ارائه روشی جدید مبتنی بر مدل کوکومو بمنظور افزایش دقت تخمین تلاش در پروژه های نرم افزاری
محورهای موضوعی : عمومىمهدیه سالاری 1 , وحید خطیبی بردسیری 2 , عمید خطیبی بردسیری 3
1 - دبیر
2 - استادیار دانشگاه آزاد اسلامی بردسیر
3 - استادیار دانشگاه آزاد اسلامی بردسیر
کلید واژه: الگوریتم فاخته, تخمین هزینه, شبکه عصبی, کوکومو,
چکیده مقاله :
تخمین و برآورد معیارها یک فعالیت حیاتی در پروژه‌های نرم‌افزاری محسوب می‌شود. به‌طوری‌که تخمین تلاش در مراحل اولیه توسعه نرم‌افزار، یکی از مهم‌ترین چالش‌های مدیریت پروژه‌های نرم‌افزاری است. تخمین نادرست می‌تواند منجر به شکست پروژه گردد. لذا یکی از فعالیت‌های اصلی و کلیدی در توسعه مؤثر و کارآمد پروژه‌های نرم‌افزاری تخمین دقیق هزینه‌های نرم‌افزار است. ازاین‌رو در این پژوهش دو روش به‌منظور تخمین تلاش در پروژه‌های نرم‌افزاری ارائه شده است، که در این روش ها سعی شده با تجزیه‌وتحلیل محرک‌ها و استفاده از الگوریتم‌های فرا ابتکاری و ترکیب با شبکه عصبی راهی برای افزایش دقت در تخمین تلاش پروژه های نرم افزاری ایجاد شود. روش اول تأثیر الگوریتم فاخته جهت بهینه‌سازی ضرایب تخمین مدل کوکومو و روش دوم به صورت ترکیبی از شبکه عصبی و الگوریتم بهینه‌سازی فا خته جهت افزایش دقت برآورد تلاش توسعه نرم‌افزار ارائه‌شده است. نتایج بدست آمده روی دو پایگاه داده واقعی نشان دهنده عملکرد مطلوب روش ارائه شده در مقایسه با سایر روشهاست.
It is regarded as a crucial task in a software project to estimate the criteria, and effort estimation in the primary stages of software development is thus one of the most important challenges involved in management of software projects. Incorrect estimation can lead the project to failure. It is therefore a major task in efficient development of software projects to estimate software costs accurately. Therefore, two methods were presented in this research for effort estimation in software projects, where attempts were made to provide a way to increase accuracy through analysis of stimuli and application of metaheuristic algorithms in combination with neural networks. The first method examined the effect of the cuckoo search algorithm in optimization of the estimation coefficients in the COCOMO model, and the second method was presented as a combination of neural networks and the cuckoo search optimization algorithm to increase the accuracy of effort estimation in software development. The results obtained on two real-world datasets demonstrated the proper efficiency of the proposed methods as compared to that of similar methods.
1. Huang, G., "Cost Modeling Based on Support Vector Regression for Complex roducts During the Early Design Phases". Requirements for the Degree of Doctor of Philosophy in Industrial and Systems Engineering, 2007.
2. Khatibi, v. and D.N.A. awawi, Software Cost Estimation Methods: A Review. Journal of Emerging Trends in Computing and Information Sciences, 2011 2: p. 21-29.
3. Abdullah, T., et al., ANALYSIS OF SOFTWARE COST ESTIMATION MODELS. IJEIR, 2012 1: p. 206-212.
4. Binish Zahra, S. and M. Nazir, A Review of Comparison among Software Estimation Techniques. Bahria University Journal of Information & Communication Technology, 2012 5: p. 39-45.
5. Boehm, B., "Software Engineering Economics". IEEE Transaction on Software Engineering, vol. SE-10, 1984 p. 4-21.
6. Lin, J.-C., et al., Using Computing Intelligence Techniques to Estimate Software Effort. International Journal of Software Engineering & Applications, 2013 4(1): p. 43.
7. khatibi bardsiri, v. and m. dorosti, An Improved COCOMO based Model to Estimate the Effort of Software Projects. 2016.
8. Sadeghi, B., et al., A Novel ICA-based Estimator for Software Cost Estimation. Journal of Advances in Computer Engineering and Technology, 2015. 1(4): p. 15-24.
9. Venkataiah, V., et al., Application of ant colony optimization techniques to predict software cost estimation, in Computer Communication, Networking and Internet Security. 2017, Springer. p. 315-325.
10. Shahpar, Z., et al., Improvement of effort estimation accuracy in software projects using a feature selection approach. Journal of Advances in Computer Engineering and Technology, 2016. 2(4): p. 31-38.
11. khatibi bardsiri, A., S.m. hashemi, and M. Razzazi, A Novel Model for Software Services Development Effort Estimation. Journal of Modeling in Engineering, 2017. 15(49): p. 245-261.
12. Khatibi, E. and V. Khatibi Bardsiri, An Improved Algorithmic Method for Software Development Effort Estimation. Journal of Advances in Computer Research, 2018. 9(1): p. 41-49.
13. Khatibi Bardsiri, A., A new combinatorial framework for software services development effort estimation. International Journal of Computers and Applications, 2018. 40(1): p. 14-24.
14. Kumari, S. and S. Pushkar. Software Cost Estimation Using Cuckoo Search. in Advances in Computational Intelligence. 2017. Singapore: Springer Singapore.
15. Puspaningrum, A. and R. Sarno, A Hybrid Cuckoo Optimization and Harmony Search Algorithm for Software Cost Estimation. Procedia Computer Science, 2017. 124: p. 461-469.
16. Çelik, E., et al. Software test automation and a sample practice for an enterprise business software. in Computer Science and Engineering (UBMK), 2017 International Conference on. 2017. IEEE.
17. Ebrahimpour, N., F. Soleimanian Gharehchopogh, and Z. Abbasi Khalifehlou, New Approach with Hybrid of Artificial Neural Network and Ant Colony Optimization in Software Cost Estimation. Journal of Advances in Computer Research, 2016. 7(4): p. 1-12.
18. Wani, Z.H. and S. Quadri. Artificial Bee Colony-Trained Functional Link Artificial Neural Network Model for Software Cost Estimation. in Proceedings of Fifth International Conference on Soft Computing for Problem Solving. 2016. Springer.
19. Chhabra, S. and H. Singh, Optimizing design parameters of fuzzy model based COCOMO using genetic algorithms. International Journal of Information Technology, 2019.
20. Desai, V.S. and R. Mohanty. ANN-Cuckoo Optimization Technique to Predict Software Cost Estimation. in 2018 Conference on Information and Communication Technology (CICT). 2018. IEEE.
21. Khazaiepoor, M., A. Khatibi Bardsiri, and F. Keynia, A Hybrid Approach for Software Development Effort Estimation using Neural networks, Genetic Algorithm, Multiple Linear Regression and Imperialist Competitive Algorithm. International Journal of Nonlinear Analysis and Applications, 2020. 11(1): p. 207-224.
22. Boehm, B., C. Abts, and S. Chulani, Software development cost estimation approaches—A survey. Annals of software engineering, 2000 10(1-4): p. 177-205.
23. Stutzke, R.D. and M. Crosstalk, Software estimating technology: A survey. 1997: Los. Alamitos, CA: IEEE Computer Society Press.
24. جهانشاهی, س., و. خطیبی بردسیری, و همکاران, کاربرد روشهای محاسبات نرم در بهبود عملکرد مدل کوکومو بمنظورتخمین هزینه پروژه های نرم افزار. همایش ملی مهندسی کامپیوتر و فناوری اطلاعات, اسفند 1392
25. Rajabioun, R., Cuckoo optimization algorithm. Applied soft computing, 2011. 11(8): p. 5508-5518.
26. Karaboga, D., B. Akay, and C. Ozturk, Artificial bee colony (ABC) optimization algorithm for training feed-forward neural networks. MDAI, 2007. 7: p. 318-319.
27. Hippert, H.S. and J.W. Taylor, An evaluation of Bayesian techniques for controlling model complexity and selecting inputs in a neural network for short-term load forecasting. Neural networks, 2010. 23(3): p. 386-395.
28. Khatibi, E. Investigating the effect of software project type on accuracy of software development effort estimation in COCOMO model. in Fourth International Conference on Machine Vision (ICMV 11). 2011 International Society for Optics and Photonics.
29. Khatibi, V. and D.N. Jawawi, Software cost estimation methods: A review 1. 2011
30. Bardsiri, V.K., et al., LMES: A localized multi-estimator model to estimate software development effort. Engineering Applications of Artificial Intelligence, 2013. 26(10): p. 2624-2640.
31. Pandey, M., R. Litoriya, and P. Pandey, Validation of existing software effort estimation techniques in context with mobile software applications. Wireless Personal Communications, 2020. 110(4): p. 1659-1677.
