S. Kanmani
Abstract
This paper discusses the application of General Regression Neural Network (GRNN) for predicting the software quality attribute -- fault ratio. This study is carried out using static Object-Oriented (OO) measures (64 in total) as the independent variables and fault ratio as the dependent variable. Software metrics used include those concerning inheritance, size, cohesion and coupling. Prediction models are designed using 15 possible combinations of the four categories of the measures. We also tested the goodness of fit of the neural network model with the standard parameters. Our study is conducted in an academic institution with the software developed by students of Undergraduate/Graduate courses.
- Khoshgoftaar T. M., R. M. Szabo and P. J. Guasti (1995): Exploring the Behavior of Neural Network Software Quality Models, Software Engineering Journal May, pp. 89--96.Google Scholar
- Specht D. F (1991):, A General Regression Neural Network, IEEE Transactions on Neural Networks, vol. 2, no. 6, pp. 568--576.Google ScholarDigital Library
- Quah T. S, and M. M. T. Thewin (2003): Application of Neural Networks for Software Quality Prediction using Object-Oriented Metrics, Proceedings of the International Conference on Software Maintenance (ICSM'03), Vol 3. Google ScholarDigital Library
- Thewin M. M, and T. S. Quah (2003): Application of Neural Networks for Predicting Software Development Faults using O-O Design Metrics. Proceedings of 9th International Conference on Neural Information Processing (ICONIP 2002), vol5, pp 2312--2316.Google Scholar
- Khoshgoftaar T. M., E. B. Allen, J. P. Hidepohl, and S. J. Aud (1997): Application of Neural Networks to Software Quality Modeling of a very Large-Scale Telecommunications Systems, IEEE Transactions on Neural Networks, vol 8, no 4, July pp. 902--909. Google ScholarDigital Library
- Khoshgoftaar T. M., E. B. Allen, and Z. Xu (2000): Predicting Testability of Program Modules using Neural Networks, Proceedings of 3rd IEEE Symposium on Applied Specific Systems and Software Engineering Techniques -- March, pp. 57--62. Google ScholarDigital Library
- Khoshgoftaar T. M, and R. M. Szabo (1995): Detecting Program Modules with Low Testability, Proceedings of the International Conference on Software Maintenance, 1995, pp. 242--250. Google ScholarDigital Library
- Khoshgoftaar T. M, and R. M. Szabo (1994): Improving Neural Network Predictions of Software Quality using Principal Components Analysis, Proceedings of IEEE International World Congress on Computational Intelligence, pp. 3295--3300.Google ScholarCross Ref
- Khoshgoftaar T. M., A. S. Pandya and H. M. More (1992): A Neural Network Approach for Predicting Software Development Faults, Proceedings of 3rd IEEE ISSRE, pp. 83--89.Google ScholarCross Ref
- Matlab Neural network Tool Box and Manual. Mathworks Inc.Google Scholar
- Briand L., J. Wust, J. W. Daly, D. V. Porter (2000): Exploring the Relationships Between Design Measures and Software Quality, Journal of Systems and Software, 51, pp. 245--273. Google ScholarDigital Library
- Kanmani S., V. Prathiba (2001): Object Oriented Metric Calculator, Technical Report, Pondicherry Engineering College.Google Scholar
- Kanmani S., V. Sankaranarayanan and P. Thambidurai (2003): A Measurement Model for C++ Program Complexity Analysis, Proceddings of the 9th International Conference EPMESC, Macao, China, pp. 575--580.Google Scholar
Index Terms
- Object oriented software quality prediction using general regression neural networks
Recommendations
Software fault prediction for object oriented systems: a literature review
There always has been a demand to produce efficient and high quality software. There are various object oriented metrics that measure various properties of the software like coupling, cohesion, inheritance etc. which affect the software to a large ...
Neural Network-Based Model for the Quality Assessment of Object-Oriented Software
Software quality assessment is an important subject among the researchers in the software development domain. The quality assessment is generally done either at the design level through some of the design attributes or through code when the product is ...
Maintainability prediction of object-oriented software system by multilayer perceptron model
To accomplish software quality, correct estimation of maintainability is essential. However there is a complex and non-linear relationship between object-oriented metrics and maintainability. Thus maintainability of object-oriented software can be ...
Comments