Project description
In this project we aim to investigate clinical unit-centric clustering. It is visible that such clusters do not partition the nodes (they overlap), however they are important identities, indicating dependency in unit-ward interactions. The goal will be to provide a framework to capture the structure of this clustering at any given time and use it to analyse temporal changes in hospital structure to prevent unintended/disruptive evolution of hospital functionality. Information theoretic measure for clustering comparison such as Normalized Mutual Information will be used to investigate temporal changes.- Please read https://researchnow.flinders.edu.au/en/publications/network-graph-analysis-of-hospital-and-health-services-functional for background information.
Note: You need to register interest in projects from different supervisors (not a number of projects with the one supervisor).
You must also contact each supervisor directly to discuss both the project details and your suitability to undertake the project.