Browse > Article

A Basic Study on the Differential Diagnostic System of Laryngeal Diseases using Hierarchical Neural Networks  

전계록 (부산대학교 의과대학 의공학교실)
김기련 (부산대학교 대학원 의공학협동과정)
권순복 (부산대학교 대학원 의공학협동과정)
예수영 (부산대학교 대학원 의공학협동과정)
이승진 (부산대학교 대학원 의공학협동과정)
왕수건 (부산대학교 의과대학 이비인후학교실)
Publication Information
Journal of Biomedical Engineering Research / v.23, no.3, 2002 , pp. 197-205 More about this Journal
Abstract
The objectives of this Paper is to implement a diagnostic classifier of differential laryngeal diseases from acoustic signals acquired in a noisy room. For this Purpose, the voice signals of the vowel /a/ were collected from Patients in a soundproof chamber and got mixed with noise. Then, the acoustic Parameters were analyzed, and hierarchical neural networks were applied to the data classification. The classifier had a structure of five-step hierarchical neural networks. The first neural network classified the group into normal and benign or malign laryngeal disease cases. The second network classified the group into normal or benign laryngeal disease cases The following network distinguished polyp. nodule. Palsy from the benign laryngeal cases. Glottic cancer cases were discriminated into T1, T2. T3, T4 by the fourth and fifth networks All the neural networks were based on multilayer perceptron model which classified non-linear Patterns effectively and learned by an error back-propagation algorithm. We chose some acoustic Parameters for classification by investigating the distribution of laryngeal diseases and Pilot classification results of those Parameters derived from MDVP. The classifier was tested by using the chosen parameters to find the optimum ones. Then the networks were improved by including such Pre-Processing steps as linear and z-score transformation. Results showed that 90% of T1, 100% of T2-4 were correctly distinguished. On the other hand. 88.23% of vocal Polyps, 100% of normal cases. vocal nodules. and vocal cord Paralysis were classified from the data collected in a noisy room.
Keywords
Laryngeal disease; Diagnosis of differential disease; Noise; Classifier; Acoustic signal;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 음향신호의 분석에 의한 후두직환의 진단에 관한 연구 /
[ 조철우;양병곤;왕수건 ] / 한국음성과학회지   과학기술학회마을
2 Harmonic-to-noise ratio as an index of the degree of hoarseness /
[ E.Yumoto;W.J.Gould;T.Baer ] / J. Acoust Soc Am   DOI   ScienceOn
3 /
[ Taik Sup Auh ] / Quantitative Analysis of Social Science Data SAS/SPSS PC+
4 Vocal shimmer in sustained phonation /
[ Y,Horri ] / Journal of Speech and Hearing Research   DOI
5 Time and Frequency Synthesis Parameters of Severely Pathological voice Qualities /
[ Abeer Alwan;Phibert Bangayan;Jody Kreiman;christopher Long ] / Proc.ICPhS 95
6 자동응답시스템을 이용한 후두질환 특징 파라미터 추출 /
[ 김기련;김용주;권순복;김광인;김대현;양병곤;왕수건;전계록 ] / 대한의료정보학회지
7 /
[ T.H.Martin;B.D.Howard;B.Mark ] / Neural network design
8 /
[ Daniel R.Boone ] / 음성과 음성치료
9 Normalized noise energy as an acoustic measure to evaluate pathologic voice /
[ H.Kasuya;S.Ogawa;K.Mashima;S.Ebihara ] / J.Acoust.Soc.Am.
10 신경회로망을 이용한 QRS 장애 음성의 식별에 관한연구 /
[ 조철루;김광인;김대횬;권순복;김기련;김용주;전계록;왕수건 ] / 한국음성과학회지   과학기술학회마을
11 /
[ 고도홍;정옥란(외 16인) ] / 음성 및 언어 분석기기 활용법
12 Anlaysis of Dysarthric Speech by meas of Formant-To-Area Mapping /
[ S.Ciocea;J.Schoentgen;L.Crevier-Buchman ] / Proc. Eurospeech 97
13 Cepstrum방법과 신경회로망을 이용한 정상, 양성종양, 악성종양 상태의 식별에 관한 연구 /
[ 조철우;김대현 ] / 한국음향학회 학술대회 논문집
14 병적 음성의 감별 진단을 위한 음향학적 변수 /
[ 왕수건;양병곤;조철우;박현민;권순복;김태섭;홍현석 ] / 대한이비인후과학회지
15 은성신호를 이용한 후두질환 감별진단 알고리듬 개발 /
[ 김기련;김용주;권순복;전계록;왕수건 ] / 대한의용생체공학회 추계학술대회
16 /
[ L.R,Rabiner;R,W,Schafer ] / Digital Processing of Speech Signal