Comparative analysis of machine learning algorithms for detection of fast radio bursts

No Thumbnail Available
Authors
Thakur, Parth
Issue Date
2020
Degree
MSc in Data Analytics
Publisher
Dublin Business School
Rights
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Abstract
Fast radio bursts are a new astronomical phenomenon that have scientists baffled. To detect and analyse these FRBs, upcoming radio telescopes will capture tremendous amount of data. At the scales of these new telescopes, traditional methods of manually analysing the data fail. There is a need for extensive research in the use of machine learning for this task. This dissertation compares the performance of various machine learning algorithms, so they can be scaled to meet the demands of these new telescopes. To that extent, this research explores ways to simulate FRBs for analysis. The study compares four algorithms, namely, K-Nearest Neighbours, Random Forests, Deep Learning, and Convolutional Neural Networks.