|Table of Contents|

[1] Chen Xiang, Lu Fengyan, Shen Yuxiang, et al. Analogy-based software effort estimationusing multi-objective feature selection [J]. Journal of Southeast University (English Edition), 2018, (3): 295-302. [doi:10.3969/j.issn.1003-7985.2018.03.003]
Copy

Analogy-based software effort estimationusing multi-objective feature selection()
Share:

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
Issue:
2018 3
Page:
295-302
Research Field:
Computer Science and Engineering
Publishing date:
2018-09-20

Info

Title:
Analogy-based software effort estimationusing multi-objective feature selection
Author(s):
Chen Xiang1 2 Lu Fengyan1 Shen Yuxiang1 Xie Junfeng1 Wen Wanzhi1
1 School of Computer Science and Technology, Nantong University, Nantong 226019, China
2 State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China
Keywords:
software effort estimation multi-objective optimization case-based reasoning feature selection empirical study
PACS:
TP311
DOI:
10.3969/j.issn.1003-7985.2018.03.003
Abstract:
The feature selection in analogy-based software effort estimation(ASEE)is formulized as a multi-objective optimization problem. One objective is designed to maximize the effort estimation accuracy and the other objective is designed to minimize the number of selected features. Based on these two potential conflict objectives, a novel wrapper-based feature selection method, multi-objective feature selection for analogy-based software effort estimation(MASE), is proposed. In the empirical studies, 77 projects in Desharnais and 62 projects in Maxwell from the real world are selected as the evaluation objects and the proposed method MASE is compared with some baseline methods. Final results show that the proposed method can achieve better performance by selecting fewer features when considering MMRE(mean magnitude of relative error), MdMRE(median magnitude of relative error), PRED(0.25), and SA(standardized accuracy)performance metrics.

References:

[1] Dejaeger K, Verbeke W, Martens D, et al. Data mining techniques for software effort estimation: A comparative study[J]. IEEE Transactions on Software Engineering, 2012, 38(2): 375-397.
[2] Keung J. Software development cost estimation using analogy: A review[C]//Australian Software Engineering Conference. Gold Cost, Australia, 2009:327-336.
[3] Idri A, Amazal F, Abran A. Analogy-based software development effort estimation: A systematic mapping and review[J]. Information and Software Technology, 2015, 58:206-230. DOI:10.1016/j.infsof.2014.07.013.
[4] Idri A, Hosni M, Abran A. Improved estimation of software development effort using classical and fuzzy analogy ensembles[J]. Applied Soft Computing, 2016, 49:990-1019. DOI:10.1016/j.asoc.2016.08.012.
[5] Kolodner J. Case-based reasoning[M]. San Francisco, USA: Morgan Kaufmann Publisher, 1993.
[6] Shepperd M, Schofield C. Estimating software project effort using analogies[J]. IEEE Transactions on Software Engineering, 1997, 23(11): 736-743. DOI:10.1109/32.637387.
[7] Kirsopp C, Shepperd M J, Hart J. Search heuristics, case-based reasoning and software project effort prediction[C]//Genetic and Evolutionary Computation Conference. New York, USA, 2002:1367-1374.
[8] Li Y F, Xie M, Goh T N.A study of mutual information based feature selection for case based reasoning in software cost estimation[J].Expert Systems with Applications, 2009, 36(3):5921-5931.DOI:10.1016/j.eswa.2008.07.062.
[9] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-Ⅱ[J].IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197. DOI:10.1109/4235.996017.
[10] Phannachitta P, Keung J, Monden A, et al. A stability assessment of solution adaptation techniques for analogy-based software effort estimation[J]. Empirical Software Engineering, 2017, 22(1): 474-504. DOI:10.1007/s10664-016-9434-8.
[11] Huang J, Li Y F, Xie M. An empirical analysis of data preprocessing for machine learning-based software cost estimation[J].Information and Software Technology, 2015, 67:108-127. DOI:10.1016/j.infsof.2015.07.004.
[12] Jing X Y, Qi F, Wu F, et al. Missing data imputation based on low-rank recovery and semi-supervised regression for software effort estimation[C]//International Conference on Software Engineering. Austin, USA, 2016:607-618.
[13] Chen Z, Menzies T, Port D, et al. Feature subset selection can improve software cost estimation accuracy[J]. ACM SIGSOFT Software Engineering Notes, 2005, 30(4): 1-6. DOI:10.1145/1082983.1083171.
[14] Mendes E, Watson I, Triggs C, et al. A comparative study of cost estimation models for web hypermedia applications[J]. Empirical Software Engineering, 2003, 8(2):163-196.DOI:10.1023/A:1023062629183.
[15] Harman M, Mansouri S A, Zhang Y. Search-based software engineering: Trends, techniques and applications[J]. ACM Computing Surveys, 2012, 45(1)::1-61. DOI:10.1145/2379776.2379787.
[16] Shepperd M, MacDonell S. Evaluating prediction systems in software project estimation[J]. Information and Software Technology, 2012, 54(8):820-827.DOI:10.1016/j.infsof.2011.12.008.
[17] Langdon W B, Dolado J, Sarro F, et al. Exact mean absolute error of baseline predictor, MARP0[J]. Information and Software Technology, 2016, 73:16-18.DOI:10.1016/j.infsof.2016.01.003.
[18] Mair C, Kadoda G, Lefley M, et al. An investigation of machine learning based prediction systems[J]. Journal of Systems and Software, 2000, 53(1):23-29.DOI:10.1016/s0164-1212(00)00005-4.
[19] Sentas P, Angelis L, Stamelos I, et al. Software productivity and effort prediction with ordinal regression[J]. Information and Software Technology, 2005, 47(1):17-29. DOI:10.1016/j.infsof.2004.05.001.
[20] Li J Z, Ruhe G, Al-Emran A, et al. A flexible method for effort estimation by analogy[J]. Empirical Software Engineering, 2007, 12(1):65-106. DOI:10.1007/s10664-006-7552-4.
[21] Qi F, Jing X Y, Zhu X, et al. Software effort estimation based on open source projects:Case study of Github[J]. Information and Software Technology, 2017, 92:145-157. DOI:10.1016/j.infsof.2017.07.015.
[22] Zitzler E, Thiele L. Multiobjective evolutionary algorithms: A comparative case study and the strength pareto approach[J]. IEEE Transactions on Evolutionary Computation, 1999, 3(4):257-271. DOI:10.1109/4235.797969.

Memo

Memo:
Biography: Chen Xiang(1980—), male, doctor, associate professor, xchencs@ntu.edu.cn.
Foundation items: The National Natural Science Foundation of China(No.61602267, 61202006), the Open Project of State Key Laboratory for Novel Software Technology at Nanjing University(No.KFKT2016B18).
Citation: Chen Xiang, Lu Fengyan, Shen Yuxiang, et al. Analogy-based software effort estimation using multi-objective feature selection[J].Journal of Southeast University(English Edition), 2018, 34(3):295-302.DOI:10.3969/j.issn.1003-7985.2018.03.003.
Last Update: 2018-09-20