Optimasi Algoritma Random Forest Untuk Deteksi Jenis Kendaraan Pada Sistem Pemantauan Lalu Lintas
Keywords:
Deteksi Kendaraan, Klasifikasi Kendaraan, Pemantauan Lalu Lintas, Random ForestAbstract
Abstrak. Peningkatan volume lalu lintas di kota-kota besar, khususnya di Indonesia, telah menyebabkan masalah seperti kemacetan, kecelakaan, dan polusi. Salah satu tantangan utama adalah deteksi otomatis dan klasifikasi jenis kendaraan dalam sistem pemantauan lalu lintas. Sistem pemantauan yang efektif tidak hanya memonitor jumlah kendaraan tetapi juga secara akurat mengidentifikasi jenis kendaraan dalam kondisi lalu lintas yang dinamis. Penelitian ini bertujuan untuk mengoptimalkan algoritma Random Forest untuk mendeteksi jenis kendaraan dengan akurasi yang tinggi pada sistem pemantauan lalu lintas berbasis citra. Metode penelitian meliputi pengumpulan data citra kendaraan dari kamera pengawas, pra-pemrosesan citra, ekstraksi fitur, penerapan algoritma Random Forest, dan evaluasi kinerja model dengan menggunakan metrik seperti akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma Random Forest dapat mengklasifikasikan jenis kendaraan dengan akurasi sebesar 92%, dengan F1-score yang baik pada setiap kategori kendaraan, yaitu mobil (0.91), motor (0.94), truk (0.89), dan bus (0.93). Pengujian hyperparameter menunjukkan bahwa jumlah pohon yang lebih banyak dan kedalaman pohon yang lebih besar meningkatkan kinerja model. Namun, tantangan yang berkaitan dengan kondisi cuaca dan kualitas citra tetap menjadi perhatian. Penelitian ini menyimpulkan bahwa algoritma Random Forest memiliki potensi besar untuk diaplikasikan dalam sistem pemantauan lalu lintas untuk meningkatkan efisiensi dan akurasi deteksi kendaraan secara real-time.
References
S. Rajagopal,M. et, al. Ensemble Random Forest-based Gradient Optimization based Energy Efficient Video Processing System for Smart Traffic Surveillance System. DOI : 10.1080/03772063.2024.2350927
Grzegorz Wieczorek, et, al. Vehicle Detection and Recognition Approach in Multi-Scale Traffic Monitoring System via Graph-Based Data Optimization. DOI : 10.3390/s23031731
Revanth Dugalam and Guru Prakash. Development of a random forest based algorithm for road health monitoring. DOI : 10.1016/j.eswa.2024.123940
Chunying Zhang, et, al. Three-Way Selection Random Forest Optimization Model for Anomaly Traffic Detection. DOI : 10.3390/electronics12081788
Presitha Aarthi M, et, al. Cloud-Based Road Safety for Real-Time Vehicle Rash Driving Alerts with Random Forest Algorithm. DOI : 10.1109/INOCON60754.2024.10511316
Miaomiao Yan and Yindong Shen. Traffic Accident Severity Prediction Based on Random Forest. DOI : 10.3390/su14031729
Hamed Khajavi and Amir Rastgoo. Predicting the carbon dioxide emission caused by road transport using a Random Forest (RF) model combined by Meta-Heuristic Algorithms. DOI : 10.1016/j.scs.2023.104503
Qiang Shang, et, al. A Hybrid Method for Traffic Incident Duration Prediction Using BOA-Optimized Random Forest Combined with Neighborhood Components Analysis. DOI : 10.1155/2019/4202735
Myounggyu Won. Intelligent Traffic Monitoring Systems for Vehicle Classification: A Survey. DOI : 10.1109/ACCESS.2020.2987634
Sunkara Teena Mrudula, et, al. Internet of things and optimized knn based intelligent transportation system for traffic flow prediction in smart cities. DOI : 10.1016/j.measen.2024.101297
Yetay Berhanu, et, al. Examining Car Accident Prediction Techniques and Road Traffic Congestion: A Comparative Analysis of Road Safety and Prevention of World Challenges in Low-Income and High-Income Countries. DOI : 10.1155/2023/6643412
Benjamin Sliwa, et, al. The Channel as a Traffic Sensor: Vehicle Detection and Classification Based on Radio Fingerprinting. DOI: 10.1109/JIOT.2020.2983207
Amit Kumar Balyan, et, al. A Hybrid Intrusion Detection Model Using EGA-PSO and Improved Random Forest Method. DOI : 10.3390/s22165986
Sangmin Lee, et, al. Intelligent traffic control for autonomous vehicle systems based on machine learning. DOI : 10.1016/j.eswa.2019.113074
Tuo Mao, et, al. Boosted Genetic Algorithm Using Machine Learning for Traffic Control Optimization. DOI: 10.1109/TITS.2021.3066958
Ibrahim Hayatu Hassan, et, al. An improved binary manta ray foraging optimization algorithm based feature selection and random forest classifier for network intrusion detection. DOI : 10.1016/j.iswa.2022.200114
Jing Gan, et, al. An Alternative Method for Traffic Accident Severity Prediction: Using Deep Forests Algorithm.DOI : 10.1155/2020/1257627
Ali Raza, et, al. Multiple Pedestrian Detection and Tracking in Night Vision Surveillance Systems. DOI: 10.32604/cmc.2023.029719
Nour El Islem Karabadji, et, al.Accuracy and diversity-aware multi-objective approach for random forest construction. DOI :10.1016/j.eswa.2023.120138
Mince Li, et, al. Sizing Optimization and Energy Management Strategy for Hybrid Energy Storage System Using Multiobjective Optimization and Random Forests. DOI : 10.1109/TPEL.2021.3070393
Preeti Rani and Rohit Sharma. Intelligent transportation system for internet of vehicles based vehicular networks for smart cities. DOI : 10.1016/j.compeleceng.2022.108543
K. Balasubadra, et, al. Real-time Glass Recycling Quality Assurance and Contamination Reduction with IoT and Random Forest algorithm. DOI : 10.1109/ICICT60155.2024.10544632
Oche Alexander Egaji, et, al. Real-time machine learning-based approach for pothole detection. DOI : 10.1016/j.eswa.2021.115562
Muammer Türkoğlu , et, al. Recognition of DDoS attacks on SD-VANET based on combination of hyperparameter optimization and feature selection. DOI : 10.1016/j.eswa.2022.117500
Vittorio Astarita, et, al. Developing new hybrid grey wolf optimization-based artificial neural network for predicting road crash severity. DOI : 10.1016/j.treng.2023.100164
RVS Praveen, et, al. Autonomous Vehicle Navigation Systems: Machine Learning for Real-Time Traffic Prediction. DOI : 10.1109/ICCCIT62592.2025.10927797
Amel Ali Alhussan, et, al. Pothole and Plain Road Classification Using Adaptive Mutation Dipper Throated Optimization and Transfer Learning for Self Driving Cars. DOI : 10.1109/ACCESS.2022.3196660
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
