Using Explainable AI LIME to Improve the understanding of Machine Learning Predictions for Traffic Accidents

Heagney, Kevin (2024) Using Explainable AI LIME to Improve the understanding of Machine Learning Predictions for Traffic Accidents. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (730kB) | Preview

Abstract

The purpose of this research is to determine the suitability of the Explainable AI tool LIME for explaining the output of Machine Learning prediction classifier tools, for traffic accident data. Many papers have involved the use of XAI LIME for other areas, for example, health care, but I have not found any cases where LIME was used for traffic accident data. The combination of a Machine Learning model and LIME can explain and increase the understanding of what features in a dataset are the most important. This information could be very helpful with accident prevention. In the research, LIME was found to produce a very clear explanation of the Machine Learning model predictions for any selected instances or records in a large dataset.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Zahoor, Sheresh UNSPECIFIED
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 > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	18 Jun 2025 11:53
Last Modified:	18 Jun 2025 11:53
URI:	https://norma.ncirl.ie/id/eprint/7913

Actions (login required)

View Item