계층적 신경회로망을 이용한 후두질환 감별 분류기

Implementation on the Classifier for Differential Diagnosis of Laryngeal Disease using Hierarchical Neural Network

  • 김경태 (부산대학교 의공학과) ;
  • 김길중 (동서대학교 전자공학과) ;
  • 전계록 (부산대학교 의과대학 의공학교실)
  • 발행 : 2002.02.01

초록

본 연구에서는 계층적 신경회로망을 사용하여 정상, 후두질환(polyp, nodule, palsy 등), 후두질환 중 성문암 시기별 감별진단이 가능한 후두질환 감별진단 분류기를 구현하였다. 후두질환을 가진 환자군과 정상군, 그리고 성문암의 각 시기별에 해당되는 환자군으로부터 /a/, /e/, /i/, /o/, /u/ 모음에 따른 분류작업을 수행하였다. 각 모음별 분류 실험을 수행한 결과 모든 입력 파라미터에 대해서 /a/모음이 다른 모음에 비해 우수한 분류율을 나타내므로, /a/모음만을 사용하여 후두질환을 감별진단하기 위한 계층적 신경회로망을 구현하였다. 구현된 계층적 신경회로망은 각 계층별로 서로 다른 파라미터들을 적용하여 여러 후두질환을 감별진단하도록 구성되었다.

In this paper, we implemented on the classifier for differential diagnosis of laryngeals disease which is normal, polyp, nodule, palsy, and each step of glottic cancer using hierarchical neural network. We conducted on classifier of various vowels as /a/, /e/, /i/, /o/, /u/ from normal group, laryngeal disease group, each step of cancer group. The experimental result on classification of each vowels as follows. A /a/ vowel shows excellent classification result to the other vowels in regard to each Input parameters. Thus we implemented the hierarchical neural network for differential diagnosis of laryngeals disease using only /a/ vowel. A implemented hierarchical neural network is composed of each other laryngeals disease apply to each other parameter in each hierarchical layer. We take the voice signals from patient who get the laryngeal disease and glottic cancer, and then use the APQ, PPQ, vAm, Jitter, Shimmer, RAP as input parameter of neural networks.

키워드

참고문헌

  1. 안회영,'음성검사법',진수출판사,1992
  2. M. Bensaid S. Ciocea, 'Estimation by means of wavelet analysis of the signal-to-noise ratio of dysphonic voices', Proceeding of the ProRISC Workshop on Circits, 1997
  3. M. Bensaid, J, Schoentgen and S. Ciocea, 'Estimation of formant frequencies by means of a wavelet transform of the speech spectrum' Proceeding of the ProRISC Workshop on Circits, 1997
  4. Nobuaki Hiraoka, Yasuhiro Kitazoe et.al., 'Harmonic-intensity analysis of normal and hoarse voices', J.Acoust. Soc. Am 76(6), December 1984
  5. Horri. Y, ' Vocal shimmer in sustained phonation', Journal of Speech and Hearing Research, Vol. 23, March 1980, pp.202-209 https://doi.org/10.1044/jshr.2301.202
  6. Horii. Y, ' Jitter and Shimmer in sustained vocal fry phonation', Folia Phoniatrica, Vol.37, 1985 pp.81-86 https://doi.org/10.1159/000265785
  7. Hideki Kasuya , Shigeki Ogawa et. al., 'Normalized noise energy as an acoustic measure to evaluate pathologic voice', J.Acoust. Soc. Am 80(5), November 1986 https://doi.org/10.1121/1.401678
  8. Askenfelt. A & Hammarberg. B., ' Speech wave- form perturbation analysis: A perceptual acoustic comparison of seven measures', Journal of Speech and Hearing Research, Vol.29, 1986
  9. Neil B. Cox , Mabo R. Ito , Murray D. Morrison, ' Technical considerations in computation of spectral harmonics to noise ratios for sustained vowels', Journal of Speech and Hearing Research, Volume 32, 203-218, March 1989 https://doi.org/10.1044/jshr.3201.203
  10. Kitajima. K, & Gould. W, ' Vocal shimmer in sustained phonation of normal and pathologic voice', Ann. Otorhinolatyngology, Vol.85, No.6, 1976