Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Compact and Extended Radio Sources Classification using Deep Convolutional Neural Networks
Upcoming surveys with new radio observatories such as the Square Kilometer Array will generate a wealth of imaging data containing large numbers of radio sources. Different classes of radio sources can be used as tracers of the cosmic environment, including the dark matter density field, to address...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Astronomy
2023
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613148356280320 |
|---|---|
| access_status_str | Open Access |
| author | Alhassan, Wathela |
| author2 | Taylor, A R |
| author_browse | Alhassan, Wathela Taylor, A R |
| author_facet | Taylor, A R Alhassan, Wathela |
| author_sort | Alhassan, Wathela |
| collection | Thesis |
| description | Upcoming surveys with new radio observatories such as the Square Kilometer Array will generate a wealth of imaging data containing large numbers of radio sources. Different classes of radio sources can be used as tracers of the cosmic environment, including the dark matter density field, to address key cosmological questions. Classifying these sources based on morphology is thus an important step toward achieving the science goals of next generation radio surveys. Extended Radio Sources have been traditionally classified as Fanaroff-Riley (FR) I and II, although some exhibit more complex 'bent' morphologies arising from environmental factors or intrinsic properties. In this work we present the FIRST Classifier, an on-line system for automated classification of Compact and Extended radio sources. We developed the FIRST Classifier based on a trained Deep Convolutional Neural Network Model to automate the morphological classification of compact and extended radio sources observed in the FIRST radio survey. Our model was trained independently for 20 times and achieved an average accuracy, precision, recall and F1 of 0.98. The current version of the FIRST classifier is able to identify the morphological class for a single source or for a list of sources as Compact or Extended (FRI, FRII and BENT). |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/37548 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:31:31.816Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | Department of Astronomy |
| publisherStr | Department of Astronomy |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/37548 Compact and Extended Radio Sources Classification using Deep Convolutional Neural Networks Alhassan, Wathela Taylor, A R Vaccari, Mattia Astronomy Upcoming surveys with new radio observatories such as the Square Kilometer Array will generate a wealth of imaging data containing large numbers of radio sources. Different classes of radio sources can be used as tracers of the cosmic environment, including the dark matter density field, to address key cosmological questions. Classifying these sources based on morphology is thus an important step toward achieving the science goals of next generation radio surveys. Extended Radio Sources have been traditionally classified as Fanaroff-Riley (FR) I and II, although some exhibit more complex 'bent' morphologies arising from environmental factors or intrinsic properties. In this work we present the FIRST Classifier, an on-line system for automated classification of Compact and Extended radio sources. We developed the FIRST Classifier based on a trained Deep Convolutional Neural Network Model to automate the morphological classification of compact and extended radio sources observed in the FIRST radio survey. Our model was trained independently for 20 times and achieved an average accuracy, precision, recall and F1 of 0.98. The current version of the FIRST classifier is able to identify the morphological class for a single source or for a list of sources as Compact or Extended (FRI, FRII and BENT). 2023-03-29T11:21:30Z 2023-03-29T11:21:30Z 2019 2023-03-29T11:20:27Z Master Thesis Masters MSc http://hdl.handle.net/11427/37548 eng application/pdf Department of Astronomy Faculty of Science |
| spellingShingle | Astronomy Alhassan, Wathela Compact and Extended Radio Sources Classification using Deep Convolutional Neural Networks |
| thesis_degree_str | Master's |
| title | Compact and Extended Radio Sources Classification using Deep Convolutional Neural Networks |
| title_full | Compact and Extended Radio Sources Classification using Deep Convolutional Neural Networks |
| title_fullStr | Compact and Extended Radio Sources Classification using Deep Convolutional Neural Networks |
| title_full_unstemmed | Compact and Extended Radio Sources Classification using Deep Convolutional Neural Networks |
| title_short | Compact and Extended Radio Sources Classification using Deep Convolutional Neural Networks |
| title_sort | compact and extended radio sources classification using deep convolutional neural networks |
| topic | Astronomy |
| url | http://hdl.handle.net/11427/37548 |
| work_keys_str_mv | AT alhassanwathela compactandextendedradiosourcesclassificationusingdeepconvolutionalneuralnetworks |