Enhancing Ambulance Resource Management through Machine Learning-based Demand Prediction in Dublin, Ireland

Jones, Ciaran (2023) Enhancing Ambulance Resource Management through Machine Learning-based Demand Prediction in Dublin, Ireland. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (763kB) | Preview
Preview	PDF (Configuration manual) Download (504kB) | Preview

Abstract

This study investigates the efficacy of machine learning models – XGBoost, Random Forest (TensorFlow Decision Forest), and MLP Neural Network – in predicting ambulance demand in Dublin city. This study, aimed at improving resource allocation within emergency medical services (EMS), bridges gaps in the current understanding of Dublin's ambulance demand dynamics. Utilizing a comprehensive dataset comprising over 850,000 historical ambulance demand records over ten years, we scrutinized the influence of diverse feature engineering techniques on the models' performance. The study primarily accomplishes three key contributions: (1) Unveiling an effective XGBoost model, coupled with astute feature selection, for ambulance demand prediction, which achieved a mean absolute error (MAE) of 0.49673, thereby contributing to strategic EMS planning; (2) Highlighting significant factors that influence ambulance demand, notably temporal and societal factors, while contesting the previously assumed importance of weather data; and (3) Underscoring the essential role of feature engineering in refining model performance. Our findings suggest potential areas of improvement in model performance, through further refinement and integration of additional data sources. This paves the way for future research to enhance these models and assess their applicability across different regions, ultimately augmenting EMS resource allocation and public health outcomes.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Trinh, Anh Duong UNSPECIFIED
Uncontrolled Keywords:	ambulance demand; machine learning; predictive modelling; Dublin; resource management; public health; feature engineering
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning R Medicine > RA Public aspects of medicine > Public Health System
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	22 Nov 2024 13:33
Last Modified:	22 Nov 2024 13:33
URI:	https://norma.ncirl.ie/id/eprint/7193

Actions (login required)

View Item