A Recurrent Neural Network Approach for Traffic Flow Prediction Using LSTM

  • Pregya Poonia, V.K. Jain

Abstract

Forecasting the flow of vehicles on road is quite a complex procedure and it is affected by various factors, such as traffic patterns, applied areas, data collection, and so on. Improving the precision of traffic flow prediction can lead benefit to the intelligent transport management on traffic regulation and blockage reduction. In recent computational traffic flow forecasting approaches, researchers have to select the traffic features and modeling parameters from the obtained data according to some fundamental assumptions applied in the past literature. In this paper, we have applied RNN-LSTM (Recurrent Neural Network) which is a type of deep learning architecture aiming to improve forecasting accuracy. It is applied to real-world data collected.

Published
2020-01-31
How to Cite
V.K. Jain, P. P. (2020). A Recurrent Neural Network Approach for Traffic Flow Prediction Using LSTM. International Journal of Advanced Science and Technology, 29(3), 539 - 546. Retrieved from http://sersc.org/journals/index.php/IJAST/article/view/3954
Section
Articles