Hello

About Me

I am a sports performance data scientist with a strong focus on applying machine learning and data analytics in sport. My work sits at the intersection of sports science and artificial intelligence, exploring how data-driven techniques can enhance performance.

Currently, I am working with the Insight Centre for Data Analytics and the Sport Ireland Institute on a sport data project, aiming to develop innovative data solutions that improves performance.

Research Overview

I recently completed my PhD, titled: “Enhancing Athlete Monitoring: A Machine Learning Approach to Predicting Ratings of Perceived Exertion and Oxygen Uptake in Team Sports.” My research explored how machine learning can model training load data, identify key performance metrics, and integrate historical records and raw sensor data to improve RPE and VO₂ estimation. By leveraging high-frequency GNSS and IMU data, I aimed to develop more precise and data-informed training prescriptions.

Current Research Projects

Enhancing RPE Prediction with Time-Series Features in Team Sports

I am currently working on a research paper exploring the use of time-series features to improve RPE prediction in team sports using raw wearable sensor data. This project investigates how extracting and leveraging temporal patterns from GNSS data can enhance the accuracy of RPE predictions, potentially leading to more personalised and precise training load monitoring strategies.

Estimating VO2 During Team Sports from IMU Wearable Sensors Data

This project focuses on estimating oxygen consumption (VO2) using Inertial Measurement Unit (IMU) data. The goal is to create robust models for physiological monitoring during team sports, providing deeper insights into athlete conditioning and metabolic demands during high-intensity activities.

Automating Event Detection in Team Sports Using Wearable Sensor Data

This research investigates automating the detection of key events and phases during sports activities using GNSS and IMU data. The project aims to develop algorithms that can recognize and classify complex movement patterns to enhance tactical and performance analysis.

Machine Learning Approach for Predicting RPE Using GNSS Wearable Sensors

This project explores how machine learning can be used to predict athletes’ Ratings of Perceived Exertion (RPE) using GNSS data. By developing models that capture the complexity of external load metrics, I aim to provide a more accurate and actionable understanding of training demands.

Research Goals

Through my research, I strive to create innovative data-informed solutions that can be applied in real-world training environments, helping practitioners optimise training load management and enhance overall athlete performance.

Feel free to explore my repositories for more details on my work, research projects, and open-source contributions!