A Neuro-Fuzzy based Automated System for Estimating Software Quality

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2022 by IJETT Journal
Volume-70 Issue-4
Year of Publication : 2022
Authors : Ritu, O. P. Sangwan
  10.14445/22315381/IJETT-V70I4P214

MLA 

MLA Style: Ritu, and Sangwan, O. P.  "A Neuro-Fuzzy based Automated System for Estimating Software Quality." International Journal of Engineering Trends and Technology, vol. 70, no. 4, Apr. 2022, pp. 164-173. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I4P214

APA Style: Ritu, & Sangwan, O. P. (2022). A Neuro-Fuzzy based Automated System for Estimating Software Quality. International Journal of Engineering Trends and Technology, 70(4), 164-173. https://doi.org/10.14445/22315381/IJETT-V70I4P214

Abstract
In this increasing digital software era, various software becomes of daily use in human life, ranging from shopping to meeting, working from home, etc. It is a necessity for good software that is easy to operate, highly secure, and highly accurate. These properties constitute the quality of software. Generally, the quality of the software is estimated based on the expert's opinion or from any other user of that software, which can be time-consuming and may not be highly accurate as it depends upon user-to-user experience. It is a demand for an automated system that the quality of software can be estimated by providing some inputs or features. Due to recent development in machine learning, the neural network has been largely employed in academia as well as industry. Thus, this paper presents a neuro-fuzzy-based automated system to estimate the quality of given software. The user needs to feed only five parameters, namely Reliability, Usability, Functionality, Efficiency, Portability, and Maintainability, and the proposed model automatically calculates the quality of software. The proposed model is based on the data collected from the 128 software, where 100 data-set are used for training the proposed neuro-fuzzy model and 28 data-set for testing purposes. The obtained results with the proposed approach closely match the actual software quality. Moreover, two fuzzy rule generation techniques, i.e. 'grid partition' and 'sub-clustering', have been designed and compared the obtained results with both approaches. It is found that the proposed approach with sub-clustering has lesser error measures like MSE, MRE, and MARE in terms of performance indexes, among other methods.

Keywords
ANFIS, Fuzzy logic, Neuro-fuzzy, Neural Networks, MATLAB Simulation, Software Quality.

Reference
[1] B. W. Boehm, J. R. Brown, and M. Lipow, Quantitative evaluation of software quality, in Proc. of 2nd international conference on Software engineering, (1976) 592-605.
[2] A. Monden, D. Nakae, T. Kamiya, S. I. Sato, and K. I. Matsumoto, Software quality analysis by code clones in industrial legacy software, in Proc. of 8th IEEE Symposium on Software Metrics, (2002) 87-94.
[3] Z. H. Zhou, Neural networks, in Proc. of Machine Learning, Springer, Singapore. (2021) 103-128.
[4] T. J., Ross, Fuzzy Logic With Engineering Applications, John Wiley & Sons. (2005).
[5] C. Catal, Software Fault Prediction: A Literature Review and Current Trends, Expert Systems with Applications, 38(4) (2011) 46264636.
[6] J., Klomjit, and A., Ngaopitakkul, Comparison of Artificial Intelligence Methods for Fault Classification of the 115-kV Hybrid Transmission System, Applied Sciences, 10(11) (2020).
[7] S. Yadav, and B. Kishan, Analysis and Assessment of Existing Software Quality Models to Predict the Reliability of Component-based Software, International Journal of Emerging Trends in Engineering Research, 8(6) (2020) 2824-2840.
[8] J. Paul and V. Bhattacherjee, Software Quality Prediction using Fuzzy Rule-Based System, International Journal of Current Research, 7(12) (2015) 24181-24185.
[9] Ritu, and O. P. Sangwan, Software Quality Prediction Method using Fuzzy Logic, Turkish Journal of Computer and Mathematics Education, 12(11) (2021) 807-817.
[10] S. S. So, S. D. Cha, and Y. R. Kwon, Empirical Evaluation of a Fuzzy Logic-based Software Quality Prediction Model, Fuzzy Sets and Systems, 127(2) (2002) 199-208.
[11] F. He, A. Ren, and Z. Ding, Software Quality Prediction Model Research Based on Object-Oriented Petri Nets, International Journal of Electronics and Electrical Engineering, 3(3) (2015) 225-229.
[12] A. Rai, T. Choudhury, S. Sharma, and K. C. Ting, An efficient method to predict software quality using soft computing techniques, in Proc. of 3rd International Conference on Applied and Theoretical Computing and Communication Technology, (2017) 347-353.
[13] A. Sandanasamy and R. T. Selvi, A Quality-Based Software Requirement Prioritization Using TakagiSugeno Neuro-Fuzzy Inference, International Journal of Computer Sciences and Engineering, 7(5) (2019).
[14] K. Sahu and R. K. Srivastava, Soft Computing Approach for Prediction of Software Reliability, ICIC Express Letters, 12(12) (2018) 1213-1222.
[15] C. Diwaker, P. Tomar, R. C. Poonia, and V. Singh, Prediction of Software Reliability using Bio-inspired Soft Computing Techniques, Journal of Medical Systems, 42(5) (2018) 1-16.
[16] N. Li, M. Shepperd, and Y. Guo, A Systematic Review of Unsupervised Learning Techniques for Software Defect Prediction, Information and Software Technology, 122 (2020).
[17] S. K. S. Durai, B. Duraisamy, and J. T. Thirukrishna, Fuzzy Interference System based Link Failure Prediction in MANET, in Proc. of Journal of Physics: Conference Series, 1964(7) (2021).
[18] W. Peng, L. Yao, and Q. Miao, An approach of software quality prediction based on relationship analysis and prediction model, in Proc. of 8th International Conference on Reliability, Maintainability and Safety, (2009) 713-717.
[19] Q. Wang, B. Yu, and J. Zhu Extract rule from software quality prediction model based on neural network, in Proc. of 16th IEEE International Conference on Tools with Artificial Intelligence, (2004) 191-195.

[20] K. Sheoran, P. Tomar, and R. Mishra, Software Quality Prediction Model with The Aid of Advanced Neural Network with HCS, Procedia Computer Science, 92 (2016) 418-424.
[21] A. Barzegar, and Y. Barzegar, Adaptive Neuro-Fuzzy Inference System for Measuring Software Quality Product, 2021.
[22] Sharma, Pragati, Software Quality Prediction using Hybrid Approach, International Journal of Computer Applications, 180(4) (2017) 0975–8887.
[23] S. Pattnaik, B. K. Pattanayak, and S. Patnaik, Prediction of Software Quality using Neuro-fuzzy Model, International Journal of Intelligent Enterprise, 5(3) (2018) 292-307.
[24] S. Sahar, and U. Qamar, and S. Ayaz, Multilayer Neural Network and Fuzzy Logic Based Software Quality Prediction, International Journal of Computer and Systems Engineering, 11(9) (2017) 1024-1028.
[25] B. S. Dhillon, Applied Reliability and Quality: Fundamentals, Methods and Procedures, Springer Science & Business Media, 2007.
[26] J. S. Jang, ANFIS: Adaptive-network-based Fuzzy Inference System, IEEE Transactions on Systems, Man, and Cybernetics, 23(3) (1993) 665-685.
[27] Y. Gershteyn, and L. Perman, Matlab: ANFIS Toolbox, The MathWorks, 2003.
[28] P. Mangayarkarasi, and R. Selvarani, A Novel Software Cost Estimation Technique: Inclusion of Reusability, International Journal of Engineering Trends and Technology, 44(1) (2017) 42-47.
[29] A. Thakur, and A. Goel, A Hybrid Neuro-Fuzzy Approach for Bug Prediction using Software Metrics, International Journal of Engineering Trends and Technology, 38(2) (2016) 85-92.