AUTOMATSKA DETEKCIJA INDIKATORA LOŠE DIZAJNIRANOG KODA BAZIRANA NA ISTORIJI PROMENA KODA
Ključne reči:
mašinsko učenje, transformer, indikatori loše dizajniranog koda
Apstrakt
Kod niskog kvaliteta sadrži strukture (code smells) koje otežavaju održavanje i dalji razvoj softvera. U ovom radu predstavljen je model zasnovan na mašinskom učenju za automatsku detekciju indikatora loše dizajniranog koda (code smell-ova) baziranu na istoriji promena koda. Ulaz modela su vrednosti metrika softverskog koda, izračunate u n revizija za posmatrani isečak koda. Izlaz iz modela je labela koja označava da li posmatrani isečak koda sadrži indikator loše dizajniranog koda ili ne. Studija slučaja izvršena je na detekciji klasa sa mnogo odgovornosti (God Class). Predloženi su koraci za poboljšanje i dalji razvoj arhitekture.
Reference
[1] Martin, R.C., 2002. Agile software development: principles, patterns, and practices. Prentice Hall.
[2] Fowler, M., 2018. Refactoring: improving the design of existing code. Addison-Wesley Professional.
[3] Fernandes, E., Oliveira, J., Vale, G., Paiva, T., and Figueiredo, E., 2016, June. A review-based comparative study of bad smell detection tools. In Proceedings of the 20th International Conference on Evaluation and Assessment in Software Engineering (p. 18.). ACM.
[4] Azeem, M.I., Palomba, F., Shi, L. and Wang, Q., 2019. Machine learning techniques for code smell detection: A systematic literature review and meta-analysis. Information and Software Technology.
[5] Lui, Y., Li, Y., Guo, J., Zhou, Y., Xu, B., 2018. Connecting Software Metrics across Versions to Predict Defects. In 2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER) (pp. 232-243). IEEE.
[6] Wen, M., Wu, R. and Cheung, S.C., 2018. How well do change sequences predict defects? Sequence learning from software changes. IEEE Transactions on Software Engineering.
[7] Barbez, A., Khomh, F. and Guéhéneuc, Y.G., 2019. Deep Learning Anti-patterns from Code Metrics History. IEEE International Conference on Software Maintenance and Evolution (ICSME) pp. 114-124.
[8] Palomba, F., Bavota, G., Di Penta, M., Fasano, F., Oliveto, R. and De Lucia, A., 2018. On the diffuseness and the impact on maintainability of code smells: a large scale empirical investigation. Empirical Software Engineering, 23(3), pp.1188-1221.
[9] Pantiuchina, J., Bavota, G., Tufano, M. and Poshyvanyk, D., 2018. Towards Just-In-Time Refactoring Recommenders. ACM/IEEE 26th International Conference on Program Comprehension.
[10] Chawla, N. V., Bowyer, K. W., Hall, L. O., Kegelmeyer, W. P., 2002. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research 16 (2002): 321–357.
[11] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, L., Polosukhin, I., 2017. Attention Is All You Need.
[2] Fowler, M., 2018. Refactoring: improving the design of existing code. Addison-Wesley Professional.
[3] Fernandes, E., Oliveira, J., Vale, G., Paiva, T., and Figueiredo, E., 2016, June. A review-based comparative study of bad smell detection tools. In Proceedings of the 20th International Conference on Evaluation and Assessment in Software Engineering (p. 18.). ACM.
[4] Azeem, M.I., Palomba, F., Shi, L. and Wang, Q., 2019. Machine learning techniques for code smell detection: A systematic literature review and meta-analysis. Information and Software Technology.
[5] Lui, Y., Li, Y., Guo, J., Zhou, Y., Xu, B., 2018. Connecting Software Metrics across Versions to Predict Defects. In 2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER) (pp. 232-243). IEEE.
[6] Wen, M., Wu, R. and Cheung, S.C., 2018. How well do change sequences predict defects? Sequence learning from software changes. IEEE Transactions on Software Engineering.
[7] Barbez, A., Khomh, F. and Guéhéneuc, Y.G., 2019. Deep Learning Anti-patterns from Code Metrics History. IEEE International Conference on Software Maintenance and Evolution (ICSME) pp. 114-124.
[8] Palomba, F., Bavota, G., Di Penta, M., Fasano, F., Oliveto, R. and De Lucia, A., 2018. On the diffuseness and the impact on maintainability of code smells: a large scale empirical investigation. Empirical Software Engineering, 23(3), pp.1188-1221.
[9] Pantiuchina, J., Bavota, G., Tufano, M. and Poshyvanyk, D., 2018. Towards Just-In-Time Refactoring Recommenders. ACM/IEEE 26th International Conference on Program Comprehension.
[10] Chawla, N. V., Bowyer, K. W., Hall, L. O., Kegelmeyer, W. P., 2002. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research 16 (2002): 321–357.
[11] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, L., Polosukhin, I., 2017. Attention Is All You Need.
Objavljeno
2020-12-23
Sekcija
Elektrotehničko i računarsko inženjerstvo
