A semi-supervised learning framework using crowdsourced UE data and building information improves RF building loss classification accuracy by up to 12.6% for outdoor-to-indoor cases over supervised learning alone.
Open government licence v3.0
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Machine-Learning-Based Classification of Radio Frequency Building Loss
A semi-supervised learning framework using crowdsourced UE data and building information improves RF building loss classification accuracy by up to 12.6% for outdoor-to-indoor cases over supervised learning alone.