Solution for classification imbalance in harmfulness prediction of clone code

doi:10.11772/j.issn.1001-9081.2016.12.3468

Journal of Computer Applications ›› 2016, Vol. 36 ›› Issue (12): 3468-3475.DOI: 10.11772/j.issn.1001-9081.2016.12.3468

Previous Articles Next Articles

Solution for classification imbalance in harmfulness prediction of clone code

WANG Huan, ZHANG Liping, YAN Sheng

College of Computer and Information Engineering, Inner Mongolia Normal University, Hohhot Nei Mongol 010022, China

Received:2016-05-30 Revised:2016-07-07 Online:2016-12-10 Published:2016-12-08
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61363017,61462071), the Natural Science Foundation of Inner Mongolia (2015MS0606), the Foundation Projects of Inner Mongolia Education Department (NJZY16045).

克隆代码有害性预测中分类不平衡问题的解决方法

王欢, 张丽萍, 闫盛

内蒙古师范大学计算机与信息工程学院, 呼和浩特 010022

通讯作者: 张丽萍
作者简介:王欢(1991-),男,内蒙古巴彦淖尔人,硕士研究生,主要研究方向:代码分析;张丽萍(1974-),女,内蒙古呼和浩特人,教授,硕士,CCF会员,主要研究方向:软件工程、软件分析;闫盛(1984-),男,内蒙古包头人,讲师,硕士,主要研究方向:软件分析、并行计算。
基金资助:
国家自然科学基金资助项目（61363017，61462071）；内蒙古自然科学基金资助项目（2015MS0606）；内蒙古自治区高等学校科学研究项目（NJZY16045）。

Abstract

Abstract: Focusing on the problem of imbalanced classification of harmful data and harmless data in the prediction of the harmful effects of clone code, a K-Balance algorithm based on Random Under-Sampling (RUS) was proposed, which could adjust the classification imbalance automatically. Firstly, a sample data set was constructed by extracting static features and evolution features of clone code. Then, a new data set of imbalanced classification with different proportion was selected. Next, the harmful prediction was carried out to the new selected data set. Finally, the most suitable percentage value of classification imbalance was chosen automatically by observing the different performance of the classifier. The performance of the harmfulness prediction model of clone code was evaluated with seven different types of open-source software systems containing 170 versions written in C language. Compared with the other classification imbalance solution methods, the experimental results show that the proposed method is increased by 2.62 percentage points to 36.7 percentage points in the classification prediction effects (Area Under ROC(Receive Operating Characteristic) Curve (AUC)) of harmful and harmless clones. The proposed method can improve the classification imbalance prediction effectively.

Key words: code clone, harmfulness, imbalanced classification, random undersampling, parameter search

摘要： 针对克隆代码有害性预测中有害和无害数据分类不平衡的问题，提出一种基于随机下采样（RUS）的能够自动调整分类不平衡的K-Balance算法。首先对克隆代码提取静态特征和演化特征构建样本数据集；然后选取比例不同的分类不平衡新数据集；接着对已选取的新数据集进行有害性预测；最后，通过观察分类器的不同表现自动选择一个最适合的分类不平衡比例值。在7款C语言开源软件共170个版本上对克隆有害性预测模型的性能进行评估，并和其他分类不平衡解决方法进行对比，实验结果表明所提方法对有害和无害克隆的分类预测效果（受试者工作特征曲线下方面积（AUC）值）提高了2.62个百分点~36.70个百分点，能有效地改善分类不平衡的预测问题。

关键词: 克隆代码, 有害性, 不平衡分类, 随机下采样, 参数搜索

CLC Number:

TP311.5

WANG Huan, ZHANG Liping, YAN Sheng. Solution for classification imbalance in harmfulness prediction of clone code[J]. Journal of Computer Applications, 2016, 36(12): 3468-3475.

王欢, 张丽萍, 闫盛. 克隆代码有害性预测中分类不平衡问题的解决方法[J]. 计算机应用, 2016, 36(12): 3468-3475.

References

[1] BETTENBURG N, SHANG W, IBRAHIM W, et al. An empirical study on inconsistent changes to code clones at release level[C]//Proceedings of the 200916th Working Conference on Reverse Engineering. Piscataway, NJ:IEEE, 2009:85-94.
[2] KOSCHKE R. Seventh international workshop on software clones[EB/OL].[2016-02-15]. http://softwareclones.org/iwsc2013/.
[3] ROY C K. Detection and analysis of near-miss software clones[C]//Proceedings of the 2009 IEEE International Conference on Software Maintenance. Washington, DC:IEEE Computer Society, 2009:447-450.
[4] 梅宏,王千祥,张路,等.软件分析技术进展[J].计算机学报,2009,32(9):1697-1710.(MEI H, WANG Q X, ZHANG L, et al. Software analysis technology progress[J]. Chinese Journal of Computers, 2009, 32(9):1697-1710.)
[5] WANG X, DANG Y, ZHANG L, et al. Can I clone this piece of code here?[C]//Proceedings of the 27th IEEE/ACM International Conference on Automated Software Engineering. New York:ACM, 2012:170-179.
[6] 李智超.基于支持向量机的克隆代码有害性评价方法研究[D].哈尔滨:哈尔滨工业大学,2013:15-17.(LI Z C. Research on SVM-based evaluation method of clone code harmfulness[D]. Harbin:Harbin Institute of Technology, 2013:15-17.)
[7] BAKOTA T. Tracking the evolution of code clones[C]//SOFSEM 2011:Proceedings of the 37th Conference on Current Trends in Theory and Practice of Computer Science, LNCS 6543. Berlin:Springer, 2011:86-98.
[8] BAKOTA T, FERENC R, GYIMOTHY T. Clone smells in software evolution[C]//ICSM 2007:Proceedings of the 2007 IEEE International Conference on Software Maintenance. Piscataway, NJ:IEEE, 2007:24-33.
[9] JUERGEBS E, DEISSENBOECK F, HUMMEL B, et al. Do code clones matter?[C]//ICSE 2009:Proceedings of the 31st International Conference on Software Engineering. Piscataway, NJ:IEEE, 2009:485-495.
[10] BARBOUR L, KHOMH F, ZOU Y. An empirical study of faults in late propagation clone genealogies[J]. Journal of Software:Evolution and Process, 2013, 25(11):1139-1165.
[11] CHAWLA N V, BOWYER K W, HALL L O,et al. SMOTE:synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2011, 16(1):321-357.
[12] ESTABROOKS A, JO T, JAPKOWICZ N. A multiple resampling method for learning from imbalanced data sets[J]. Computational Intelligence, 2004, 20(1):18-36.
[13] JAPKOWICZ N, MYERS C, GLUCK M A. A novelty detection approach to classification[C]//IJCAI'95:Proceedings of the 14th International Joint Conference on Artificial Intelligence. San Francisco, CA:Morgan Kaufmann Publishers, 1995:518-523.
[14] ZHOU Z H, LIU X Y. Training cost-sensitive neural networks with methods addressing the class imbalance problem[J]. IEEE Transactions on Knowledge and Data Engineering, 2006, 18(1):63-77.
[15] HO T K, HULL J J, SRIHARI S N. Decision combination in multiple classifier systems[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(1):66-75.
[16] ROKACH L. Ensemble-based classifiers[J]. Artificial Intelligence Review, 2010, 33(1/2):1-39.
[17] WANG S, CHEN H., YAO X. Negative correlation learning for classification ensembles[C]//Proceedings of the 2010 IEEE International Joint Conference on Neural Networks. Piscataway, NJ:IEEE, 2010:2893-2900.
[18] WANG S, YAO X. Using class imbalance learning for software defect prediction[J]. IEEE Transactions on Reliability, 2013, 62(2):434-443.
[19] BREIMAN L. Bagging predictors[J]. Machine Learning, 1996, 24(2):123-140.
[20] BROWN G, WYATT J L, TINO P. Managing diversity in regression ensembles[J]. Journal of Machine Learning Research, 2005, 6(1):1621-1650.
[21] TANG E K, SUGANTHAN P N, YAO X. An analysis of diversity measures[J]. Machine Learning, 2006, 65(1):247-271.
[22] MANI I, ZHANG B J. KNN approach to unbalanced data distributions:a case study involving information extraction[C]//Proceedings of the 2003 Workshop on Learning from Imbalanced Datasets Ⅱ. Washington DC:ICML, 2003:42-48.
[23] SEIFFERT C, KHOSHGOFTAAR T M, HULSE J V, et al. A comparative study of data sampling and cost sensitive learning[C]//Proceedings of the 2008 IEEE International Conference on Data Mining Workshops. Washington, DC:IEEE Computer Society, 2008:46-52.
[24] 侯敏,张丽萍,史庆庆,等.基于后缀数组检测函数克隆[J].计算机应用研究,2014,31(4):1082-1085.(HOU M, ZHANG L P, SHI Q Q, et al. Detecting code clone based on suffix array[J]. Application Research of Computers, 2014, 31(4):1082-1085.)
[25] 张瑞霞,张丽萍,王春晖,等.基于主题建模技术的克隆群映射方法[J].计算机工程与设计,2015,36(6):1524-1529.(ZHANG R X, ZHANG L, WANG C H, et al. Clone group mapping method based on topic modeling[J]. Journal of Computer Engineering and Design, 2015, 36(6):1524-1529.)
[26] 涂颖,张丽萍,王春晖,等.基于软件多版本演化提取克隆谱系[J].计算机应用,2015,35(4):1169-1173.(TU Y, ZHANG L P, WANG C H, et al. Clone genealogies extraction based on software evolution over multiple versions[J]. Journal of Computer Applications, 2015, 35(4):1169-1173.)
[27] WITTEN I H, FRANK E. Data Mining:Practical Machine Learning Tools and Techniques[M]. 2nd ed. San Francisco, CA:Morgan Kaufmann Publishers, 2005:206-207.
[28] 张丽萍,张瑞霞,王欢,等.基于贝叶斯网络的克隆代码有害性预测[J].计算机应用,2016,36(1):260-265.(ZHANG L P, ZHANG R X, WANG H, et al. Harmfulness prediction of clone code based on Bayesian network[J]. Journal of Computer Applications, 2016, 36(1):260-265.)

Solution for classification imbalance in harmfulness prediction of clone code

克隆代码有害性预测中分类不平衡问题的解决方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 8

Recommended Articles

Metrics

[1]	LI Hao, ZHU Yan. Xgboost algorithm optimization based on gradient distribution harmonized strategy [J]. Journal of Computer Applications, 2020, 40(6): 1633-1637.
[2]	MO Zan, GAI Yanrong, FAN Guanlong. Credit card fraud classification based on GAN-AdaBoost-DT imbalanced classification algorithm [J]. Journal of Computer Applications, 2019, 39(2): 618-622.
[3]	SHE Rongrong, ZHANG Liping, HOU Min, YAN Sheng. Recommending clone refactoring method based on decision tree [J]. Journal of Computer Applications, 2018, 38(7): 2037-2043.
[4]	WANG Huan, ZHANG Liping, YAN Sheng, LIU Dongsheng. Feature selection model for harmfulness prediction of clone code [J]. Journal of Computer Applications, 2017, 37(4): 1135-1142.
[5]	CHEN Musheng, LU Xiaoyong. Three random under-sampling based ensemble classifiers for Web spam detection [J]. Journal of Computer Applications, 2017, 37(2): 535-539.
[6]	ZHANG Jiujie, ZHAI Ye, WANG Chunhui, ZHANG Liping, LIU Dongsheng. Evolution pattern recognition and genealogy construction based on clone mapping of versions [J]. Journal of Computer Applications, 2016, 36(7): 2021-2030.
[7]	CHEN Zhuo, ZHANG Liping, WANG Huan, ZHANG Jiujie, WANG Chunhui. Clone group mapping method based on improved vector space model [J]. Journal of Computer Applications, 2016, 36(7): 2031-2037.
[8]	ZHANG Liping, ZHANG Ruixia, WANG Huan, YAN Sheng. Harmfulness prediction of clone code based on Bayesian network [J]. Journal of Computer Applications, 2016, 36(1): 260-265.