The effect of generalized discriminate analysis (GDA) to the classification of optic nerve disease from VEP signals.
Comput Biol Med
; 38(1): 62-8, 2008 Jan.
Article
en En
| MEDLINE
| ID: mdl-17709102
ABSTRACT
In this paper, we have investigated the effect of generalized discriminate analysis (GDA) on classification performance of optic nerve disease from visual evoke potentials (VEP) signals. The GDA method has been used as a pre-processing step prior to the classification process of optic nerve disease. The proposed method consists of two parts. First, GDA has been used as pre-processing to increase the distinguishing of optic nerve disease from VEP signals. Second, we have used the C4.5 decision tree classifier, Levenberg Marquart (LM) back propagation algorithm, artificial immune recognition system (AIRS), linear discriminant analysis (LDA), and support vector machine (SVM) classifiers. Without GDA, we have obtained 84.37%, 93.75%, 75%, 76.56%, and 53.125% classification accuracies using C4.5 decision tree classifier, LM back propagation algorithm, AIRS, LDA, and SVM algorithms, respectively. With GDA, 93.75%, 93.86%, 81.25%, 93.75%, and 93.75% classification accuracies have been obtained using the above algorithms, respectively. These results show that the GDA pre-processing method has produced very promising results in diagnosis of optic nerve disease from VEP signals.
Buscar en Google
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Procesamiento de Señales Asistido por Computador
/
Enfermedades del Nervio Óptico
/
Potenciales Evocados Visuales
Tipo de estudio:
Diagnostic_studies
/
Prognostic_studies
Límite:
Adult
/
Female
/
Humans
/
Male
/
Middle aged
Idioma:
En
Revista:
Comput Biol Med
Año:
2008
Tipo del documento:
Article
País de afiliación:
Turquía