Traffic Prediction Using Gated Recurrent Unit Neural Networks

Traffic Prediction Using Gated Recurrent Unit Neural Networks

Authors

  • Paulin Paul ktu
  • Meenu Philip

DOI:

https://doi.org/10.5281/zenodo.6179023

Keywords:

LSTM, GRU, RNN, traffic flow prediction

Abstract

In an intelligent transportation system, traffic
prediction is vital. Accurate traffic forecasting can help with
route selection, vehicle dispatching, and traffic congestion
reduction. Due to the complex and dynamic spatio-temporal
relationships between different parts in the road network, this
problem is difficult to solve. Recently, a large amount of
research work has been committed to this area, particularly the
machine learning method, which has substantially improved
traffic forecast abilities. Despite the fact that the infrastructure
is outdated and can only support a small population, there is an
influx of residents looking for work and opportunity. Fuel
combustion is enhanced as a result of traffic congestion. In this
project, i will be able to be exploring the dataset of
4 junctions and built a model to predict traffic on an
equivalent . This could potentially help in solving the traffic
jam problem by providing a far better understanding of
traffic patterns which will further help in building an
infrastructure to eliminate the matter

Published

2023-02-23

How to Cite

Paulin Paul, & Meenu Philip. (2023). Traffic Prediction Using Gated Recurrent Unit Neural Networks. National Conference on Emerging Computer Applications, 4(1). https://doi.org/10.5281/zenodo.6179023
Loading...