사상체질의학회지 (Journal of Sasang Constitutional Medicine)

  • 제33권4호
  • /
  • Pages.1-9
  • /
  • 2021
  • /
  • 1226-4075(pISSN)
  • /
  • 2287-786X(eISSN)
사상체질의학회 (The Society Of Sasang Constitutional Medicine)
권호 표지
DOI QR코드

DOI QR Code

머신러닝 기반 음성분석을 통한 체질량지수 분류 예측 - 한국 성인을 중심으로

Application of Machine Learning on Voice Signals to Classify Body Mass Index - Based on Korean Adults in the Korean Medicine Data Center

  • 김준호 (한국한의학연구원 한의약데이터부) ;
  • 박기현 (한국한의학연구원 한의약데이터부) ;
  • 김호석 (한국한의학연구원 한의약데이터부) ;
  • 이시우 (한국한의학연구원 한의약데이터부) ;
  • 김상혁 (한국한의학연구원 한의약데이터부)
  • Kim, Junho (KM Data Division, Korea Institute of Oriental Medicine) ;
  • Park, Ki-Hyun (KM Data Division, Korea Institute of Oriental Medicine) ;
  • Kim, Ho-Seok (KM Data Division, Korea Institute of Oriental Medicine) ;
  • Lee, Siwoo (KM Data Division, Korea Institute of Oriental Medicine) ;
  • Kim, Sang-Hyuk (KM Data Division, Korea Institute of Oriental Medicine)
  • 투고 : 2021.09.08
  • 심사 : 2021.10.18
  • 발행 : 2021.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objectives The purpose of this study was to check whether the classification of the individual's Body Mass Index (BMI) could be predicted by analyzing the voice data constructed at the Korean medicine data center (KDC) using machine learning. Methods In this study, we proposed a convolutional neural network (CNN)-based BMI classification model. The subjects of this study were Korean adults who had completed voice recording and BMI measurement in 2006-2015 among the data established at the Korean Medicine Data Center. Among them, 2,825 data were used for training to build the model, and 566 data were used to assess the performance of the model. As an input feature of CNN, Mel-frequency cepstral coefficient (MFCC) extracted from vowel utterances was used. A model was constructed to predict a total of four groups according to gender and BMI criteria: overweight male, normal male, overweight female, and normal female. Results & Conclusions Performance evaluation was conducted using F1-score and Accuracy. As a result of the prediction for four groups, The average accuracy was 0.6016, and the average F1-score was 0.5922. Although it showed good performance in gender discrimination, it is judged that performance improvement through follow-up studies is necessary for distinguishing BMI within gender. As research on deep learning is active, performance improvement is expected through future research.

키워드

과제정보

이 연구는 2021년도 한국한의학연구원의 '빅데이터 기반 한의 예방 치료 원천기술 개발'(KSN2022120)의 지원을 받아 수행되었습니다.

참고문헌

  1. Rajkomar A, Dean J, Kohane I. Machine Learning in Medicine. N Engl J Med. 2019;380:1347-1358. https://doi.org/10.1056/NEJMra1814259
  2. Kim H, Yang SB, Kang Y, Park YB, Kim JH. Machine learning approach to blood stasis pattern identification based on self-reported symptoms. Korean J Acupunct. 2016;33(3):102-113. (Korean) DOI:10.14406/acu.2016.011
  3. Kim E, Park YB, Lim YW, Ok JM, Noh EY, Song TM, et al. Application of Machine Learning to Predict Weight Loss in Overweight, and Obese Patients on Korean Medicine Weight Management Program. J Korean Med. 2020;41(2):58-79. (Korean) DOI:10.13048/jkm.20015
  4. Sharma K, Kaur A, Gujral S. Brain tumor detection based on machine learning algorithms. Int J Comput Appl. 2014;103(1):7-11. https://doi.org/10.5120/18036-6883
  5. Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI. Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J. 2015;13:8-17. DOI:10.1016/j.csbj.2014.11.005
  6. Wu CC, Hsu WD, Islam MM, Poly TN, Yang HC, Nguyen PA, et al. An artificial intelligence approach to early predict non-ST-elevation myocardial infarction patients with chest pain. Comput Methods Programs Biomed. 2019;173:109-117. DOI:10.1016/j.cmpb.2019.01.013
  7. Wang S, Summers RM. Machine learning and radiology. Med Image Anal. 2012;16(5):933-51. DOI:10.1016/j.media.2012.02.005
  8. Cho DU. Sasang Constitution Classification by Speech Signal Processing, J of Korea Information and Communications Society. 2006;31(5C):548-555. (Korean)
  9. Ghazanfar, Asif A, Rendall D. Evolution of human vocal production. Current Biology. 2008;18(11):R457-R460. DOI: 10.1016/j.cub.2008.03.030.
  10. Evans S, Neave N, Wakelin D. Relationships between vocal characteristics and body size and shape in human males: An evolutionary explanation for a deep male voice. Biological Psychology. 2006;72(2):160-163. DOI: 10.1016/j.biopsycho.2005.09.003.
  11. Y. F. Liao, M. L. Chuang, C. S. Huang, and Y. Y. Tsai. Upper airway and its surrounding structures in obese and nonobese patients with sleep-disordered breathing. Laryngoscope. 2004;114(6):1052-1059. https://doi.org/10.1097/00005537-200406000-00018
  12. Lee BJ, Ku B, Jang JS, Kim JY. A Novel Method for Classifying Body Mass Index on the Basis of Speech Signals for Future Clinical Applications: A Pilot Study. Evid Based Complement Alternat Med. 2013;2013:150265. DOI: 10.1155/2013/150265.
  13. Pisanski K, Jones B, Fink B, O'Connor J, DeBruine L, Roder S, et al. Voice parameters predict sex-specific body morphology in men and women. Animal Behaviour. 2016;112:13-22. DOI:10.1016/j.anbehav.2015.11.008
  14. L. L. Yan, M. L. Daviglus, K. Liu et al. BMI and health-related quality of life in adults 65 years and older. Obesity Research. 2004;12(1):69-76. DOI:10.1038/oby.2004.10
  15. Park HS, Yun YS, Park JY, Kim YS, Choi JM. Obesity, abdominal obesity, and clustering of cardiovascular risk factors in South Korea. Asia Pacific Journal of Clinical Nutrition. 2003;12(4):411-418.
  16. Kim JY, Chang HM, Cho JJ, Yoo SH, Kim SY. Relationship between obesity and depression in the Korean working population. J Korean Medical Science. 2010;25(11):1560-1567. DOI: 10.3346/jkms.2010.25.11.1560
  17. Anuurad E, Shiwaku K, Nogi A, Kitajima K, Enkhmaa B, Shimono K, et al. The new BMI criteria for asians by the regional office for the western pacific region of WHO are suitable for screening of overweight to prevent metabolic syndrome in elder Japanese workers. J Occup Health. 2003;45(6):335-43. DOI:10.1539/joh.45.335
  18. Hall WL, Larkin GL, Trujillo MJ, Hinds JL, Delaney KA. Errors in weight estimation in the emergency department: comparing performance by providers and patients. J Emerg Med. 2004; 27(3):219-24. DOI: 10.1016/j.jemermed.2004.04.008.
  19. Kang HJ. Factors Influencing Korean Adolescents' Body Weight Perceptions and Weight Change Efforts. Perspectives in Nursing Science. 2012;9(1):24-35. (Korean)
  20. Ministry of Justice. Immigration Statistics. Available from:URL:https://www.moj.go.kr/moj/2412/sub view.do accessed Sep 22,2021. (Korean)
  21. Kang JH, Do JH, Kim JY. Voice Classification Algorithm for Sasang Constitution Using Support Vector Machine. J of Sasang Constitutional Medicine. 2010;22(1):17-25. (Korean)
  22. Muda L, Begam M, Elamvazuthi I. Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. J Computing. 2010;2(3):138-143.
  23. Ahn S. Deep Learning Architectures and Applications. J Intell Inform Syst. 2016;22(2):127-142. (Korean) https://doi.org/10.13088/JIIS.2016.22.2.127
  24. Gonzalez J. Formant frequencies and body size of speaker: a weak relationship in adult humans. J Phonetics. 2004;32(2):277-287. DOI: 10.1016/S0095-4470(03)00049-4
  25. Hong SJ, Lee SW, Yoon MS et al. Trends and Prospects in the Application of AI Technology for Creative Contents. Electronics and Telecommunications Trends. 2020;35(5):123-133. (Korean) DOI: 10.22648/ETRI.2020.J.350511
  26. Chae H, Lyoo IK, Lee SJ et al. An alternative way to individualized medicine: psychological and physical traits of Sasang typology. J Alternative and Complementary Medicine. 2003;9(4):519-528. DOI: 10.1089/107555303322284811.
  27. Pham DD, Do JH, Ku B, Lee HJ, Kim H, Kim JY. Body mass index and facial cues in Sasang typology for young and elderly persons. Evid Based Complement Alternat Med. 2011;2011:749209. DOI:10.1155/2011/749209
  28. Kim SH, Park KH, Baek YH, Jang ES, Lee S. The Reduction of Question Items in KS-15 (Korea Sasang Constitutional Diagnostic Questionnaire). J Sasang Constitut Med. 2020;32(1):30-38. (Korean) DOI: 10.7730/JSCM.2020.32.1.30