{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T20:48:16Z","timestamp":1785703696157,"version":"3.56.0"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406215"],"award-info":[{"award-number":["62406215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72402156"],"award-info":[{"award-number":["72402156"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Internet of Things"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.iot.2026.101990","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:32:24Z","timestamp":1780327944000},"page":"101990","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["RoadFed: A multimodal federated learning system for improving road safety"],"prefix":"10.1016","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7498-002X","authenticated-orcid":false,"given":"Yachao","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9510-1727","authenticated-orcid":false,"given":"Zhen","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yali","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingwen","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5166-4873","authenticated-orcid":false,"given":"Thar","family":"Baker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.iot.2026.101990_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2024.103996","article-title":"Privacy-preserving federated learning for proactive maintenance of IoT-empowered multi-location smart city facilities","volume":"231","author":"Tan","year":"2024","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.iot.2026.101990_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2025.104134","article-title":"Advanced aerial monitoring and vehicle classification for intelligent transportation systems with YOLOv8 variants","volume":"237","author":"Bakirci","year":"2025","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.iot.2026.101990_bib0003","series-title":"Global Status Report on Road Safety 2023","author":"Organization","year":"2023"},{"key":"10.1016\/j.iot.2026.101990_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.rineng.2025.105844","article-title":"Generative AI-driven edge-cloud system for intelligent road infrastructure inspection","volume":"27","author":"Ejaz","year":"2025","journal-title":"Results Eng."},{"key":"10.1016\/j.iot.2026.101990_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113332","article-title":"Diffusion-based road defect detection model integrating edge information and efficient multi-scale convolution","volume":"178","author":"Wang","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.iot.2026.101990_bib0006","series-title":"Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.iot.2026.101990_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2024.104087","article-title":"Adaptive differential privacy in asynchronous federated learning for aerial-aided edge computing","volume":"235","author":"Zhang","year":"2025","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.iot.2026.101990_bib0008","doi-asserted-by":"crossref","first-page":"8064","DOI":"10.1109\/TCSS.2024.3405556","article-title":"Community awareness personalized federated learning for defect detection","volume":"11","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"issue":"14","key":"10.1016\/j.iot.2026.101990_bib0009","doi-asserted-by":"crossref","first-page":"2223","DOI":"10.1111\/mice.13186","article-title":"Federated learning\u2013based global road damage detection","volume":"39","author":"Saha","year":"2024","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"10.1016\/j.iot.2026.101990_bib0010","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume":"33","author":"Geiping","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3\u20134","key":"10.1016\/j.iot.2026.101990_bib0011","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork","year":"2014","journal-title":"Found. Trends\u00ae Theor. Comput. Sci."},{"issue":"2","key":"10.1016\/j.iot.2026.101990_bib0012","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TII.2021.3073925","article-title":"Privacy threat and defense for federated learning with non-iid data in AIoT","volume":"18","author":"Xiong","year":"2021","journal-title":"IEEE Trans. Ind. Inf."},{"issue":"19","key":"10.1016\/j.iot.2026.101990_bib0013","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1111\/mice.13233","article-title":"Snow-or ice-covered road detection in winter road surface conditions using deep neural networks","volume":"39","author":"Moroto","year":"2024","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"10.1016\/j.iot.2026.101990_bib0014","series-title":"Proceedings of the Winter Conference on Applications of Computer Vision","first-page":"669","article-title":"Interpreting the unexpected: a multimodal framework for out-of-label hazard detection and explanation in autonomous driving","author":"Abbariki","year":"2025"},{"key":"10.1016\/j.iot.2026.101990_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.treng.2024.100228","article-title":"A multimodal deep learning approach for gravel road condition evaluation through image and audio integration","volume":"16","author":"Saeed","year":"2024","journal-title":"Transp. Eng."},{"key":"10.1016\/j.iot.2026.101990_bib0016","unstructured":"L. Zhouxiang, O. Petrosian, Driver assistance system based on multimodal data hazard detection, arXiv preprint arXiv: 2502.03005(2025)."},{"key":"10.1016\/j.iot.2026.101990_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14679","article-title":"Multimodal categorization of crisis events in social media","author":"Abavisani","year":"2020"},{"issue":"20","key":"10.1016\/j.iot.2026.101990_bib0018","doi-asserted-by":"crossref","first-page":"3304","DOI":"10.3390\/electronics11203304","article-title":"Collaborative road damage classification and recognition based on edge computing","volume":"11","author":"Dang","year":"2022","journal-title":"Electronics"},{"key":"10.1016\/j.iot.2026.101990_bib0019","doi-asserted-by":"crossref","first-page":"10512","DOI":"10.1109\/TITS.2025.3544240","article-title":"The real-time pavement distress detection system based on edge-cloud collaborative computing","volume":"26","author":"Liu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.iot.2026.101990_bib0020","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/OJITS.2024.3432176","article-title":"FedRSC: a federated learning analysis for multi-label road surface classifications","volume":"5","author":"Vondikakis","year":"2024","journal-title":"IEEE Open J. Intell. Transp. Syst."},{"key":"10.1016\/j.iot.2026.101990_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108218","article-title":"A hierarchical federated learning framework for collaborative quality defect inspection in construction","volume":"133","author":"Wu","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.iot.2026.101990_bib0022","series-title":"2024 IEEE Smart World Congress (SWC)","first-page":"1446","article-title":"Road damage detection across borders: federated learning insights from Japan, China, Norway and the USA","author":"Dwivedi","year":"2024"},{"key":"10.1016\/j.iot.2026.101990_bib0023","series-title":"International Conference on Machine Learning and Big Data Analytics for IoT Security and Privacy","first-page":"969","article-title":"Assistant driving safety early warning system based on internet of vehicles","author":"Wang","year":"2021"},{"key":"10.1016\/j.iot.2026.101990_bib0024","series-title":"IOP Conference Series: Materials Science and Engineering","first-page":"012017","article-title":"Monitoring of road damage detection systems using image processing methods and Google map","volume":"1010","author":"Sulistyowati","year":"2021"},{"issue":"6","key":"10.1016\/j.iot.2026.101990_bib0025","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1111\/mice.13366","article-title":"Damage-level classification considering both correlation between image and text data and confidence of attention map","volume":"40","author":"Maeda","year":"2025","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"10.1016\/j.iot.2026.101990_bib0026","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1109\/OJITS.2025.3574866","article-title":"Multimodal learning for traffic risk prediction: combining aerial imagery with contextual data","volume":"6","author":"Tian","year":"2025","journal-title":"IEEE Open J. Intell. Transp. Syst."},{"key":"10.1016\/j.iot.2026.101990_bib0027","first-page":"1709","article-title":"QSGD: communication-efficient SGD via gradient quantization and encoding","volume":"30","author":"Alistarh","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.iot.2026.101990_bib0028","unstructured":"Y. Zhao, M. Li, L. Lai, N. Suda, D. Civin, V. Chandra, Federated learning with non-iid data, arXiv preprint arXiv: 1806.00582(2018)."},{"issue":"9","key":"10.1016\/j.iot.2026.101990_bib0029","doi-asserted-by":"crossref","first-page":"16693","DOI":"10.1109\/JIOT.2024.3354942","article-title":"IOFL: intelligent-optimization-based federated learning for non-iid data","volume":"11","author":"Li","year":"2024","journal-title":"IEEE Internet Things J."},{"issue":"10","key":"10.1016\/j.iot.2026.101990_bib0030","doi-asserted-by":"crossref","first-page":"9352","DOI":"10.1109\/TMC.2024.3365295","article-title":"Feature matching data synthesis for non-iid federated learning","volume":"23","author":"Li","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.iot.2026.101990_bib0031","series-title":"International Conference on Advanced Information Networking and Applications","first-page":"501","article-title":"Expectation-maximization estimation for key-value data randomized with local differential privacy","author":"Horigome","year":"2023"},{"key":"10.1016\/j.iot.2026.101990_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2019.101699","article-title":"Distributed K-Means clustering guaranteeing local differential privacy","volume":"90","author":"Xia","year":"2020","journal-title":"Comput. Secur."},{"key":"10.1016\/j.iot.2026.101990_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119717","article-title":"A secure and privacy preserved infrastructure for VANETs based on federated learning with local differential privacy","volume":"652","author":"Batool","year":"2024","journal-title":"Inf. Sci."},{"key":"10.1016\/j.iot.2026.101990_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2024.104165","article-title":"WF-LDPSR: a local differential privacy mechanism based on water-filling for secure release of trajectory statistics data","volume":"148","author":"Li","year":"2025","journal-title":"Comput. Secur."},{"key":"10.1016\/j.iot.2026.101990_bib0035","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1109\/TCE.2024.3444824","article-title":"Ensuring zero trust IoT data privacy: differential privacy in blockchain using federated learning","volume":"71","author":"Hussain","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.iot.2026.101990_bib0036","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"2021","article-title":"FedPAQ: a communication-efficient federated learning method with periodic averaging and quantization","author":"Reisizadeh","year":"2020"},{"key":"10.1016\/j.iot.2026.101990_bib0037","unstructured":"X. Li, K. Huang, W. Yang, S. Wang, Z. Zhang, On the convergence of fedavg on non-iid data, arXiv preprint arXiv: 1907.02189(2019)."},{"key":"10.1016\/j.iot.2026.101990_bib0038","series-title":"Low-Power Computer Vision","first-page":"291","article-title":"A survey of quantization methods for efficient neural network inference","author":"Gholami","year":"2022"},{"key":"10.1016\/j.iot.2026.101990_bib0039","unstructured":"Pytorch, The documents of Dynamic Quantization in Pytorch, 2021 (last accessed January 11, 2024). https:\/\/pytorch.org\/tutorials\/recipes\/recipes\/dynamic_quantization.html."},{"key":"10.1016\/j.iot.2026.101990_bib0040","series-title":"Advances in Neural Information Processing Systems","first-page":"2879","article-title":"Extremal mechanisms for local differential privacy","author":"Kairouz","year":"2014"},{"key":"10.1016\/j.iot.2026.101990_bib0041","series-title":"Proceedings of the Twentieth ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems","first-page":"274","article-title":"Database-friendly random projections","author":"Achlioptas","year":"2001"},{"key":"10.1016\/j.iot.2026.101990_bib0042","series-title":"2024 IEEE International Conference on Web Services (ICWS)","first-page":"799","article-title":"Edge-LLM: a collaborative framework for large language model serving in edge computing","author":"Cai","year":"2024"},{"key":"10.1016\/j.iot.2026.101990_bib0043","series-title":"2025 International Joint Conference on Neural Networks (IJCNN)","first-page":"1","article-title":"LLMs at the edge: performance and efficiency evaluation with ollama on diverse hardware","author":"Huang","year":"2025"},{"key":"10.1016\/j.iot.2026.101990_bib0044","series-title":"Proceedings of the International AAAI Conference on Web and Social Media","article-title":"CrisisMMD: multimodal twitter datasets from natural disasters","volume":"12","author":"Alam","year":"2018"},{"key":"10.1016\/j.iot.2026.101990_bib0045","series-title":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","first-page":"965","article-title":"Federated learning on non-iid data silos: an experimental study","author":"Li","year":"2022"},{"key":"10.1016\/j.iot.2026.101990_bib0046","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.iot.2026.101990_bib0047","series-title":"International Conference on Machine Learning","first-page":"5132","article-title":"Scaffold: stochastic controlled averaging for federated learning","author":"Karimireddy","year":"2020"},{"key":"10.1016\/j.iot.2026.101990_bib0048","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4510","article-title":"MobileNetv2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"10.1016\/j.iot.2026.101990_bib0049","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"issue":"10","key":"10.1016\/j.iot.2026.101990_bib0050","doi-asserted-by":"crossref","first-page":"636","DOI":"10.3390\/ijgi10100636","article-title":"Disaster image classification by fusing multimodal social media data","volume":"10","author":"Zou","year":"2021","journal-title":"ISPRS Int. J. Geo-Inf."},{"issue":"16","key":"10.1016\/j.iot.2026.101990_bib0051","doi-asserted-by":"crossref","first-page":"2489","DOI":"10.3390\/electronics11162489","article-title":"A hybrid multimodal data fusion-based method for identifying gambling websites","volume":"11","author":"Wang","year":"2022","journal-title":"Electronics"},{"key":"10.1016\/j.iot.2026.101990_bib0052","series-title":"Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers","first-page":"693","article-title":"EmbraceNet for activity: a deep multimodal fusion architecture for activity recognition","author":"Choi","year":"2019"},{"key":"10.1016\/j.iot.2026.101990_bib0053","series-title":"Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)","first-page":"62","article-title":"Exploring multimodal features and fusion strategies for analyzing disaster tweets","author":"Pranesh","year":"2022"}],"container-title":["Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2542660526001204?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2542660526001204?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T19:54:24Z","timestamp":1785700464000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2542660526001204"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":53,"alternative-id":["S2542660526001204"],"URL":"https:\/\/doi.org\/10.1016\/j.iot.2026.101990","relation":{},"ISSN":["2542-6605"],"issn-type":[{"value":"2542-6605","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RoadFed: A multimodal federated learning system for improving road safety","name":"articletitle","label":"Article Title"},{"value":"Internet of Things","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.iot.2026.101990","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"101990"}}