TRAP@NCI

Investigating Human Factors in Predictive Accident Models

Killeen, Darren (2014) Investigating Human Factors in Predictive Accident Models. Diploma thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Diploma)
Download (3MB) | Preview

Abstract

Predictive accident models which are used to model and predict the number of accidents that will occur at specific junctions or segments of roads have been of interest for a number of years. While previous models have focused on accounting for variation using measures of exposure related to traffic flow or road length, the current study attempted to investigate human factors such as age and gender. The data was collected from the STATS19 database for accidents in the UK between 2000 and 2012. The current study investigated this data using General Linear Models based on both Poisson and Negative Binomial error models. The resulting models were not found to produce accurate predictions nor did there appear to be any significant differences in estimates produced by the two models in question. Failings of the data set and the models are considered and further areas for specific study are suggested.

Item Type: Thesis (Diploma)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions: School of Computing > Higher Diploma in Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 15 Dec 2014 10:32
Last Modified: 15 Dec 2014 10:32
URI: http://trap.ncirl.ie/id/eprint/1856

Actions (login required)

View Item View Item