Prediction of Software Reliability Using Connectionist Models
IEEE Transactions on Software Engineering
C4.5: programs for machine learning
C4.5: programs for machine learning
The nature of statistical learning theory
The nature of statistical learning theory
Handbook of software reliability engineering
Handbook of software reliability engineering
Data mining: practical machine learning tools and techniques with Java implementations
Data mining: practical machine learning tools and techniques with Java implementations
Data mining: concepts and techniques
Data mining: concepts and techniques
On the neural network approach in software reliability modeling
Journal of Systems and Software
ECML '95 Proceedings of the 8th European Conference on Machine Learning
Software Reliability Engineering: More Reliable Software Faster and Cheaper
Software Reliability Engineering: More Reliable Software Faster and Cheaper
System Software Reliability (Springer Series in Reliability Engineering)
System Software Reliability (Springer Series in Reliability Engineering)
On-line prediction of software reliability using an evolutionary connectionist model
Journal of Systems and Software
Software reliability forecasting by support vector machines with simulated annealing algorithms
Journal of Systems and Software
Software reliability prediction by soft computing techniques
Journal of Systems and Software
Application of support vector machine to predict fault prone classes
ACM SIGSOFT Software Engineering Notes
Predicting software reliability with neural network ensembles
Expert Systems with Applications: An International Journal
Software Process: Improvement and Practice
Application of feed-forward neural networks for software reliability prediction
ACM SIGSOFT Software Engineering Notes
Hi-index | 0.00 |
Application of a soft computing approach in place of traditional statistical techniques has shown a remarkable improvement in reliability prediction. This paper examines and compares Linear Regression (LR) and five machine learning methods: (Artificial Neural Network, Support Vector Machine, Decision Tree, Fuzzy Inference System and Adaptive Neuro-Fuzzy Inference System). These methods are explored empirically to find the effect of severity of errors for the assessment of software testing time. We use two publicly available failure datasets to analyse and compare the regression and machine learning methods for assessing the software testing time. The performance of the proposed model is compared by computing mean absolute error (MAE) and root mean square error (RMSE). Based on the results from rigours experiments, it is observed that model accuracy using FIS and ANFIS method is better and outperformed the model predicted using linear regression and other machine learning methods. Finally, we conclude that Adaptive Neuro-fuzzy Inference System is useful in constructing software quality models having better capability of generalization and less dependent on sample size.