基于机器学习理论的软件可靠性预测研究

由于软件可靠性早期预测在测试前就能够使开发和测试的相关人员对软件的可靠性有一定的了解．所以对于软件如何进一步开发、测试和质量的控制都具有十分重要的作用。该文将支持向量机理论引入到软件可靠性早期预测领域中来，提出了基于支持向量机的软件可靠性早期预测模型。通过对比仿真实验，证实了此模型同传统模型相比具有预测精度更高、泛化能力更强、对样本数量的依赖程度更低的特点。

The Study of Software Reliability Prediction Based on Machine Learn

As the early prediction of software reliability enables the developers and testers to get general ideas about the software reliability before testing it, it is important for further development, testing and quality control of software. This paper introduces SVM theory into the field of software reliability early prediction, and advances the software reliability early prediction model based on SVM. Simulation shows that compared with classic models, the new model has a better prediction precision, better generalization ability and a lower dependence on the number of samples.