Spatio-temporal analysis of traffic incidents and their effect on speed
Intelligent Transportation Systems (ITS) represent a major transition in transportation on many dimensions. Advancements in sensor technologies have enhanced the efficiency of existing transportation and increased the safety of traffic operations. A detailed set of traffic information is part and pa...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Theses and Dissertations |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/68957 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | Intelligent Transportation Systems (ITS) represent a major transition in transportation on many dimensions. Advancements in sensor technologies have enhanced the efficiency of existing transportation and increased the safety of traffic operations. A detailed set of traffic information is part and parcel of modern ITS system in which available data is more reliable, easy to collect and more complete. Traffic incidents have long been recognised as the main contributor of congestion in road way network. Traffic Response Systems for traffic related congestion during peak periods continues to be one of the most important challenges facing road management.In this project we identify incident-components on different highways and try to correlate them with traffic parameters, (e.g., traffic speed) to help improve the traffic response and route planner systems. We integrated these data sets obtained from LTA Singapore (incidents and speed data) and other sources, and evaluated the effects of traffic incidents on average traffic speed on the affected links. We also investigate different incident patterns (spatial and temporal) to investigate the impact of incidents on traffic speed especially in its neighbouring links. The objective of this project is to help avoid traffic congestion and help make route guidance better by building an efficient and robust traffic prediction model. The numerical results show that specific incident types have a considerable effect on traffic speed. These obtained results can be utilised in future research to build the proposed traffic prediction model. |
---|