Prediction of Software Readiness Using Neural Network

In this paper, we explore the behaviour of neural network in predicting software readiness. Our neural network model aims to predict the number of faults (including object- oriented faults) of a software under development. We use Ward neural network that is a backpropagation network with different activation functions. Different activation functions are applied to hidden layer slabs to detect different features in a pattern processed through a network. In our experiments, hyperbolic tangent, Gaussian, Gaussian-complement and linear functions are used as activation functions to improve prediction. This paper also compares the prediction results from multiple regression model and neural network model. Object-oriented design metrics are used as the independent variables in our study. Our study is conducted on three industrial real-time systems that contain a number of natural faults that has been reported over a period of three years.

[1]  Taghi M. Khoshgoftaar,et al.  Exploring the behaviour of neural network software quality models , 1995, Softw. Eng. J..

[2]  Javam C. Machado,et al.  The prediction of faulty classes using object-oriented design metrics , 2001, J. Syst. Softw..

[3]  Kapsu Kim,et al.  Identifying fault prone modules: an empirical study in telecommunication system , 1998, Proceedings of the Second Euromicro Conference on Software Maintenance and Reengineering.

[4]  Mei-Hwa Chen,et al.  An empirical study on object-oriented metrics , 1999, Proceedings Sixth International Software Metrics Symposium (Cat. No.PR00403).

[5]  L. Darrell Whitley,et al.  Prediction of software reliability using neural networks , 1991, Proceedings. 1991 International Symposium on Software Reliability Engineering.

[6]  L. Darrell Whitley,et al.  Prediction of Software Reliability Using Connectionist Models , 1992, IEEE Trans. Software Eng..

[7]  Lionel C. Briand,et al.  A Unified Framework for Coupling Measurement in Object-Oriented Systems , 1999, IEEE Trans. Software Eng..

[8]  Chris F. Kemerer,et al.  Towards a metrics suite for object oriented design , 2017, OOPSLA '91.

[9]  Hakim Lounis.  Identifying and Measuring Coupling on Modular Systems , 1997 .

[10]  Abhijit S. Pandya,et al.  A comparative study of pattern recognition techniques for quality evaluation of telecommunications software , 1994, IEEE J. Sel. Areas Commun..

[11]  Premkumar T. Devanbu,et al.  An Investigation into Coupling Measures for C++ , 1997, Proceedings of the (19th) International Conference on Software Engineering.

[12]  Victor R. Basili,et al.  A Validation of Object-Oriented Design Metrics as Quality Indicators , 1996, IEEE Trans. Software Eng..

[13]  Taghi M. Khoshgoftaar,et al.  Predicting testability of program modules using a neural network , 2000, Proceedings 3rd IEEE Symposium on Application-Specific Systems and Software Engineering Technology.

[14]  James M. Bieman,et al.  Cohesion and reuse in an object-oriented system , 1995, SSR '95.

[15]  Abhijit S. Pandya,et al.  A neural network approach for predicting software development faults , 1992, [1992] Proceedings Third International Symposium on Software Reliability Engineering.

[16]  Lionel C. Briand,et al.  Assessing the Applicability of Fault-Proneness Models Across Object-Oriented Software Projects , 2002, IEEE Trans. Software Eng..

[17]  Walcélio L. Melo,et al.  Polymorphism measures for early risk prediction , 1999, Proceedings of the 1999 International Conference on Software Engineering (IEEE Cat. No.99CB37002).

[18]  Sallie M. Henry,et al.  Object-oriented metrics that predict maintainability , 1993, J. Syst. Softw..

[19]  Kapsu Kim,et al.  Identifying fault-prone function blocks using the neural networks - an empirical study , 1997, 1997 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, PACRIM. 10 Years Networking the Pacific Rim, 1987-1997.

[20]  Chris F. Kemerer,et al.  A Metrics Suite for Object Oriented Design , 2015, IEEE Trans. Software Eng..

[21]  Lionel C. Briand,et al.  Predicting fault-prone classes with design measures in object-oriented systems , 1998, Proceedings Ninth International Symposium on Software Reliability Engineering (Cat. No.98TB100257).