Multi-linear regression models for traffic prediction in large-scale networks

• Main Author: Zhao, XinYue
• Other Authors: School of Electrical and Electronic Engineering
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Mathematics and analysis::Simulations
• Online Access: http://hdl.handle.net/10356/61176
• Institution: Nanyang Technological University

Because of the urbanization trend and the development of technology and economy, transportation is becoming an important part for people’s daily life. Congestion is a common scene in most modern cities. Under such circumstance, accurate and efficiency prediction of traffic condition is in great demand and it can have a significant effect on both helping traffic management department and providing necessary guidelines for ordinary travelers. Meanwhile, the technology development also makes it possible to collect large amount of data from the low cost sensors and monitors implemented on the roads. Various methods have been practice in the traffic forecasting study and some algorithms that used in other fields like In this paper we apply 3 multi-linear regression models on the speed data collected from 266 road segments in Singapore, which are Partial Least Square, High-Order Partial Least Square and N-way Partial Least Square model. By generating the prediction result, calculating the error between result and actual data, as well as comparing the difference between the prediction results we can have a better understanding about how can multi-linear regression model being used to solve traffic prediction problems.