NSSC OpenIR
Classification of Spectrum Images of Solar Radio Bursts Based on Deep Learning
Alternative TitleWOS:000557886100050
Xu, Xirong1,3; Wang, Zhiyang; Hong, Yu; Xia, Tianfan; Cheng, Jun1,2; Jiang, Jingqing3
Source Publication2019 15TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS 2019)
2019
Pages241-246
DOI10.1109/CIS.2019.00058
Language英语
ISBN978-1-7281-6092-4
AbstractViolent solar eruptions, such as solar flares and sundial jets, will have a serious impact on the Earth. Not only does it disrupt communication facilities and navigation equipment, but also produce a large number of radio phenomena. Further research on the solar radio phenomena will help us to understand of the activities of solar energy. With the rapid development of deep learning, the feature extraction and classification identification of solar radio spectrum images based on deep learning technology have been widely used. In this paper, gamma transformation, channel normalization, gray stretching, background suppression, image denoising and other image processing techniques, are used to preprocess the spectrum image of solar radio burst. Then we use CNN model, CNN-Capsule model and CNN-LSTM model to research the classification of spectrum images of solar radio burst types. The experimental results show that our approach can effectively improve the classification effect of solar radio burst types.
Keywordsolar radio Deep learning Image classification Digital image processing Capsule Networks CNN LSTM
Conference Name15th International Conference on Computational Intelligence and Security (CIS)
Conference DateDEC 13-16, 2019
Conference PlaceMacao, PEOPLES R CHINA
Indexed ByCPCI
Citation statistics
Document Type会议论文
Identifierhttp://ir.nssc.ac.cn/handle/122/7766
Collection中国科学院国家空间科学中心
Affiliation1.Dalian Univ Technol, Sch Comp Sci & Technol, Dalian 116024, Peoples R China
2.Natl Astron Observ, CAS Key Lab Solar Act, Beijing 100101, Peoples R China
3.Chinese Acad Sci, State Key Lab Space Weather, Beijing 100190, Peoples R China
4.Inner Mongolia Univ Nationalities, Sch Comp Sci & Technol, Tongliao, Inner Mongolia, Peoples R China
Recommended Citation
GB/T 7714
Xu, Xirong,Wang, Zhiyang,Hong, Yu,et al. Classification of Spectrum Images of Solar Radio Bursts Based on Deep Learning[C],2019:241-246.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xu, Xirong]'s Articles
[Wang, Zhiyang]'s Articles
[Hong, Yu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xu, Xirong]'s Articles
[Wang, Zhiyang]'s Articles
[Hong, Yu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xu, Xirong]'s Articles
[Wang, Zhiyang]'s Articles
[Hong, Yu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.