Adaptive fuzzy inference system-based deep learning model for early-phase software dependability analysis

Abstract

Conducting software dependability analysis in the beginning stages of development lowers the likelihood of failures and enhances the overall quality of the system. Some crucial dependability attributes are aging, security, performance, and reliability. The efficiency of traditional dependability analysis and prediction of attributes is limited due to their inability to handle ambiguous, inaccurate, and missing data. This research suggests a fuzzy inference system-based deep neural network model for early-phase software dependability analysis to overcome these difficulties. In order to effectively anticipate dependability attributes and manage the uncertainty of software measurements, a rule formulation algorithm is first developed for the fuzzy inference system model. The estimated dependability attributes are then used to build a deep neural network model that classifies dependable and non-dependable software modules during the early development phase. The deep learning model can reliably classify software modules as trustworthy or not, and it can manage nonlinear interactions of several dependability attributes. Experiments show that the suggested model works better in terms of accuracy, resilience, and flexibility than traditional statistical and machine-learning techniques. This study offers a fresh and clever framework for proactive software dependability evaluation that helps developers to reduce risks early in the software development process.

References

• A. O. C. Ayres and F. J. Von Zuben. Multitask learning applied to evolving fuzzy-rule-based predictors. Evolv. Sys. 12 (2021), pp. 407–422. doi: 10.1007/s12530-019-09300-w
• S. Chakraborty, R. Krishna, Y. Ding, and B. Ray. Deep learning based vulnerability detection: Are we there yet? IEEE Trans. Softw. Eng. 48 (2022), pp. 3280–3296. doi: 10.1109/TSE.2021.3087402
• S. Chatterjee and B. Maji. A Bayesian belief network based model for predicting software faults in early phase of software development process. Appl. Intel. 48 (2018), pp. 2214–2228. doi: 10.1007/s10489-017-1078-x
• S. Chatterjee and B. Maji. A fuzzy logic-based model for classifying software modules in order to achieve dependable software. Int. J. Serv. Sci. Man. Eng. Tech. 11 (2020), pp. 45–57. doi: 10.4018/IJSSMET.2020100103
• S. Chatterjee and D. Saha. IT2F-SEDNN: An interval type-2 fuzzy logic-based stacked ensemble deep learning approach for early phase software dependability analysis. Innov. Syst. Softw. Eng. 21 (2025), pp. 727–746. doi: 10.1007/s11334-024-00563-4
• S. Chatterjee and D. Saha. Software dependability analysis under neutrosophic environment using optimized Elman recurrent neural network-based classification algorithm and Mahalanobis distance-based ranking algorithm. Ann. Oper. Res. 340 (2024), pp. 83–115. doi: 10.1007/s10479-024-05888-8
• S. Chatterjee, D. Saha, and A. Sharma. Multi-upgradation software reliability growth model with dependency of faults under change point and imperfect debugging. J. Softw.: Evol. Proc. 33.6, e2344 (2021). doi: 10.1002/smr.2344
• S. Chatterjee, D. Saha, A. Sharma, and Y. Verma. Reliability and optimal release time analysis for multi up-gradation software with imperfect debugging and varied testing coverage under the effect of random field environments. Ann. Oper. Res. 312 (2022), pp. 65–85. doi: 10.1007/s10479-021-04258-y
• D. Cotroneo, R. Natella, and R. Pietrantuono. Predicting aging-related bugs using software complexity metrics. Perform. Eval. 70 (2013), pp. 163–178. doi: 10.1016/j.peva.2012.09.004
• N. E. Fenton and N. Ohlsson. Quantitative analysis of faults and failures in a complex software system. IEEE Trans. Softw. Eng. 26.8 (2000), pp. 797–814. doi: 10.1109/32.879815
• N. Fenton, M. Neil, and D. Marquez. Using Bayesian networks to predict software defects and reliability. Proc. Inst. Mech. Eng. O. J. Risk Reliab. 222 (2008), pp. 701–712. doi: 10.1243/1748006XJRR161
• K. Filus, P. Boryszko, J. Domańska, M. Siavvas, and E. Gelenbe. Efficient feature selection for static analysis vulnerability prediction. Sensors 21, 1133 (2021). doi: 10.3390/s21041133
• S. Gupta and A. Chug. Software maintainability prediction using an enhanced random forest algorithm. J. Disc. Math. Sci. Crypto. 23 (2020), pp. 441–449. doi: 10.1080/09720529.2020.1728898
• S. Jha, R. Kumar, L. H. Son, M. Abdel-Basset, I. Priyadarshini, R. Sharma, and H. V. Long. Deep learning approach for software maintainability metrics prediction. IEEE Access 7 (2019), pp. 61840–61855. doi: 10.1109/ACCESS.2019.2913349
• J. C. Laprie. Dependability: Basic concepts and terminology. Dependable computing and fault-tolerant dystems. Springer, 1992. doi: 10.1007/978-3-7091-9170-5
• C. Manjula and L. Florence. Deep neural network based hybrid approach for software defect prediction using software metrics. Cluster Comput. 22 (2019), pp. 9847–9863. doi: 10.1007/s10586-018-1696-z
• P. Martín-Muñoz and F. J. Moreno-Velo. FuzzyCN2: An algorithm for extracting fuzzy classification rule lists. 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 (2010). url: https://sci2s.ugr.es/keel/pdf/keel/congreso/fuzzycn2moreno2010.pdf
• G Mauša, T. Galinac Grbac, and B. D. Bašić. Multivariate logistic regression prediction of fault-proneness in software modules. 2012 Proceedings of the 35th International Convention MIPRO. 2012, pp. 698–703. url: https://ieeexplore.ieee.org/abstract/document/6240735
• T. J. McCabe. A complexity measure. IEEE Transa. Softw. Eng. SE-2.4 (1976), pp. 308–320. doi: 10.1109/TSE.1976.233837
• C. K. N. C. K. Mohd and F. Shahbodin. Personalized learning environment: Alpha testing, beta testing and user acceptance test. Procedia Soc. Behav. Sci. 195 (2015), pp. 837–843. doi: 10.1016/j.sbspro.2015.06.319
• A. Mukherjee and D. P. Siewiorek. Measuring software dependability by robustness benchmarking. IEEE Trans. Softw. Eng. 23.6 (1997), pp. 366–378. doi: 10.1109/32.601075
• H. Pham. System software reliability. International series of monographs on physics. Springer, 2006. doi: 10.1007/1-84628-295-0
• D. Saha and S. Chatterjee. Optimized decision tree-based early phase software dependability analysis in uncertain environment. 2022 International Interdisciplinary Conference on Mathematics, Engineering and Science (MESIICON). 2022, pp. 1–6. doi: 10.1109/MESIICON55227.2022.10093237
• J. Sametinger. Software Security. 2013 20th IEEE International Conference and Workshops on Engineering of Computer Based Systems (ECBS). 2013, pp. 216–216. doi: 10.1109/ECBS.2013.24
• P. S. Sandhu, S. Khullar, S. Singh, S. K. Bains, M. Kaur, and G. S. A Study on Early Prediction of Fault Proneness in Software Modules using Genetic Algorithm. World Acad. Sci. Eng. Tech. 4.12 (2010), pp. 648–653. url: https://publications.waset.org/10544/astudy-on-early-prediction-of-fault-proneness-in-softwaremodules-using-genetic-algorithm
• P. Singh, N. R. Pal, S. Verma, and O. P. Vyas. Fuzzy rule-based approach for software fault prediction. IEEE Trans. Sys. Man. Cybern. Sys. 47 (2017), pp. 826–837. doi: 10.1109/TSMC.2016.2521840
• W. Wang, F. Dumont, N. Niu, and G. Horton. Detecting software security vulnerabilities via requirements dependency analysis. IEEE Trans. Softw. Eng. 48 (2022), pp. 1665–1675. doi: 10.1109/TSE.2020.3030745
• P. Yu and X. Yan. Stock price prediction based on deep neural networks. Neural Comput. Appl. 32 (2020), pp. 1609–1628. doi: 10.1007/s00521-019-04212-x
• H. Zhang and X. Zhang. Comments on Data mining static code attributes to learn defect predictors. IEEE Trans. Softw. Eng. 33 (2007), pp. 635–636. doi: 10.1109/TSE.2007.70706