. Objectives: Voice diagnosis has been used to classify individuals into the Sasang constitution in SCM(Sasang Constitution Medicine) and to recognize his/her health condition in TKM(Traditional Korean Medicine). In this paper, we purposed a new speech classification algorithm for Sasang constitution. 2. Methods: This algorithm is based on the SVM(Support Vector Machine) technique, which is a classification method to classify two distinct groups by finding voluntary nonlinear boundary in vector space. It showed high performance in classification with a few numbers of trained data set. We designed for this algorithm using 3 SVM classifiers to classify into 4 groups, which are composed of 3 constitutional groups and additional indecision group. 3. Results: For the optimal performance, we found that 32.2% of the voice data were classified into three constitutional groups and 79.8% out of them were grouped correctly. 4. Conclusions: This new classification method including indecision group appears efficient compared to the standard classification algorithm which classifies only into 3 constitutional groups. We find that more thorough investigation on the voice features is required to improve the classification efficiency into Sasang constitution.

Keywords

References

  1. WHO. "WHO International Standard Terminologies on Traditional Medicine in The Western Pacific Region". 2007. Available from : URL : http://www.who.int
  2. 김달래. 동의수세보원초고. 청담. 1999. (Korean)
  3. Cho DU. Sasang Constitution Classification by Speech Signal Processing, J of Korea Information and Communications Society. 2006;31(5C):548-555. (Korean)
  4. Moon SJ, Tak JH, Hwang HJ. A Phonetic study of 'Sasang Constitution'. Malsori. 2005;55:1-14. (Korean)
  5. V. N. Vapnik, Statistical Learning Theory, Wiley, New York, 1988.
  6. Kim CK, Park JW, Hur KI. Robust Feature Parameter for Implementation of Speech Recognizer Using Support Vector Machines. J of the Institute of Electronics Engineers of Korea SP. 2004;41(3):195-200. (Korean)
  7. Choi JW, Song HS, Han DY, Cho SE, Wang HL, Jeon JW, et al. A Study on the Characteristics of the Korean Adult Male Sound According to Sasang Constitution Using PSCC with a Sentence. J of Sasang Constitutional Med. 2006;18(3):64-74. (Korean)
  8. Youn JY, Yoon WY, Cho SE, Wang HL, Jeon JW, Yoo JS, et al. A Study on the Characteristics of the Korean Adult Female Sound According to Sasang Constitution Using PSSC with a Sentence. J of Sasang Constitutional Med. 2006;18(3):75-93. (Korean)
  9. 한국한의학연구원 용역보고서. <오감형 센서기반 체질건강 모니터링 시스템>을 위한 사상체질진단과 변증에 대한 임상정보/지식 구축. 2007.
  10. Kang JH, Yoo JH, Lee HJ, Kim JY. Automated Speech Analysis Applied to Sasang Constitution Classification. J of the Korean society of Speech Sciences. 2009;1(3): 159-165. (Korean)