An evolutionary computational approach to probabilistic neural network with application to hepatic cancer diagnosis

Author

Gorunescu, F. ; Gorunescu, M. ; El-Darzi, E. ; Gorunescu, S.

Author_Institution

Dept. of Math., Biostat. & Comput. Sci., Univ. of Medicine & Pharmacy of Craiova, Romania

fYear

2005

fDate

23-24 June 2005

Firstpage

461

Lastpage

466

Abstract

The performance of a probabilistic neural network is strongly influenced by the smoothing parameter. This paper introduces an evolutionary approach based on genetic algorithm to optimise the search of the smoothing parameter in a modified probabilistic neural network. A Java implementation is introduced and the computational results showed the viability of this hybrid approach to determine the optimum diagnosis for hepatic diseases.

Keywords

Java; cancer; genetic algorithms; liver; medical diagnostic computing; neural nets; search problems; tumours; Java implementation; evolutionary computational approach; genetic algorithm; hepatic cancer diagnosis; hybrid approach; probabilistic neural network; search optimisation; smoothing parameter; Application software; Biological neural networks; Cancer; Computer networks; Computer science; Electronic mail; Genetic algorithms; Mathematics; Neural networks; Smoothing methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 2005. Proceedings. 18th IEEE Symposium on

Conference_Location

Dublin

ISSN

1063-7125

Print_ISBN

0-7695-2355-2

Type

conf

DOI

10.1109/CBMS.2005.24

Filename

1467734