Title :
Evaluation of neural classifiers using statistic methods for identification of laryngeal pathologies
Author :
de O.Rosa, M. ; Pereira, Jose Casimiro ; Carvalho, C. P L F
Author_Institution :
Escola de Engenharia, Sao Paulo Univ., Brazil
Abstract :
The use of statistical elements, like nonparametric tests and principal components analysis, allows the evaluation of the behavior and the performance of artificial neural networks when acoustical measurements are used to identify larynx diseases from which patterns are naturally overlapped. In this work, techniques to improve the results of neural network through the manipulation of the training patterns and convergence control will be discussed
Keywords :
acoustic signal processing; diseases; medical diagnostic computing; medical expert systems; medical signal processing; pattern classification; statistical analysis; PCA; acoustical measurements; convergence control; laryngeal pathology identification; larynx diseases; neural classifier evaluation; nonparametric tests; principal components analysis; statistical elements; statistical methods; training patterns; Acoustic measurements; Cancer; Diseases; Frequency; Jitter; Larynx; Pathology; Power harmonic filters; Speech; Statistics;
Conference_Titel :
Neural Networks, 1998. Proceedings. Vth Brazilian Symposium on
Conference_Location :
Belo Horizonte
Print_ISBN :
0-8186-8629-4
DOI :
10.1109/SBRN.1998.731033
