Accident Severity Prediction: Comparing ANN and Pattern search methods

Mathew, Jiliya (2022) Accident Severity Prediction: Comparing ANN and Pattern search methods. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (909kB) | Preview
Preview	PDF (Configuration manual) Download (11kB) | Preview

Abstract

Vehicle accidents cost the United States thousands of billions of dollars in both monetary and cultural terms every year. A limited number of major incidents are responsible for a large part of the damages. However, preventing road collisions, particularly major accidents, is an ongoing concern. The study's long-term objective has been to a better understanding of the elements that influence the likelihood of a traffic fatality. Accident and severity prediction is critical for the effective deployment of this technique. We may be able to apply systematic responses and improved safe driving regulations if we can discover the tendencies and hidden layers of how these massive catastrophes occur. The goal of this study was to evaluate the magnitude of road crashes utilizing accident-related factors in pattern search and ANN modeling methodologies, as well as to investigate the impact of weather or other environmental factors on accident occurrence. The most current dataset release may be useful for investigating how COVID- 19 influences accidents and driving habits. The project's goal has been to gain a greater understanding of the factors that influence the likelihood of a highway deadly accident. For feature selection, the particle swarm technique, Gray wolf optimization, Mutation Architecture, and Weight initialization GA are utilized. Classification techniques such as ANN, Boosting, pattern search deep neural network, and Bagging are defined and assessed.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	ANN; Pattern Search Methods; Boosting; Bagging; Accident Severity Prediction; particle swarm approach; Gray wolf optimization; Mutation Architecture; Weight initialization GA
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine T Technology > TL Motor vehicles. Aeronautics. Astronautics
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	22 Feb 2023 17:47
Last Modified:	22 Feb 2023 17:47
URI:	https://norma.ncirl.ie/id/eprint/6222

Actions (login required)

View Item