Application of statistical pattern recognition and deep learning for morphological classification in radio astronomy

Simple item page
dc.contributor.advisorGrobler, Trienkoen_ZA
dc.contributor.authorBecker, Adolf Burgeren_ZA
dc.contributor.otherStellenbosch University. Faculty of Science. Dept. of Computer Science.en_ZA
dc.date.accessioned2022-03-01T10:36:37Z
dc.date.accessioned2022-04-29T09:26:43Z
dc.date.available2022-03-01T10:36:37Z
dc.date.available2022-04-29T09:26:43Z
dc.date.issued2022-04
dc.descriptionThesis (MSc)--Stellenbosch University, 2022.en_ZA
dc.description.abstractENGLISH ABSTRACT: The morphological classification of radio sources is important to gain a full under standing of galaxy evolution processes and their relation with local environmental properties. Furthermore, the complex nature of the problem, its appeal for citi zen scientists and the large data rates generated by existing and upcoming radio telescopes combine to make the morphological classification of radio sources an ideal test case for the application of machine learning techniques. One approach that has shown great promise recently is Convolutional Neural Networks (CNNs). Literature, however, lacks two major things when it comes to CNNs and radio galaxy morphological classification. Firstly, a proper analysis to identify whether overfitting occurs when training CNNs to perform radio galaxy morphological clas sification is needed. Secondly, a comparative study regarding the practical appli cability of the CNN architectures in literature is required. Both of these short comings are addressed in this thesis. Multiple performance metrics are used for the latter comparative study, such as inference time, model complexity, compu tational complexity and mean per class accuracy. A ranking system based upon recognition and computational performance is proposed. MCRGNet, ATLAS and ConvXpress (novel classifier) are the architectures that best balance computational requirements with recognition performance.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING: Die morfologiese klassifikasie van radiobronne is belangrik om ’n volledige begrip van die evolusieprosesse binnein sterrestelsels te ontwikkel, asook die rol wat hul plaaslike omgewings hierin speel. As gevolg van die ingewikkelde aard van die probleem, asook die aantrekkingskrag daarvan vir “burgerwetenskaplikes” en die groot hoeveelhede data wat deur bestaande en opkomende radioteleskope gege nereer word, maak die morfologiese klassifikasie van radiobronne ’n ideale proef gebied vir die toepassing van masjienleertegnieke. ’n Benadering wat belowend lyk, is Konvolusionele Neurale Netwerke (KNNe). Literatuur ontbreek egter twee belangrike dinge as dit kom by KNNe en die morfologiese klassifikasie van radio sterrestelsels. Eerstens is daar ’n analise nodig rondom die identifikasie van oor passing wanneer KNNe afgerig word om radio sterrestelsels volgens morfologie te klassifiseer. Tweedens word ’n vergelykende studie oor die praktiese toepaslik heid van die KNN-argitekture in literatuur benodig. Albei hierdie tekortkominge word in hierdie tesis aagespreek. Veelvuldige prestasiemetings word vir laasgenoemde vergelykende studie gebruik, soos inferensietyd, modelkompleksiteit, berekeningkompleksiteit en gemiddelde akkuraatheid per klas. ’n Rangorde skema word voorgestel gebaseer op herkenning en berekeningsprestasie. MCRGNet, AT LAS en ConvXpress (nuwe bydrae) is die argitekture wat berekeningsvereistes en herkenningsprestasie die beste balanseer.af_ZA
dc.description.versionMastersen_ZA
dc.format.extent127 pagesen_ZA
dc.identifier.urihttp://hdl.handle.net/10019.1/124690
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subjectMachine Learningen_ZA
dc.subjectUCTDen_ZA
dc.subjectRadio astronomyen_ZA
dc.subjectPattern recognition systemsen_ZA
dc.subjectDeep learning (Machine learning)en_ZA
dc.subjectMorphological classificationen_ZA
dc.titleApplication of statistical pattern recognition and deep learning for morphological classification in radio astronomyen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
becker_statistical_2022.pdf
Size:
4.15 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Masters Degrees (Computer Science)