A New Approach Based on Requirements Engineering in Software Projects Development Using Random Forest Algorithm  
  Authors : Vahab Yousefi Davood-Khani; Soheil Afraz


Due to the development and growth of information technology, software systems and server organizations have encountered a huge amount of information and new requirements. The requirements that change over time and elicitation of these requirements from an aggregation of needs are an important challenge. To overcome these problems, researchers for development of your projects presented different techniques and approaches. Software projects developers are among the pioneers in this field and are focusing on the requirements engineering approach using elicitation techniques. This paper presents a new approach based on requirements engineering has been developed in software projects by Random Forest algorithm. The approach consists of three phases. In the first phase, the integrated modeling language graphs were used to formal description of the architecture and system used to identify the project risks and bottlenecks. In the second phase, the features and diagnosis indicators as learning are given to Random Forest algorithm. In the last phase, a dynamic model is presented to evaluate the reliability of detection with colored petri Nets, which shows the risks and critical conditions in the project. In Comparison of proposed approach with another works, the results show that identification of software projects risks and bottlenecks is a critical and necessity to make progress in the software development based on Requirement Engineering activities.


Published In : IJCAT Journal Volume 5, Issue 3

Date of Publication : March 2018

Pages : 31-39

Figures :11

Tables :02

Publication Link :A New Approach Based on Requirements Engineering in Software Projects Development Using Random Forest Algorithm




Vahab Yousefi Davood-Khani : Department of Computer Engineering, Ardabil Branch, Islamic Azad University, Ardabil, IRAN.

Soheil Afraz : Department of Computer Engineering, Ardabil Branch, Islamic Azad University, Ardabil, IRAN.








Requirements Engineering, Random Forest Algorithm, Software Development, Machine Learning, Colored Petri-Nets

In this paper, an approach was presented based on requirements engineering in the development of software projects using random forest algorithm. The proposed approach using the documentation and analysis of the indicators affecting the risk of bottlenecks was identified with the help of random forest algorithm and reveals the effects of indicators in the software development process are based on the requirements engineering. A dynamic Petri-Nets based network model was proposed to assess and evaluate the reliability and availability of the proposed approach. The results of the three different runs indicate that the proposed approach has high reliability and availability for development in software projects. The disadvantages and shortcomings of this approach are the lack of support for the agile software development methodology and the high response time. Future works are focused on supporting different software development methodologies and also the study of privileges indicators with high power of learning.










[1] Allen, R., Douence, A. ,“Specifying Dynamism in Software Architectures”, Journal of Systems Engineering ,Vol. 6, No. 4, pp . 52-94,2007. [2] B. Leo. "Random forests." Machine learning 45.1, 5- 32.2001. [3] Farjaminejad.F and Harounabadi.A, “Modeling and Evaluation of Performance and Reliability of Component-based Software Systems using Formal” International Journal of Computer Applications Technology and Research Volume 3– Issue 1, 73 - 78, 2014. [4] Gharooni fard, G., Moein darbari, F., Deldari, H., Morvaridi, A., “Scheduling of scientific workflows using a chaos- genetic algorithm”, Procedia Computer Science, Elsevier, Vol. 1, No.1, pp. 1445- 1454, 2010. [5] Jensen, K., “Colored Petri Nets: Basic Concepts, Analysis Methods and Practical Use”, EATCS Monographs on Theoretical Computer Science, Vol. 29, No .2, pp70-120,2013. [6] Jörg, H., Ruslan, B., Matthias, M., Schmelter, D., Tschirner, C.,“Integrated Systems Engineering and Software Requirements Engineering for Technical Systems”, Tallinn, Estonia,,ACM, 978-1-4503-3346- 7/15/,2015. [7] Kryftis, Y., Mastorakis, G., Mavromoustakis, C., Mongay Batalla, J., Pallis, E. and Kormentzas, G.,“Efficient Entertainment Services Provision over a Novel Network Architecture”. To be published in IEEE Wireless Communications Magazine.2016. [8] M. Abdel-Aty, and K. Haleem. "Analyzing angle crashes at unsignalized intersections using machine learning techniques." Accident Analysis & Prevention 43.1,461- 470,2011. [9] Motameni, H., Movaghar, A. Siasifar, M.,“Analytical evaluation on Petri net by using Markov chain theory to achieve optimized Model”. World Appl. Sci. J. 3 (3) 504–513,2008. [10] Onesmus Emeka, B., Liu, Sh.,“Security Requirement Engineering using Structured Object-oriented Formal Language for M-banking Applications”, IEEE International Conference on Software Quality, Reliability and Security, 978-1-5386-0592-9/17,2017. [11] Parra, E., Dimou, C., Llorens, J., Moreno, V., Fraga A., “A methodology for the classification of quality of requirements using machine learning techniques”, Information and Software Technology, elsevir,180- 195,2015. [12] Prihartini,N., Laksmiwati, R., Rendradjaya, B.,“Identifying Aspects of Web e-Leaming in LMSbased for Requirement Engineering Process Modeling”, IEEE Future of Software Engineering,978-1-5090- 5671,2016. [13] Sitthithanasakul, S., Choosri, N.,“Using Ontology to Enhance Requirement Engineering in Agile Software Process”, International Conference on Software, Knowledge, Information Management & Applications (SKIMA),IEEE, 978-1-5090-3298-3,2016. [14] Yaniv, M., Dov, D.,“Model-Based Requirements Engineering: Architecting for System Requirements with Stakeholders in Mind”, IEEE,978-1-5386-3403- 5/17,2017. [15] Yu. Rongjie, and M. Abdel-Aty. "Analyzing crash injury severity for a mountainous freeway incorporating realtime traffic and weather data." Safety science 63 ,50- 56,2014.