A predictive metric based on discriminant statistical analysis
ICSE '97 Proceedings of the 19th international conference on Software engineering
Empirical Data Modeling in Software Engineering Using Radial Basis Functions
IEEE Transactions on Software Engineering
Computational intelligence as an emerging paradigm of software engineering
SEKE '02 Proceedings of the 14th international conference on Software engineering and knowledge engineering
Uncertain Classification of Fault-Prone Software Modules
Empirical Software Engineering
Machine Learning and Software Engineering
Software Quality Control
Knowledge-Sharing Issues in Experimental Software Engineering
Empirical Software Engineering
Comparative Assessment of Software Quality Classification Techniques: An Empirical Case Study
Empirical Software Engineering
A performance study of gaussian kernel classifiers for data mining applications
ADMA'06 Proceedings of the Second international conference on Advanced Data Mining and Applications
Hi-index | 0.00 |
During software development, early identification of critical components is of much practical significance since it facilitates allocation of adequate resources to these components in a timely fashion and thus enhance the quality of the delivered system. The purpose of this paper is to develop a classification model for evaluating the criticality of software components based on their software characteristics. In particular, we employ the radial basis function machine learning approach for model development where our new, innovative algebraic algorithm is used to determine the model parameters. For experiments, we used the USA-NASA metrics database that contains information about measurable features of software systems at the component level. Using our principled modeling methodology, we obtained parsimonious classification models with impressive performance that involve only design metrics available at earlier stage of software development. Further, the classification modeling approach was non-iterative thus avoiding the usual trial-and-error model development process.