Efficient Traffic Flow Prediction with CNN-Based Deep Learning Techniques

DOI

10.2991/978-94-6463-738-0_89How to use a DOI?

Keywords

Smart Roads Networks (SRN); Convolutional Neural Networks (CNN); Long Short-Term Memory (LSTM)

Abstract

Smart Roads Networks (SRNs) that manage roads by intelligently de-congestion streaks and promoting smart urban projects benefit a great deal from receiving accurate and efficient forecasting traffic. CNN is the secret math; it is most useful for expressing space-temporal data. This study proposes a special method for traffic prediction. The distinction from what may have already been done is that CNN models are best used in traffic prediction due to their superior ability to learn and behave with complex sequences- quite contrary to conventional models, which cannot always capture complex spatial relations from traffic information. The road network structure is combined with meteorological and consideration of the volume of previous traffic. By applying different convolutional layers, the model aims at capturing the spatial scantily that exists in the data on traffic, while the temporal evolution of traffic over a time series frames it. The entire test validates the efficacy of the use of a CNN-based approach in traffic aesthetics with the conventional traffic-predictive styles, like ARIMA and Long Short-Term Memory (LSTM), demonstrating higher accuracy and efficiency in computation. In summary, the CNN design is suitable for immediate-time rush-hour management strategies since it scales effectively for large datasets and produces a higher-quality stream of traffic estimations. The study’s findings demonstrate how deep learning methods could greatly enhance predicted traffic abilities and expedite the invention of innovative mobility alternatives for modern cities.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Poonam Bhartiya
AU  - Mukta Bhatele
AU  - Akhilesh A. Waoo
PY  - 2025
DA  - 2025/06/22
TI  - Efficient Traffic Flow Prediction with CNN-Based Deep Learning Techniques
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 1153
EP  - 1173
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_89
DO  - 10.2991/978-94-6463-738-0_89
ID  - Bhartiya2025
ER  -