{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:57:11Z","timestamp":1790269031240,"version":"4.1.0"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"name":"Natural Science Foundation of Jiangsu Province, China","award":["BK20230477"],"award-info":[{"award-number":["BK20230477"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62106167"],"award-info":[{"award-number":["62106167"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62332013"],"award-info":[{"award-number":["62332013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"},{"DOI":"10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012246","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Suzhou Frontier Science and Technology Program","award":["SYG202310"],"award-info":[{"award-number":["SYG202310"]}]},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"crossref","award":["2022-04123"],"award-info":[{"award-number":["2022-04123"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"crossref"}]},{"name":"EU MSCA","award":["101086219"],"award-info":[{"award-number":["101086219"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Sen. Netw."],"published-print":{"date-parts":[[2026,5,30]]},"abstract":"<jats:p>\n                    WiFi-based human activity recognition (HAR) holds significant promise for ubiquitous sensing in smart environments. A critical challenge is enabling systems to dynamically adapt to evolving scenarios, learn new activities without catastrophically forgetting prior knowledge, and meet edge devices\u2019 computational constraints. Current approaches struggle to reconcile these due to high historical data storage demands and inefficient parameter utilization. We propose WECAR, an end-edge collaborative inference and training framework for WiFi-based continuous HAR. In this framework, edge devices handle model training, lightweight optimization, and updates, while end devices perform efficient inference. WECAR introduces two key innovations, i.e., dynamic continual learning with parameter efficiency and hierarchical distillation for end deployment. For the former, we propose a transformer-based architecture enhanced by task-specific dynamic model expansion and stability-aware selective retraining. For the latter, we propose a dual-phase distillation mechanism that includes multi-head self-attention relation distillation and prefix relation distillation. We implement WECAR based on heterogeneous hardware using\n                    <jats:italic toggle=\"yes\">Jetson Nano<\/jats:italic>\n                    as edge devices and the\n                    <jats:italic toggle=\"yes\">ESP32<\/jats:italic>\n                    as end devices, respectively. Our experiments across three public WiFi datasets reveal that WECAR not only outperforms several state-of-the-art methods in performance and parameter efficiency, but also achieves a substantial reduction in the model\u2019s parameter count post-optimization without sacrificing accuracy.\n                  <\/jats:p>","DOI":"10.1145\/3799718","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T11:46:00Z","timestamp":1772192760000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["WECAR: An End-Edge Collaborative Inference and Training Framework for WiFi-Based Continuous Human Activity Recognition"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1646-6141","authenticated-orcid":false,"given":"Rong","family":"Li","sequence":"first","affiliation":[{"name":"Soochow University School of Computer Science and Technology","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0122-5247","authenticated-orcid":false,"given":"Tao","family":"Deng","sequence":"additional","affiliation":[{"name":"Soochow University School of Computer Science and Technology","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4286-4793","authenticated-orcid":false,"given":"Siwei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2768-6607","authenticated-orcid":false,"given":"He","family":"Huang","sequence":"additional","affiliation":[{"name":"Soochow University School of Computer Science and Technology","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8276-7640","authenticated-orcid":false,"given":"Juncheng","family":"Jia","sequence":"additional","affiliation":[{"name":"School of of Computer Science and Technology, Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8119-5206","authenticated-orcid":false,"given":"Di","family":"Yuan","sequence":"additional","affiliation":[{"name":"Uppsala University Department of Information Technology","place":["Uppsala, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-4048","authenticated-orcid":false,"given":"Keqin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, State University of New York","place":["New Paltz, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2013.31"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708323"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3529897"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2984320"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3279608"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715130"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2878233"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-9376-8_1"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3438454"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Kai Zhu Wei Zhai Yang Cao Jiebo Luo and Zheng-Jun Zha. 2022. Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning. (2022). arXiv:2203.06359. Retrieved from https:\/\/arxiv.org\/abs\/2203.06359","DOI":"10.1109\/CVPR52688.2022.00908"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02695"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/APWiMob.2014.6920266"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218525"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3377708"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.7"},{"key":"e_1_3_1_18_2","unstructured":"Fei Wang Stanislav Panev Ziyi Dai Jinsong Han and Dong Huang. 2019. Can WiFi estimate person pose? arXiv:1904.00277. Retrieved from https:\/\/arxiv.org\/abs\/1904.00277"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23073591"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3132622"},{"key":"e_1_3_1_24_2","unstructured":"Andrei A. Rusu Neil C. Rabinowitz Guillaume Desjardins Hubert Soyer James Kirkpatrick Koray Kavukcuoglu Razvan Pascanu and Raia Hadsell. 2016. Progressive neural networks. arXiv:1606.04671. Retrieved from https:\/\/arxiv.org\/abs\/1606.04671"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_25"},{"key":"e_1_3_1_27_2","first-page":"1093","volume-title":"International Conference on Machine Learning","author":"Asadi Nader","year":"2023","unstructured":"Nader Asadi, MohammadReza Davari, Sudhir Mudur, Rahaf Aljundi, and Eugene Belilovsky. 2023. Prototype-sample relation distillation: Towards replay-free continual learning. In International Conference on Machine Learning. 1093\u20131106."},{"key":"e_1_3_1_28_2","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in Neural Information Processing Systems 33 (2020), 18661\u201318673.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"e_1_3_1_29_2","first-page":"857","article-title":"Self-supervised learning: Generative or contrastive","volume":"35","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, and Jie Tang. 2021. Self-supervised learning: Generative or contrastive. IEEE Transactions on Knowledge and Data Engineering 35, 1 (2021), 857\u2013876.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00814"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00542"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08389-0"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3278091"},{"key":"e_1_3_1_34_2","unstructured":"Qunhang Fu Fei Wang Mengdie Zhu Han Ding Jinsong Han and Tony Xiao Han. 2024. CCS: Continuous Learning for Customized Incremental Wireless Sensing Services. (2024). arXiv:2412.04821. Retrieved from https:\/\/arxiv.org\/abs\/2412.04821"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3593406"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3613290"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643832.3661889"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3749477"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33565"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16103"},{"key":"e_1_3_1_41_2","unstructured":"Bruce X. B. Yu Jianlong Chang Lingbo Liu Qi Tian and Chang Wen Chen. 2022. Towards a unified view on visual parameter-efficient transfer learning. arXiv:2210.00788. Retrieved from https:\/\/arxiv.org\/abs\/2210.00788"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6452-2_1"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2947024"},{"key":"e_1_3_1_44_2","article-title":"MM-Fi: Multi-modal non-intrusive 4D human dataset for versatile wireless sensing","volume":"36","author":"Yang Jianfei","year":"2024","unstructured":"Jianfei Yang, He Huang, Yunjiao Zhou, Xinyan Chen, Yuecong Xu, Shenghai Yuan, Han Zou, Chris Xiaoxuan Lu, and Lihua Xie. 2024. MM-Fi: Multi-modal non-intrusive 4D human dataset for versatile wireless sensing. Advances in Neural Information Processing Systems 36 (2024), 18756\u201318768.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643552"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"e_1_3_1_48_2","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et\u00a0al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems 32 (2019), 1\u201312.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_49_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"}],"container-title":["ACM Transactions on Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T10:51:27Z","timestamp":1774867887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,30]]}},"alternative-id":["10.1145\/3799718"],"URL":"https:\/\/doi.org\/10.1145\/3799718","relation":{},"ISSN":["1550-4859","1550-4867"],"issn-type":[{"value":"1550-4859","type":"print"},{"value":"1550-4867","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"2025-10-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}