Comparison of the Ensemble and Stacking Approaches in Predicting Mortality in Vehicle Collisions in New York

Dhandapani, Subramanyam (2024) Comparison of the Ensemble and Stacking Approaches in Predicting Mortality in Vehicle Collisions in New York. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Traffic collisions are becoming a major cause of deaths and injuries worldwide which draws attention for the need of technology in addressing and identifying the important aspects which makes these accidents to happen. This Research aims to analyse the New York Motor Collision data by applying various machine learning techniques and statistical methods to identify the factors and trends which has a huge impact on the survivability of the person during the motor collision. This research uses KDD methodology to identify patterns and trends in the collision dataset. Also, for this research two datasets are used where one contain the data about the crashes and the other contains the person’s information. This study compares the stacking model to an ensemble approach with the evaluation of metrics F1 score, accuracy, precision and recall. This Research uses three classification algorithms namely decision tree, random forest and k-nearest neighbor comparing to each other by applying stacking and ensemble approaches among them.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Simiscuka, Anderson UNSPECIFIED
Uncontrolled Keywords:	KDD Methodology; Stacking Approach; Motor Collision; Ensemble Approach; Injury Severity
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TL Motor vehicles. Aeronautics. Astronautics Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	15 Aug 2025 17:23
Last Modified:	15 Aug 2025 17:23
URI:	https://norma.ncirl.ie/id/eprint/8551

Actions (login required)

View Item