Machine learning-enhanced 3GPP channel modeling for 5G networks: A vendor-calibrated framework with cross-scenario validation
Md Ifthakhar Khan Sagor, Md Zillur Rahman, Partha Mandal · 2026
Read Machine learning-enhanced 3GPP channel modeling for 5G networks: A vendor-calibrated framework with cross-scenario validation by Md Ifthakhar Khan Sagor, Md Zillur Rahman, Partha Mandal (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/plos-pone-0353163.txt.
Description
Sagor, Rahman, and Mandal combined standard radio models with machine learning for fifth-generation networks in a 2026 study. Planning such networks needs good guesses of signal strength and speed in cities, villages, and indoor spaces. The team trained five learning methods on ten thousand worked examples built from an official channel guide and real gear details.
Two methods, a neural network and a decision tree, predicted data speed with very high accuracy. Simpler straight-line methods did far worse, which shows how sharply radio behavior bends with place and frequency. Because the training data came from formulas, not field tests, the authors warn that real-world checks still need to follow.
Catalog record
| CREATOR | Md Ifthakhar Khan Sagor, Md Zillur Rahman, Partha Mandal |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65626 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |