Optimization of Object-Oriented Metrics using Hopfield Neural Network
Vijay Pal Dhaka1, Swati Agrawal2
1Dr.Vijay Pal Dhaka, Head of Computer & Engg.Deptt. Jaipur National University, India
2Swati Agrawal, Research scholar, Computer & Engg.Deptt. Jaipur National University, India.
Manuscript received on June 03, 2013. | Revised Manuscript received on June 29, 2013. | Manuscript published on July 05, 2013. | PP: 165-168 | Volume-3 Issue-3, July 2013. | Retrieval Number: C1688073313/2013©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: This paper examined the application of Artificial neural network for software quality prediction using objectoriented metrics. Quality estimation include estimating maintainability of software. In this study maintenance effort was chosen as the dependent variable and principal components of object-oriented metrics as the dependent variables. We are prediction the number of lines per changed per class. Two neural network models are used, they are ward neural network and Hopfield neural network. The Artificial neural network prossesses the advantages of predicting software quality accurately and identifies the defects by efficient discovery mechanisms.
Keywords: Software quality metrics, maintainability, object-oriented, neural network, principal component analysis.