A Novel Method for Software Reliability Assessment via Neuro-Fuzzy System

Document Type : Original Research Article


Department of Computer Engineering, Ayatollah Amoli Branch, Islamic Azad University, Mazandaran, Iran


Nowadays, the utilization of software engineering in various areas of technology is remarkably increased. As a matter of fact, it is used in many critical applications such as eye surgery, autopilot systems of airplanes, centralized traffic control (CTC), and so on. Therefore, the reliability of software is very important, and it plays an essential role in the lifetime of the software. Software reliability is one of the main characteristics of software quality. Moreover, the rapid assessment of the reliability of the application is essential during the software life cycle. In this paper, Iuse the neuro-fuzzy methods to assess the software's reliability in order to cope with uncertainties in measuring the actual parameters of the software. By designing neuro-fuzzy inference systems and applying four parameters of the ISO/IEC 9126quality model(i.e., the maturity of software, fault-tolerant, recoverability, and reliability compliance) and finding the parameters of a fuzzy system by exploiting approximation techniques from neural networks, Ipresent an integrated assessment model for evaluation of software reliability. The case study used in this paper to evaluate the proposed method is the software income tax calculator. By applying the input parameters, Iobserve that the software reliability is 0.65. software reliability in our proposed method is more exact than software reliability in the fuzzy multi-criteria and fuzzy method because The weights of the input parameters have been set by experts and software developers, and simulations are carried out using MATLAB tool (ANFIS). Simulations confirm that the proposed method provides acceptable results.


Main Subjects

[1]     R. Dadhich and B. Mathur, "BM, Measuring Reliability of an Aspect Oriented Software Using Fuzzy Logic Approach," International Journal of Engineering and Advanced Technology (IJEAT), vol. 1, no. 5, pp. 233-237, 2012.
[2]     P. Gandhi, M. Z. Khan, R. K. Sharma, O. H. Alhazmi, S. Bhatia, and C. Chakraborty, "Software Reliability Assessment Using Hybrid Neuro-Fuzzy Model," Comput. Syst. Sci. Eng., vol. 41, no. 3, pp. 891-902, 2022.
[3]     J. Vieira, F. M. Dias, and A. Mota, "Neuro-fuzzy systems: a survey," in 5th WSEAS NNA international conference on neural networks and applications, Udine, Italia, pp. 1-6, 2004.
[4]     R. Kruse, "Fuzzy neural network," Scholarpedia, vol. 3, no. 11, p. 6043, 2008.
[5]     W. A. Adnan and M. H. Yaacob, "An integrated neural-fuzzy system of software reliability prediction," in Proceedings of 1st International Conference on Software Testing, Reliability and Quality Assurance (STRQA'94), IEEE, pp. 154-158, 1994.
[6]     S. Aljahdali and A. F. Sheta, "Predicting the reliability of software systems using fuzzy logic," in Eighth International Conference on Information Technology: New Generations (ITNG), IEEE, pp. 36-40, 2011.
[7]     O. Georgieva and A. Dimov, "Software reliability assessment via fuzzy logic model," in Proceedings of the 12th International Conference on Computer Systems and Technologies, pp. 653-658, 2011.
[8]     J. S. Challa, A. Paul, Y. Dada, V. Nerella, P. R. Srivastava, and A. P. Singh, "Integrated software quality evaluation: a fuzzy multi-criteria approach," Journal of Information Processing Systems, vol. 7, no. 3, pp. 473-518, 2011.
[9]     B. Kotaiah and R. Khan, "Software Reliability Assessment by using Neural Networks with Fuzzy Logic based systems‖," in International Conference on Advances in Computer Science (AET-ACS), Elsevier,2013.
[10]  B. Kotaiah, M. Prasad, and R. Khan, "An analysis of software reliability assessment with neuro-fuzzy based expert systems," Procedia Computer Science, vol. 62, pp. 92-98, 2015.
[11]  M. Zavvar and F. Ramezani, "A method based on fuzzy system for assessing the reliability of software based aspects," Advances in Science and Technology. Research Journal, vol. 9, no. 27, 2015.
[12]  M. Milovancevic, A. Dimov, K. B. Spasov, L. Vračar, and M. Planić, "Neuro-Fuzzy Evaluation of the Software Reliability Models by Adaptive Neuro Fuzzy Inference System," Journal of Electronic Testing, vol. 37, no. 4, pp. 439-452, 2021.
[13]  E. Elghamry, M. A. Eldamcesse, and M. S. Nayel, "Reliability Model of Fuzzy Consecutive k-out-of-n: F System," International Journal of Reliability, Risk and Safety: Theory and Application, vol. 2, no. 1, pp. 1-4, 2019.
[14]  Coallier, F. "Software engineering–Product quality–Part 1: Quality model." International Organization for Standardization: Geneva, Switzerland, 2001.
[15]  P. C. Nayak, K. Sudheer, D. Rangan, and K. Ramasastri, "A neuro-fuzzy computing technique for modeling hydrological time series," Journal of Hydrology, vol. 291, no. 1-2, pp. 52-66, 2004.
[16]  M. Zounemat-Kermani and M. Teshnehlab, "Using adaptive neuro-fuzzy inference system for hydrological time series prediction," Applied soft computing, vol. 8, no. 2, pp. 928-936, 2008.