DocumentCode
2447272
Title
An Experiment on the Design of Radial Basis Function Neural Networks for Software Cost Estimation
Author
Idri, Ali ; Abran, Alain ; Mbarki, Samir
Author_Institution
Dept. of Software Eng., Mohamed V Univ., Rabat
Volume
1
fYear
0
fDate
0-0 0
Firstpage
1612
Lastpage
1617
Abstract
This paper is concerned with the use of radial basis function (RBF) neural networks for software cost estimation. The study is devoted to the design of these networks, especially their middle layer composed of receptive fields, using two clustering techniques: the C-means and the APC-III algorithms. A comparison between an RBFN using C-means and an RBFN using APC-III, in terms of estimates accuracy, is hence presented. This study is based on the COCOMO´81 dataset
Keywords
radial basis function networks; software cost estimation; APC-III algorithms; C-means clustering; COCOMO´81 dataset; radial basis function neural networks; software cost estimation; Artificial neural networks; Biological system modeling; Clustering algorithms; Computer architecture; Cost function; Electronic mail; Neural networks; Neurons; Programming; Radial basis function networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Information and Communication Technologies, 2006. ICTTA '06. 2nd
Conference_Location
Damascus
Print_ISBN
0-7803-9521-2
Type
conf
DOI
10.1109/ICTTA.2006.1684625
Filename
1684625
Link To Document