NORMA eResearch @NCI Library

Big Data-driven Performance Improvement of Traffic Flow Prediction and Speed Limit Classification using Deep Learning

Venkatraman, Sankara Subramanian (2020) Big Data-driven Performance Improvement of Traffic Flow Prediction and Speed Limit Classification using Deep Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (3MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (3MB) | Preview


Traffic flow and vehicle speed limit are the common problems faced in day-today life by every country. Improving the performance of traffic flow and speed limit benefits the road users and transportation authorities. In urban traffic network, it is challenging to predict the traffic parameters (flow, speed and occupancy) due to their complex nature. Additionally, various non-traffic parameters such as weather, light and road surface conditions influence traffic parameters. Several studies in the past have taken these parameters with lesser or aggregated data. This research considers the non-traffic parameters and traffic big data of the United Kingdom between the years 2010 and 2018. The significance of using non-traffic parameters along with traffic parameters during peak and non-peak hours is analysed. In the first part of this research, the traffic flow is predicted using different Long Short-Term Memory (LSTM) models, and the second part involves the classification of speed limit using Convolutional Neural Network (CNN) model. Finally, the models are validated using evaluation metrics of training and testing accuracy, RMSE (Root Mean Squared Error) value and confusion matrix. Traffic flow prediction and speed limit classification with non traffic parameters perform better than traffic-only parameters with increased accuracy (1%) and lowered RMSE value (30% (traffic flow) and 33% (speed limit)).

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 21 Jan 2021 11:50
Last Modified: 21 Jan 2021 11:50

Actions (login required)

View Item View Item