Research on Urban Traffic Flow Prediction Algorithm Based on Neural Network

View at publisher Summarise with VIRAT
Authors: Zhaoning Wang, Zhenyin Zhang
Cited by: 0
References: 2

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

With the acceleration of urbanization, the problem of traffic congestion is becoming increasingly serious, and accurate traffic flow prediction has become a core link in intelligent transportation systems. This paper aims at the limitations of traditional single models in capturing the nonlinearity, temporality and spatial correlation of traffic data, and proposes a hybrid neural network model - CNN-LSTM that integrates the advantages of long short-term memory networks and convolutional neural networks. LSTM excels at handling long-term series dependencies and can effectively model the temporal dynamic changes of traffic flow. CNN has a powerful ability to extract local features and can mine the spatial correlations between adjacent road sections in the traffic network. This paper combines the two to construct a hierarchical prediction architecture: Firstly, CNN is used to extract spatial features and reduce dimensions of multi-source traffic data (such as historical traffic flow, time information, and weather conditions), and then the extracted feature sequence is input into the LSTM network for time series modeling and future traffic flow prediction. The experiment was verified based on a real traffic dataset of a certain city. The results show that the proposed CNN-LSTM model outperforms the models using either LSTM or CNN alone in terms of root mean square error and mean absolute error, significantly improving the prediction accuracy and robustness, and providing more reliable technical support for urban traffic management and guidance.

Fields of Study & Subjects

Traffic Prediction and Management Techniques Hydrological Forecasting Using AI Traffic control and management

Publication details

Journal / source
IEEE International Conference on Power, Electronics and Green Energy (ICPEGE)
Pages
748–753
Publication date
28 January 2026
Language
EN