组合统计模型在程序错误定位中的应用  

Apply composed statistical model in program fault localization

作　　者：骆桢轩[1] 

机构地区：[1]上海交通大学计算机科学与工程系

出　　处：《计算机工程与设计》2010年第19期4218-4220,4231,共4页Computer Engineering and Design

基　　金：国家自然科学基金项目(60673120)

摘　　要：为了解决用单一统计模型进行程序错误定位时存在的泛化能力较弱、错误类型覆盖不广和对测试用例过度依赖等问题,提出了组合统计模型的方法。该方法根据各个弱计算模型的特点,对它们进行了加权组合。组合统计模型具有更好的错误查找性能和抗噪能力,能够有效定位程序中不同类型的错误代码。通过组合模型和单一模型的对比实验结果表明,组合模型有效地提升了系统的分析能力和泛化性能。To deal with the problems such as weak generalization, poor coverage on bug patterns and strong dependence on test suites that happened in applying unique statistical model in bug localization, a method of composed statistical model is proposed. Composed statistical model assembles several weak models into one system by weights according to their characteristics. This model, which has stronger capability on fault localization and noise tolerance, can find the bugs in various patterns effectively. The improvement on analysis performance and generalization is verified by comparative experiments between composed model and unique model.

关 键 词：错误定位 统计分析 组合统计模型 运行时状态 程序测试 

分 类 号：TP311.55[自动化与计算机技术—计算机软件与理论]