An Expert Analysis of AI-Driven Solutions for RF Path Loss Prediction.

Sagar Baburao Samrat; Sangram T Patil

doi:10.36948/ijfmr.2025.v07i05.55188

An Expert Analysis of AI-Driven Solutions for RF Path Loss Prediction.

Author(s)	Mr. Sagar Baburao Samrat, Dr. Sangram T Patil
Country	India
Abstract	Traditional empirical models for radio frequency (RF) path loss prediction often lack the accuracy and adaptability required for planning and optimizing modern 5G networks.[1, 1, 1] This report presents a data-driven framework that leverages machine learning to predict path loss with high fidelity.[1, 1] Utilizing a comprehensive 5G network dataset that includes a rich array of operational, environmental, and performance variables, a robust proxy for path loss is engineered from received signal strength measurements.[1, 1] A comparative analysis of multiple algorithms—including Linear Regression, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Random Forest, and Gradient Boosting (XGBoost)—is conducted.[1, 1] The final tuned XGBoost model demonstrates superior predictive performance, achieving an R-squared value of 0.924 and a Mean Absolute Error (MAE) of 3.51 dB on unseen test data.[1, 1] Feature importance analysis confirms that the operating frequency band, geographic location, and dynamic network congestion level are the most significant predictors of path loss.[1, 1] This study validates the superiority of advanced ensemble methods over simpler models and delivers a practical, accurate, and context-aware tool for real-world 5G network planning and management.[1, 1]
Keywords	RF Path Loss, Machine Learning, XGBoost, Ensemble Methods, Wireless Communication, 5G Networks, Regression Analysis, Feature Engineering, Network Planning, Signal Propagation, Okumura-Hata Model, Data-driven approach.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 7, Issue 5, September-October 2025
Published On	2025-09-07
DOI	https://doi.org/10.36948/ijfmr.2025.v07i05.55188

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

An Expert Analysis of AI-Driven Solutions for RF Path Loss Prediction.

Share this