Klasifikasi Kendaraan Bermotor Berdasarkan Jumlah Gandar Menggunakan Adaptive Minimal Ensemble
DOI:
https://doi.org/10.37859/coscitech.v7i1.11239
Abstract
The increasing volume of motor vehicles requires automated monitoring for the classification of heavy vehicle categories (Category I–V) based on the number of axles using side-view cameras. This process represents a complex fine-grained visual classification challenge due to the similar body shapes of trucks. To address the dilemma between the need for high accuracy and computational efficiency, this study implements an Adaptive Minimal Ensemble (AME) architecture that adaptively combines small-scale models. The model is evaluated using a confusion matrix along with accuracy, precision, recall, and F1-score metrics. The testing results demonstrate that a single EfficientNetV2-S model is only able to achieve a maximum accuracy of 83% and exhibits significant limitations in extracting crucial distinguishing features, leading to misclassification of Category 4 and 5 vehicles. In contrast, the AME architecture, which utilizes the two best-performing EfficientNetV2-S base models, successfully achieves a substantial performance improvement with 95% accuracy, 95.21% precision, 95% recall, and a 94.99% F1-score. In conclusion, the adaptive layer mechanism in AME is proven to be highly effective in compensating for the individual prediction weaknesses of its base models, resulting in a significantly more precise vehicle classification monitoring system.
Downloads
References
Faris Humami, “Analisis Emisi Gas Buang Kendaraan Komersial Berdasarkan Karakteristik Kendaraan Bermotor,” Jan. 2024.
B. P. S. Indonesia, “Jumlah Kendaraan Bermotor Menurut Provinsi dan Jenis Kendaraan (unit), 2023 - Tabel Statistik,” 2023, Badan Pusat Statistik Indonesia. [Online]. Available: https://www.bps.go.id/id/statistics-table/3/VjJ3NGRGa3dkRk5MTlU1bVNFOTVVbmQyVURSTVFUMDkjMw==/jumlah-kendaraan-bermotor-menurut-provinsi-dan-jenis-kendaraan–unit—2023.html
Kementrian Pekerjaan Umum, “Keputusan Menteri Pekerjaan Umum Nomor 370/KPTS/M/2007 tentang Penetapan Gol Jenis Kendaraan Bermotor pada Ruas Jalan Tol yang sudah Beroperasi dan Besarnya Tarif Tol pada Beberapa Ruas Jalan Tol,” Oct. 2021.
Vinsensius Budiman Pantas, Niakku Imanuel Maggang, and Anie Adrianti Tuati, “Analisis Pengaruh Kendaraan Over Dimension Overload (ODOL) Terhadap Perkerasan Pada Ruas Jalan Timor Raya,” Jurnal Teknologi dan Manajemen Industri Terapan, vol. 4, no. I, pp. 181–189, Mar. 2025, doi: 10.55826/jtmit.v4iI.1028.
A. S. Alghamdi, T. Imran, K. T. Mursi, A. Ejaz, M. Kamran, and A. Alamri, “A Vehicle Classification System for Intelligent Transport System using Machine Learning in Constrained Environment,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 7, 2023, doi: 10.14569/IJACSA.2023.0140746.
Ade Irma, Nasron, and Martinus Mujur Rose, “Implementasi Aplikasi Berbasis Teknologi IoT pada Perangkat Tracking dan Kendali Kendaraan Bermotor,” Jurnal CoSciTech (Computer Science and Information Technology), vol. 1, no. 2, pp. 57–64, Oct. 2020, doi: 10.37859/coscitech.v1i2.2191.
J. Barreyro, L. R. Yoshioka, C. L. Marte, C. G. Piccirillo, M. M. D. Santos, and J. F. Justo, “Assessment of Vehicle Category Classification Method Based on Optical Curtains and Convolutional Neural Networks,” IEEE Access, vol. 12, pp. 133532–133544, 2024, doi: 10.1109/ACCESS.2024.3410160.
L. A. Marcomini and A. L. Cunha, “Truck Axle Detection with Convolutional Neural Networks,” Mar. 2023, [Online]. Available: http://arxiv.org/abs/2204.01868
M. E. Prasetyo, M. R. Faza, R. Pratama, S. N. H. Alhabsy, H. Purwanti, and A. P. A. Masa, “Klasifikasi Ragam Kendaraan Menggunakan Metode Convolutional Neural Network (Cnn),” Adopsi Teknologi dan Sistem Informasi (ATASI), vol. 2, no. 2, pp. 142–148, Dec. 2023, doi: 10.30872/atasi.v2i2.1156.
R. A. Syahputra, W. Firmantara, S. F. Rosyad, and F. Muttaqin, “Klasifikasi Citra Diabetic Foot Ulcer Menggunakan ResNet50 dengan Evaluasi Confusion Matrix pada Dataset Validasi,” vol. 4, no. 1, doi: 10.31284/p.semtik.2025-1.8481.
K. U. Haqiqi, F. M. Hana, and H. Aulida, “KLASIFIKASI JENIS GOLONGAN KENDARAAN DI GERBANG TOL MENGGUNAKAN ARSITEKTUR CNN VGG16,” 2024.
A. T. Sasongko and M. Ivan Fanany, “Indonesia Toll Road Vehicle Classification Using Transfer Learning with Pre-trained Resnet Models,” in 2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), IEEE, Dec. 2019, pp. 373–378. doi: 10.1109/ISRITI48646.2019.9034590.
A. R. Priambodo, A. A. Hakim, Chiristian, F. T. Vierino, and H. Maulana, “Klasifikasi Golongan Kendaraan Tol menggunakan CNN Tensorflow,” Jurnal Ilmiah Teknologi Informasi dan Robotika, doi: 10.33005/jifti.v7i1.151.
E. Strubell, A. Ganesh, and A. McCallum, “Energy and Policy Considerations for Deep Learning in NLP,” Jun. 2019.
M. Tan and Q. V Le, “EfficientNetV2: Smaller Models and Faster Training,” 2021. [Online]. Available: https://github.com/google/
A. Bruno et al., “Improving plant disease classification by adaptive minimal ensembling,” Front. Artif. Intell., vol. 5, Sep. 2022, doi: 10.3389/frai.2022.868926.
