Analisis Performa Algoritma Decision Tree dengan Correlation-based Feature Selection (CFS) untuk Deteksi Serangan Jaringan
DOI:
https://doi.org/10.70404/jikteks.v4i03.726Keywords:
Decision Tree, CFS, CICIDS2017, Deteksi Instruksi Jaringan, Tradeoff Efisiensi-AkurasiAbstract
Keamanan jaringan membutuhkan Intrusion Detection System (IDS) yang mampu mendeteksi serangan secara akurat dan efisien. Tingginya jumlah fitur pada data jaringan dapat meningkatkan kompleksitas model dan beban komputasi. Penelitian ini mengevaluasi pengaruh Correlation-based Feature Selection (CFS) terhadap kinerja algoritma Decision Tree pada dataset NSL-KDD dan CICIDS2017. Model tanpa seleksi fitur digunakan sebagai baseline dan dibandingkan dengan model berbasis CFS menggunakan metrik Accuracy, Precision, Recall, F1-Score, ROC-AUC, serta waktu pelatihan. Hasil menunjukkan bahwa CFS secara signifikan mengurangi jumlah fitur dan waktu pelatihan pada kedua dataset, tetapi berdampak pada penurunan performa klasifikasi, terutama Recall pada NSL-KDD. Uji Wilcoxon Signed-Rank pada 10-Fold Cross-Validation menunjukkan adanya perbedaan yang signifikan (p = 0,001953). Temuan ini menunjukkan adanya trade-off antara efisiensi komputasi dan kemampuan deteksi, sehingga penerapan CFS perlu disesuaikan dengan prioritas sistem IDS.
Downloads
References
L. Iriani, M. N. Hafizh, and K. E. Setyaputri, "Analisis Forensik Jaringan Serangan ARP Spoofing Menggunakan Metode National Institute of Justice (NIJ)," IT-Explore: Jurnal Penerapan Teknologi Informasi dan Komunikasi, vol. 4, no. 2, pp. 150-160, 2025, doi: 10.24246/itexplore.v4i2.2025.pp150-160.
I. Anshori, K. E. S. Putri, and U. Ghoni, "Analisis Barang Bukti Digital Aplikasi Facebook Messenger pada Smartphone Android Menggunakan Metode NIJ," IT Journal Research and Development, vol. 5, no. 2, pp. 118-134, 2021, doi: 10.25299/itjrd.2021.vol5(2).4664.
Z. Azam, M. M. Islam, and M. N. Huda, "Comparative Analysis of Intrusion Detection Systems and Machine Learning-Based Model Analysis Through Decision Tree," IEEE Access, vol. 11, pp. 80015-80034, 2023, doi: 10.1109/ACCESS.2023.3296444.
W. Y. Sulistyo and J. Supriyanto, "Integrasi Moodle API dan LLM dalam Otomasi Monitoring Capaian Pembelajaran Lulusan Berbasis OBE," JITU: Journal Informatic Technology and Communication, vol. 10, no. 1, pp. 172-182, 2026, doi: 10.36596/jitu.v10i1.2307.
N. F. Rozam, T. N. Sari, M. R. A. Yudianto, and D. F. Rahman, "Deteksi Anomali Lalu Lintas Jaringan Berbasis Machine Learning Menggunakan Dataset CIC-IDS2017," UPGRADE: Jurnal Pendidikan Teknologi Informasi, vol. 3, no. 2, 2026, doi: 10.30812/upgrade.v3i2.6174.
S. Kumar and A. Sharma, "Enhancing IoT Data Analysis with Machine Learning: A Comprehensive Overview," International Journal for Multidisciplinary Research (IJFMR), 2024.
Y. G. Damtew, H. Chen, and Z. Yuan, "Heterogeneous Ensemble Feature Selection for Network Intrusion Detection System," International Journal of Computational Intelligence Systems, vol. 16, no. 1, Art. no. 9, 2023, doi: 10.1007/s44196-022-00174-6.
J. Manurung, A. Mardamsyah, and B. Sianipar, "Enhanced Cyber Attack Detection Using Optimized Random Forest with SMOTE-Based Class Balancing and Feature Selection," Journal of Defense Technology and Engineering, 2026.
F. Ahmad et al., "A Comprehensive Review of Feature Selection Methods in Financial Machine Learning Applications," IEEE Access, 2023.
R. Panigrahi, S. Borah, A. K. Bhoi, M. F. Ijaz, M. Pramanik, Y. Kumar, and R. R. Jha, "A Performance Evaluation of Supervised Machine Learning Algorithms for Network Intrusion Detection," IEEE Access, vol. 9, pp. 83701-83713, 2021, doi: 10.1109/ACCESS.2021.3087593.
M. Di Mauro, G. Galatro, and F. Postiglione, "Feature Selection for Network Intrusion Detection Systems: A Systematic Review and Comparative Study," IEEE Access, vol. 9, pp. 127265-127284, 2021, doi: 10.1109/ACCESS.2021.3112444.
S. Bhaskara, B. Sriman, and K. V. S. N. Murthy, "Detection of DDoS Attacks Using Correlation-Based Feature Selection and Ensemble Learning in CSE-CIC-IDS2018 Dataset," International Journal of Information Security and Privacy, vol. 16, no. 1, pp. 1-18, 2022, doi: 10.4018/IJISP.292150.
S. Gu and X. Lu, "An Adaptive Correlation-Based Feature Selection Method for Network Intrusion Detection System," Journal of Cloud Computing, vol. 10, no. 1, pp. 1-14, 2021, doi: 10.1186/s13677-021-00251-x.
K. Kurniabudi, D. Stiawan, A. Darmawahyuni, A. Hanis, and R. Budiarto, "CICIDS2017 Dataset Feature Selection Using Random Forest," JOIV: International Journal on Informatics Visualization, vol. 5, no. 2, pp. 160-165, 2021, doi: 10.30630/joiv.5.2.551.
A. Maulana, S. Anam, and H. A. Bukhori, "Improving Lateral-Movement Intrusion Detection in Virtualized Networks Using SHAP Feature Selection, SMOTE, and a Voting Ensemble Classifier," Jurnal Teknik Informatika (JUTIF), vol. 6, no. 4, 2025, doi: 10.52436/1.jutif.2025.6.4.5233.
D. J. Sheskin, Handbook of Parametric and Nonparametric Statistical Procedures, 6th ed. Boca Raton, FL, USA: CRC Press, 2020.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Pandu Satria, Wickas
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
