Short-Term and Long-Term Traffic Flow Prediction in Dublin Using Deep Learning

Gangadharan, Gayathri (2024) Short-Term and Long-Term Traffic Flow Prediction in Dublin Using Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (856kB) | Preview

Abstract

Efficient traffic control relies on accurate predictions of traffic distribution, particularly in highly interconnected cities like Dublin. This work assesses the effectiveness of Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs) for predicting traffic flow across short-term (hourly) and long-term (daily and monthly) intervals. The models were assessed using Dublin’s traffic flow dataset with metrics such as R2, RMSE, MSE, and MAE. The results revealed that ANN outperformed CNN in short-term (hourly) predictions due to its suitability for structured data. In contrast, CNN demonstrated superior performance in long-term (daily and monthly) predictions by effectively capturing temporal dependencies. However, both the models exhibited limitations in daily predictions. Additionally, regional analysis highlighted the sensitivity of the models to localized traffic dynamics, emphasizing the challenges in accurately simulating specific regional traffic behaviors. This paper explores the strengths and weaknesses of deep learning models for traffic forecasting in Dublin, providing valuable insights into their application for developing intelligent traffic systems. These findings contribute to a deeper understanding of the potential roles of ANN and CNN in enhancing smart traffic solutions for urban environments

Item Type:	Thesis (Masters)
Supervisors:	Name Email Anant, Aaloka UNSPECIFIED
Uncontrolled Keywords:	SCATS; Deep learning methods; Artificial Neural Networks; Convolutional Neural networks; Short-Term and Long-Term traffic forecasting; Traffic flow prediction
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TL Motor vehicles. Aeronautics. Astronautics D History General and Old World > DA Great Britain > Ireland > Dublin
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2025 11:31
Last Modified:	02 Sep 2025 11:31
URI:	https://norma.ncirl.ie/id/eprint/8699

Actions (login required)

View Item