Reference Hub15
Functional Link Artificial Neural Networks for Software Cost Estimation

Functional Link Artificial Neural Networks for Software Cost Estimation

B. Tirimula Rao, Satchidananda Dehuri, Rajib Mall
Copyright: © 2012 |Volume: 3 |Issue: 2 |Pages: 21
ISSN: 1942-3594|EISSN: 1942-3608|EISBN13: 9781466610729|DOI: 10.4018/jaec.2012040104
Cite Article Cite Article

MLA

Rao, B. Tirimula, et al. "Functional Link Artificial Neural Networks for Software Cost Estimation." IJAEC vol.3, no.2 2012: pp.62-82. http://doi.org/10.4018/jaec.2012040104

APA

Rao, B. T., Dehuri, S., & Mall, R. (2012). Functional Link Artificial Neural Networks for Software Cost Estimation. International Journal of Applied Evolutionary Computation (IJAEC), 3(2), 62-82. http://doi.org/10.4018/jaec.2012040104

Chicago

Rao, B. Tirimula, Satchidananda Dehuri, and Rajib Mall. "Functional Link Artificial Neural Networks for Software Cost Estimation," International Journal of Applied Evolutionary Computation (IJAEC) 3, no.2: 62-82. http://doi.org/10.4018/jaec.2012040104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Software cost estimation is the process of predicting the effort required to develop a software system. Software development projects often overrun their planned effort as defined at preliminary design review. Software cost estimation is important for budgeting, risk analysis, project planning, and software improvement analysis. In this paper, the authors propose a faster functional link artificial neural network (FLANN) based software cost estimation. By means of preprocessing, i.e., optimal reduced datasets (ORD), the authors make the functional link artificial neural network faster. Optimal reduced datasets, which reduce the whole project base into small subsets that consist of only representative projects. The representative projects are given as input to FLANN and tested on eight state-of-the-art polynomial expansions. The proposed methods are validated on five real time datasets. This approach yields accurate results vis-à-vis conventional FLANN, support vector machine regression (SVR), radial basis function (RBF), classification, and regression trees (CART).

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.