van de Weerd, Michaël (2021) Detecting Astronomical Objects with Machine Learning. Master's Thesis / Essay, Computing Science.
|
Text
INMA_2021_vdWeerdMP.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (119kB) |
Abstract
Over the years, ML has solidified its reputation as a quick and easy solution to all problems that are in some way, shape or form related to classification. In a lot of cases, this reputation is justified, as the ratio of effort of implementation to the quality of the results is often very low. As such, finding new areas in which ML might play a role is a worthwhile endeavor. In this master's thesis, an effort is made to apply ML in order to detect astronomical objects. This is done by constructing a max-tree out of astronomical data, computing feature vectors representing the component attributes found in the tree and determining the significance of these components using a LVQ classifier, resulting in a segmentation of the astronomical objects from the background and noise. Using an embedded Python implementation of LVQ, the MTO segmentation software has been extended in order to produce these results from astronomical data in the optical domain, with their qualities being measured and compared to that of other MTO using a statistical segmentation method. These measurements show that LVQ does improve the recall of the segmentations, although at the cost of a significant amount of precision. Therefore, it is concluded that LVQ is not a suitable method to classify astronomical objects. Future research is required to further investigate the possibility of utilizing LVQ and ML in general in other ways.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Wilkinson, M.H.F. and Biehl, M. |
| Degree programme: | Computing Science |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 02 Feb 2021 12:37 |
| Last Modified: | 02 Feb 2021 12:37 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/23854 |
Actions (login required)
 |
View Item |