Thesis icon

Thesis

Algorithmic approaches to quantify coordination between people in contact team sports

Abstract:
Thesis outline In Chapter 1, the background, research aims, and limitations to the study have been explained. In Chapter 2, a systematic literature review is provided, exploring the research question: Can coordination be used to predict injury? The absence of a concrete and agreed-upon definition for coordination is shown, alongside the absence of a generally-applicable coordination measurement method. A broadly applicable definition of coordination is developed. In Chapter 3, the Coordination Game is developed. A control dataset is collected and analysed using a simple correlation by association method (Pearson correlation coefficients) and IMUs on pairs of participants. A general range of Pearson correlation coefficients is shown to classify whether a pair of participants are most likely coordinated or most likely uncoordinated; however, the classification of coordination is not concrete per person with this methodology, only with multiple tests of multiple participants. A more complex methodology must be tested. In Chapter 4, machine learning classifiers are utilized to classify segments of coordinated and uncoordinated tasks, specifically, the Support Vector Machine (SVM) Kernel and the coarse K-nearest neighbours classifiers. These classification methodologies did not perform as well as expected, only obtaining testing accuracy scores of 62.1% and 55.6%, maximum. Further implementation of classification methods should be explored, as only the surface of machine learning has been delved into in this work. In Chapter 5, an overview of this research and essential future work is discussed.

Actions

Access Document

Files:

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Sub department:
Institute of Biomedical Engineering
Research group:
Podium Institute
Oxford college:
St Hugh's College
Role:
Author
ORCID:
0000-0002-8822-4433

Contributors

Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Sub department:
Institute of Biomedical Engineering
Role:
Supervisor
ORCID:
0000-0001-7306-2630
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Sub department:
Institute of Biomedical Engineering
Role:
Supervisor
ORCID:
0000-0002-5404-4004


More from this funder
Funding agency for:
Levens, E
Programme:
Podium Institute


DOI:
Type of award:
MSc by Research
Level of award:
Masters
Awarding institution:
University of Oxford

Terms of use


Views and Downloads

Views and downloads will return soon






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP