《计算机应用研究》|Application Research of Computers

SVM应用于测试用例生成的方法

Method for application of SVM into test case generation

免费全文下载 (已被下载 次)  
获取PDF全文
作者 赵咏斌,朱嘉钢,陆晓
机构 1.江南大学 物联网工程学院,江苏 无锡 214122;2.江南大学晓山股份联合实验室,江苏 无锡 214122
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2015)01-0115-06
DOI 10.3969/j.issn.1001-3695.2015.01.027
摘要 针对在小样本情况下BP神经网络在生成软件测试用例的过程中可能产生的过学习问题及识别正确率较差的缺点,运用支持向量机具有更好的泛化性能的原理,提出了应用支持向量机生成测试用例的方法。对五个软件测试实例针对多组不同数量的训练样本所做的实验表明,在小样本情况下与BP神经网络相比,应用支持向量机得到的测试用例预期结果的正确率提高了10个百分点以上,说明了该方法的有效性。
关键词 软件工程;软件测试;支持向量机;BP神经网络;测试用例生成
基金项目 江苏省产学研项目(BY2013015-40)
本文URL http://www.arocmag.com/article/01-2015-01-027.html
英文标题 Method for application of SVM into test case generation
作者英文名 ZHAO Yong-bin, ZHU Jia-gang, LU Xiao
机构英文名 1. School of IOT Engineering, Jiangnan University, Wuxi Jiangsu 214122, China; 2. CoLab in Hillsun LTD. of Jiangnan University, Wuxi Jiangsu 214122, China
英文摘要 In the condition of small samples, overlearning problems and the disadvantage of poor recognition accuracy may occur in the process of generating software test cases by BP neural network. As SVM has better generalization performance, this paper proposed a method of using SVM to generate test cases, and performed experiment on five practical cases with multi-groups of different number of training samples. The results show that, in the condition of small samples, compare with BP neural network, this method can improve the accuracy of expected results by more than 10 percentage points. The results indicate the effectiveness of this method.
英文关键词 software engineering; software testing; SVM algorithm; BP neural network; test case generation
参考文献 查看稿件参考文献
  [1] SUN Yang, BOSCH L T, BOVES L. Hybrid HMM/BLSTM-RNN for robust speech recognition[C] //Proc of the 13th International Confe-rence on TSD. 2010:400-407. [2] WHITTAKER J A. What is software testing? And why is it so hard?[J] . IEEE Software, 2000, 17(1):70-79.
[3] DENNIS K P, DAVID L P. Generating a test oracle from program documentation[C] //Proc of International Symposium on Software Testing and Analysis. New York:ACM Press, 1995:58-65.
[4] BOUSQUET L, OUABDESSELAM F, RICHIER J, et al. Lutess:a specification-driven testing environment for synchronous software[C] //Proc of the 21st International Conference on Software Engineering. New York:ACM Press, 1999:267-276.
[5] DILLON L K, RAMAKRISHNA Y S. Generating oracles from your favorite temporal logic specifications[C] //Proc of the 4th ACM SIGSOFT Symposium on the Foundations of Software Engineering. New York:ACM Press, 1996:106-117.
[6] SCHROEDER P J, FAHERTY P, KOREL B. Generating expected results for automated blackbox testing[C] //Proc of the 17th IEEE International Conference on Automated Software Engineering. 2002:139-148.
[7] VANMALI M, LAST M, KANDEL A. Using a neural network in the software testing process[J] . International Journal of Intelligent Systems, 2002, 17(1):45-62.
[8] AGGARWAL K K, SINGH Y, KAUR A, et al. A neural net based approach to test oracle[J] . ACM SIGSOFT Software Engineering Notes, 2004, 29(3):1-6.
[9] JIN Hu, WANG Yi, CHEN Nian-wei, et al. Artificial neural network for automatic test oracles generation[C] //Proc of International Conference on Computer Science and Software Engineering. 2008:12-14.
[10] SHAHAMIRI S R, WAN M N, WAN K, et al. Artificial neural networks as multi-networks automated test oracle[J] . Automated Software Engineering, 2012, 19(3):303-334.
[11] 高述涛. SVM与ANN在网络安全风险评估中的比较研究[J] . 电脑知识与技术, 2009, 5(33):9380-9381.
[12] CRISTIANINI N, TAYLOR J S. An introduction to support vector machines and other kernel-based learning methods[M] . Cambridge:Cambridge University Press, 2003:103-104.
[13] CHEN M S, HO T Y, HUANG D Y. Online transductive support vector machines for classification[C] //Proc of International Conference on Information Security and Intelligence Control. 2012:258-261.
[14] 林关成, 李亚安. 基于ANN与SVM的分类和回归比较研究[J] . 声学技术, 2008, 27(4):229-230.
[15] 丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J] . 电子科技大学学报, 2011, 40(1):2-10.
收稿日期 2014/1/1
修回日期 2014/3/3
页码 115-120
中图分类号 TP311.52
文献标志码 A