Classification of Solar Radio Spectrum Based on Swin Transformer
Open Access
Abstract
Solar radio observation is a method used to study the Sun. It is very important for space weather early warning and solar physics research to automatically classify solar radio spectrums in real time and judge whether there is a solar radio burst. As the number of solar radio burst spectrums is small and uneven, this paper proposes a classification method for solar radio spectrums based on the Swin transformer. First, the method transfers the parameters of the pretrained model to the Swin transformer model. Then, the hidden layer weights of the Swin transformer are frozen, and the fully connected layer of the Swin transformer is trained on the target dataset. Finally, parameter tuning is performed. The experimental results show that the method can achieve a true positive rate of 100%, which is more accurate than previous methods. Moreover, the number of our model parameters is only 20 million, which is 80% lower than that of the traditional VGG16 convolutional neural network with more than 130 million parameters.Keywords
All Related Versions
Funding Information
- Natural Science Foundation of China (12263008, 11941003, 2021YFA1600500, 202001BB050032, 202201BF070001-005, 202202AD080004, KLSA202115, 2021Y269)
- Natural Science Foundation of China (12263008, 11941003, 2021YFA1600500, 202001BB050032, 202201BF070001-005, 202202AD080004, KLSA202115, 2021Y269)
- MOST (12263008, 11941003, 2021YFA1600500, 202001BB050032, 202201BF070001-005, 202202AD080004, KLSA202115, 2021Y269)
- the Application and Foundation Project of Yunnan Province (12263008, 11941003, 2021YFA1600500, 202001BB050032, 202201BF070001-005, 202202AD080004, KLSA202115, 2021Y269)
- Yunnan Provincial Department of Science and Technology–Yunnan University Joint Special Project for Double-Class Construction (12263008, 11941003, 2021YFA1600500, 202001BB050032, 202201BF070001-005, 202202AD080004, KLSA202115, 2021Y269)
- Key R&D Projects of Yunnan Province (12263008, 11941003, 2021YFA1600500, 202001BB050032, 202201BF070001-005, 202202AD080004, KLSA202115, 2021Y269)
- the Open Project of CAS Key Laboratory of Solar Activity, National Astronomical Observatories (12263008, 11941003, 2021YFA1600500, 202001BB050032, 202201BF070001-005, 202202AD080004, KLSA202115, 2021Y269)
- 13th Postgraduate Innovation Project of Yunnan University (12263008, 11941003, 2021YFA1600500, 202001BB050032, 202201BF070001-005, 202202AD080004, KLSA202115, 2021Y269)
This publication has 11 references indexed in Scilit:
- An Appearance Defect Detection Method for Cigarettes Based on C-CenterNetElectronics, 2022
- A deep learning method for the recognition of solar radio burst spectrumPeerJ Computer Science, 2022
- Classification of Solar Radio Spectrum Based on VGG16 Transfer Learning2021
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- Auto Recognition of Solar Radio Bursts Using the C-DCGAN MethodFrontiers in Physics, 2021
- IPRT/AMATERAS: A New Metric Spectrum Observation System for Solar Radio BurstsSolar Physics, 2012
- AUTOMATIC RECOGNITION OF CORONAL TYPE II RADIO BURSTS: THE AUTOMATED RADIO BURST IDENTIFICATION SYSTEM METHOD AND FIRST OBSERVATIONSThe Astrophysical Journal Letters, 2010
- Automatic recognition of type III solar radio bursts: Automated Radio Burst Identification System method and first observationsSpace Weather, 2009
- Nonlinear calibration and data processing of the solar radio burstScience China Mathematics, 2002
- Solar Feature Identification using Contrasts and ContiguitySolar Physics, 2001