{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:32:10Z","timestamp":1776357130999,"version":"3.51.2"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:00:00Z","timestamp":1750291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:p>Contactless Human Activity Recognition (HAR) has played a critical role in smart healthcare and elderly care homes to monitor patient behavior, detect falls or abnormal activities in real time. The effectiveness of non-invasive HAR is often hindered by location-centric variations in Channel State Information (CSI). These variations limit the ability of HAR models to generalize across new unseen cross-domain environments, for instance, a model trained in one location might not perform well in another physical location. To address this challenge, in this study, we present a novel federated learning (FL) algorithm designed to train a robust global model from local datasets in different localizations. The proposed Federated Weighted Averaging for HAR (Fed-WAHAR) algorithm mitigates location-induced disparities, including heterogeneity and non-Independent and Identically Distributed (non-IID) data distributions. Fed-WAHAR employs a dynamic weighting approach based on local models' accuracy to improve global model classification accuracy and reduce convergence time effectively. We evaluated the performance of Fed-WAHAR using various metrics, including accuracy, precision, recall, F1 score, confusion matrix, and convergence analysis. Experimental results demonstrate that Fed-WAHAR achieves an accuracy of 85% in recognizing human activities across different locations, enhancing the ability of model to infer across new unseen locations.<\/jats:p>","DOI":"10.3389\/fncom.2025.1612928","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:32:42Z","timestamp":1750311162000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Generalizing location-centric variations to enhance contactless human activity recognition"],"prefix":"10.3389","volume":"19","author":[{"given":"Fawad","family":"Khan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syed","family":"Yaseen Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jawad","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alanoud","family":"Al Mazroa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adnan","family":"Zahid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammed","family":"Ilyas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qammer Hussain","family":"Abbasi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syed Aziz","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"907","DOI":"10.3390\/s25030907","article-title":"Federated learning for IOMT-enhanced human activity recognition with hybrid LSTM-GRU networks","volume":"25","author":"Albogamy","year":"2025","journal-title":"Sensors"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1109\/TMTT.2025.3544958","article-title":"\u201cImproving vital signs monitoring in real-world environments with w-band phased-array radars,\u201d","author":"Antolinos","year":"2025","journal-title":"IEEE Transactions on Microwave Theory and Techniques"},{"key":"B3","doi-asserted-by":"publisher","first-page":"8119","DOI":"10.3390\/s22218119","article-title":"An overview of indoor localization system for human activity recognition (HAR) in healthcare","volume":"22","author":"Bibb\u00f2","year":"2022","journal-title":"Sensors"},{"key":"B4","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1109\/TMC.2021.3073969","article-title":"RF-based human activity recognition using signal adapted convolutional neural network","volume":"22","author":"Chen","year":"2021","journal-title":"IEEE Trans. Mobile Comput"},{"key":"B5","doi-asserted-by":"publisher","first-page":"3900","DOI":"10.1109\/JBHI.2023.3275438","article-title":"Protohar: prototype guided personalized federated learning for human activity recognition","volume":"27","author":"Cheng","year":"2023","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B6","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1109\/TTHZ.2016.2599075","article-title":"Thz time-domain spectroscopy of human skin tissue for in-body nanonetworks","volume":"6","author":"Chopra","year":"2016","journal-title":"IEEE Trans. Terahertz Sci. Technol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.05173","article-title":"DWFL: enhancing federated learning through dynamic weighted averaging","author":"Chourasia","year":"2024","journal-title":"arXiv"},{"key":"B8","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.compeleceng.2019.02.011","article-title":"An efficient monitoring of eclamptic seizures in wireless sensors networks","volume":"75","author":"Haider","year":"2019","journal-title":"Comput. Electr. Eng"},{"key":"B9","doi-asserted-by":"publisher","first-page":"12628","DOI":"10.1109\/JIOT.2021.3137793","article-title":"WiFederated: scalable WiFi sensing using edge-based federated learning","volume":"9","author":"Hernandez","year":"2021","journal-title":"IEEE Internet Things J"},{"key":"B10","doi-asserted-by":"publisher","first-page":"5806","DOI":"10.3390\/app12125806","article-title":"Weighted averaging federated learning based on example forgetting events in label imbalanced non-IID","volume":"12","author":"Hong","year":"2022","journal-title":"Appl. Sci"},{"key":"B11","doi-asserted-by":"publisher","first-page":"101458","DOI":"10.1016\/j.iot.2024.101458","article-title":"A hybrid deep learning model for uwb radar-based human activity recognition","volume":"29","author":"Khan","year":"2025","journal-title":"Internet Things"},{"key":"B12","doi-asserted-by":"publisher","first-page":"9018","DOI":"10.1109\/JSEN.2022.3160796","article-title":"Non-invasive localization using software-defined radios","volume":"22","author":"Khan","year":"2022","journal-title":"IEEE Sens. J"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27024-1","author":"Klonovs","year":"2015","journal-title":"Distributed Computing and Monitoring Technologies for Older Patients"},{"key":"B14","doi-asserted-by":"publisher","first-page":"27833","DOI":"10.1109\/ACCESS.2025.3540716","article-title":"Advances in non-contact human vital sign detection: a detailed survey of radar and wireless solutions","volume":"13","author":"Kouhalvandi","year":"2025","journal-title":"IEEE Access"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/s12028-025-02230-3","article-title":"Utility and value of movement recording with combined EEG-EMG monitoring in the intensive care unit","author":"L\u00e9vi-Strauss","year":"2025","journal-title":"Neurocrit. Care"},{"key":"B16","doi-asserted-by":"publisher","first-page":"927","DOI":"10.3390\/s140100927","article-title":"Precise point positioning with the BeiDou navigation satellite system","volume":"14","author":"Li","year":"2014","journal-title":"Sensors"},{"key":"B17","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1674","DOI":"10.1109\/TMC.2023.3242324","article-title":"Towards collaborative and cross-domain Wi-Fi sensing: a case study for human activity recognition","volume":"23","author":"Li","year":"2023","journal-title":"IEEE Trans. Mobile Comput"},{"key":"B19","first-page":"1","article-title":"\u201cA research on csi-based human motion detection in complex scenarios,\u201d","volume-title":"2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom)","author":"Liu","year":"2017"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/TMTT.2025.3542183","article-title":"\u201cGait symmetry analysis with FMCW MIMO radar,\u201d","author":"L\u00f3pez-Delgado","year":"2025","journal-title":"IEEE Transactions on Microwave Theory and Techniques"},{"key":"B21","doi-asserted-by":"publisher","first-page":"102125","DOI":"10.1016\/j.sysarc.2021.102125","article-title":"Fast-convergent federated learning with class-weighted aggregation","volume":"117","author":"Ma","year":"2021","journal-title":"J. Syst. Architect"},{"key":"B22","doi-asserted-by":"publisher","first-page":"4507","DOI":"10.3390\/s19204507","article-title":"A meta-review of indoor positioning systems","volume":"19","author":"Mendoza-Silva","year":"2019","journal-title":"Sensors"},{"key":"B23","doi-asserted-by":"publisher","first-page":"4363","DOI":"10.18203\/2394-6040.ijcmph20175306","article-title":"An ageing world of the 21st century: a literature review","volume":"4","author":"Naja","year":"2017","journal-title":"Int. J. Community Med. Public Health"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3554980","article-title":"Clusterfl: a clustering-based federated learning system for human activity recognition","volume":"19","author":"Ouyang","year":"2022","journal-title":"ACM Trans. Sens. Netw"},{"key":"B25","doi-asserted-by":"publisher","first-page":"12041","DOI":"10.1109\/JSEN.2023.3265867","article-title":"Software-defined radio-based contactless localization for diverse human activity recognition","volume":"23","author":"Saeed","year":"2023","journal-title":"IEEE Sens. J"},{"key":"B26","doi-asserted-by":"publisher","first-page":"5217","DOI":"10.1109\/TVT.2018.2810307","article-title":"Accurate location tracking from CSI-based passive device-free probabilistic fingerprinting","volume":"67","author":"Shi","year":"2018","journal-title":"IEEE Tran. Veh. Technol"},{"key":"B27","doi-asserted-by":"crossref","first-page":"1698","DOI":"10.1109\/ICIRCA51532.2021.9544975","article-title":"\u201cBluetooth low energy based indoor positioning system using esp32,\u201d","volume-title":"2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA)","author":"Sophia","year":"2021"},{"key":"B28","first-page":"1103","article-title":"\u201cHuman activity recognition using federated learning,\u201d","volume-title":"2018 IEEE Intl Conf on Parallel &Distributed Processing with Applications, Ubiquitous Computing &Communications, Big Data &Cloud Computing, Social Computing &Networking, Sustainable Computing &Communications (ISPA\/IUCC\/BDCloud\/SocialCom\/SustainCom)","author":"Sozinov","year":"2018"},{"key":"B29","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1145\/2809695.2809718","article-title":"\u201cSmart devices are different: assessing and mitigatingmobile sensing heterogeneities for activity recognition,\u201d","volume-title":"Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems","author":"Stisen","year":"2015"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2653","DOI":"10.3390\/s20092653","article-title":"An intelligent non-invasive real-time human activity recognition system for next-generation healthcare","volume":"20","author":"Taylor","year":"2020","journal-title":"Sensors"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3377165","article-title":"On CSI-based vital sign monitoring using commodity wifi","volume":"1","author":"Wang","year":"2020","journal-title":"ACM Trans. Comput. Healthc"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3465593","article-title":"Enhancing human activity recognition with FEDPA: focusing on non-IID data challenges in federated learning","author":"Wen","year":"2024","journal-title":"IEEE Sens. J"},{"key":"B33","doi-asserted-by":"publisher","first-page":"107338","DOI":"10.1016\/j.knosys.2021.107338","article-title":"A federated learning system with enhanced feature extraction for human activity recognition","volume":"229","author":"Xiao","year":"2021","journal-title":"Knowl.-Based Syst"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2676430","article-title":"Mobility increases localizability: a survey on wireless indoor localization using inertial sensors","volume":"47","author":"Yang","year":"2015","journal-title":"ACM Comput. Surv"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2543581.2543592","article-title":"From RSSI to CSI: indoor localization via channel response","volume":"46","author":"Yang","year":"2013","journal-title":"ACM Comput. Surv"},{"key":"B36","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1080\/08839514.2016.1138787","article-title":"Human activity recognition using tag-based radio frequency localization","volume":"30","author":"Yurtman","year":"2016","journal-title":"Appl. Artif. Intell"},{"key":"B37","doi-asserted-by":"publisher","first-page":"117821","DOI":"10.1016\/j.measurement.2025.117821","article-title":"Federated learning framework for Wi-Fi-based cross-environment human action recognition","volume":"253","author":"Zhang","year":"2025","journal-title":"Measurement"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2025.1612928\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:32:45Z","timestamp":1750311165000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2025.1612928\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,19]]},"references-count":37,"alternative-id":["10.3389\/fncom.2025.1612928"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2025.1612928","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,19]]},"article-number":"1612928"}}