Using SVM Models to Predict Risk of Avionics Software Fix

摘要：

In the various stages of the avionics software life cycle, any changes of the software may introduce some new defects. The prediction for the defects brought by the software fixes in the early stage of software development is important for the project risk management and the plan of the software regression test. In this paper, a method to predict defects based on the SVM is proposed. This method can solve the problem that the defect brought by the software is hard to control. The prediction results lie on the following metrics: software fix metrics, program structural metrics and dependency metrics. The experiment shows that this method is feasible and effective.

关键词： SVM avionics software software fix risk predictions software defect prediction

作者: Zheng Jun Yu Siwen Liu Chang

作者单位: A VIC Aero Poly-technology Establishment Beijing, China

会议类型: 国际会议

会议名称: 2011 International Conference on Information and Industrial Electronics(2011年信息与工业电子国际会议 ICIIE 2011)

会议地点: 成都

会议语种:英文

页码: 847-851

在线出版日期: 2011-01-14（万方平台首次上网日期，不代表论文的发表时间）