Implementasi Deep Learning Dengan Feature Selection Untuk Prediksi Cacat Perangkat Lunak Pada Dataset Nasa Metrics Data Program

Dwi Agung  Septian; Bobi Agustian

doi:10.69693/ijim.v4i3.1836

Authors

Dwi Agung Septian Universitas Pamulang
Bobi Agustian Universitas Pamulang

DOI:

https://doi.org/10.69693/ijim.v4i3.1836

Keywords:

Software Defect Prediction, Multi Layer Perceptron, Deep Learning, Machine Learning, NASA Metrics Data Program

Abstract

Prediksi cacat perangkat lunak sangat penting untuk menjaga kualitas sistem, tetapi sering kali menghadapi masalah dimensi atribut yang tidak relevan dan ketidakseimbangan kelas data yang ekstrem. Penelitian ini bertujuan menganalisis pengaruh Feature Selection menggunakan Information Gain dan Synthetic Minority Over-sampling Technique (SMOTE) untuk mengatasi ketidakseimbangan data terhadap performansi model Multi Layer Perceptron (MLP). Dataset yang digunakan berasal dari NASA Metrics Data Program (NASA MDP) yang menggabungkan enam dataset dengan total 28.258 data. Tahap preprocessing data meliputi standardisasi label, median imputation untuk data hilang di bawah 30 persen, eliminasi atribut dengan data hilang di atas 30 persen, standardisasi StandardScaler, dan SMOTE. Feature Selection Information Gain digunakan untuk memilih 10 atribut terbaik. Model MLP dilatih dan dievaluasi menggunakan Stratified 10-Fold Cross Validation. Hasil penelitian menunjukkan bahwa penggunaan SMOTE secara signifikan meningkatkan kemampuan model mendeteksi kelas cacat (Defective), ditandai dengan kenaikan recall dari 0,1897 menjadi 0,7112. Skenario terbaik diperoleh pada kombinasi MLP dengan seleksi fitur dan SMOTE yang menghasilkan akurasi sebesar 0,7549, presisi 0,2368, recall mencapai nilai tertinggi sebesar 0,8267, F1-Score 0,3681, dan Area Under Curve (AUC) sebesar 0,8670. Kombinasi ini berhasil meminimalkan risiko kegagalan sistem akibat cacat yang tidak terdeteksi (false negative). Penelitian ini berkontribusi memberikan panduan metodologis yang efektif bagi pengembang perangkat lunak untuk mengidentifikasi potensi cacat sejak tahap awal pengembangan guna meningkatkan efisiensi pengujian.

Downloads

Download data is not yet available.

References

Altalhan, M., Algarni, A., & Turki-Hadj Alouane, M. (2025). Imbalanced Data Problem In Machine Learning: A Review. IEEE Access, 13, 13686-13699. Https://Doi.Org/10.1109/ACCESS.2025.3531662

Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaria, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review Of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions. Journal Of Big Data, 8(1). Https://Doi.Org/10.1186/S40537-021-00444-8

Buyukkececi, M., & Okur, M. C. (2023). A Comprehensive Review Of Feature Selection And Feature Selection Stability In Machine Learning. Gazi University Journal Of Science, 36(4), 1506-1520. Https://Doi.Org/10.35378/Gujs.993763

Corbacioglu, S. K., & Aksel, G. (2023). Receiver Operating Characteristic Curve Analysis In Diagnostic Accuracy Studies: A Guide To Interpreting The Area Under The Curve Value. Turkish Journal Of Emergency Medicine, 23(4), 195-198. Https://Doi.Org/10.4103/Tjem.Tjem_182_23

Desai, M., & Shah, M. (2021). An Anatomization On Breast Cancer Detection And Diagnosis Employing Multi-Layer Perceptron Neural Network (MLP) And Convolutional Neural Network (CNN). Clinical Ehealth, 4, 1-11. Https://Doi.Org/10.1016/J.Ceh.2020.11.002

Goyal, J., & Sinha, R. R. (2023). A New Improved Prediction Of Software Defects Using Machine Learning-Based Boosting Techniques With NASA Dataset. International Journal On Recent And Innovation Trends In Computing And Communication, 11(10s), 492-504. Https://Doi.Org/10.17762/Ijritcc.V11i10s.7659

Han, J., Pei, J., & Tong, H. (2022). Data Mining: Concepts And Techniques, Fourth Edition. Morgan Kaufmann. Https://Doi.Org/10.1016/C2013-0-18660-6

Jorayeva, M., Akbulut, A., Catal, C., & Mishra, A. (2022). Machine Learning-Based Software Defect Prediction For Mobile Applications: A Systematic Literature Review. Sensors, 22(7), 2551. Https://Doi.Org/10.3390/S22072551

Jude, A., & Uddin, J. (2024). Explainable Software Defects Classification Using SMOTE And Machine Learning. Annals Of Emerging Technologies In Computing, 8(1), 35-49. Https://Doi.Org/10.33166/Aetic.2024.01.00

Kabir, M. A., Ahmed, F., Islam, M. M., & Ahmed, Md. R. (2024). Python For Data Analytics: A Systematic Literature Review Of Tools, Techniques, And Applications. Academic Journal On Science, Technology, Engineering & Mathematics Education, 4(4), 134-154. Https://Doi.Org/10.69593/Ajsteme.V4i04.146

Kemendikbud, T., Wintana, D., Sulaeman, H., & Bahri, S. (2024). Penerapan Multi Layer Perceptron Dan Diskrit Pada Prediksi Cacat Software. J-INTECH (Journal Of Information And Technology), 12(1), 45-53.

Khalid, A., Badshah, G., Ayub, N., Shiraz, M., & Ghouse, M. (2023). Software Defect Prediction Analysis Using Machine Learning Techniques. Sustainability (Switzerland), 15(6), 5517. Https://Doi.Org/10.3390/Su15065517

Liang, Q. (2024). Research On Software Defect Prediction Model Based On Deep Learning. Highlights In Science, Engineering And Technology, 10, 112-120.

Malakouti, S. M., Menhaj, M. B., & Suratgar, A. A. (2023). The Usage Of 10-Fold Cross-Validation And Grid Search To Enhance ML Methods Performance In Solar Farm Power Generation Prediction. Cleaner Engineering And Technology, 15, 100664. Https://Doi.Org/10.1016/J.Clet.2023.100664

Mustaqeem, M., Mustajab, S., & Alam, M. (2024). A Hybrid Approach For Optimizing Software Defect Prediction Using A Gray Wolf Optimization And Multilayer Perceptron. International Journal Of Intelligent Computing And Cybernetics, 17(2), 241-260. Https://Doi.Org/10.1108/IJICC-11-2023-0385

Ningsih, D., Sukmasetya, P., & Gustian, D. (2026). Implementasi Algoritma Machine Learing Pada Data Tidak Seimbang Menggunakan SMOTE Untuk Klasifikasi Kemiskinan Di Indonesia. Jurnal Algoritme, 6(2), 296-309. Https://Doi.Org/10.35957/Algoritme.V6i2.13518

Pachouly, J., Ahirrao, S., Kotecha, K., Selvachandran, G., & Abraham, A. (2022). A Systematic Literature Review On Software Defect Prediction Using Artificial Intelligence: Datasets, Data Validation Methods, Approaches, And Tools. Engineering Applications Of Artificial Intelligence, 111, 104773. Https://Doi.Org/10.1016/J.Engappai.2022.104773

Pudjihartono, N., Fadason, T., Kempa-Liehr, A. W., & O'Sullivan, J. M. (2022). A Review Of Feature Selection Methods For Machine Learning-Based Disease Risk Prediction. Frontiers In Bioinformatics, 2, 927312. Https://Doi.Org/10.3389/Fbinf.2022.927312

Rainio, O., Teuho, J., & Klen, R. (2024). Evaluation Metrics And Statistical Tests For Machine Learning. Scientific Reports, 14(1), 5670. Https://Doi.Org/10.1038/S41598-024-56706-X

Ramadhani, A. A. P., Nugroho, R. A., Faisal, M. R., Abadi, F., & Herteno, R. (2024). The Impact Of Software Metrics In NASA Metric Data Program Dataset Modules For Software Defect Prediction. Telkomnika (Telecommunication Computing Electronics And Control), 22(4), 846-853. Https://Doi.Org/10.12928/TELKOMNIKA.V22i4.25787

Ratra, R., Gulia, P., & Gill, N. S. (2021). Performance Analysis Of Classification Techniques In Data Mining Using WEKA. SSRN Electronic Journal, 12, 1-10. Https://Doi.Org/10.2139/Ssrn.3879610

Sapta Nugraha, A., Reza Faisal, M., Abadi, F., Adi Nugroho, R., & Herteno, R. (2021). Deep Neural Network On Software Defect Prediction. Journal Of Data Science And Software Engineering, 8(2), 112-121.

Sarker, I. H. (2021a). Deep Learning: A Comprehensive Overview On Techniques, Taxonomy, Applications And Research Directions. SN Computer Science, 2(6), 420. Https://Doi.Org/10.1007/S42979-021-00815-1

Sarker, I. H. (2021b). Machine Learning: Algorithms, Real-World Applications And Research Directions. SN Computer Science, 2(3), 160. Https://Doi.Org/10.1007/S42979-021-00592-Y

Sathyanarayanan, S. (2024). Confusion Matrix-Based Performance Evaluation Metrics. African Journal Of Biomedical Research, 27(4), 4023-4031.

Siswantoro, M. Z. F. N., & Yuhana, U. L. (2023). Software Defect Prediction Based On Optimized Machine Learning Models: A Comparative Study. Teknika, 12(2), 166-172. Https://Doi.Org/10.34148/Teknika.V12i2.634

Sweet, L., Müller, C., Anand, M., & Zscheischler, J. (2023). Cross-Validation Strategy Impacts The Performance And Interpretation Of Machine Learning Models. Atmosphere, 14(10), 1205. Https://Doi.Org/10.1175/AIES-D-23