Research on a Method of Software Reliability Prediction Model

Software defects seriously affect software reliability. Software reliability is accurately predicted, which can guarantee normal use of software. For the prediction of software reliability, a software reliability prediction model based on support vector regression is constructed. Firstly, software metrics are extracted. Then data is preprocessed by the method of normalization and random sequence, and it is divided into training sets and testing sets for regression prediction; Secondly, the grid search method is introduced to optimize parameters in the support vector regression model; Finally, through experimental comparison and analysis, it is proved that this prediction method can indeed greatly improve the prediction accuracy of software reliability.

[1]  A. Jefferson Offutt,et al.  Increased software reliability through input validation analysis and testing , 1999, Proceedings 10th International Symposium on Software Reliability Engineering (Cat. No.PR00443).

[2]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[3]  Olcay Taner Yildiz,et al.  Software defect prediction using Bayesian networks , 2012, Empirical Software Engineering.

[4]  Changzhen Hu,et al.  Software defect prediction model based on improved LLE-SVM , 2015, 2015 4th International Conference on Computer Science and Network Technology (ICCSNT).

[5]  Suhaimi Ibrahim,et al.  A Prediction Model for System Testing Defects using Regression Analysis , 2012, SOCO 2012.

[6]  Jongmoon Baik,et al.  Value-cognitive boosting with a support vector machine for cross-project defect prediction , 2014, Empirical Software Engineering.

[7]  Divya Tomar,et al.  Prediction of software defects using Twin Support Vector Machine , 2014, 2014 International Conference on Information Systems and Computer Networks (ISCON).

[8]  Ali Selamat,et al.  An empirical study based on semi-supervised hybrid self-organizing map for software fault prediction , 2015, Knowl. Based Syst..