An Assessment of Classification Approaches in Identifying Martian Geological Features

MacNamara, Tom (2022) An Assessment of Classification Approaches in Identifying Martian Geological Features. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Image classification is a field with many viable methods towards solving problems within it. It is therefore important to analyse and determine whether there exists a best machine learning technique which can be applied when categorising images. This report analyses nine approaches: K-nearest Neighbours; Support Vector Machine; Random Forest; Logistic Regression; Gaussian Naive Bayes; Multinomial Naive Bayes; Complement Naive Bayes; LightGBM; and a Convolutional Neural Network to determine if one of these approaches is ideal in classifying images of the surface of Mars.

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 > QB Astronomy Q Science > QE Geology Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	22 Feb 2023 16:33
Last Modified:	02 Mar 2023 09:32
URI:	https://norma.ncirl.ie/id/eprint/6217

Actions (login required)

View Item