Research of Software Failure Prediction Based on Support Vector Regression

DOI

10.2991/iccasm.2012.329How to use a DOI?

Keywords

Software Reliability Prediction, Support Vector Regression, Artificial Neural Network

Abstract

Software failure prediction is currently a hot subject of research all over the world. The support vector regressions (SVRs) are very efficiency for solving regression problems. The parameters just as C performs very important roles in the generalization of SVR, and it’s hard for beginner to choose them. But in formar models, they diden’t care about this problem.A SVR-based generic model adaptive to the characteristic of the given data set is used for software failure time prediction. We also compare the prediction accuracy of software reliability prediction models based on 1-norm SVM, 2-norm SVM, v- SVM and artificial neural network (ANN). Experimental results by four data sets show that the new software reliability prediction model could achieve higher prediction accuracy than that of the ANN-based or SVM-based models.

Copyright

© 2012, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Qiuhong Zheng
PY  - 2012/08
DA  - 2012/08
TI  - Research of Software Failure Prediction Based on Support Vector Regression
BT  - Proceedings of the 2012 International Conference on Computer Application and System Modeling (ICCASM 2012)
PB  - Atlantis Press
SP  - 1289
EP  - 1292
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccasm.2012.329
DO  - 10.2991/iccasm.2012.329
ID  - Zheng2012/08
ER  -