Modeling Propagation Loss at 5.8 GHz: A Comparison of Log-Distance Models and Machine Learning with Empirical Measurements

This study evaluates several propagation loss models by comparing them with empirical data collected from measurement campaigns at the Pontifical Catholic University of Rio de Janeiro (PUCRio) at a central frequency of 5.8 GHz. The analysis covers five models: the Free Space Path Loss (FSPL) model, the Log-Distance Path Loss Model (LDPM), the Log-Distance Path Loss Model with Shadowing (LDPM-S) with fixed parameters (n=3, =6), LDPM-S with parameters obtained empirically, and the ADAM algorithm for machine learning. The results demonstrate that the ADAM algorithm achieved significantly higher accuracy than the traditional deterministic models, highlighting its potential to enhance performance in path loss estimation.