Hierarchical Classification of Variable Stars Using Deep Convolutional and Recurrent Neural Networks

Please enable javascript in your browser.

Abdollahi, Mahdi | 2021

514 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 54821 (04)
University: Sharif University of Technology
Department: Physics
Advisor(s): Rahvar, Sohrab; Raeisi, Sadegh
Abstract:
The importance of using a fast and automatic method to classify variable stars for large amounts of data is undeniable. There have been many attempts for classifying variable stars by traditional algorithms, which require long pre-processing time. In recent years, neural networks as classifiers have come to notice. This thesis proposes the Hierarchical Classification technique, which contains several models with the same network structure. Our pre-processing method produces input data by using light curves and the period. We use OGLE-IV variable stars database to train and test the performance of Convolutional Neural Networks based on the Hierarchical Classification technique. We see that Convolutional Neural Networks work faster than Recurrent Neural Networks and traditional methods, and have more accurate predictions. We obtain an accuracy of 98% for class classification and 93% for subclasses classification
Keywords:
Machine Learning ; Hierarchical Classification ; Convolutional Neural Network ; Recurrent Neural Networks ; Variable Stars