Predicción de Defectos de Software Utilizando Enfoques Bayesianos
Palabras clave:
anticipación de defectos en software, Redes Bayesianas, categorización, aprendizaje automáticoResumen
En el ámbito de la ingeniería de software, la anticipación de fallas en el software tiene una importancia significativa, ya que permite a los desarrolladores identificar y corregir problemas antes de que se conviertan en errores costosos y desafiantes. La identificación oportuna de defectos de software no solo ahorra tiempo y recursos en el ciclo de desarrollo de software, sino que también garantiza la calidad final del producto. Este estudio busca evaluar tres algoritmos para construir Redes Bayesianas, con el objetivo de clasificar proyectos como susceptibles a defectos. Mientras que Naive Bayes es el método predominante en la literatura, esta investigación presenta K2, Hill Climbing y TAN como alternativas para construir Redes Bayesianas. Mientras tanto, se emplean tres conjuntos de datos públicos de PROMISE, que incorporan métricas de complejidad de McCabe y Halstead. Los resultados obtenidos se comparan con enfoques ampliamente utilizados como Decision Tree y Random Forest. Las métricas de rendimiento aplicadas en un proceso de validación cruzada revelan que los resultados de clasificación están a la par con Decision Tree y Random Forest. Es importante destacar que los algoritmos bayesianos muestran una menor variabilidad, mejorando la robustez de las predicciones en ingeniería de software. Esta ventaja es evidente en los resultados consistentes de la selección de datos de entrenamiento y prueba, lo que los distingue de los resultados variables observados en los enfoques de Decision Tree y Random Forest.
Citas
Meiliana, S.K., Karim, S., Warnars, H.L.H.S., Gaol, F.L., Abdurachman, E., Soewito, B. Software Metrics for Fault Prediction Using Machine Learning Approaches: A Literature Review with PROMISE Repository Dataset. In Proceedings of the 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom), Phuket, Thailand, 20–22 November 2017.
Hammanouri, A., Hammad, M., Alnabhan, M., Alsarayrah, F. Software Bug Prediction using Machine Learning Approach. Int. J. Adv. Comput. Sci. Appl. 2018, 9, 78–83.
Misirli, A., Bener, A.B. A Mapping Study on Bayeasian Networks for Software Quality Prediction. In Proceedings of the 3rd International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering (RAISE), Hyderabad, India, 3 June 2014.
Herzing, K., Just, S., Zeller, A. It’s Not a Bug, It’s a Feature: How Misclassification Impacts Bug Prediction. In Proceedings of 2013 35th International Conference on Software Engineering (ICSE), San Francisco, CA, USA, 18–26 May 2013.
Hernández-Molinos, M.J., Sánchez-García, Á.J., Barrientos-Martínez, R.E. Classification Algorithms for Software Defect Prediction: A Systematic Literature Review. In Proceedings of the 2021 9th International Conference in Software Engineering Research and Innovation (CONISOFT), San Diego, CA, USA, 25–29 October 2021.
Li, R., Zhou, L., Zhang, S., Liu, H., Huang, X., Sun, Z. Software Defect Prediction Based on Ensemble Learning. In Proceedings of 2019 2nd International Conference on Data Science and Information Technology (DSIT), Seoul, Republic of Korea, 19–21 July 2019.
Aydin, Z.B.G., Samli, R. Performance Evaluation of Some Machine Learning Algorithms in NASA Defect Prediction Data Sets. In Proceedings of the 2020 5th International Conference on Computer Science and Engineering (UBMK), Diyarbakir, Turkey, 9–11 September 2020.
Goyal, S. Heterogeneous Stacked Ensemble Classifier for Software Defect Prediction. In Proceedings of the 2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC), Waknaghat, India, 6–8 November 2020.
Aljamaan, H., Alazba, A. Software Defect Prediction using Tree-Based Ensembles. In Proceedings of the 16th ACM International Conference on Predictive Models and Data Analytics in Software Engineering (PROMISE), Online, 8–9 November 2020.
Ge, J., Liu, J., Liu, W. Comparative Study on Defect Prediction Algorithms of Supervised Learning Software Based on Imbalanced Classification Data Sets. In Proceedings of the 2018 19th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), Busan, Republic of Korea, 27–29 June 2018.
Prahba, C.L., Shivahumar, N. Software Defect Prediction Using Machine Learning Techniques. In Proceedings of the 2020 4th International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 15–17 June 2020.
Ahmed, M.R., Ali, M.A., Ahmed, N., Zamal, M.F.B., Shamrat, F.M.J.M. The Impact of Software Fault Prediction in Real-World Application: An Automated Approach for Software Engineering. In Proceedings of the 2020 the 6th International Conference on Computing and Data Engineering (ICCDE), Sanya, China, 4–6 January 2020.
Nehi, M.M., Fakhrpoor, Z., Moosavi, M.R. Defects in The Next Release; Software Defect Prediction Based on Source Code Versions. In Proceedings of the Iranian Conference on Electrical Engineering (ICEE), Mashhad, Iran, 8–10 May 2018
Zhou, Y., Shan, C., Sun, S., Wei, S., Zhang, S. Software Defect Prediction Model Based On KPCA-SVM. In Proceedings of the 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), Leicester, UK, 19–23 August 2019.
El-Shorbagy, S.A., El-Gammal, W.M., Abdelmoez, W.M. Using SMOTE and Heterogeneous Stacking in Ensemble learning for Software Defect Prediction. In Proceedings of the 7th International Conference on Software and Information Engineering (ICSIE), Cairo, Egypt, 2-4 May 2018.
Bhutamapuram, U.S.; Sadam, R. Within-project defect prediction using bootstrap aggregation based diverse ensemble learning
technique. J. King Saud Univ. Comput. Inf. Sci. [Year], [Volume], [Pages].
Goyal, S. Handling class-imbalance with KNN (neighbourhood) under-sampling for software defect prediction. Artif. Intell. Rev.
[Year], [Volume], [Pages].
Malhotra, R.; Meena, S. Defect prediction model using transfer learning. Soft Comput. [Year], [Volume], [Pages].
Goyal, S. Effective software defect prediction using support vector machines (SVMs). Int. J. Syst. Assur. Eng. Manag. [Year], [Volume],
[Pages].
Cornfield, J. Bayes Theorem. Rev. De L’institut Int. De Stat. [Year], [Volume], [Pages].
Madden, M.G. On the classification performance of TAN and general Bayesian networks. In Research and Development in Intelligent
Systems XXV. SGAI 2008; Springer: London, UK, [Year]; pp. 3–16.
Friedman, N.; Geiger, D.; Goldszmidt, M. Bayesian network classifiers. Mach. Learn. [Year], [Volume], [Pages].
Gámez, J.A.; Mateo, J.L.; Puerta, J.M. Learning Bayesian networks by hill climbing: Efficient methods based on progressive
restriction of the neighborhood. Data Min. Knowl. Discov. [Year], [Volume], [Pages].
Cooper, G.F.; Herskovits, E. A Bayesian method for the induction of probabilistic networks from data. Mach. Learn. [Year], [Volume],
[Pages].
He, Y.L.; Zhao, W.J.; Xu, Y.; Zhu, Q.X. Research and Improvement of K2 Algorithm Based on Topological Sorting. In Proceedings
of the 2021 China Automation Congress (CAC), Beijing, China, [Year]; pp. 4623–4626.
Shirabad, J.S.; Menzies, T.J. The PROMISE Repository of Software Engineering Databases [Data Set]; School of Information Technology and Engineering, University of Ottawa: Ottawa, ON, Canada, [Year]; Available online: http://promise.site.uottawa.ca/
SERepository (accessed on 1 February 2022).
McCabe, T.J. A Complexity Measure. IEEE Trans. Softw. Eng. [Year], [Volume], [Pages].
Halstead, M.H. Elements of Software Science (Operating and Programming Systems Series) [Data Set]; Elsevier Science Inc.: Amsterdam,
The Netherlands, [Year].
Henry, S.; Selig, C. Predicting Source-Code Complexity at the Design Stage. IEEE Softw. [Year], [Volume], [Pages].
Fushiki, T. Estimation of Prediction Error by Using K-Fold Cross-Validation. Statics Comput. [Year], [Volume], [Pages].
Das, N.N.; Kumar, N.; Kaur, M.; Kumar, V.; Singh, D. Automated deep transfer learning-based approach for detection of
COVID-19 infection in chest X-rays. Irbm [2022], [43], [114-119].
