Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.25675 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912616965734400 |
|---|---|
| author | Geng, Haobo Li, Yaoyao Tong, Weiping Meng, Youwei Xiao, Houpu Liu, Yicong |
| author_facet | Geng, Haobo Li, Yaoyao Tong, Weiping Meng, Youwei Xiao, Houpu Liu, Yicong |
| contents | With the rapid advancement of electronic information technology, the number and variety of unknown radiation sources have increased significantly. Some of these sources share common characteristics, which offers the potential to effectively address the challenge of identifying unknown radiation sources. However, research on the classification of radiation sources remains relatively limited. This paper proposes a big data analysis method that combines linear discriminant analysis (LDA) with a rough neighborhood set (NRS) for radiation source classification, and its effectiveness is validated on the RadioML 2018 dataset. The results indicate that, under certain constraints, all modulation types can be categorized into four distinct classes, laying a foundation for further research on cognitive interference signal cancellation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25675 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Novel Statistical Analysis Method for Radiation Source Classification Geng, Haobo Li, Yaoyao Tong, Weiping Meng, Youwei Xiao, Houpu Liu, Yicong Signal Processing With the rapid advancement of electronic information technology, the number and variety of unknown radiation sources have increased significantly. Some of these sources share common characteristics, which offers the potential to effectively address the challenge of identifying unknown radiation sources. However, research on the classification of radiation sources remains relatively limited. This paper proposes a big data analysis method that combines linear discriminant analysis (LDA) with a rough neighborhood set (NRS) for radiation source classification, and its effectiveness is validated on the RadioML 2018 dataset. The results indicate that, under certain constraints, all modulation types can be categorized into four distinct classes, laying a foundation for further research on cognitive interference signal cancellation. |
| title | A Novel Statistical Analysis Method for Radiation Source Classification |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2509.25675 |