基于改进BP算法的软件缺陷预测模型研究

Research on software defect prediction model based on improved BP algorithm

针对传统软件测试成本高及测试过程依赖于软件用例的设置等问题,设计了基于BP,JCUDA_BP和JCUDASA_BP的软件缺陷预测模型,并通过调研、实验的方式对基于改进BP算法的软件缺陷预测算法进行了相关的研究分析,探讨了JCUDA技术对于BP算法的影响,证明了模拟退火算法与JCUDA技术相结合的方式具有改进软件缺陷预测模型的可能性。

Since the cost of traditional software testing is high,and the test process relies on the set of software use case,a software defect prediction model based on BP,JCUDA_BP and JCUDASA_BP was designed. The software defect prediction algorithm based on improved BP algorithm is relevantly researched and analyzed by means of survey and experiment. The influence of JCUDA technology on BP algorithm is discussed,which proved that the combination of simulated annealing algorithm and JCUDA technology can improve the software defect prediction model.