Maintainability Prediction of Object Oriented Software System by using Artificial Neural Network Approach
Yajnaseni Dash1, Sanjay Kumar Dubey2, Ajay Rana3
1Yajnaseni Dash, Department of Computer Science & Engineering, Amity School of Engineering & Technology, Amity University, Sec-125, Noida, U.P., 201301, India.
2Sanjay Kumar Dubey, Department of Computer Science & Engineering, Amity School of Engineering & Technology, Amity University, Sec-125, Noida, U.P., 201301, India.
3Ajay Rana, Department of Computer Science & Engineering, Amity School of Engineering & Technology, Amity University, Sec-125, Noida, U.P., 201301, India.
Manuscript received on April 11, 2012. | Revised Manuscript received on April 14, 2012. | Manuscript published on May 05, 2012. | PP: 420-423 | Volume-2 Issue-2, May 2012 . | Retrieval Number: B0636042212/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Maintainability is an imperative attribute of software quality. However the prediction of this attribute is a cumbersome process. Therefore various methodologies are proposed so far to estimate the maintainability of software. Among them Artificial Neural Network is one of the sophisticated techniques which have immense prediction capability and this paper explores its application to evaluate maintainability of the object-oriented software. In this study maintenance effort was chosen as the dependent variable and principal components of object-oriented metrics as the independent variables. Prediction of maintainability is performed by Multi Layer Perceptron (MLP) neural network model. The results obtained from the current study are also compared with other models and it is revealed that the presented model is more useful than the previous one.
Keywords: Artificial neural network, Maintainability, Object oriented metrics, Principal component analysis.