Modulation-Prior Enhanced Cross-Modal Graph Learning for Low-SNR Automatic Modulation Recognition
Haibo Su, Yixiang Luomei, Zhentao Yang, Feiyu Mou, Zhenghong Lu, Yi Chen · 2026
Read Modulation-Prior Enhanced Cross-Modal Graph Learning for Low-SNR Automatic Modulation Recognition by Haibo Su, Yixiang Luomei, Zhentao Yang, Feiyu Mou, Zhenghong Lu, Yi Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611178.txt.
Description
Haibo Su and co-authors build a graph learning frame that names radio signal types even when noise runs high, in a 2026 paper. Naming the modulation of a signal aids spectrum sensing and quiet monitoring. At low signal strength, noise smears both wave shapes and time-frequency views, and fixed blends of the two can mislead.
Their net, MPCG-Net, first enriches both views with prior knowledge about modulation and aligns them in a noise-aware way. A memory block then polishes the blend before a time-linked graph learns the signal's shape. On three public sets, the net beat the best rival by clear steps in the low range, while staying light in size.
Catalog record
| CREATOR | Haibo Su, Yixiang Luomei, Zhentao Yang, Feiyu Mou, Zhenghong Lu, Yi Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |