NORMA eResearch @NCI Library

A comparative study on deep & machine learning techniques used for football injury prediction & prevention

Dunne, Michael (2021) A comparative study on deep & machine learning techniques used for football injury prediction & prevention. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (511kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (541kB) | Preview


Football as a sport is rapidly growing and has reached levels that no other sport was come close to in terms of popularity of watching, playing and the financial enterprise that surrounds this sport. A big part of this professional game is to keep players running at optimal performance and fitness levels to achieve all of the success within the competition and the financial rewards that come with this. To keep football players at this level of performance, the fitness screening of players health is common practice in today’s world to negate players getting injured. The purpose of this research is to predict and prevent injuries occurring to footballers so they can preform at optimal fitness levels. This research aims to use deep learning and machine learning techniques to predict an injury occurring to a player and classifying that player as a high or low injury risk. The use of techniques will be compared and contrasted to establish which approach should be used for future research, techniques that have been used in research carried out in this field have been implemented with novel approaches to determine the best fit for the prediction of football injuries. The research looks at predicting and evaluating the injury proneness of a player using both regression and classification methods. The lowest MAE is achieved by DNN model when using LR selected data. This is closely followed by CNN model. However, the difference is not statistically significant. Support Vector Regression performs the worst in all experiments in terms of MAE.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > RC Internal medicine > RC1200 Sports Medicine
G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports > Soccer
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 24 Jan 2023 12:59
Last Modified: 03 Mar 2023 12:58

Actions (login required)

View Item View Item