dc.rights.license | CC-BY-NC-ND | |
dc.contributor.advisor | Augustijn, Ellen-Wien | |
dc.contributor.author | Liempd, Bart van | |
dc.date.accessioned | 2022-04-20T23:00:31Z | |
dc.date.available | 2022-04-20T23:00:31Z | |
dc.date.issued | 2022 | |
dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/41506 | |
dc.description.abstract | The world is currently facing the COVID-19 pandemic. To be able to understand the scale of the outbreak
and to respond appropriately, it is required to track the spread of the virus. Currently, this tracking is done
with the use of either temporal or spatial data. This research proposes a method to combine both
dimensions to be able to track COVID-19 differently. This method is called the Self Organizing Map (SOM).
With the use of SOM five datasets are compared to each other. These datasets are the positive percentage
of tests, positive percentage of inhabitants, virus particles in sewage water, deceased cases, and
hospitalized cases. For these datasets, the change of the spatial situation over time and the distribution
of the local temporal variations over space are analyzed. Furthermore, the different waves of COVID-19
are compared to each other in the same way based on the virus particles in sewage water. In short, the
positive percentage of tests and positive percentage of inhabitants showed nearly identical patterns.
Hospitalized cases and deceased cases showed similar patterns, although not as similar as the datasets
described above. The sewage dataset was the most similar to the hospitalized cases and deceased cases.
To investigate this further, other methods should be used to evaluate the similarities. Primarily other
clustering algorithms could provide a useful addition to the research. | |
dc.description.sponsorship | Utrecht University | |
dc.language.iso | EN | |
dc.subject | In deze scriptie worden patronen onderzocht in de verspreiding en ontwikkeling van verschillende COVID-19 datasets in gemeenten in Nederland. | |
dc.title | Exploring Spatial-Temporal Patterns in COVID-19 Disease Data | |
dc.type.content | Master Thesis | |
dc.rights.accessrights | Open Access | |
dc.subject.keywords | COVID-19, Machine learning | |
dc.subject.courseuu | Geographical Information Management and Applications (GIMA) | |
dc.thesis.id | 3476 | |