A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks
Debin Wei, Chuanqi Guo, Li Yang, Yongqiang Xu, Chintha Tellambura · 2023
Read A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks by Debin Wei, Chuanqi Guo, Li Yang, Yongqiang Xu, Chintha Tellambura (2023) 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-10743012.txt.
Description
Debin Wei and co-authors tackle a routing headache in low Earth orbit satellite networks: telling apart why data packets get lost. In space links, errors from the harsh channel are common, while ground-style TCP treats every loss as congestion and slows down needlessly. A good loss differentiation method must spot the true cause.
Their method, LDM-HEL, first picks the most telling features using Relief and mutual information ranking. Four different classifiers then vote as an ensemble, with weights tuned by gradient descent during training. Simulations check whether the blended judgment beats single models. Fewer false congestion calls mean satellite links keep their speed.
Catalog record
| CREATOR | Debin Wei, Chuanqi Guo, Li Yang, Yongqiang Xu, Chintha Tellambura |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |