Balancing Prediction Accuracy and Explanation Power of Path Loss Modeling in a University Campus Environment via Explainable AI

For efficient radio network planning, empirical path loss (PL) prediction models are utilized to predict signal attenuation in different environments. Alternatively, machine learning (ML) models are proposed to predict path loss. While empirical models are transparent and require less computational...

Full description

Saved in:
Bibliographic Details
Main Authors: Hamed Khalili, Hannes Frey, Maria A. Wimmer
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/4/155
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713383590330368
author Hamed Khalili
Hannes Frey
Maria A. Wimmer
author_facet Hamed Khalili
Hannes Frey
Maria A. Wimmer
author_sort Hamed Khalili
collection DOAJ
description For efficient radio network planning, empirical path loss (PL) prediction models are utilized to predict signal attenuation in different environments. Alternatively, machine learning (ML) models are proposed to predict path loss. While empirical models are transparent and require less computational capacity, their predictions are not able to generate accurate forecasting in complex environments. While ML models are precise and can cope with complex terrains, their opaque nature hampers building trust and relying assertively on their predictions. To fill the gap between transparency and accuracy, in this paper, we utilize glass box ML using Microsoft research’s explainable boosting machines (EBM) together with the PL data measured for a university campus environment. Moreover, polar coordinate transformation is applied in our paper, which unravels the superior explanation capacity of the feature transmitting angle beyond the feature distance. PL predictions of glass box ML are compared with predictions of black box ML models as well as those generated by empirical models. The glass box EBM exhibits the highest performance. The glass box ML, furthermore, sheds light on the important explanatory features and the magnitude of their effects on signal attenuation in the underlying propagation environment.
format Article
id doaj-art-a4ca2f4145b54583aa6be166df9f84a1
institution DOAJ
issn 1999-5903
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-a4ca2f4145b54583aa6be166df9f84a12025-08-20T03:13:58ZengMDPI AGFuture Internet1999-59032025-03-0117415510.3390/fi17040155Balancing Prediction Accuracy and Explanation Power of Path Loss Modeling in a University Campus Environment via Explainable AIHamed Khalili0Hannes Frey1Maria A. Wimmer2Research Group Computer Networks, Faculty of Computer Science, University of Koblenz, D-56070 Koblenz, GermanyResearch Group Computer Networks, Faculty of Computer Science, University of Koblenz, D-56070 Koblenz, GermanyResearch Group E-Government, Faculty of Computer Science, University of Koblenz, D-56070 Koblenz, GermanyFor efficient radio network planning, empirical path loss (PL) prediction models are utilized to predict signal attenuation in different environments. Alternatively, machine learning (ML) models are proposed to predict path loss. While empirical models are transparent and require less computational capacity, their predictions are not able to generate accurate forecasting in complex environments. While ML models are precise and can cope with complex terrains, their opaque nature hampers building trust and relying assertively on their predictions. To fill the gap between transparency and accuracy, in this paper, we utilize glass box ML using Microsoft research’s explainable boosting machines (EBM) together with the PL data measured for a university campus environment. Moreover, polar coordinate transformation is applied in our paper, which unravels the superior explanation capacity of the feature transmitting angle beyond the feature distance. PL predictions of glass box ML are compared with predictions of black box ML models as well as those generated by empirical models. The glass box EBM exhibits the highest performance. The glass box ML, furthermore, sheds light on the important explanatory features and the magnitude of their effects on signal attenuation in the underlying propagation environment.https://www.mdpi.com/1999-5903/17/4/155path lossradio propagationwireless channelcomparative analysis of machine learning methodsexplainable artificial intelligence
spellingShingle Hamed Khalili
Hannes Frey
Maria A. Wimmer
Balancing Prediction Accuracy and Explanation Power of Path Loss Modeling in a University Campus Environment via Explainable AI
Future Internet
path loss
radio propagation
wireless channel
comparative analysis of machine learning methods
explainable artificial intelligence
title Balancing Prediction Accuracy and Explanation Power of Path Loss Modeling in a University Campus Environment via Explainable AI
title_full Balancing Prediction Accuracy and Explanation Power of Path Loss Modeling in a University Campus Environment via Explainable AI
title_fullStr Balancing Prediction Accuracy and Explanation Power of Path Loss Modeling in a University Campus Environment via Explainable AI
title_full_unstemmed Balancing Prediction Accuracy and Explanation Power of Path Loss Modeling in a University Campus Environment via Explainable AI
title_short Balancing Prediction Accuracy and Explanation Power of Path Loss Modeling in a University Campus Environment via Explainable AI
title_sort balancing prediction accuracy and explanation power of path loss modeling in a university campus environment via explainable ai
topic path loss
radio propagation
wireless channel
comparative analysis of machine learning methods
explainable artificial intelligence
url https://www.mdpi.com/1999-5903/17/4/155
work_keys_str_mv AT hamedkhalili balancingpredictionaccuracyandexplanationpowerofpathlossmodelinginauniversitycampusenvironmentviaexplainableai
AT hannesfrey balancingpredictionaccuracyandexplanationpowerofpathlossmodelinginauniversitycampusenvironmentviaexplainableai
AT mariaawimmer balancingpredictionaccuracyandexplanationpowerofpathlossmodelinginauniversitycampusenvironmentviaexplainableai