{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T17:46:25Z","timestamp":1791740785358,"version":"4.3.4"},"reference-count":33,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Technology and Health Care"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>AI-driven healthcare monitoring systems are increasingly being developed to support elderly individuals through continuous and discreet monitoring of routine behavioral patterns.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop a multimodal framework for identifying mobility patterns by integrating inertial and vision-based sensor data to improve the accuracy and robustness of behavioral recognition.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Inertial data are denoised using a median filter, while video feeds are converted into grayscale frame sequences and enhanced using a Gaussian filter. Rectangular windowing is applied to inertial data, whereas U-Net is used for visual segmentation. Features are extracted using Gammatone Filter Cepstrum (GFC), Gaussian Likelihood Threshold Model (GLTM), Power Spectral Density (PSD), and temporal moments from inertial data, and Distance Transform, Gist, ORB, and SURF from visual data. The modalities are fused using shared class labels, followed by fuzzy-logic-based feature optimization and classification using a CNN-GRU hybrid model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed multimodal framework achieves 95.20% accuracy on the Continuous Multimodal Human Action Dataset (C-MHAD) and 94.79% on the multi-modal 3D human pose estimation dataset using mmWave, RGB-D, and inertial sensors (mRI) dataset, demonstrating improved behavioral categorization compared with unimodal approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The results highlight the potential of multimodal inertial and vision-based sensing for robust AI-assisted healthcare monitoring. However, evaluation is currently limited to public benchmark datasets and requires further validation in clinical settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/09287329261495179","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T12:13:42Z","timestamp":1791461622000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-driven biosensor data fusion for multimodal activity recognition in health monitoring systems"],"prefix":"10.1177","author":[{"given":"Iqra Aijaz","family":"Abro","sequence":"first","affiliation":[{"name":"Department of Computer Science, Air University, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatimah","family":"Alhayan","sequence":"additional","affiliation":[{"name":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadeel","family":"Alsolai","sequence":"additional","affiliation":[{"name":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bayan","family":"Alabdullah","sequence":"additional","affiliation":[{"name":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Jalal","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Air University, Islamabad, Pakistan"},{"name":"Department of Computer Science and Engineering, College of Informatics, Korea University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Guodian Nanjing Automation Co., Ltd., Nanjing, China"},{"name":"Jiangsu Key Laboratory of Intelligent Medical Image Computing, School of Artificial Intelligence (School of Future Technology), Nanjing University of Information Science and Technology, Nanjing, China"},{"name":"Cognitive Systems Lab, University of Bremen, Bremen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15151914"},{"key":"e_1_3_3_3_2","unstructured":"World Health Organization. Global Health and Aging. Available online: http:\/\/www.who.int\/ageing\/publications\/global_health\/en\/ (accessed on 25 March 2015)."},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2021.12.469"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42835-020-00554-y"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20226670"},{"key":"e_1_3_3_7_2","first-page":"1238","article-title":"High-level features for recognizing human actions in daily living environments using wearable sensors","volume":"2","author":"Lopez-Nava IH","year":"2018","unstructured":"Lopez-Nava IH, Mu\u00f1oz-Mel\u00e9ndez A. High-level features for recognizing human actions in daily living environments using wearable sensors. Proc AMIA Annu Fall Symp 2018; 2: 1238.","journal-title":"Proc AMIA Annu Fall Symp"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ECTIDAMTNCON53731.2022.9720358"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.17762\/ijritcc.v11i4.9853"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/iraset60544.2024.10548402"},{"key":"e_1_3_3_11_2","unstructured":"Nebisoy A Malekzadeh S. Video action recognition using spatio-temporal optical flow video frames. arXiv 2021. https:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr2103.html#abs-2103-05101."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23146384"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/icecc63398.2024.00011"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.61173\/r332rr75"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23187927"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3146137"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC53108.2024.10782799"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23115281"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDECS59733.2023.10502527"},{"key":"e_1_3_3_20_2","first-page":"2564","volume-title":"ORB: an efficient alternative to SIFT or SURFProceedings of the 2011 International Conference on Computer Vision (ICCV)","author":"Rublee E","year":"2011","unstructured":"Rublee E, Rabaud V, Konolige K, et al. ORB: an efficient alternative to SIFT or SURF. In: Proceedings of the 2011 International Conference on Computer Vision (ICCV), 2011, pp. 2564\u20132571."},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_34"},{"key":"e_1_3_3_22_2","first-page":"778","volume-title":"BRIEF: binary robust independent elementary featuresComputer Vision \u2013 ECCV 2010","author":"Calonder M","year":"2010","unstructured":"Calonder M, Lepetit V, Strecha C, et al. BRIEF: binary robust independent elementary features. In: Computer Vision \u2013 ECCV 2010, 2010, pp. 778\u2013792. Springer."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1967.1161901"},{"key":"e_1_3_3_24_2","volume-title":"Pattern recognition and machine learning","author":"Bishop CM.","year":"2006","unstructured":"Bishop CM. Pattern recognition and machine learning. Springer, 2006."},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20102905"},{"key":"e_1_3_3_26_2","first-page":"27414","volume-title":"MRI: multi-modal 3D human pose estimation dataset using mmWave, RGB-D, and inertial sensorsAdvances in Neural Information Processing Systems 35 (NeurIPS 2022)","author":"An S","year":"2022","unstructured":"An S, Li Y, Ogras U. MRI: multi-modal 3D human pose estimation dataset using mmWave, RGB-D, and inertial sensors. In: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022, pp. 27414\u201327426."},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2022.03.123"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Yadav SK Kumar N Sharma R et al. A novel two stream decision level fusion of vision and inertial sensors data for automatic multimodal human activity recognition system. arXiv 2023 arXiv:2306.15765. 10.48550\/arXiv.2306.15765.","DOI":"10.48550\/arXiv.2306.15765"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2025.1631910"},{"key":"e_1_3_3_30_2","first-page":"1","article-title":"Toward intelligent rehabilitation: multimodal human pose modeling with parametric meshes and graph-based temporal reasoning","volume":"12","author":"Kamal A","year":"2026","unstructured":"Kamal A, Wu Y, Najam S, et al. Toward intelligent rehabilitation: multimodal human pose modeling with parametric meshes and graph-based temporal reasoning. Digit Health 2026; 12: 1\u201331.","journal-title":"Digit Health"},{"key":"e_1_3_3_31_2","unstructured":"World Health Organization. Disability and Rehabilitation. Available online: http:\/\/www.who.int\/disabilities\/en\/ (accessed on 25 March 2015)."},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1583459"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22228620"}],"container-title":["Technology and Health Care"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/09287329261495179","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/09287329261495179","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/09287329261495179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T17:05:44Z","timestamp":1791738344000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/09287329261495179"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":33,"alternative-id":["10.1177\/09287329261495179"],"URL":"https:\/\/doi.org\/10.1177\/09287329261495179","relation":{},"ISSN":["0928-7329","1878-7401"],"issn-type":[{"value":"0928-7329","type":"print"},{"value":"1878-7401","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]},"article-number":"09287329261495179"}}