Comparison of CNN Models Using EfficientNetB0, MobileNetV2, and ResNet50 for Traffic Density with Transfer Learning
DOI:
https://doi.org/10.64878/jistics.v1i1.6Keywords:
Convolutional Neural Network, EfficientNetB0, MobileNetV2, ResNet50, Traffic Density Classification, Transfer LearningAbstract
Traffic congestion in urban areas poses a significant and widespread challenge, stemming from the essential role of modern transportation in daily human activities. To address this issue, artificial intelligence (AI), particularly through applying convolutional neural networks (CNN), offers a promising solution for developing automated, accurate, and efficient traffic density classification systems. However, the performance of such systems is critically dependent on the selection of optimal model architecture. This study comprehensively analyzes three leading pre-trained CNN models: EfficientNetB0, MobileNetV2, and ResNet50. Utilizing a transfer learning approach, the models were trained over 20 epochs to classify traffic density into five categories: Empty, Low, Medium, High, and Traffic Jam. The research methodology was based on the public Traffic Density Singapore dataset. To enhance model robustness and address class imbalances, the initial dataset of 4,038 images was expanded to 6,850 images through data augmentation techniques. All images were subsequently resized to a uniform size of 224x224 pixels. The evaluation results conclusively demonstrate that the ResNet50 architecture delivered superior performance, achieving a validation accuracy of approximately 85%. Furthermore, ResNet50 consistently yielded higher precision, recall, and f1-score values across most classes. For comparison, EfficientNetB0 and MobileNetV2 achieved 81% and 79% validation accuracies, respectively. This study concludes that ResNet50 is the optimal architecture for this classification task, and these findings establish a foundation for developing real-world, intelligent traffic monitoring systems.
Downloads
References
[1] S. Dikshit, A. Atiq, M. Shahid, V. Dwivedi, and A. Thusu, "The Use of Artificial Intelligence to Optimize the Routing of Vehicles and Reduce Traffic Congestion in Urban Areas," EAI Endorsed Transactions on Energy Web, vol. 10, Dec. 2023, doi: 10.4108/ew.4613.
[2] N. Darapaneni et al., “Traffic Density Determination Using Advanced Computer Vision,” 2022, pp. 375–386. doi: 10.1007/978-981-19-0011-2_34.
[3] H. Beenish, T. Javid, M. Fahad, Y. Shahzad, and F. Ishaq, “Contemporary Study of Machine Learning Algorithms for Traffic Density Estimation in Intelligent Transportation Systems,” 2023.
[4] L. A. Nugroho, “Dampak Jumlah Kendaraan Besar Terhadap Kemacetan Lalu Lintas di Jalan Tol,” 2023.
[5] M. Akhtar and S. Moridpour, “A Review of Traffic Congestion Prediction Using Artificial Intelligence,” J Adv Transp, vol. 2021, pp. 1–18, Jan. 2021, doi: 10.1155/2021/8878011.
[6] R. C. R. Nampalli, “Leveraging AI in Urban Traffic Management: Addressing Congestion and Traffic Flow with Intelligent Systems,” Journal of Artificial Intelligence and Big Data, vol. 1, no. 1, pp. 86–99, May 2021, doi: 10.31586/jaibd.2021.1151.
[7] W. Wahyuningsih, G. S. Nugraha, and R. Dwiyansaputra, “Classification Of Dental Caries Disease In Tooth Images Using A Comparison Of Efficientnet-B0, Mobilenetv2, Resnet-50, Inceptionv3 Architectures,” Jurnal Teknik Informatika (Jutif), vol. 5, no. 4, pp. 177–185, Jul. 2024, doi: 10.52436/1.jutif.2024.5.4.2187.
[8] D. Mane, R. Bidwe, B. Zope, and N. Ranjan, “Traffic Density Classification for Multiclass Vehicles Using Customized Convolutional Neural Network for Smart City,” in Lecture Notes in Networks and Systems, Springer Science and Business Media Deutschland GmbH, 2022, pp. 1015–1030. doi: 10.1007/978-981-19-2130-8_78.
[9] J. Chung, G. Kim, and K. Sohn, “Transferability of a Convolutional Neural Network (CNN) to Measure Traffic Density,” Electronics (Switzerland), vol. 10, no. 10, May 2021, doi: 10.3390/electronics10101189.
[10] M. Hasan, S. Das, and M. N. T. Akhand, “Estimating Traffic Density on Roads using Convolutional Neural Network with Batch Normalization,” in 2021 5th International Conference on Electrical Engineering and Information and Communication Technology, ICEEICT 2021, Institute of Electrical and Electronics Engineers Inc., 2021. doi: 10.1109/ICEEICT53905.2021.9667860.
[11] D. Hartanto and R. Herawati, “Comparative Analysis of Efficientnet and Resnet Models in The Classification of Skin Cancer,” 2024.
[12] B. A. Wijaya, P. J. Gea, A. D. Gea, A. Sembiring, and C. M. S. Hutagalung, “Satellite Images Classification using MobileNet V-2 Algorithm,” sinkron, vol. 8, no. 4, pp. 2316–2326, Oct. 2023, doi: 10.33395/sinkron.v8i4.12949.
[13] M. Banjaransari and A. Prahara, “Image Classification of Wayang Using Transfer Learning and Fine-Tuning of CNN Models,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 5, no. 4, pp. 632–641, Feb. 2024, doi: 10.12928/biste.v5i4.9977.
[14] Y. Gulzar, “Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique,” Sustainability (Switzerland), vol. 15, no. 3, Feb. 2023, doi: 10.3390/su15031906.
[15] A. Bhandari, “Confusion Matrix in Machine Learning,” Analytics Vidhya. Accessed: Apr. 06, 2025. [Online]. Available: https://www.analyticsvidhya.com/blog/2020/04/confusion-matrix-machine-learning/
[16] T. Wiratama Putra and A. Triayudi, “Analisis Sentimen Pembelajaran Daring menggunakan Metode Naïve Bayes, KNN, dan Decision Tree,” Jurnal Teknologi Informasi dan Komunikasi), vol. 6, no. 1, p. 2022, 2022, doi: 10.35870/jti.
[17] S. Clara, D. Laksmi Prianto, R. Al Habsi, E. Friscila Lumbantobing, and N. Chamidah, Implementasi Seleksi Fitur Pada Algoritma Klasifikasi Machine Learning Untuk Prediksi Penghasilan Pada Adult Income Dataset. 2021.
[18] I. Daqiqil Id, Machine Learning : Teori, Studi Kasus dan Implementasi Menggunakan Python, 1st ed. 2021. doi: 10.5281/zenodo.5113507.
[19] N. Musfirah, “Identifikasi Jenis Serangan Hama Pada Buah Kakao Menggunakan Image Processing,” 2023.
[20] A. Semma, S. Lazrak, Y. Hannad, M. Boukhani, and Y. El Kettani, “Writer Identification: The Effect of Image Resizing on CNN Performance,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLVI-4/W5-2021, pp. 501–507, Dec. 2021, doi: 10.5194/isprs-archives-XLVI-4-W5-2021-501-2021.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Journal of Intelligent Systems Technology and Informatics
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
License:
This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
