High-performance traffic volume prediction: An evaluation of RNN, GRU, and CNN for accuracy and computational trade-offs

Open Access

Issue		BIO Web Conf. Volume 148, 2024 International Conference of Biological, Environment, Agriculture, and Food (ICoBEAF 2024)


Article Number		02034
Number of page(s)		15
Section		Environment
DOI		https://doi.org/10.1051/bioconf/202414802034
Published online		09 January 2025

B. Medina-Salgado, E. Sánchez-DelaCruz, P. Pozos-Parra, and J. E. Sierra, Urban traffic flow prediction techniques: A review, Sustain. Comput. Informatics Syst. 35, 100739 (2022). https://doi.org/10.1016/j.suscom.2022.100739 [CrossRef] [Google Scholar]
K. Nellore and G. Hancke, A Survey on Urban Traffic Management System Using Wireless Sensor Networks, Sensors 16, 157 (2016). https://doi.org/10.3390/s16020157 [CrossRef] [PubMed] [Google Scholar]
A. Boukerche and J. Wang, Machine Learning-based traffic prediction models for Intelligent Transportation Systems, Comput. Networks 181, 107530 (2020). https://doi.org/10.1016/j.comnet.2020.107530 [CrossRef] [Google Scholar]
A. Khan, M. M. Fouda, D.-T. Do, A. Almaleh, and A. U. Rahman, Short-Term Traffic Prediction Using Deep Learning Long Short-Term Memory: Taxonomy, Applications, Challenges, and Future Trends, IEEE Access 11, 94371 (2023). https://doi.org/10.1109/ACCESS.2023.3309601 [Google Scholar]
Y. Mao, A. Pranolo, A. P. Wibawa, A. B. Putra Utama, F. A. Dwiyanto, and S. Saifullah, Selection of Precise Long Short Term Memory (LSTM) Hyperparameters based on Particle Swarm Optimization, in 2022 Int. Conf. Appl. Artif. Intell. Comput. (IEEE, 2022), pp. 1114–1121. https://doi.org/10.1109/ICAAIC53929.2022.9792708 [Google Scholar]
I. D. Mienye, T. G. Swart, and G. Obaido, Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications, Information 15, 517 (2024). https://doi.org/10.3390/info15090517 [Google Scholar]
E. Elgohary, M. Galal, M. Aref, and M. Gharib, Long Short-Term Memory and Gated Recurrent Unit for Automated Deep Learning Prediction, IJCI. Int. J. Comput. Inf. 0 (2024). https://doi.org/10.21608/ijci.2024.235027.1119 [Google Scholar]
K. Cao, T. Zhang, and J. Huang, Advanced hybrid LSTM-transformer architecture for real-time multi-task prediction in engineering systems, Sci. Rep. 14, 4890 (2024). https://doi.org/10.1038/s41598-024-55483-x [CrossRef] [Google Scholar]
D. Salman, C. Direkoglu, M. Kusaf, and M. Fahrioglu, Hybrid deep learning models for time series forecasting of solar power, Neural Comput. Appl. 36, 9095 (2024). https://doi.org/10.1007/s00521-024-09558-5 [CrossRef] [Google Scholar]
Y. He, P. Huang, W. Hong, Q. Luo, L. Li, and K.-L. Tsui, In-Depth Insights into the Application of Recurrent Neural Networks (RNNs) in Traffic Prediction: A Comprehensive Review, Algorithms 17, 398 (2024). https://doi.org/10.3390/a17090398 [CrossRef] [Google Scholar]
K. Ibrahim Mohammad Ata, M. Khair Hassan, A. Ghany Ismaeel, S. Abdul Rahman Al-Haddad, T. Alquthami, and S. Alani, A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow prediction, Ain Shams Eng. J. 103045 (2024). https://doi.org/10.1016/j.asej.2024.103045 [Google Scholar]
H. Hewamalage, C. Bergmeir, and K. Bandara, Recurrent Neural Networks for Time Series Forecasting: Current status and future directions, Int. J. Forecast. 37, 388 (2021). https://doi.org/10.1016/j.ijforecast.2020.06.008 [CrossRef] [Google Scholar]
H. Abbasimehr and R. Paki, Improving time series forecasting using LSTM and attention models, J. Ambient Intell. Humaniz. Comput. 13, 673 (2022). https://doi.org/10.1007/s12652-020-02761-x [CrossRef] [Google Scholar]
N. Ranjan, S. Bhandari, H. P. Zhao, H. Kim, and P. Khan, City-Wide Traffic Congestion Prediction Based on CNN, LSTM and Transpose CNN, IEEE Access 8, 81606 (2020). https://doi.org/10.1109/ACCESS.2020.2991462 [CrossRef] [Google Scholar]
M. Dwarampudi and N. V. S. Reddy, Effects of padding on LSTMs and CNNs, (2019) [Google Scholar]
D. Munandar, B. N. Ruchjana, A. S. Abdullah, and H. F. Pardede, Literature Review on Integrating Generalized Space-Time Autoregressive Integrated Moving Average (GSTARIMA) and Deep Neural Networks in Machine Learning for Climate Forecasting, Mathematics 11, 2975 (2023). https://doi.org/10.3390/math11132975 [CrossRef] [Google Scholar]
F. Kaytez, A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption, Energy 197, 117200 (2020). https://doi.org/10.1016/j.energy.2020.117200 [CrossRef] [Google Scholar]
J. Wang, Vehicular Traffic Flow Prediction Model Using Machine Learning-Based Model, These (2021). https://doi.org/10.20381/ruor-26510 [Google Scholar]
A. Boukerche, Y. Tao, and P. Sun, Artificial intelligence-based vehicular traffic flow prediction methods for supporting intelligent transportation systems, Comput. Networks 182, 107484 (2020). https://doi.org/10.1016/j.comnet.2020.107484 [CrossRef] [Google Scholar]
B. Lim and S. Zohren, Time-series forecasting with deep learning: a survey, Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 379, 20200209 (2021). https://doi.org/10.1098/rsta.2020.0209 [CrossRef] [PubMed] [Google Scholar]
A. Sherstinsky, Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network, Phys. D Nonlinear Phenom. 404, 132306 (2020). https://doi.org/10.1016/j.physd.2019.132306 [NASA ADS] [CrossRef] [Google Scholar]
C. M. Nawej, P. A. Owolawi, and T. Walingo, Toward a Realistic Comparative Analysis of Recurrent Neural Network’s Methods via Long-Term Memory Approaches, Yang, XS., Sherratt, R.S., Dey, N., Joshi, A. Proc. Ninth Int. Congr. Inf. Commun. Technol. ICICT 2024 2024. Lect. Notes Networks Syst. 1054, 245 (2025). https://doi.org/10.1007/978-981-97-5035-1_19 [Google Scholar]
A. H. Ribeiro, K. Tiels, L. A. Aguirre, and T. Schön, Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness, in Proc. Twenty Third Int. Conf. Artif. Intell. Stat., edited by S. Chiappa and R. Calandra (PMLR, 2020), pp. 2370–2380 [Google Scholar]
P. B. Weerakody, K. W. Wong, G. Wang, and W. Ela, A review of irregular time series data handling with gated recurrent neural networks, Neurocomputing 441, 161 (2021). https://doi.org/https://doi.org/10.1016/j.neucom.2021.02.046 [CrossRef] [Google Scholar]
G. Van Houdt, C. Mosquera, and G. Nápoles, A review on the long short-term memory model, Artif. Intell. Rev. 53, 5929 (2020). https://doi.org/10.1007/s10462-020-09838-1 [CrossRef] [Google Scholar]
S. Zhang, L. Yao, A. Sun, and Y. Tay, Deep Learning Based Recommender System, ACM Comput. Surv. 52, 1 (2020). https://doi.org/10.1145/3285029 [Google Scholar]
H. H. Goh, B. He, H. Liu, D. Zhang, W. Dai, T. A. Kurniawan, and K. C. Goh, Multi-Convolution Feature Extraction and Recurrent Neural Network Dependent Model for Short-Term Load Forecasting, IEEE Access 9, 118528 (2021). https://doi.org/10.1109/ACCESS.2021.3107954 [CrossRef] [Google Scholar]
L. Chen, H. Yan, J. Yan, J. Wang, T. Tao, K. Xin, S. Li, Z. Pu, and J. Qiu, Short-term water demand forecast based on automatic feature extraction by one-dimensional convolution, J. Hydrol. 606, 127440 (2022). https://doi.org/10.1016/j.jhydrol.2022.127440 [CrossRef] [Google Scholar]
H. Jayadianti, B. A. Arianti, N. H. Cahyana, S. Saifullah, and R. Dreżewski, Improving sentiment analysis on PeduliLindungi comments: a comparative study with CNN-Word2Vec and integrated negation handling, Sci. Inf. Technol. Lett. 4, 75 (2023). https://doi.org/10.31763/sitech.v4i2.1184 [Google Scholar]
R. Munif and A. Prahara, Betta fish classification using transfer learning and fine-tuning of CNN models, Sci. Inf. Technol. Lett. 5, 16 (2024). https://doi.org/10.31763/sitech.v5i1.1378 [Google Scholar]
A. Shewalkar, D. Nyavanandi, and S. A. Ludwig, Performance Evaluation of Deep Neural Networks Applied to Speech Recognition: RNN, LSTM and GRU, J. Artif. Intell. Soft Comput. Res. 9, 235 (2019). https://doi.org/10.2478/jaiscr-2019-0006 [Google Scholar]
I. Ebtehaj and H. Bonakdari, CNN vs. LSTM: A Comparative Study of Hourly Precipitation Intensity Prediction as a Key Factor in Flood Forecasting Frameworks, Atmosphere (Basel). 15, 1082 (2024). https://doi.org/10.3390/atmos15091082 [CrossRef] [Google Scholar]
F. M. Shiri, T. Perumal, N. Mustapha, and R. Mohamed, A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU, (2023) [Google Scholar]
J. Hogue, Metro Interstate Traffic Volume, (2019) [Google Scholar]
M. Shantal, Z. Othman, and A. A. Bakar, A Novel Approach for Data Feature Weighting Using Correlation Coefficients and Min–Max Normalization, Symmetry (Basel). 15, 2185 (2023). https://doi.org/10.3390/sym15122185 [CrossRef] [Google Scholar]
L. B. V. de Amorim, G. D. C. Cavalcanti, and R. M. O. Cruz, The choice of scaling technique matters for classification performance, Appl. Soft Comput. 133, 109924 (2023). https://doi.org/10.1016/j.asoc.2022.109924 [CrossRef] [Google Scholar]
C. Xu, P. Zhao, Y. Liu, J. Xu, V. S. S. S. Sheng, Z. Cui, X. Zhou, and H. Xiong, Recurrent Convolutional Neural Network for Sequential Recommendation, in World Wide Web Conf. (ACM, New York, NY, USA, 2019), pp. 3398–3404. https://doi.org/10.1145/3308558.3313408 [CrossRef] [Google Scholar]
C.-L. Liu, W.-H. Hsaio, and Y.-C. Tu, Time Series Classification With Multivariate Convolutional Neural Network, IEEE Trans. Ind. Electron. 66, 4788 (2019). https://doi.org/10.1109/TIE.2018.2864702 [CrossRef] [Google Scholar]
K. Fauvel, T. Lin, V. Masson, É. Fromont, and A. Termier, XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification, Mathematics 9, 3137 (2021). https://doi.org/10.3390/math9233137 [CrossRef] [Google Scholar]
D. Chicco, M. J. Warrens, and G. Jurman, The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation, PeerJ Comput. Sci. 7, e623 (2021). https://doi.org/10.7717/peerj-cs.623 [Google Scholar]

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.