Neural Network Based Effort Estimation Using Class Points for OO Systems

Authors:
S. Kanmani;J. Kathiravan;S. Senthil Kumar;M. Shanmugam
Affiliations:
Pondicherry Engineering College, India;Pondicherry Engineering College, India;Pondicherry Engineering College, India;Pondicherry Engineering College, India
Venue:
ICCTA '07 Proceedings of the International Conference on Computing: Theory and Applications
Year:
2007

Citing 0
Cited 3

A Comparison of Neural Network Model and Regression Model Approaches Based on Sub-functional Components

IWSM '09 /Mensura '09 Proceedings of the International Conferences on Software Process and Product Measurement
Component Point: A system-level size measure for Component-Based Software Systems

Journal of Systems and Software
Probabilistic size proxy for software effort prediction: A framework

Information and Software Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Class points have been accepted to estimate the size of Object Oriented (OO) products and to directly predict the effort, cost and duration of the software projects. Most estimation models in use or proposed in the literature are based on regression techniques. In this paper, we attempt on using neural networks to estimate the development effort of OO systems using class points. The estimation model uses class points as the independent variable and development effort as the dependent variable. The results show that the estimation accuracy is higher in neural networks compared to the regression model. This experiment is carried out using the data set used in the literature.