Hierarchical Classification of Variable Stars Using Deep Convolutional Neural Networks
The importance of using fast and automatic methods to classify variable stars for large amounts of data is undeniable. There have been many attempts to classify variable stars by traditional algorithms like Random Forest. In recent years, neural networks as classifiers have come to notice because of...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Damghan university
2022-04-01
|
| Series: | Iranian Journal of Astronomy and Astrophysics |
| Subjects: | |
| Online Access: | https://ijaa.du.ac.ir/article_302_c2901d4f6a6dc82f720b22a07e388167.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841545099342774272 |
|---|---|
| author | Mahdi Abdollahi Nooshin Torabi Sadegh Raeisi Sohrab Rahvar |
| author_facet | Mahdi Abdollahi Nooshin Torabi Sadegh Raeisi Sohrab Rahvar |
| author_sort | Mahdi Abdollahi |
| collection | DOAJ |
| description | The importance of using fast and automatic methods to classify variable stars for large amounts of data is undeniable. There have been many attempts to classify variable stars by traditional algorithms like Random Forest. In recent years, neural networks as classifiers have come to notice because of their lower computational cost compared to traditional algorithms. This paper uses the Hierarchical Classification technique, which contains two main steps of predicting class and then subclass of stars. All the models in both steps have same network structure and we test both Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). Our pre-processing method uses light curves and period of stars as input data. We consider most of the classes and subclasses of variable stars in OGLE-IV database and show that using Hierarchical Classification technique and designing appropriate preprocessing can increase accuracy of predicting smaller classes, ACep and T2Cep. We obtain an accuracy of 98% for class classification and 93% for subclasses classification. |
| format | Article |
| id | doaj-art-118ba5291e4141b4941b311cafc75cb4 |
| institution | Kabale University |
| issn | 2322-4924 2383-403X |
| language | English |
| publishDate | 2022-04-01 |
| publisher | Damghan university |
| record_format | Article |
| series | Iranian Journal of Astronomy and Astrophysics |
| spelling | doaj-art-118ba5291e4141b4941b311cafc75cb42025-01-12T10:09:59ZengDamghan universityIranian Journal of Astronomy and Astrophysics2322-49242383-403X2022-04-0191314410.22128/ijaa.2022.603.1131302Hierarchical Classification of Variable Stars Using Deep Convolutional Neural NetworksMahdi Abdollahi0Nooshin Torabi1Sadegh Raeisi2Sohrab Rahvar3School of Astronomy, Institute for Research in Fundamental Sciences (IPM)Department of Physics, Sharif University of TechnologyDepartment of Physics, Sharif University of TechnologyDepartment of Physics, Sharif University of TechnologyThe importance of using fast and automatic methods to classify variable stars for large amounts of data is undeniable. There have been many attempts to classify variable stars by traditional algorithms like Random Forest. In recent years, neural networks as classifiers have come to notice because of their lower computational cost compared to traditional algorithms. This paper uses the Hierarchical Classification technique, which contains two main steps of predicting class and then subclass of stars. All the models in both steps have same network structure and we test both Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). Our pre-processing method uses light curves and period of stars as input data. We consider most of the classes and subclasses of variable stars in OGLE-IV database and show that using Hierarchical Classification technique and designing appropriate preprocessing can increase accuracy of predicting smaller classes, ACep and T2Cep. We obtain an accuracy of 98% for class classification and 93% for subclasses classification.https://ijaa.du.ac.ir/article_302_c2901d4f6a6dc82f720b22a07e388167.pdfvariable starshierarchical methodconvolutional neural networks |
| spellingShingle | Mahdi Abdollahi Nooshin Torabi Sadegh Raeisi Sohrab Rahvar Hierarchical Classification of Variable Stars Using Deep Convolutional Neural Networks Iranian Journal of Astronomy and Astrophysics variable stars hierarchical method convolutional neural networks |
| title | Hierarchical Classification of Variable Stars Using Deep Convolutional Neural Networks |
| title_full | Hierarchical Classification of Variable Stars Using Deep Convolutional Neural Networks |
| title_fullStr | Hierarchical Classification of Variable Stars Using Deep Convolutional Neural Networks |
| title_full_unstemmed | Hierarchical Classification of Variable Stars Using Deep Convolutional Neural Networks |
| title_short | Hierarchical Classification of Variable Stars Using Deep Convolutional Neural Networks |
| title_sort | hierarchical classification of variable stars using deep convolutional neural networks |
| topic | variable stars hierarchical method convolutional neural networks |
| url | https://ijaa.du.ac.ir/article_302_c2901d4f6a6dc82f720b22a07e388167.pdf |
| work_keys_str_mv | AT mahdiabdollahi hierarchicalclassificationofvariablestarsusingdeepconvolutionalneuralnetworks AT nooshintorabi hierarchicalclassificationofvariablestarsusingdeepconvolutionalneuralnetworks AT sadeghraeisi hierarchicalclassificationofvariablestarsusingdeepconvolutionalneuralnetworks AT sohrabrahvar hierarchicalclassificationofvariablestarsusingdeepconvolutionalneuralnetworks |