Prediksi Cacat Perangkat Lunak Dengan Implementasi GAN Dan Seleksi Fitur Metrik

• MOCHAMMAD RIZKY KUSUMAYUDHA
• 14220091

---

ABSTRAK

ABSTRAK

Nama               : Mochammad Rizky Kusumayudha

NIM                  : 14220091

Program Studi : Ilmu Komputer

Fakultas          : Teknologi Informasi

Jenjang           : Strata Dua (S2)

Konsentrasi     : Software Engineering

Judul           : “Prediksi Cacat Perangkat Lunak Dengan Implementasi GAN Dan Seleksi Fitur Metrik”

Penelitian ini mengkaji prediksi defek perangkat lunak dengan memanfaatkan metode pemilihan fitur metrik dan algoritma klasifikasi, termasuk Neural Network, Random Forest, k-Nearest Neighbor, dan Decision Tree. Pendekatan ini memanfaatkan dua metrik perangkat lunak, yakni Line of Code (LOC) dan Miscellaneous (MISC), sebagai fitur masukan, sambil menggunakan metode Generative Adversarial Network (GAN) untuk mempelajari distribusi data asli dan menciptakan data sintetis yang serupa. Hasil eksperimen menunjukkan bahwa penerapan metode pemilihan fitur metrik dan teknik GAN secara signifikan meningkatkan kemampuan prediksi cacat perangkat lunak. Algoritma neural network mendapatkan nilai tertinggi sebesar 0.886 untuk nilai spesifisitas dan algoritma decision tree mendapatkan nilai tertinggi sebesar 0.512 untuk nilai sensitivitas. Temuan ini memberikan pemahaman yang lebih baik tentang strategi pemilihan fitur dan teknik penanganan ketidakseimbangan kelas dalam konteks prediksi cacat perangkat lunak. Hasil penelitian ini memiliki potensi aplikasi praktis dalam pengembangan perangkat lunak yang lebih andal dan mengurangi risiko defek.

KATA KUNCI

Prediksi Defek,LoC,MISC,GAN,Perangkat Lunak

---

DAFTAR PUSTAKA

DAFTAR REFERENSI

[1] T. Thaher, M. Mafarja, H. Turabieh, P. A. Castillo, H. Faris, and I. Aljarah, “Teaching Learning-Based Optimization with Evolutionary Binarization Schemes for Tackling Feature Selection Problems,” IEEE Access, vol. 9, pp. 41082–41103, 2021, doi: 10.1109/ACCESS.2021.3064799.

[2] L. T. Giang, D. Kang, and D. H. Bae, “Software fault prediction models for Web applications,” in Proceedings - International Computer Software and Applications Conference, 2010, pp. 51–56. doi: 10.1109/COMPSACW.2010.19.

[3] T. Hidayat, A. F. Habibi, and U. L. Yuhana, “Software Defect Prediction Menggunakan Algoritma K-Nn Yang Dioptimasi Dengan Pso,” SCAN - J. Teknol. Inf. dan Komun., vol. 15, no. 1, pp. 16–21, 2020, doi: 10.33005/scan.v15i1.1848.

[3] X. He, Z. Chang, L. Zhang, H. Xu, H. Chen, and Z. Luo, “A Survey of Defect Detection Applications Based on Generative Adversarial Networks,” IEEE Access, vol. 10, pp. 113493–113512, 2022, doi: 10.1109/ACCESS.2022.3217227.

[4] Z. Xu et al., “Cross Project Defect Prediction via Balanced Distribution Adaptation Based Transfer Learning,” J Comput Sci Technol, vol. 34, no. 5, pp. 1039–1062, 2019, doi: 10.1007/s11390-019.

[5] A. Jalil, R. Bin Faiz, S. Alyahya, and M. Maddeh, “Impact of Optimal Feature Selection Using Hybrid Method for a Multiclass Problem in Cross Project Defect Prediction,” Applied Sciences (Switzerland), vol. 12, no. 23, Dec. 2022, doi: 10.3390/app122312167.

[6] S. Pal and A. Sillitti, “Cross-Project Defect Prediction: A Literature Review,” IEEE Access, vol. 10. Institute of Electrical and Electronics Engineers Inc., pp. 118697–118717, 2022. doi: 10.1109/ACCESS.2022.3221184.

[7] Y. Xing, X. M. Qian, Y. Guan, S. H. Zhang, M. C. Zhao, and W. T. Lin, “Cross-project Defect Prediction Method Using Adversarial Learning,” Ruan Jian Xue Bao/Journal of Software, vol. 33, no. 6, pp. 2097–2112, Jun. 2022, doi: 10.13328/j.cnki.jos.006571.

[8] Z. Li, X. Y. Jing, and X. Zhu, “Progress on approaches to software defect prediction,” IET Softw., vol. 12, no. 3, pp. 161–175, 2018, doi: 10.1049/ietsen.2017.0148.

[9] F. Porto, L. Minku, E. Mendes, and A. Simao, “A Systematic Study of CrossProject Defect Prediction With Meta-Learning”.

[10] D. Radjenovi?, M. Heri?ko, R. Torkar, and A. Živkovi?, “Software fault prediction metrics: A systematic literature review,” Inf. Softw. Technol., vol. 55, no. 8, pp. 1397–1418, 2013, doi: 10.1016/j.infsof.2013.02.009.

[11] D. Ryu and J. Baik, “Effective multi-objective naïve Bayes learning for crossproject defect prediction,” Appl. Soft Comput. J., pp. 1–16, 2016, doi: 10.1016/j.asoc.2016.04.009.

[12] T. Lamba, Kavita, and A. K. Mishra, “Optimal Machine learning Model for Software Defect Prediction,” Int. J. Intell. Syst. Appl., vol. 11, no. 2, pp. 36– 48, 2019, doi: 10.5815/ijisa.2019.02.05.

[13] R. Malhotra and J. Jain, “Handling Imbalanced Data using Ensemble Learning in Software Defect Prediction,” 10th Int. Conf. Cloud Comput. Data Sci. Eng. (Confluence), pp. 300–304, 2020, doi: 10.1109/Confluence47617.2020.9058124.

[14] A. Agrawal and R. Malhotra, “Cross project defect prediction for open source software,” Int. J. Inf. Technol., vol. 14, no. 1, pp. 587–601, 2022, doi: 10.1007/s41870-019-00299-6.

[15] S. I. Ayon, “Neural Network based Software Defect Prediction using Genetic Algorithm and Particle Swarm Optimization,” 1st Int. Conf. Adv. Sci. Eng. Robot. Technol. 2019, ICASERT 2019, vol. 2019, no. Icasert, pp. 1–4, 2019, doi: 10.1109/ICASERT.2019.8934642.

[16] F. Matloob et al., “Software defect prediction using ensemble learning: A systematic literature review,” IEEE Access, vol. 9, pp. 98754–98771, 2021, doi: 10.1109/ACCESS.2021.3095559.

[17] A. O. et al. Balogun, “SMOTE-Based Homogeneous Ensemble Methods for Software Defect Prediction,” Comput. Sci. Its Appl. – ICCSA, vol. 12254. Spr, 2020, doi: Springer, Cham.

[18] Y. Zhong, K. Song, S. K. Lv, and P. He, “An Empirical Study of Software Metrics Diversity for Cross-Project Defect Prediction,” Math. Probl. Eng., vol. 2021, 2021, doi: 10.1155/2021/3135702.

[19] H. Faris, I. Aljarah, and P. A. Castillo, “Teaching Learning-Based Optimization With Evolutionary Binarization Schemes for Tackling Feature Selection Problems,” vol. 9, 2021, doi: 10.1109/ACCESS.2021.3064799.

[20] P. A. Habibi, V. Amrizal, and R. B. Bahaweres, “Cross-Project Defect Prediction for Web Application Using Naive Bayes (Case Study: Petstore Web Application),” 2018 Int. Work. Big Data Inf. Secur. IWBIS 2018, pp. 13– 18, 2018, doi: 10.1109/IWBIS.2018.8471