Accident prediction model at un-signalized intersections using multiple regression method
Nowadays, accident increased relatively from year to year although many programs have been carried out by the authority in order to reduce the number of accident. In Johor areas, seventeen accident hotspots have been identified in the state. The road accident increase proportionate to growth i...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English English English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/2868/1/24p%20WAN%20NADIAH%20WAN%20MANAN.pdf http://eprints.uthm.edu.my/2868/2/WAN%20NADIAH%20WAN%20MANAN%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/2868/3/WAN%20NADIAH%20WAN%20MANAN%20WATERMARK.pdf |
| Summary: | Nowadays, accident increased relatively from year to year although many programs
have been carried out by the authority in order to reduce the number of accident. In
Johor areas, seventeen accident hotspots have been identified in the state. The road
accident increase proportionate to growth in population, economic in development,
industrialization and motorization that encountered by the country. The roadway
geometric and traffic condition are among important factors in causes to traffic
accidents. Field work is carried out to collect data such as traffic volume, mean speed
of vehicles, lane width, shoulder width, lane used, number of intersection and also
number legs intersection at the selected locations. Metrocount and odometer were used
for this purpose. By considering the factors that contribute to the accident, this study
was carried out to develop the accident prediction model using Multiple Regression
approach. Accident prediction models are invaluable tools that have many applications
in road safety analysis. In accident analysis, statistical models have been used in
highway and traffic safety studies. From the results shows that accident point weigtage
can be explained by increase of traffic volume and vehicle speed in Federal Route 001
and Federal Route 024 are the contributors to traffic accidents. Meanwhile, an
increment of lane width and shoulder width will reduce the weighting point rates
Finally, the Accident Prediction Model developed in this study not only can be used to
reduce the number of accidents in the future but also for intersection treatment or
upgrading. Using the model, appropriate design parameters of un-signalized
intersection could be specified. |
|---|