NORMA eResearch @NCI Library

Leveraging Advanced Machine Learning Techniques to Predict High-Risk Workplace Incidents: Insights from Ireland

Gopal, Aishwarya Rani (2023) Leveraging Advanced Machine Learning Techniques to Predict High-Risk Workplace Incidents: Insights from Ireland. Masters thesis, Dublin, National College of Ireland.

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

Abstract

This study looks into the important problem of safety at work, especially in Ireland’s industries where the risk of death and serious injuries is still a concern. The study shows a new way to look at and predict workplace accidents by combining machine learning and deep learning methods. This is because this field needs more advanced ways to predict accidents. The research was motivated by the limitations of current safety protocols, which often fail to preemptively identify and stop the risks of severe accidents. To deal with this, a comprehensive methodology was used, which included a collection of workplace incidents in Ireland. Techniques like SMOTE (Synthetic Minority Oversampling Technique) and RUS (Random Under Sampling) were used to fix class imbalances in the dataset. Support Vector Machine, AdaBoost, XGBoost, Naive Bayes, and Neural Networks were used to identify the fatality. The results showed that these algorithms, especially XGBoost, are good at predicting high-risk events. This is not only a big improvement over traditional ways of evaluating safety, but it is also a useful tool for making things safer in the real world. This research adds to what is already known by using a more data-driven and predictive method to look at workplace safety. Unfortunately, which was never employed in Ireland. It also used a secondary dataset to benchmark the results from Ireland’s data. It shows how machine learning can change the way safety management is done, laying the groundwork for future progress in this important area.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Jain, Mayank
UNSPECIFIED
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HD Industries. Land use. Labor > Issues of Labour and Work > Health and Safety at Work.
D History General and Old World > DA Great Britain > Ireland
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: 08 May 2025 12:13
Last Modified: 08 May 2025 12:13
URI: https://norma.ncirl.ie/id/eprint/7518

Actions (login required)

View Item View Item