A Comparative Analysis on Effort Estimation for Agile and Non-agile Software Projects Using DBN-ALO

被引：14

作者：

Kaushik, Anupama ^{[1
,2
]}

Tayal, Devendra Kr ^{[3
]}

Yadav, Kalpana ^{[4
]}

机构：

[1] Maharaja Surajmal Inst Technol, Dept IT, New Delhi, India

[2] IGDTUW, Delhi, India

[3] IGDTUW, Dept Comp Sci, Delhi, India

[4] IGDTUW, Dept IT, Delhi, India

来源：

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING | 2020年 / 45卷 / 04期

关键词：

Software development effort; Deep belief network; Antlion optimization; Agile software development; Non-agile software development; MODELS; OPTIMIZATION; UNCERTAINTY;

D O I：

10.1007/s13369-019-04250-6

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

At present, in the software industry, agile and non-agile software development approaches are followed and effort estimation is an intrinsic part of both the approaches. This work investigates the application of deep belief network (DBN) along with antlion optimization (ALO) technique for effort prediction in both agile as well as non-agile software development environment. The study also provides a prediction interval of effort to handle uncertainty in estimation. This will help the project managers to estimate the effort in ranges instead of a crisp value. The proposed DBN-ALO approach is applied on four promise repository datasets for traditional software development (non-agile), and on three agile datasets. It provides the best results in all the evaluation criteria used. The proposed approach is also statistically validated using nonparametric tests, and it is found that DBN-ALO worked best for both agile and non-agile development approaches.

引用

页码：2605 / 2618

页数：14

共 45 条

[11]

Britto R, 2014, LECT NOTES BUS INF P, V199, P182

[12] Bayesian network model for task effort estimation in agile software development [J].

Dragicevic, Srdjana ;

Celar, Stipe ;

Turic, Mili .

JOURNAL OF SYSTEMS AND SOFTWARE, 2017, 127 :109-119

[13] Uncertainty management in software effort estimation using a consistent fuzzy analogy-based method [J].

Ezghari, Soufiane ;

Zahi, Azeddine .

APPLIED SOFT COMPUTING, 2018, 67 :540-557

[14] A simulation study of the model evaluation criterion MMRE [J].

Foss, T ;

Stensrud, E ;

Kitchenham, B ;

Myrtveit, I .

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2003, 29 (11) :985-995

[15] RANK METHODS FOR COMBINATION OF INDEPENDENT EXPERIMENTS IN ANALYSIS OF VARIANCE [J].

HODGES, JL ;

LEHMANN, EL .

ANNALS OF MATHEMATICAL STATISTICS, 1962, 33 (02) :482-+

[16]

HOLM S, 1979, SCAND J STAT, V6, P65

[17] An effort prediction interval approach based on the empirical distribution of previous estimation accuracy [J].

Jorgensen, M ;

Sjoberg, DIK .

INFORMATION AND SOFTWARE TECHNOLOGY, 2003, 45 (03) :123-136

[18]

Karhunen J., 2015, Advances in Independent Component Analysis and Learning Machines, P125, DOI [10.1016/B978-0-12-802806-3.00007-5, DOI 10.1016/B978-0-12-802806-3.00007-5]

[19] FF-SMOTE: A Metaheuristic Approach to Combat Class Imbalance in Binary Classification [J].

Kaur, Prabhjot ;

Gosain, Anjana .

APPLIED ARTIFICIAL INTELLIGENCE, 2019, 33 (05) :420-439

[20] Software cost optimization integrating fuzzy system and COA-Cuckoo optimization algorithm [J].

Kaushik A. ;

Verma S. ;

Singh H.J. ;

Chhabra G. .

International Journal of System Assurance Engineering and Management, 2017, 8 (Suppl 2) :1461-1471

← 1 2 3 4 5 →