{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T21:30:30Z","timestamp":1773869430120,"version":"3.50.1"},"reference-count":56,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.131992","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:26:14Z","timestamp":1773361574000},"page":"131992","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Robust federated learning for dynamic and heterogeneous environments: an adaptive client selection approach"],"prefix":"10.1016","volume":"318","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2324-0030","authenticated-orcid":false,"given":"Rui","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0636-5084","authenticated-orcid":false,"given":"Dongyang","family":"Bao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0900-2340","authenticated-orcid":false,"given":"Ning","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8529-3399","authenticated-orcid":false,"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131992_bib0001","series-title":"International conference on learning representations","article-title":"Federated learning based on dynamic regularization","author":"Acar","year":"2021"},{"key":"10.1016\/j.eswa.2026.131992_bib0002","article-title":"Enhancing federated learning in connected and autonomous vehicles through cost optimization and advanced model selection","author":"Cai","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.131992_bib0003","article-title":"LEAF: A benchmark for federated settings","volume":"abs\/1812.01097","author":"Caldas","year":"2018","journal-title":"CoRR"},{"key":"10.1016\/j.eswa.2026.131992_bib0004","doi-asserted-by":"crossref","first-page":"65525","DOI":"10.52202\/079017-2093","article-title":"Heterogeneity-guided client sampling: Towards fast and efficient non-iid federated learning","volume":"37","author":"Chen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131992_bib0005","article-title":"Client selection for wireless federated learning with data and latency heterogeneity","author":"Chen","year":"2024","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.eswa.2026.131992_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.iot.2023.100729","article-title":"An evaluation methodology to determine the actual limitations of a tinyml-based solution","volume":"22","author":"Delnevo","year":"2023","journal-title":"Internet of Things"},{"issue":"1","key":"10.1016\/j.eswa.2026.131992_bib0007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the em algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"Journal of the Royal Statistical Society: Series B (methodological)"},{"issue":"6","key":"10.1016\/j.eswa.2026.131992_bib0008","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.eswa.2026.131992_bib0009","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/PROC.1973.9030","article-title":"The viterbi algorithm","volume":"61","author":"Forney","year":"2005","journal-title":"Proceedings of the IEEE"},{"issue":"9","key":"10.1016\/j.eswa.2026.131992_bib0010","doi-asserted-by":"crossref","first-page":"10650","DOI":"10.1109\/TPAMI.2023.3262813","article-title":"Automatic transformation search against deep leakage from gradients","volume":"45","author":"Gao","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"10.1016\/j.eswa.2026.131992_bib0011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3708984","article-title":"Fedpref: Federated learning across heterogeneous multi-objective preferences","volume":"10","author":"Hartmann","year":"2025","journal-title":"ACM Transactions on Modeling and Performance Evaluation of Computing Systems"},{"key":"10.1016\/j.eswa.2026.131992_bib0012","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13935","article-title":"Trail: Trust-aware client scheduling for semi-decentralized federated learning","volume":"39","author":"Hu","year":"2025"},{"issue":"1","key":"10.1016\/j.eswa.2026.131992_bib0013","doi-asserted-by":"crossref","first-page":"7128","DOI":"10.1038\/s41467-025-62491-6","article-title":"Using an ordinary differential equation model to separate rest and task signals in FMRI","volume":"16","author":"Kashyap","year":"2025","journal-title":"Nature Communications"},{"key":"10.1016\/j.eswa.2026.131992_bib0014","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.eswa.2026.131992_bib0015","doi-asserted-by":"crossref","first-page":"2340","DOI":"10.1109\/TIFS.2024.3350375","article-title":"Deep learning gradient visualization-based pre-silicon side-channel leakage location","volume":"19","author":"Li","year":"2024","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"10.1016\/j.eswa.2026.131992_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2024.104161","article-title":"A robust federated learning algorithm for partially trusted environments","volume":"148","author":"Li","year":"2025","journal-title":"Computers & Security"},{"key":"10.1016\/j.eswa.2026.131992_bib0017","article-title":"Fedphe: A secure and efficient federated learning via packed homomorphic encryption","author":"Li","year":"2025","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"10.1016\/j.eswa.2026.131992_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10154","article-title":"Rscfed: Random sampling consensus federated semi-supervised learning","author":"Liang","year":"2022"},{"key":"10.1016\/j.eswa.2026.131992_bib0019","series-title":"2025 IEEE 41st international conference on data engineering (ICDE)","first-page":"2575","article-title":"Fedecover: Fast and stable converging model-heterogeneous federated learning with efficient-coverage submodel extraction","author":"Liang","year":"2025"},{"key":"10.1016\/j.eswa.2026.131992_bib0020","series-title":"Proceedings of the ACM web conference 2024","first-page":"2936","article-title":"Incentive and dynamic client selection for federated unlearning","author":"Lin","year":"2024"},{"key":"10.1016\/j.eswa.2026.131992_bib0021","series-title":"IEEE INFOCOM 2022 - IEEE conference on computer communications","first-page":"1739","article-title":"Tackling system and statistical heterogeneity for federated learning with adaptive client sampling","author":"Luo","year":"2022"},{"issue":"12","key":"10.1016\/j.eswa.2026.131992_bib0022","doi-asserted-by":"crossref","first-page":"3654","DOI":"10.1109\/JSAC.2021.3118435","article-title":"Fedsa: A semi-asynchronous federated learning mechanism in heterogeneous edge computing","volume":"39","author":"Ma","year":"2021","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"10.1016\/j.eswa.2026.131992_bib0023","series-title":"2022 29th IEEE international conference on electronics, circuits and systems (ICECS)","first-page":"1","article-title":"Fedclamp: An algorithm for identification of anomalous client in federated learning","author":"Manzoor","year":"2022"},{"issue":"11","key":"10.1016\/j.eswa.2026.131992_bib0024","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000436","article-title":"A recurrent neural network and parallel hidden markov model algorithm to segment and detect heart murmurs in phonocardiograms","volume":"3","author":"McDonald","year":"2024","journal-title":"PLOS Digital Health"},{"key":"10.1016\/j.eswa.2026.131992_bib0025","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.eswa.2026.131992_bib0026","series-title":"Adjunct proceedings of the 2023 ACM international joint conference on pervasive and ubiquitous computing & the 2023 ACM international symposium on wearable computing","first-page":"246","article-title":"Assessment and analysis of wearables and companion mobile (health) applications: A usability evaluation framework","author":"Moorthy","year":"2023"},{"issue":"6","key":"10.1016\/j.eswa.2026.131992_bib0027","doi-asserted-by":"crossref","first-page":"6538","DOI":"10.1109\/TMC.2023.3323645","article-title":"Contextual client selection for efficient federated learning over edge devices","volume":"23","author":"Pan","year":"2023","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"10.1016\/j.eswa.2026.131992_bib0028","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"2002","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.eswa.2026.131992_bib0029","series-title":"International conference on machine learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.eswa.2026.131992_bib0030","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12279","article-title":"Relaxed contrastive learning for federated learning","author":"Seo","year":"2024"},{"key":"10.1016\/j.eswa.2026.131992_bib0031","series-title":"Proceedings of the 20th annual international conference on mobile systems, applications and services (MobiSys)","first-page":"436","article-title":"Fedbalancer: Data and pace control for efficient federated learning on heterogeneous clients","author":"Shin","year":"2022"},{"key":"10.1016\/j.eswa.2026.131992_bib0032","doi-asserted-by":"crossref","unstructured":"Sun, Y., Sun, A., Pan, S., Fu, Z., Guo, J., 2025. Fedapa: Server-side gradient-based adaptive personalized aggregation for federated learning on heterogeneous data.arXiv: 2502.07456.","DOI":"10.24963\/ijcai.2025\/692"},{"key":"10.1016\/j.eswa.2026.131992_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"23763","article-title":"Adapted weighted aggregation in federated learning","volume":"38","author":"Tang","year":"2024"},{"key":"10.1016\/j.eswa.2026.131992_bib0034","unstructured":"F. Team, 2023. On-device federated finetuning for speech classification. accessed: 2023-10-15. https:\/\/flower.ai\/docs\/examples\/whisper-federated-finetuning.html."},{"key":"10.1016\/j.eswa.2026.131992_bib0035","series-title":"Proceedings of the 41st international conference on machine learning","article-title":"Ranking-based client imitation selection for efficient federated learning","author":"Tian","year":"2024"},{"issue":"17","key":"10.1016\/j.eswa.2026.131992_bib0036","doi-asserted-by":"crossref","first-page":"28480","DOI":"10.1109\/JIOT.2024.3403082","article-title":"Client selection in hierarchical federated learning","volume":"11","author":"Trindade","year":"2024","journal-title":"IEEE Internet of Things Journal"},{"issue":"7","key":"10.1016\/j.eswa.2026.131992_bib0037","doi-asserted-by":"crossref","first-page":"3797","DOI":"10.1109\/TIT.2014.2320500","article-title":"R\u00e9nyi divergence and Kullback-Leibler divergence","volume":"60","author":"Van Erven","year":"2014","journal-title":"IEEE Transactions on Information Theory"},{"key":"10.1016\/j.eswa.2026.131992_bib0038","series-title":"International conference on artificial intelligence and statistics","first-page":"6459","article-title":"Qlsd: Quantised langevin stochastic dynamics for bayesian federated learning","author":"Vono","year":"2022"},{"key":"10.1016\/j.eswa.2026.131992_bib0039","series-title":"IEEE INFOCOM 2020 - IEEE conference on computer communications","first-page":"1698","article-title":"Optimizing federated learning on non-iid data with reinforcement learning","author":"Wang","year":"2020"},{"key":"10.1016\/j.eswa.2026.131992_bib0040","series-title":"INFOCOM","first-page":"1","article-title":"Fedmos: Taming client drift in federated learning with double momentum and adaptive selection","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.131992_bib0041","series-title":"Proceedings of the ACM web conference 2024","first-page":"2902","article-title":"Feddse: Distribution-aware sub-model extraction for federated learning over resource-constrained devices","author":"Wang","year":"2024"},{"issue":"2","key":"10.1016\/j.eswa.2026.131992_bib0042","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1109\/TBDATA.2024.3423677","article-title":"A survey on truth discovery: Concepts, methods, applications, and opportunities","volume":"11","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.eswa.2026.131992_bib0043","series-title":"Proceedings of the thirty-ninth AAAI conference on artificial intelligence and thirty-seventh conference on innovative applications of artificial intelligence and fifteenth symposium on educational advances in artificial intelligence","article-title":"Reinforcement active client selection for federated heterogeneous graph learning","author":"Wang","year":"2025"},{"key":"10.1016\/j.eswa.2026.131992_bib0044","article-title":"Speech commands: a dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"ArXiv e-prints"},{"issue":"4","key":"10.1016\/j.eswa.2026.131992_bib0045","doi-asserted-by":"crossref","first-page":"6814","DOI":"10.1109\/TII.2024.3353848","article-title":"Virtual network embedding for task offloading in IIoT: A drl-assisted federated learning scheme","volume":"20","author":"Wu","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.131992_bib0046","unstructured":"Xiao, H., Rasul, K., Vollgraf, R., 2017. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. http:\/\/arxiv.org\/abs\/cs.LG\/1708.07747arXiv:cs.LG\/1708.07747."},{"issue":"12","key":"10.1016\/j.eswa.2026.131992_bib0047","doi-asserted-by":"crossref","first-page":"4835","DOI":"10.1109\/TPDS.2022.3205714","article-title":"Tdfl: Truth discovery based byzantine robust federated learning","volume":"33","author":"Xu","year":"2022","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"10.1016\/j.eswa.2026.131992_bib0048","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v39i20.35480","article-title":"Federated learning with sample-level client drift mitigation","author":"Xu","year":"2025"},{"key":"10.1016\/j.eswa.2026.131992_bib0049","article-title":"Update if you dare: Demystifying bare-metal device firmware update security of appified IoT systems","author":"Xue","year":"2024","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"10.1016\/j.eswa.2026.131992_bib0050","doi-asserted-by":"crossref","first-page":"5182","DOI":"10.1109\/TKDE.2021.3054853","article-title":"An unsupervised bayesian neural network for truth discovery in social networks","volume":"34","author":"Yang","year":"2021","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"9","key":"10.1016\/j.eswa.2026.131992_bib0051","doi-asserted-by":"crossref","first-page":"4411","DOI":"10.1109\/TKDE.2023.3332770","article-title":"Aifed: An adaptive and integrated mechanism for asynchronous federated data mining","volume":"36","author":"You","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"1","key":"10.1016\/j.eswa.2026.131992_bib0052","doi-asserted-by":"crossref","first-page":"3739","DOI":"10.1038\/s41467-025-59217-z","article-title":"A framework reforming personalized internet of things by federated meta-learning","volume":"16","author":"You","year":"2025","journal-title":"Nature Communications"},{"key":"10.1016\/j.eswa.2026.131992_bib0053","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"9091","article-title":"A multi-agent reinforcement learning approach for efficient client selection in federated learning","volume":"36","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.131992_bib0054","first-page":"3921","article-title":"Understanding deep gradient leakage via inversion influence functions","volume":"36","author":"Zhang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131992_bib0055","series-title":"International conference on machine learning","first-page":"41399","article-title":"No one idles: Efficient heterogeneous federated learning with parallel edge and server computation","author":"Zhang","year":"2023"},{"issue":"2","key":"10.1016\/j.eswa.2026.131992_bib0056","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742600905X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742600905X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:12:45Z","timestamp":1773843165000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095741742600905X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":56,"alternative-id":["S095741742600905X"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131992","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Robust federated learning for dynamic and heterogeneous environments: an adaptive client selection approach","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131992","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"131992"}}