Classification of Deep Space Objects using Deep Learning Techniques

Ó Foghlú, Cillín (2020) Classification of Deep Space Objects using Deep Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (3MB) | Preview

Abstract

Throughout the ages people have gazed into the nights sky and wondered. This research looked at the use of modern computer image recognition algorithms and reviewed some of the best performing against each other to see how they adapted to deep space object imagery. Images from both the Slone Deep Space Survey and the Space Telescope Science Institute Kepler images were used as training input to deep learning models – ResNet50, VGG16, Xception and MobileNet. The model’s performance is validated against unseen images and the level of accuracy used to ascertain their performance. Using pre-trained models as a base then project shows that these models can be trained to leant new features and classify deep space objects with accuracy of 80% plus. This will allow astronomers to focus their limited telescope time on the objects of greatest interest. The resents of review literature and identified gaps are also presented.
Keywords: CNN, Slone Deep Space Survey, STScI, Image Classification, Astronomy

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software Q Science > QB Astronomy
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	18 Jan 2021 14:33
Last Modified:	18 Jan 2021 14:33
URI:	https://norma.ncirl.ie/id/eprint/4370

Actions (login required)

View Item