An ensemble ML framework combining lidar simulation data, SMOTE, and real measurements reduces path loss prediction MAE by up to 50% versus real-data-only models and improves cross-environment generalization.
Mixing real and synthetic data to enhance neural network training–a review of current approaches,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Simulation-Driven Ensemble Machine Learning for Robust and Generalizable Path Loss Prediction
An ensemble ML framework combining lidar simulation data, SMOTE, and real measurements reduces path loss prediction MAE by up to 50% versus real-data-only models and improves cross-environment generalization.