Sparse Federated Learning-Enabled Multimodal Human-Centric Traffic Systems: Resolving Privacy and Cross-Regional Adaptation Issues in ITS

Sparse Federated Learning-Enabled Multimodal Human-Centric Traffic Systems: Resolving Privacy and Cross-Regional Adaptation Issues in ITS | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 20 November 2025 V1 Latest version Share on Sparse Federated Learning-Enabled Multimodal Human-Centric Traffic Systems: Resolving Privacy and Cross-Regional Adaptation Issues in ITS Author : Daniele Pillan 0009-0005-2131-2980 [email protected] Authors Info & Affiliations https://doi.org/10.22541/au.176365740.09019219/v1 84 views 55 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Intelligent Transportation Systems (ITS) face persistent barriers to large-scale deployment: privacy risks arising from centralized data processing, excessive communication costs, poor adaptability to heterogeneous cross-regional traffic patterns, and insufficient integration of human-centric design. To address these interconnected challenges in a comprehensive manner, this paper presents a human-centric traffic system built on sparse federated learning (FL). The system's FL backbone employs adaptive weight pruning to significantly reduce data transmission scale, while integrating few-shot aggregation technology to enable rapid adaptation to traffic scenarios in new regions. For optimized human-machine interaction, multimodal modules are integrated into the system: a context-gated spoken language understanding module parses driver commands with high accuracy, a zero-shot recommendation module provides personalized travel suggestions tailored to individual preferences, and a VR-based interface effectively alleviates drivers ' cognitive load. Furthermore, driver state inference-supported by physiological signal analysis-dynamically adjusts alert mechanisms based on the driver ' s real-time status, further enhancing driving safety. A standardized SBM-DEA evaluation framework is utilized to comprehensively assess the system ' s performance across three key dimensions: technical efficiency (including prediction accuracy and communication cost), user experience (covering satisfaction and cognitive load), and adaptability (encompassing adaptation time and error reduction). Experimental results on the METR-LA and PEMS-BAY datasets demonstrate that the system achieves a mean absolute error (MAE) of 2.30, a communication cost of 18.1 MB per round, and an SBM-DEA efficiency score of 0.89-outperforming baseline models such as FedAvg, FedFewShot, and SparseFed. This work delivers a scalable and practical solution for modern ITS, which seamlessly combines privacy protection, strong cross-regional adaptability, and human-centric design principles. Supplementary Material File (manuscript2(1).pdf) Download 261.86 KB Information & Authors Information Version history V1 Version 1 20 November 2025 Copyright This work is licensed under a Creative Commons Attribution 4.0 International License Keywords cross-regional few-shot adaptation human-centric intelligent transportation systems multimodal human-machine interaction sbm-dea evaluation sparse federated learning Authors Affiliations Daniele Pillan 0009-0005-2131-2980 [email protected] View all articles by this author Metrics & Citations Metrics Article Usage 84 views 55 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Daniele Pillan. Sparse Federated Learning-Enabled Multimodal Human-Centric Traffic Systems: Resolving Privacy and Cross-Regional Adaptation Issues in ITS. Authorea . 20 November 2025. DOI: https://doi.org/10.22541/au.176365740.09019219/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.176365740.09019219/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a00ca04e4a48df88',t:'MTc3OTYyOTEyNA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();