Research on Multiclassification Algorithm of Ultrawideband Pulsar RFI Based on MobileNetV2
文献类型：期刊论文
| 作者 | Cai, Wenna2,4; Zhang, Hailong1,2,3,4; Zhang, Yazhou2; Wang, Jie1,2,4; Du, Xu2,4; Zhang, Ting2,4; Jiao, Yuyue2,4; Tang, Hongmei2; Ye, Xinchen1,2,3; Wang, Wanqiong2 |
| 刊名 | ASTRONOMICAL JOURNAL
 |
| 出版日期 | 2026-02-02 |
| 卷号 | 171期号:2页码:94 |
| ISSN号 | 0004-6256 |
| DOI | 10.3847/1538-3881/ae2ad5 |
| 产权排序 | 1 |
| 英文摘要 | Radio telescopes are susceptible to radio frequency interference (RFI) during observations, which introduces noise and artificial signals into astronomical data. Failure to properly process RFI-contaminated data can severely compromise data reliability and even lead to erroneous scientific conclusions. Consequently, RFI identification and mitigation have become critical scientific challenges in radio astronomy. This study proposes an RFI recognition and data cleaning method based on a deep learning image classification algorithm (RFI-MobileNetV2, RFI-MN). By performing feature extraction and preliminary classification on visual astronomical data, the method aims to effectively mitigate RFI, improve the data signal-to-noise ratio, and provide more reliable data support for astronomical research. Using the lightweight convolutional neural network MobileNetV2 as the core architecture, the model achieves efficient extraction and classification of diverse RFI features, thereby providing an effective solution for subsequent RFI suppression tasks. For the experiments, a dataset containing multiple RFI types was constructed as a training sample. During model optimization, performance was significantly enhanced through the integration of an attention mechanism, modification of the activation function in inverted residuals, and multiscale feature fusion. Evaluation metrics including precision, recall, and F1 score were employed to verify the scheme's effectiveness through baseline training, inference, multimodel comparison, and ablation experiments. The results demonstrate that the optimized RFI-MN achieves performance exceeding 94%, substantially outperforming other comparative models and providing an effective solution for RFI-affected astronomical data preprocessing. |
| WOS关键词 | RADIO-FREQUENCY INTERFERENCE ; IDENTIFICATION ; MITIGATION |
| 资助项目 | National Key R&D Program of China[2021YFC2203502] ; National Natural Science Foundation of China[12173077] ; National Natural Science Foundation of China[12573113] ; Chinese Academy of Sciences CAS Light of West China Program[xbzg-zdsys-202410] ; Tianshan Talent Project of Xinjiang Uygur Autonomous Region[2022TSYCCX0095] ; Tianshan Talent Project of Xinjiang Uygur Autonomous Region[2023TSYCCX0112] ; Tianshan Innovation Team Plan of Xinjiang Uygur Autonomous Region[2025D14014] ; Scientific Instrument Developing Project of the Chinese Academy of Sciences[PTYQ2022YZZD01] ; China National Astronomical Data Center (NADC) ; Operation, Maintenance and Upgrading Fund for Astronomical Telescopes and Facility Instruments ; Ministry of Finance of China |
| WOS研究方向 | Astronomy & Astrophysics |
| 语种 | 英语 |
| WOS记录号 | WOS:001662364800001 |
| 出版者 | IOP Publishing Ltd |
| 资助机构 | National Key R&D Program of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences CAS Light of West China Program ; Tianshan Talent Project of Xinjiang Uygur Autonomous Region ; Tianshan Innovation Team Plan of Xinjiang Uygur Autonomous Region ; Scientific Instrument Developing Project of the Chinese Academy of Sciences ; China National Astronomical Data Center (NADC) ; Operation, Maintenance and Upgrading Fund for Astronomical Telescopes and Facility Instruments ; Ministry of Finance of China |
| 源URL | [http://ir.xao.ac.cn/handle/45760611-7/8490]  |
| 专题 | 新疆天文台_计算机技术室 |
| 通讯作者 | Zhang, Hailong |
| 作者单位 | 1.Natl Astron Data Ctr, Beijing 100101, Peoples R China 2.Chinese Acad Sci, Xinjiang Astron Observ, Urumqi 830011, Peoples R China 3.Chinese Acad Sci, Key Lab Radio Astron, Nanjing 210008, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Cai, Wenna,Zhang, Hailong,Zhang, Yazhou,et al. Research on Multiclassification Algorithm of Ultrawideband Pulsar RFI Based on MobileNetV2[J]. ASTRONOMICAL JOURNAL,2026,171(2):94. |
| APA | Cai, Wenna.,Zhang, Hailong.,Zhang, Yazhou.,Wang, Jie.,Du, Xu.,...&Li, Jia.(2026).Research on Multiclassification Algorithm of Ultrawideband Pulsar RFI Based on MobileNetV2.ASTRONOMICAL JOURNAL,171(2),94. |
| MLA | Cai, Wenna,et al."Research on Multiclassification Algorithm of Ultrawideband Pulsar RFI Based on MobileNetV2".ASTRONOMICAL JOURNAL 171.2(2026):94. |
入库方式： OAI收割
来源：新疆天文台
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。