{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T16:58:36Z","timestamp":1791565116906,"version":"4.3.4"},"reference-count":18,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University-Industry Collaborative Education Program of the Ministry of Education, China","award":["231104472272600"],"award-info":[{"award-number":["231104472272600"]}],"id":[{"id":"https:\/\/ror.org\/03m01yf64","id-type":"ROR","asserted-by":"crossref"}]},{"name":"UESTC-ZHIXIAOJING Joint Research Center of Smart Home","award":["H04W210180"],"award-info":[{"award-number":["H04W210180"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human Activity Recognition (HAR) in smart home environments is essential for Ambient Assisted Living (AAL). However, existing methods utilizing Graph Neural Networks (GNNs) typically rely on static sensor topologies and fail to adequately capture the dynamic spatio-temporal dependencies and heterogeneous nature of multi-sensor data. To address these challenges, this paper proposes a Dynamic Spatio-Temporal Graph Attention Network (DSTGAT) for robust HAR in smart homes. First, a multi-modal feature embedding mechanism is introduced to unify temporal, spatial, sensor type, and observation data into a cohesive representation. Second, a Cascade-LSTM architecture, combining bidirectional and unidirectional LSTMs, is designed to model the asymmetric temporal dependencies of human activities. Furthermore, to overcome the limitations of fixed graphs, a dynamic graph learning module based on Gumbel-Softmax sampling is proposed to adaptively reconstruct the sensor adjacency matrix. Finally, a Talking-Head graph attention mechanism is employed to facilitate cross-head feature interaction, enhancing global semantic fusion. Extensive experiments on four public CASAS smart home datasets (Aruba, Milan, Cairo, and Kyoto7) demonstrate that DSTGAT attains the highest F1 score on all four datasets, with improvements of 2.70 to 9.26 percentage points over the strongest baseline on each dataset; repeated runs with paired statistical tests confirm that these margins are significant on three of the four datasets (p &lt; 0.01). Additionally, the proposed model degrades by no more than 0.6 percentage points with 30% missing sensor data on three of the four datasets. This research provides a highly efficient and reliable solution for non-intrusive activity monitoring in smart home deployments.<\/jats:p>","DOI":"10.3390\/s26196191","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:33:12Z","timestamp":1790699592000},"page":"6191","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DSTGAT: A Spatio-Temporal Dynamic Graph Attention Network for User Activity Recognition"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4460-3722","authenticated-orcid":false,"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]},{"given":"Maoquan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Jinming","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Chunjie","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Software Engineering, Chengdu Jincheng College, Chengdu 611731, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103859","DOI":"10.1016\/j.engappai.2020.103859","article-title":"Sensor-based activity recognition of solitary elderly via stigmergy and two-layer framework","volume":"95","author":"Xu","year":"2020","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1145\/3472290","article-title":"A Survey on Deep Learning for Human Activity Recognition","volume":"54","author":"Gu","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Comai, S., Cortinovis, M., Girelli, R., and Salice, F. (2025). Noninvasive Acoustic Recognition of Water Flow Sources for Human Activity Monitoring in Smart Homes. Sensors, 25.","DOI":"10.3390\/s25196221"},{"key":"ref_4","first-page":"48","article-title":"Evaluating Machine Learning Techniques for Activity Classification in Smart Home Environments","volume":"12","author":"Alshammari","year":"2018","journal-title":"Int. J. Inf. Syst. Comput. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MC.2012.328","article-title":"CASAS: A Smart Home in a Box","volume":"46","author":"Cook","year":"2013","journal-title":"Computer"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"179","DOI":"10.3233\/AIS-210384","article-title":"Computational methods for predicting human behaviour in smart environments","volume":"15","author":"Dunne","year":"2023","journal-title":"J. Ambient Intell. Smart Environ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"85154","DOI":"10.1109\/ACCESS.2022.3197618","article-title":"Future Activities Prediction Framework in Smart Homes Environment","volume":"10","author":"Mohamed","year":"2022","journal-title":"IEEE Access"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"56855","DOI":"10.1109\/ACCESS.2020.2982225","article-title":"LSTM-CNN Architecture for Human Activity Recognition","volume":"8","author":"Xia","year":"2020","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1109\/JBHI.2020.3027967","article-title":"Fall Detection with UWB Radars and CNN-LSTM Architecture","volume":"25","author":"Maitre","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"7414","DOI":"10.1038\/s41598-024-57912-3","article-title":"TCN-attention-HAR: Human Activity Recognition Based on Attention Mechanism Time Convolutional Network","volume":"14","author":"Wei","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ye, J., Jiang, H., and Zhong, J. (2023). A Graph-Attention-Based Method for Single-Resident Daily Activity Recognition in Smart Homes. Sensors, 23.","DOI":"10.3390\/s23031626"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"P, S., and Pl\u00f6tz, T. (2024). Using Graphs to Perform Effective Sensor-Based Human Activity Recognition in Smart Homes. Sensors, 24.","DOI":"10.3390\/s24123944"},{"key":"ref_13","unstructured":"Battaglia, P.W., Hamrick, J.B., Bapst, V., Sanchez-Gonzalez, A., Zambaldi, V., Malinowski, M., Tacchetti, A., Raposo, D., Santoro, A., and Faulkner, R. (2018). Relational inductive biases, deep learning, and graph networks. arXiv."},{"key":"ref_14","first-page":"7444","article-title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","volume":"32","author":"Yan","year":"2018","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4300","DOI":"10.1007\/s10489-021-02648-0","article-title":"Adaptive spatial-temporal graph attention networks for traffic flow forecasting","volume":"52","author":"Kong","year":"2021","journal-title":"Appl. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bouchabou, D., Nguyen, S.M., Lohr, C., LeDuc, B., and Kanellos, I. (2021). Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes. Electronics, 10.","DOI":"10.3390\/electronics10202498"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1016\/j.neucom.2018.10.104","article-title":"A sequential deep learning application for recognising human activities in smart homes","volume":"396","author":"Liciotti","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, X., and Zhang, S. (2023, January 17\u201319). Human Activity Recognition based on Transformer in Smart Home. Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning, New York, NY, USA. CACML \u201923.","DOI":"10.1145\/3590003.3590100"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6191\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T16:44:22Z","timestamp":1791564262000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":18,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196191"],"URL":"https:\/\/doi.org\/10.3390\/s26196191","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]}}}