Semantic Feature Driven Consensus-Based Model for Software Reliability Assessment: A Reusability Sensitive Verification Paradigm

Semantic Feature Driven Consensus-Based Model for Software Reliability Assessment: A Reusability Sensitive Verification Paradigm

© 2022 by IJETT Journal
Volume-70 Issue-4
Year of Publication : 2022
Authors : Prakash V. Parande, M K. Banga
DOI :  10.14445/22315381/IJETT-V70I4P209

How to Cite?

Prakash V. Parande, M K. Banga, "Semantic Feature Driven Consensus-Based Model for Software Reliability Assessment: A Reusability Sensitive Verification Paradigm," International Journal of Engineering Trends and Technology, vol. 70, no. 4, pp. 107-121, 2022. Crossref,

The exponential rise in global competitiveness and quality concern has forced software enterprises to ensure cost-efficiency with uncompromising product reliability. Software developers often intend to use the free-open-source software or class-reuse paradigm to reduce development costs. However, excessive reuse of software components often leads to pre-mature ageing, smells, and malfunction. To alleviate such issues, assessing each class for its reusability can be of great significance. Despite the numerous efforts, the existing approaches have failed to address the problems like class imbalance, shallow feature learning, and, more importantly, low accuracy. In this paper, a robust semantic-feature-driven consensus-based software reusability prediction model is developed for software reliability assessment. To achieve it, at first, it exploits a set of 17 Chidamber and Kamerer OOP matrices obtained by means of WSImport and the CKJM tool. To further enrich intrinsic feature information for future learning, s-Skip Gram-based semantic feature extraction over each metric for every class and SMOTE-ENNresampling algorithm has been employed with variance threshold algorithm and Mann-Whitney significant predictor tests. Min-Max normalization was done on the results to handle issues that rose from convergence and the over-fitting behaviour of classifiers. The simulation results confirmed that the proposed semantic-feature-driven consensus model achieves an accuracy of 98.27%, F-score of 0.983, and AUC of 0.996, which is the highest performance across the existing state-of-art methods.

Software Reliability, Reusability Prediction, Consensus Learning, Semantic Features, Software Metrics.

[1] Q. Li and H. Pham, A Generalized Software Reliability Growth Model with Consideration of the Uncertainty of Operating Environments, in IEEE Access,. 7(2019)84253-84267.
[2] Martínez-Fernández et al., Continuously Assessing and Improving Software Quality with Software Analytics Tools: A Case Study, in IEEE Access 7(2019). 68219-68239.
[3] Stapic M. M. Reusability metrics of Software Components: Survey, Conference Paper (2015).
[4] M. Lafi, J. W. Botros, H. Kafaween, A. B. Al-Dasoqi, and A. Al-Tamimi, Code Smells Analysis Mechanisms, Detection Issues, and Effect on Software Maintainability, IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (2019)663-666.
[5] H. Liu, Q. Liu, Z. Niu, and Y. Liu, Dynamic and Automatic Feedback-Based Threshold Adaptation for Code Smell Detection, in IEEE Transactions on Software Engineering, 42(6) (2016)544-558.
[6] Baaba, H. B. Zulzalil, S. Hassan and S. B. Baharom, Software Architecture Degradation in Open-Source Software: A Systematic Literature Review, in IEEE Access, 8(2020) 173681-173709.
[7] F. Palomba, M. Zanoni, F. A. Fontana, A. De Lucia, and R. Oliveto, Toward a Smell-Aware Bug Prediction Model, in IEEE Transactions on Software Engineering, 45(2) (2019)194-218.
[8] J. L. Barros Justo, N. Martinez Araujo, and A. Gonzalez Garcia, Software Reuse and Continuous Software Development: A Systematic Mapping Study, in IEEE Latin America Trans 16(5) (2018)1539-1546.
[9] Diwaker et al., A New Model for Predicting Component-Based Software Reliability Using Soft Computing, in IEEE Access, 7(2019) pp. 147191-203.
[10] M. -C. Chiang, C. -Y. Huang, C. -Y. Wu and C. -Y. Tsai, Analysis of a Fault-Tolerant Framework for Reliability Prediction of Service-Oriented Architecture Systems, in IEEE Trans. on Reliability, 70(1)(2021) 13-48.
[11] S. Maggo and C. Gupta, A Machine Learning-based Efficient Software Reusability Prediction Model for Java-Based Object-Oriented Software, Intl. Journal of Information Tech. And Comp. Sci. 6(2)(2014)1-13.
[12] Sanyam, Prediction of Reusability of Object-Oriented Software Systems using Clustering Approach, World Academy of Science, Engineering and Technology, 43(2010)853-56.
[13] Huda, A. Huneiti and I. Othman, Software Reusability Classification and Predication Using Self-Organizing Map (SOM), Communications and Network, 8(2016)179-192.
[14] P. V. Parande and M. K. Banga, Web-of-Service Software Reusability Prediction using Heterogeneous Ensemble Classifier, Intl. Journal of Innovative Tech. And Exploring Engg., 8(9S3)(2019)1276-82.
[15] N. Padhy, S. C. Stapathy, J. R. Mohanty and R. Panigrahi, Software Reusability Metrics Prediction by Using Evolutionary Algorithms: The Interactive Mobile Learning Application RozGaar, International Journal of Knowledge-based and Intelligent Engg. Sys. 22(4)(2018) 261-276.
[16] R. Panigrahi, S. K. Kunar, L. Kumar, N. Padhy and S. C. Satapathy, Software reusability metrics prediction and cost estimation by using machine learning algorithms, International Journal of Knowledge-based and Intelligent Engineering Systems, 23(4)(2019)317-328.
[17] N. Padhy, R. P. Singh, S. C. Stapathy, Cost-effective and fault-resilient reusability prediction model by using adaptive genetic algorithm-based neural network for web-of-service applications, Cluster Computing, 22(2019)14559-81.
[18] N. Padhy, R. P. Singh, S. C. Stapathy, Enhanced Evolutionary Computing Based Artificial Intelligence Model for Web-Solutions Software Reusability Estimation, Cluster Computing, 22(2019)9787–9804.
[19] L. Gong, S. Jiang, L. Bo, L. Jiang, and J. Qian, A Novel Class-Imbalance Learning Approach for Both Within-Project and Cross-Project Defect Prediction, in IEEE Trans. on Reliability, 69(1)(2020)40-54.
[20] P. R. Bal and S. Kumar, WR-ELM: Weighted Regularization Extreme Learning Machine for Imbalance Learning in Software Fault Prediction, in IEEE Transactions on Reliability, 69(4)(2020)1355-1375.
[21] Singhani H., Suri R. P. Testability Assessment model for Object-Oriented Software Based on Internal and External Quality Factors, Global Journal of Computer Science and Technology: C Software & Data Engineering, 15(5)(2015).
[22] Mijac M., Stapic Z. Reusability Metrics of Software Components: Survey, Central European conf. On Information and Intelligent sys. (2015).
[23] Srivastava S. and Kumar R. An Indirect Method to Measure Software Quality using CK-OO suite, Intelligent Systems and Signal Processing (ISSP), International Conference on, Gujarat, (2013) 47-51.
[24] Goel B.M. and Bhatia P.K. Analysis of reusability of an object-oriented system using CK metrics, International Journal of Computer Applications, 60(10) (2012)0975–8887.
[25] Rosenberg L.H. and Hyatt L.E. Software Quality Metrics for Object-Oriented Environments, Crosstalk Journal, 10(1997)1-16.
[26] Chidamber S.R. and. Kemerer C. F. A metrics suite for object-oriented design, IEEE Transactions on Software Engineering, IEEE Press Piscataway, NJ, USA. 20(1994) 476-493.
[27] Antony P.J. Predicting Reliability of Software Using Thresholds of CK Metrics, Intl. Journal of Advanced Networking &Appl, 4(6)(2013).
[28] Hudiab A., Al-Zaghoul F., Saadeh M., and Saadeh H. ADTEM—Architecture Design Testability Evaluation Model to Assess Software Architecture Based on Testability Metrics, Journal of Software Engineering and Applications, 8 (2015)201-210.
[29] Berander P., Damm L-O-, Eriksson J., Gorschek T., Henningsson K., Jönsson P., Kågström S., Milicic D., Mårtensson F., Rönkkö K. Software quality attributes and trade-offs. Blekinge Instt. of Tech, Blekinge. (2005).
[30] Shatnawi R. A Quantitative Investigation of the Acceptable Risk levels of Object-oriented metrics in open-source systems, IEEE Transactions on Software Engineering, 36 (2010)216-225.
[31] Shatnawi R., Li W., Swain J., and Newman T. Finding software metrics threshold values using roc curves, Journal of Software Maintenance and Evolution: Research and Practice, John Wiley & Sons, Inc. New York, NY, USA. 22 (2010)1-16.
[32] Neelamdhab P., Satapathy S., Singh R. Utility of an Object-Oriented Reusability Metrics and Estimation Complexity. Indian Journal of Science and Technology, 10(3)(2017).
[33] Normi Sham Awang Abu Bakar. The analysis of object-oriented metrics in C++ programs, Lecture Notes on Software Engineering, Springer, 4(1)(2016).
[34] Zahara S. I., Ilyas M., and Zia T. A study of Comparative Analysis of Regression Algorithms for Reusability Evaluation of Object-oriented based Software Components, Open-Source Systems and Technologies (ICOSST), International Conference on, Lahore, (2013) 75-80.
[35] Torkamani M. A. Metric suite to evaluate reusability of software product line, International Journal of Electrical and Computer Engineering (ICE), 4(2) (2014)285-294.
[36] Aloysius A., and Maheswar K. A review on component-based software metrics, Intern. J. Fuzzy Mathematical Archive, vol. 7( 2) (2015)185-194. ISSN: 2320 –3242 (P), (2015) 2320 –3250.
[37] Cho E.S., Kim M.S., and Kim S.D. Component metrics to measure component quality, Proceedings of the 8th Asia Pacific Software Engineering Conference (APSEC), Macau,. 4-7 (2001) 419-426.
[38] Canul-Reich J., Shoemaker L., Hall L.O. Ensembles of fuzzy Classifiers, in IEEE International Fuzzy Systems Conference, (2007)1–6.
[39] Rodriguez J.J., Kuncheva L.I. Rotation forest: a new classifier ensemble method, IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (10) (2006)1619–1630.
[40] Z. Chun-Xia, Zhang Jiang-She. RotBoost: a technique for combining rotation forest and AdaBoost, Pattern Recognition Letters 29(2008)1524–1536.
[41] Nanni L., Lumini A. Ensemble generation and feature selection for the identification of students with learning disabilities, Expert Systems with Applications 36 (2009)3896–3900.
[42] Zhang X., Wang S., Shan T., Jiao L.C. Selective SVMs Ensemble-driven by Immune Clonal Algorithm, in Rothlauf, F. (Ed.) Proc. of the EvoWork- Shops, Springer, Berlin, (2005) 325–333.
[43] Zhou Z.H., Wu J., Tang W. Ensembling Neural Networks: many could be Better than all, Artificial Intelligence 137 (1–2) (2002) 239–263.
[44] Partalas I., Tsoumakas G., Vlahavas I. Focused Ensemble selection: a Diversity-based Method for Greedy Ensemble selection, in Proceedings of the 18th International Conference on Artificial Intelligence, (2008)117–121.
[45] Dong YS., Han KS. A Comparison of Several Ensemble methods for Text Categorization, Services Computing, (SCC 2004). Proceedings. IEEE International Conference (2004) 419-422.
[46] Roli F., Giacinto G., Vernazza G. Methods for Designing Multiple Classifier Systems. Proceedings of the Second International Workshop on Multiple Classifier Systems. Cambridge, UK, (2001)78–87.
[47] Banfield R. (2007). A Comparison of Decision Tree Ensemble Creation Techniques. IEEE Trans. on Pattern Analysis and Mach. Intell, 29 (2007) 173–180.
[48] Nanni L., Lumini A. Ensemble generation and Feature Selection for the Identification of Students with Learning disabilities, Expert Systems with Applications 36 (2009)3896–3900.
[49] Zhang X., Wang S., Shan T., Jiao L.C. Selective SVMs Ensemble-driven by Immune Clonal Algorithm, in Rothlauf, F. (Ed.) Proc. of the EvoWork- shops, Springer, Berlin, (2005)325–33.
[50] Bi Y., Bell D., Wang H., Guo G., Guan J. Combining Multiple Classifiers Using Dempster`s Rule for Text Categorization. Appl. Artif. Intell. 21(2007) 211-239.
[51] Y. An, F. Qin, B. Chen, R. Simon, and H. Wu, OntoPLC: Semantic Model of PLC Programs for Code Exchange and Software Reuse, in IEEE Trans. on Industrial Informatics,17(3) (2021) 1702-1711.
[52] N. V. Chawla, K.W. Bowyer, L. O. Hall, and. P. Kegelmeyer, SMOTE: Synthetic Minority Over-Sampling Technique, J. Artif. Intell. Res., 16(2002)321–357.
[53] He H, Garcia EA Learning from Imbalanced Data. IEEE Trans Knowledge Data Eng 21(2009)1263–1284.
[54] García V, Sánchez JS, Mollineda RA On the Effectiveness of Pre-processing Methods when Dealing with Different Levels of Class Imbalance. Knowl Based Syst. (2012)
[55] Galar M, Fernández A, Barrenechea E, Herrera F EUSBoost: Enhancing Ensembles for Highly Imbalanced data-sets by Evolutionary Undersampling. Pattern Recognit 46 (2013) 3460–3471.
[56] Q. Li, W. Li, J. Wang, and M. Cheng, A SQL Injection Detection Method Based on Adaptive Deep Forest, IEEE Access, 7(2019) 145385-94.