NORMA eResearch @NCI Library

Comparison of machine learning in Intelligence Traffic System

Yan, Hongyi (2021) Comparison of machine learning in Intelligence Traffic System. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


After the previous literature survey, it is found that short-term traffic flow prediction is very important in Intelligent Traffic System(ITS). In the introduction and literature review of this paper, the research direction and value will be determined. High precision prediction results play a positive role in traffic data transmission and congestion intelligent regulation. In the introduction part, the structure and development of ITS will be described in detail. In the data exploration stage, the basic analysis of the data set will be carried out. At this part, the actual analysis will be carried out in combination with the reality and research value, visual analyses is also included. In addition, ARIMA and LSTM are used to predict time series. The seasonal concept ARIMA and ordinary ARIMA are introduced to compare the results to prove whether these is seasonality in the traffic data. In order to compare the prediction accuracy with the traditional machine learning algorithm, the more promising deep learning algorithm is also implemented. Finally, the results of this study are summarized, and the future research direction is discussed to improve the traffic flow prediction accuracy.

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: Clara Chan
Date Deposited: 15 Dec 2021 14:11
Last Modified: 15 Dec 2021 14:11

Actions (login required)

View Item View Item