Enhancing Traffic Flow Prediction using Real Time Data with deep learning Techniques

Kazi, Nihad (2023) Enhancing Traffic Flow Prediction using Real Time Data with deep learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This study focuses on the implementation and comparative analysis of traffic patterns using deep learning techniques namely LSTM and GRU using two distinct datasets: traffic sensor data and traffic regional data. The integration of real time data is pivotal in research, as it aims to enhance the accuracy of traffic flow predictions. The results delves into implementation of data transformation techniques, exploratory data analysis, training of model with standard hyper parameters, comprehensive evaluation of models using R-squared, Mean Squared Error (MSE), Mean Absolute(MAE) and Root Mean Squared Error (RMSE) evaluation metrics. The output results revealed that both the models fairly performed on real time sensor data, they struggled with historical regional due to its vastness, complexity and lack of granularity. The study highlights the significance of granularity in enhancing predictive capabilities and suggests potential applications for real-time traffic management systems. Future research aims to enhance forecasts by integrating more external factors and creating real-time analysis frameworks that enable quicker reactions to shifting traffic situations. The output results revealed that both the models performed fairly on real time sensor data with best scores for

GRU: R-squared 0.890899, RMSE 0.229130 and MAE 0.168262 and LSTM: R-squared 0.893829, RMSE 0.226033 and MAE 0.163932 Regional data

GRU: R-squared 0.404736, RMSE 0.999625 and MAE 0.653231 and LSTM: R-squared 0.402661, RMSE 1.001367 and MAE 0.676723

Item Type:	Thesis (Masters)
Supervisors:	Name Email Qayum, Abdul UNSPECIFIED
Uncontrolled Keywords:	LSTM; GRU; sensor data; regional data; R-squared; RMSE; MAE
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 Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Motor Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	14 May 2025 11:20
Last Modified:	14 May 2025 11:20
URI:	https://norma.ncirl.ie/id/eprint/7544

Actions (login required)

View Item