Supplementary Files
Keywords
LSTM
GRU
Traffic density prediction
Historical visual image
How to Cite
Abstract
The problem of traffic congestion in urban areas requires adaptive and data-based predictive solutions. This study aims to develop vehicle density detection and prediction patterns based on historical visual data by integrating YOLOv5 object detection algorithms and sequential neural network models, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The study also compared the effectiveness of LSTM and GRU in capturing vehicle movement patterns over time. LSTM can be implemented on long-term prediction accuracy by preserving more complex historical contexts, while GRU can be implemented for better training efficiency and processing time due to its simpler architecture. The dataset consists of 254 videos and 13,435 frames with an average VPS of 10.0. The GRU model obtained an MSE value of 5.81, lower than LSTM 6.05, indicating that the mean squared difference between the prediction and the actual value was smaller in the GRU. The RMSE value in the GRU is 2.41, also lower than the LSTM 2.46. The difference of about 0.05 points, although it seems small, still shows consistency that the GRU prediction error is lower. In MAE, the GRU has a value of 1.84, lower than the LSTM 1.89, which means that the mean absolute difference between the prediction and the actual value is smaller in the GRU. This research not only contributes to intelligent transportation systems but also opens up opportunities to develop traffic monitoring systems that are responsive to vehicle dimensions and traffic environment dynamics in real-time.
References
Abdullah, S. M., Periyasamy, M., Kamaludeen, N. A., Towfek, S. K., Marappan, R., Kidambi Raju, S., Alharbi, A. H., & Khafaga, D. S. (2023). Optimizing Traffic Flow in Smart Cities: Soft GRU-Based Recurrent Neural Networks for Enhanced Congestion Prediction Using Deep Learning. Sustainability. 15(7). 5949. https://doi.org/10.3390/SU15075949
Abdushkour, M., Khadidos, H.A., Alshareef, A.O., Alyoubi, A.M., Khadidos, K.H., Mustafa, A., Rienow, A., Ragab, M., Abdushkour, H. A., Khadidos, A. O., Alshareef, A. M., Alyoubi, K. H., & Khadidos, A. O. (2023). Improved Deep Learning-Based Vehicle Detection for Urban Applications Using Remote Sensing Imagery. Remote Sensing. 15(19). 4747. https://doi.org/10.3390/RS15194747
Akhmedov, F., Khujamatov, H., Abdullaev, M., & Jeon, H.S. (2025). Joint Driver State Classification Approach: Face Classification Model Development and Facial Feature Analysis Improvement. Sensors. 25(5). 1472. https://doi.org/10.3390/S25051472
Alahi, M.E.E., Sukkuea, A., Tina, F.W., Nag, A., Kurdthongmee, W., Suwannarat, K., & Mukhopadhyay, S.C. (2023). Integration of IoT-Enabled Technologies and Artificial Intelligence (AI) for Smart City Scenario: Recent Advancements and Future Trends. Sensors. 23(11). 5206. https://doi.org/10.3390/S23115206
Alsaade, F.W., & Hmoud Al-Adhaileh, M. (2021). Cellular Traffic Prediction Based on an Intelligent Model. Mobile Information Systems. 1, 6050627. https://doi.org/10.1155/2021/6050627
Arora, S., Mittal, R., Arora, D., & Shrivastava, A.K. (2024). A Robust Approach for Licence Plate Detection Using Deep Learning. Inteligencia Artificial: Revista Iberoamericana de Inteligencia Artificial. 27(73). 129. https://doi.org/10.4114/INTARTIF.VOL27ISS73PP129-141
Ballesteros, J. R., Sanchez-Torres, G., & Branch-Bedoya, J. W. (2022). HAGDAVS: Height-Augmented Geo-Located Dataset for Detection and Semantic Segmentation of Vehicles in Drone Aerial Orthomosaics. Data. 7(4). 50. https://doi.org/10.3390/DATA7040050
Beltran, J., Madridano, Á., De Miguel, M.Á., Ervin, L., Eastepp, M., Mcvicker, M., & Ricks, K. (2025). Evaluation of Semantic Segmentation Performance for a Multimodal Roadside Vehicle Detection System on the Edge. Sensors. 25(2), 370. https://doi.org/10.3390/S25020370
Bi, J., Zhang, X., Yuan, H., Zhang, J., & Zhou, M. C. (2022). A hybrid prediction method for realistic network traffic with temporal convolutional network and LSTM. IEEE Transactions on Automation Science and Engineering. 19(3). 1869–1879. https://doi.org/10.1109/TASE.2021.3077537
Bittencourt, J.C.N., Costa, D.G., Portugal, P., & Vasques, F. (2024). A Survey on Adaptive Smart Urban Systems. IEEE Access, 12, 102826–102850. https://doi.org/10.1109/ACCESS.2024.3433381
Butploy, N., Kanarkard, W., Intapan, P.M., & Sanpool, O. (2023). An Approach for Egg Parasite Classification Based on Ensemble Deep Learning. Journal of Advanced Computational Intelligence and Intelligent Informatics. 27(6). 1113–1121. https://doi.org/10.20965/JACIII.2023.P1113
Choe, D.E., Kim, H.C., & Kim, M.H. (2021). Sequence-based modeling of deep learning with LSTM and GRU networks for structural damage detection of floating offshore wind turbine blades. Renewable Energy. 174, 218–235. https://doi.org/10.1016/J.RENENE.2021.04.025
Dong, X., Yan, S., & Duan, C. (2022). A lightweight vehicles detection network model based on YOLOv5. Engineering Applications of Artificial Intelligence. 113, 104914. https://doi.org/10.1016/J.ENGAPPAI.2022.104914
Esmaeil Abbasi, A., Mangini, A. M., & Fanti, M. P. (2024). Object and Pedestrian Detection on Road in Foggy Weather Conditions by Hyperparameterized YOLOv8 Model. Electronics. 13(18), 3661. https://doi.org/10.3390/ELECTRONICS13183661
Fatima, Z., Hassan Tanveer, M., Mariam, H., Voicu, R.C., Rehman, T., & Riaz, R. (2024). Performance comparison of object detection models for road sign detection under different conditions. International Journal of Advanced Computer Science & Applications. 15(12), 996. https://doi.org/10.14569/IJACSA.2024.0151299
Izzulhaq, M.A., Tjatur Widodo, R., & Oktavianto, H. (2024). A comparative study of GRU and LSTM time-series forecasting for precise river dam hydrodynamic prediction. International Electronics Symposium: Shaping the Future: Society 5.0 and Beyond, IES 2024 - Proceeding, 473–478. https://doi.org/10.1109/IES63037.2024.10665796
Jiang, S., Feng, Y., Zhang, W., Liao, X., Dai, X., Onasanya, B.O.A., Jiang, S., Feng, Y., Zhang, W., Liao, X., Dai, X., & Onasanya, B.O. (2024). A New Multi-Branch Convolutional Neural Network and Feature Map Extraction Method for Traffic Congestion Detection. Sensors. (13). 4272. https://doi.org/10.3390/S24134272
Li, Y., Yu, X., & Koudas, N. (2021). Data Acquisition for improving machine learning models. Proceedings of the VLDB Endowment. 14(10). 1832–1844. https://doi.org/10.14778/3467861.3467872
Liu, B., Ma, Y., Zhang, J., Kuang, Y., Bian, J., & Jiang, X. (2024). Unveiling urban traffic accessibility patterns and phase diagrams of traffic direction through real-time navigation data in Beijing. Information Processing & Management. 61(3). 103660. https://doi.org/10.1016/J.IPM.2024.103660
LiYifan, YuXiaohui, & KoudasNick. (2024). Data Acquisition for Improving Model Confidence. Proceedings of the ACM on Management of Data. 2(3). 1–25. https://doi.org/10.1145/3654934
Lu, E.H., Gozdzikiewicz, C?;, Chang, M.?;, Ciou, K.H.?;, Lu, E.H.C., Gozdzikiewicz, M., Chang, K.H., & Ciou, J.M. (2022). A Hierarchical Approach for Traffic Sign Recognition Based on Shape Detection and Image Classification. Sensors. 22(13), 4768. https://doi.org/10.3390/S22134768
Lv, C., Mittal, U., Madaan, V., & Agrawal, P. (2024). Vehicle detection and classification using an ensemble of EfficientDet and YOLOv8. PeerJ Computer Science. 10, e2233. https://doi.org/10.7717/PEERJ-CS.2233
Nasr Azadani, M., & Boukerche, A. (2022). A novel multimodal vehicle path prediction method based on temporal convolutional networks. IEEE Transactions on Intelligent Transportation Systems. 23(12). 25384–25395. https://doi.org/10.1109/TITS.2022.3151263
Nespoli, P., Chung, K.L., Samo, M., Mosima Mafeni Mase, J., & Figueredo, G. (2023). Deep learning with attention mechanisms for road weather detection. Sensors. 23(2). 798. https://doi.org/10.3390/S23020798
Nishat, A. (2022). The role of IoT in building smarter cities and sustainable infrastructure. International Journal of Digital Innovation. 3(1). https://researchworkx.com/index.php/ijdi/article/view/56
Peng, B., Zhang, H., Yang, N., & Xie, J. (2022). Vehicle recognition from unmanned aerial vehicle videos based on fusion of target pre-detection and deep learning. Sustainability. 14(13), 7912. https://doi.org/10.3390/SU14137912
Shi, H., & Zhao, D. (2023). License plate recognition system based on improved YOLOv5 and GRU. IEEE Access. 11, 10429–10439. https://doi.org/10.1109/ACCESS.2023.3240439
Shiri, F. M., Perumal, T., Mustapha, N., & Mohamed, R. (2025). A Comprehensive overview and comparative analysis on deep learning models: CNN, RNN, LSTM, GRU. Journal on Artificial Intelligence. 6(1). 301–360. https://doi.org/10.32604/jai.2024.054314
Tahir, H., Jung, E.S., Tahir, H., & Jung, E.S. (2023). Comparative study on distributed lightweight deep learning models for road pothole detection. Sensors. 23(9). 4347. https://doi.org/10.3390/S23094347
Tsalikidis, N., Mystakidis, A., Koukaras, P., Ivaškevi?ius, M., Mork?nait?, L., Ioannidis, D., Fokaides, P.A., Tjortjis, C., & Tzovaras, D. (2024). Urban traffic congestion prediction: a multi-step approach utilizing sensor data and weather information. Smart Cities. 7(1). 233–253. https://doi.org/10.3390/SMARTCITIES7010010
Vignesh, U., & Moolchandani, T. (2024). Revolutionizing autonomous parking: GNN-powered slot detection for enhanced efficiency. Interdisciplinary Journal of Information, Knowledge, and Management. 19. https://doi.org/10.28945/5334
Yang, P., Yu, D., & Yang, G. (2023). Object detection in aerial remote sensing images using bidirectional enhancement FPN and attention module with data augmentation. Multimedia Tools and Applications. 83(13). 38635–38656. https://doi.org/10.1007/S11042-023-16973-8
Yang, Z., Zhao, C., Maeda, H., & Sekimoto, Y. (2022). Development of a large-scale roadside facility detection model based on the mapillary dataset. Sensors.22(24). 9992. https://doi.org/10.3390/S22249992
Zafar, N., Haq, I. U., Chughtai, J. U. R., & Shafiq, O. (2022). Applying hybrid LSTM-GRU model based on heterogeneous data sources for traffic speed prediction in urban areas. Sensors. 22(9). 3348. https://doi.org/10.3390/S22093348
Zarzycki, K., ?awry´nczuk, M., ?awry´nczuk, ?., & Lenci, S. (2021). LSTM and GRU neural networks as models of dynamical processes used in predictive control: a comparison of models developed for two chemical reactors. Sensors. 21(16). 5625. https://doi.org/10.3390/S21165625
Zhang, Y., Guo, Z., Wu, J., Tian, Y., Tang, H., & Guo, X. (2022). Real-time vehicle detection based on improved YOLO V5. Sustainability. 14(19). 12274. https://doi.org/10.3390/SU141912274
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2026 Array