{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T17:19:43Z","timestamp":1777310383114,"version":"3.51.4"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Path loss prediction is crucial to facilitate reliable vehicle-to-infrastructure (V2I) communications. In this study, machine learning techniques are investigated for path loss modeling using empirical measurements at 5.9\u202fGHz from eight Road Side Unit (RSU) sites. The performance of Extreme Gradient Boosting (XGBoost) and Multilayer Perceptron (MLP) models is contrasted with traditional empirical models such as the Dual Slope and 3rd Generation Partnership Project (3GPP) models in three varied urban environments: open, suburban, and densely urbanized cities. The findings indicate that machine learning models, in particular XGBoost, consistently outperform traditional models with the lowest Root Mean Square Error (RMSE) in complicated urban environments. For additional robustness in prediction, we propose an innovative environmental classification system based on building density, street geometry, and transmitter position. Feature importance examination reveals that distance, environmental class, and transmitter height are the most significant factors affecting path loss prediction accuracy. These observations aid the development of adaptive V2I communication systems and provide valuable guidelines for enhancing reliability in diverse urban environments.<\/jats:p>","DOI":"10.3389\/frai.2025.1597981","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T05:24:36Z","timestamp":1752211476000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Machine learning for improved path loss prediction in urban vehicle-to-infrastructure communication systems"],"prefix":"10.3389","volume":"8","author":[{"given":"Mongi","family":"Ben Ameur","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jalel","family":"Chebil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed Hadi","family":"Habaebi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jamel Bel Hadj","family":"Tahar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,11]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1109\/TITS.2013.2251905","article-title":"Measurement-based analysis of vehicle-to-vehicle propagation channels for ITS applications","volume":"14","author":"Abbas","year":"2013","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.9734\/JERR\/2018\/v1i39775","article-title":"Determination of an outdoor path loss model and signal penetration level in some selected modern residential and office apartments in Ogbomosho, Oyo state, Nigeria","author":"Akpaida","year":"2018","journal-title":"J. Eng. Res. Rep."},{"key":"ref3","volume-title":"Pattern recognition and machine learning","author":"Bishop","year":"2006"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/JSAC.2011.110102","article-title":"Impact of vehicles as obstacles in vehicular communication environments","volume":"29","author":"Boban","year":"2011","journal-title":"IEEE J Sel Areas Commun"},{"key":"ref9003","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1109\/25.554747","article-title":"Environment-adaptation mobile radio propagation prediction using radial basis function neural networks","volume":"46","author":"Chang","year":"1997","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.48550\/arXiv.1810.04805","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"Devlin","year":"2019","journal-title":"Proc. NAACL-HLT 2019"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"4334","DOI":"10.3390\/s24134334","article-title":"Dual-slope path loss model for integrating vehicular sensing applications in urban and suburban environment","volume":"24","author":"Fern\u00e1ndez","year":"2024","journal-title":"Sensors"},{"key":"ref7","first-page":"1","article-title":"Impact of RSU height on V2I communication performance in urban environments","author":"Filippi","year":"2021"},{"key":"ref9007","first-page":"878","article-title":"Application of RBF neural networks to the prediction of propagation loss over irregular terrain","volume":"2","author":"Fraile","year":"2000","journal-title":"Proceedings of the Vehicular Technology Conference Fall (VTC)"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2157","DOI":"10.1109\/COMST.2019.2917261","article-title":"A comparative study on dimensionality reduction techniques for wireless channel modeling","volume":"21","author":"Gho","year":"2019","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref9","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1109\/TIV.2022.3145621","article-title":"Adaptive Kalman filtering for V2X path loss estimation in urban areas","volume":"7","author":"Gozalvez","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref9008","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1109\/MCOM.2012.6194400","article-title":"IEEE802.11p vehicle to infrastructure communications in urban environments","volume":"50","author":"Gozalvez","year":"2012","journal-title":"IEEE Communications Magazine"},{"key":"ref9009","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1109\/T-VT.1980.23859","article-title":"Empirical formula for propagation loss in land mobile radio services","volume":"29","author":"Hata","year":"1980","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1088\/1742-6596\/1003\/1\/012028","article-title":"Analyzing study of path loss propagation models in wireless communications at 0.8 GHz","volume":"1003","author":"Hoomod","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"key":"ref9010","doi-asserted-by":"crossref","first-page":"3939","DOI":"10.1109\/TAP.2022.3149663","article-title":"Artificial intelligence enabled radio propagation for communications\u2014Part I: Channel characterization and antenna channel optimization","volume":"70","author":"Huang","year":"","journal-title":"IEEE Transactions on Antennas and Propagation"},{"key":"ref9011","doi-asserted-by":"crossref","first-page":"3955","DOI":"10.1109\/TAP.2022.3149665","article-title":"Artificial intelligence enabled radio propagation for communications\u2014Part II: Scenario identification and channel modeling,","volume":"70","author":"Huang","year":"","journal-title":"IEEE Transactions on Antennas and Propagation"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1109\/JPROC.2011.2132790","article-title":"Dedicated short-range communications (DSRC) standards in the United States","volume":"99","author":"Kenney","year":"2011","journal-title":"Proc. IEEE"},{"key":"ref13","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"ref9001","volume-title":"Wireless Communications","author":"Molisch","year":"2011"},{"key":"ref14","volume-title":"Machine learning: A probabilistic perspective","author":"Murphy","year":"2012"},{"key":"ref9002","first-page":"128","article-title":"ANN microcell electric field level prediction model","volume":"1","author":"Neskovic","year":"2001","journal-title":"Proceedings of EUROCON International Conference on Trends in Communications Technology and Programming"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1109\/TCCN.2017.2765439","article-title":"A machine-learning-based connectivity model for complex terrain large-scale low-power wireless deployments","volume":"3","author":"Oroza","year":"2017","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MWC.2020.9182765","article-title":"Ray-tracing-based path loss models for V2X communication at 5.9 GHz","volume":"27","author":"P\u00e4tzold","year":"2020","journal-title":"IEEE Wirel. Commun."},{"key":"ref9004","volume-title":"Wireless Communications: Principles and Practice","author":"Rappaport","year":"2002"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"45123","DOI":"10.1109\/ACCESS.2022.3165432","article-title":"Path loss models for V2I communications in urban environments: performance analysis and improvements","volume":"10","author":"Tarhuni","year":"2022","journal-title":"IEEE Access"},{"key":"ref9005","doi-asserted-by":"publisher","first-page":"11592","DOI":"10.1109\/TVT.2020.3012345","article-title":"Deep learning-based path loss prediction for urban environments","volume":"69","author":"Thrane","year":"2020","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref18","first-page":"1","article-title":"On the use of support vector machines for the prediction of propagation losses in smart metering systems","author":"Uccellari","year":"2016"},{"key":"ref9006","first-page":"35","article-title":"Received power prediction for suburban environment based on neural network","author":"Wu","year":"2020","journal-title":"Proceedings of the International Conference on Information Networking (ICOIN)"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1109\/TAP.2023.3256789","article-title":"An enhanced Hata model for high-frequency bands (3 GHz\u20136 GHz) in urban environments","volume":"71","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"3541","DOI":"10.3390\/s19163541","article-title":"A real-time channel prediction model based on neural networks for dedicated short-range communications","volume":"19","author":"Zhang","year":"2019","journal-title":"Sensors"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1908","DOI":"10.3390\/app9091908","article-title":"Path loss prediction based on machine learning: principle, method, and data expansion","volume":"9","author":"Zhang","year":"2019","journal-title":"Appl. Sci."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1597981\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T05:24:38Z","timestamp":1752211478000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1597981\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,11]]},"references-count":32,"alternative-id":["10.3389\/frai.2025.1597981"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1597981","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,11]]},"article-number":"1597981"}}