DETEKSI ANOMALI PERGERAKAN KAPAL MENGGUNAKAN ISOLATION FOREST DAN ONE CLASS SVM DI PELABUHAN TANJUNG PRIOK

Sari Ningsih - Universitas Nasional
Panca Dewi Pamungkasari - Universitas Nasional
Tunggul Puliwarna - Bakamla Republik Indonesia
Babag Purbantoro - BRIN Jakarta
Endah Tri Esti Handayani - Universitas Nasional
Ratih Titi Komala Sari - Universitas Nasional
Ahmad Rifqi - Universitas Nasional
Fauziah Fauziah - Universitas Nasional
Muhammad Zahran Alfarizi - Universitas Nasional
Erina Rahmazani - Universitas Nasional

Abstract


Ship movement activities in busy port areas have the potential to generate abnormal movement patterns that may disrupt maritime security and operational efficiency. The main problem addressed in this program is the need for an early detection system capable of identifying vessel movement anomalies quickly and accurately. This Community Service Program (PKM) aimed to develop an anomaly detection model for ship movements at Tanjung Priok Port using the Isolation Forest and One Class Support Vector Machine (OC-SVM) methods. The novelty of this program lies in the integration of these two methods into a maritime traffic data-based anomaly detection system developed collaboratively with the Indonesian Maritime Security Agency (Bakamla RI) to support smarter and more adaptive maritime surveillance. The implementation method consisted of ship movement data collection, data preprocessing, machine learning model development, system testing, and dissemination of results to the Indonesian Maritime Security Agency (Bakamla RI) as the partner institution. The results showed that the developed model was able to identify abnormal ship movement patterns, such as sudden direction changes, unusual speed, and movement outside designated shipping lanes. The resulting system provided faster data visualization and anomaly information, thereby supporting more effective and efficient maritime surveillance processes. This activity also created opportunities for broader implementation across Indonesian waters.

 

ABSTRAK

Aktivitas pergerakan kapal di kawasan pelabuhan yang padat memiliki potensi terjadinya pola pergerakan tidak normal yang dapat mengganggu keamanan dan kelancaran operasional maritim. Permasalahan utama yang dihadapi adalah kebutuhan akan sistem deteksi dini yang mampu mengidentifikasi anomali pergerakan kapal secara cepat dan akurat. Kegiatan Pengabdian Kepada Masyarakat (PKM) ini bertujuan mengembangkan model deteksi anomali pergerakan kapal di Pelabuhan Tanjung Priok menggunakan metode Isolation Forest dan One Class Support Vector Machine (OC-SVM). Kebaruan kegiatan ini terletak pada penerapan dan integrasi kedua metode tersebut dalam sistem deteksi anomali berbasis data pelayaran yang dikembangkan bersama Bakamla RI untuk mendukung pengawasan maritim secara lebih cerdas dan adaptif. Metode pelaksanaan dilakukan melalui tahapan pengumpulan data pergerakan kapal, praproses data, pemodelan menggunakan algoritma machine learning, pengujian sistem, serta sosialisasi hasil kepada mitra Badan Keamanan Laut Republik Indonesia (Bakamla RI). Hasil kegiatan menunjukkan bahwa model yang dikembangkan mampu mengidentifikasi pola pergerakan kapal yang menyimpang dari rute normal, seperti perubahan arah mendadak, kecepatan tidak wajar, dan pergerakan di luar jalur pelayaran. Sistem yang dihasilkan memberikan visualisasi data dan informasi anomali secara lebih cepat sehingga mendukung proses pengawasan maritim yang lebih efektif dan efisien. Kegiatan ini juga membuka peluang implementasi sistem pada wilayah perairan Indonesia secara lebih luas.


Keywords


Anomaly Detection, Ship Movement, Isolation Forest, One Class Svm, Maritime Security ; Deteksi Anomali, Pergerakan Kapal, Isolation Forest, One Class Svm, Keamanan Maritim.

Full Text:

PDF

References


Airlangga, G. (2023). Unsupervised machine learning for seismic anomaly detection: isolation forest algorithm application to Indonesian earthquake data. 4(3), 1827–1836. https://doi.org/10.46306/lb.v4i

Alam, M. N., Laxmi, V., Kumar, N., Kumari, R., & Sharma, S. (2025). Unsupervised Machine Learning for Anomaly Detection: A Systematic Review. SSRG International Journal of Electrical and Electronics Engineering, 12(7), 34–72. https://doi.org/10.14445/23488379/IJEEE-V12I7P104

Bischl, B., Binder, M., Lang, M., Pielok, T., Richter, J., Coors, S., Thomas, J., Ullmann, T., Becker, M., Boulesteix, A. L., Deng, D., & Lindauer, M. (2023). Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges. In Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery (Vol. 13, Number 2). John Wiley and Sons Inc. https://doi.org/10.1002/widm.1484

Boži?, J., Fu?ka, M., Zavrtanik, V., & Sko?aj, D. (2025). Robustness of unsupervised methods for image surface-anomaly detection. Pattern Analysis and Applications, 28(2). https://doi.org/10.1007/s10044-025-01477-y

Guo, S., Mou, J., Chen, L., & Chen, P. (2021). An anomaly detection method for AIS trajectory based on kinematic interpolation. Journal of Marine Science and Engineering, 9(6). https://doi.org/10.3390/jmse9060609

Hoerunisa, Y., Alfian, E., Sijabat, S., & Setyawati, A. (2023). Analysis of Factors Influencing Container Shortage in Tanjung Priok Port, Jakarta. In International Journal of Innovative Science and Research Technology (Vol. 8). www.ijisrt.com

Ikhsan, M. R., Pamungkasari, P. D., Purbantoro, B., Sholihati, I. D., Farahdinna, F., Sumantyo, J. T. S., & Heezen, D. M. (2025). Grid-Based Ship Density Analysis and Anomaly Detection for Ship Movements Monitoring at Tanjung Priok Port. International Journal of Advances in Data and Information Systems, 6(1), 107–118. https://doi.org/10.59395/ijadis.v6i1.1367

Iturbe-Araya, J. I., & Rifà-Pous, H. (2025). Enhancing unsupervised anomaly-based cyberattacks detection in smart homes through hyperparameter optimization. International Journal of Information Security, 24(1). https://doi.org/10.1007/s10207-024-00961-6

Leon-López, K., Fabre, S., Laurent Mirambell, F. M., & Tourneret, J.-Y. (2024). A Multiscale Anomaly Detection Framework for AIS Trajectories via Heat Graph Laplacian Diffusion. IEEE. https://doi.org/10.23919/eusipco63174.2024.10715305

Mangé, V., Tourneret, J.-Y., Vincent, F., Mirambell, L., & Vieira, F. M. (2024). Graphical Abstract Anomaly Detection in Ship Trajectories Using Machine Learning and Dynamic Time Warping. https://doi.org/10.1016/j.engappai.2025.111185

Muñoz, A., & Moguerza, J. M. (2004). LNCS 3287 - One-Class Support Vector Machines and Density Estimation: The Precise Relation.

Pandjaitan, M. B., Khusaini, K., Aminuddin, M. F., & Suwarno, P. (2025). Peran Kemaritiman Dalam Memperkuat Perekonomian Indonesia. Jurnal Sains Teknologi Transportasi Maritim, 7(1), 17–27. https://doi.org/10.51578/j.sitektransmar.v7i1.104

Pasillas-Díaz, J. R., & Ratté, S. (2016). An Unsupervised Approach for Combining Scores of Outlier Detection Techniques, Based on Similarity Measures. Electronic Notes in Theoretical Computer Science, 329, 61–77. https://doi.org/10.1016/j.entcs.2016.12.005

Sari Ningsih, P., Pamungkasari, P. D., Purbantoro, B., Awaludin, A., Yulian, D., Sholihati, I. D., … Alfarizi, M. Z. (2026). Web Sosialisasi Deteksi Anomali Kapal Menggunakan Kecerdasan Buatan. Masyarakat Berkarya: Jurnal Pengabdian dan Perubahan Sosial, 3(1), 21–30. https://doi.org/10.62951/karya.v3i1.2972

Siech, A. F., Arifianto, A. Z., Hasin, M. K., Adhitya, R. Y., Munadhif, I., Kurnia, M., Sari, M., Studi, P., Otomasi, T., Teknik, J., Kapal, K., Perkapalan, P., & Surabaya, N. (2025). Deteksi Anomali Jalur Pelayaran Alur Laut Kepulauan Indonesia II (ALKI II) Berbasis Data AIS dengan Mean Fullstack Application. In Jurnal Pustaka Nusantara Multidisplin (Vol. 3, Number 2). https://doi.org/10.59945/jpnm.v3i2.463

Tahir, M., Li, M., Ayoub, N., & Aamir, M. (2019). Efficacy improvement of anomaly detection by using intelligence sharing scheme. Applied Sciences (Switzerland), 9(3). https://doi.org/10.3390/app9030364

Wolsing, K., Roepert, L., Bauer, J., & Wehrle, K. (2022). Anomaly Detection in Maritime AIS Tracks: A Review of Recent Approaches. In Journal of Marine Science and Engineering (Vol. 10, Number 1). MDPI. https://doi.org/10.3390/jmse10010112

Yang, Y., Liu, Y., Li, G., Zhang, Z., & Liu, Y. (2024). Harnessing the Power of Machine Learning for AIS Data-Driven Maritime Research: A Comprehensive Review. Transportation Research Part E: Logistics and Transportation Review, 183. https://doi.org/10.1016/j.tre.2024.103426

Zhang, L., Zhu, Y., Ren, J., Lu, W., & Yao, Y. (2023). A method for detecting abnormal behavior of ships based on multi-dimensional density distance and an abnormal isolation mechanism. Mathematical Biosciences and Engineering, 20(8), 13921–13946. https://doi.org/10.3934/mbe.202362




DOI: https://doi.org/10.59818/jpm.v6i3.2907