{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T23:00:52Z","timestamp":1789945252865,"version":"4.0.1"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>This article proposes using dual-body sensor placement on the right ankle and wrist with raw multi-sensor fusion (accelerometer, magnetometer, and gyroscope at 66.6 Hz) to capture complementary upper- and lower-body kinematics across nine complex daily activities and real-time integration with smart homes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Two independent datasets were obtained from participants performing different activities each at intervals of 5\u201310 min and with real-time labeling. Classification was carried out using six different machine learning architectures (SVM, Logistic Regression, ANN, C&amp;amp;RT, Random Forest, and C5.0).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Random Forest and Multilayer Perceptron (ANN) models demonstrate superior cross-dataset generalization, achieving 93.48% accuracy when evaluated on fully independent sessions. Predictor importance analysis reveals distinct kinematic dependencies, where leg magnetometers dominate elevation-based activities (stair climbing) and wrist accelerometers drive fine-motor actions (typing, writing). Integrating a 120-sample majority-voting filter effectively eliminates transient classification noise without compromising real-time responsiveness (&amp;lt; 2s latency). Finally, the framework is validated via C#, PMML extraction, and Falcon.NET integration for real-time KNX smart home control.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The study findings highlight the feasibility of integrating wearable HAR systems into smart homes for real-time monitoring and adaptive assistance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fbioe.2026.1926076","type":"journal-article","created":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T22:10:38Z","timestamp":1789942238000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sensor-based human activity recognition using wrist and ankle wearables"],"prefix":"10.3389","volume":"14","author":[{"given":"Ojan Majidzadeh","family":"Gorjani","sequence":"first","affiliation":[{"name":"Department of Cybernetics and Biomedical Engineering, Faculty of Electrical Engineering and Computer Science, VSB\u2013Technical University of Ostrava","place":["Ostrava, Czechia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rene","family":"Jaros","sequence":"additional","affiliation":[{"name":"Department of Cybernetics and Biomedical Engineering, Faculty of Electrical Engineering and Computer Science, VSB\u2013Technical University of Ostrava","place":["Ostrava, Czechia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petr","family":"Bilik","sequence":"additional","affiliation":[{"name":"Department of Cybernetics and Biomedical Engineering, Faculty of Electrical Engineering and Computer Science, VSB\u2013Technical University of Ostrava","place":["Ostrava, Czechia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/978-3-642-14715-9_5","article-title":"Human activity recognition using inertial\/magnetic sensor units","volume-title":"International Workshop on Human Behavior Understanding","author":"Altun","year":"2010"},{"key":"B2","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1007\/978-981-16-5157-1_54","article-title":"Human activity recognition using 1D convolutional neural network","volume-title":"Sentimental Analysis and Deep Learning","author":"Banjarey","year":"2022"},{"key":"B3","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1007\/s00371-021-02064-y","article-title":"DTR-HAR: deep temporal residual representation for human activity recognition","volume":"38","author":"Basly","year":"2022","journal-title":"Vis. Comput."},{"key":"B4","doi-asserted-by":"publisher","first-page":"88","DOI":"10.3390\/eng7020088","article-title":"A prototypical fuzzy similarity-based classification framework for ultrasonic defect detection in concrete","volume":"7","author":"Cacciola","year":"2026","journal-title":"Eng"},{"key":"B5","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1007\/s12530-023-09518-9","article-title":"A multi-agent optimization algorithm and its application to training multilayer perceptron models","volume":"15","author":"Chauhan","year":"2024","journal-title":"Evol. Syst."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447744","article-title":"Deep learning for sensor-based human activity recognition: overview, challenges, and opportunities","volume":"54","author":"Chen","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"B7","doi-asserted-by":"publisher","first-page":"189","DOI":"10.14358\/PERS.82.3.189","article-title":"Approximating prediction uncertainty for random forest regression models","volume":"82","author":"Coulston","year":"2016","journal-title":"Photogrammetric Eng. and Remote Sens."},{"key":"B8","doi-asserted-by":"publisher","first-page":"9280","DOI":"10.1109\/JIOT.2019.2911669","article-title":"Adaptive fusion and category-level dictionary learning model for multiview human action recognition","volume":"6","author":"Gao","year":"2019","journal-title":"IEEE Internet Things J."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3102735","article-title":"Deep neural networks for sensor-based human activity recognition using selective kernel convolution","volume":"70","author":"Gao","year":"","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"B10","doi-asserted-by":"publisher","first-page":"107728","DOI":"10.1016\/j.asoc.2021.107728","article-title":"DanHAR: Dual attention network for multimodal human activity recognition using wearable sensors","volume":"111","author":"Gao","year":"","journal-title":"Appl. Soft Comput."},{"key":"B11","doi-asserted-by":"publisher","first-page":"4507","DOI":"10.1007\/s11063-021-10611-w","article-title":"Time analysis in human activity recognition","volume":"53","author":"Gil-Mart\u00edn","year":"2021","journal-title":"Neural Process. Lett."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.21227\/08XK-R309","article-title":"Human activity recognion har_omg1","author":"Gorjnai","year":"2024","journal-title":"IEEE DataPort"},{"key":"B13","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/s12662-022-00817-y","article-title":"Validation of human activity recognition using a convolutional neural network on accelerometer and gyroscope data","volume":"52","author":"Hysenllari","year":"2022","journal-title":"Ger. J. Exerc. Sport Res."},{"key":"B14","unstructured":"IBM SPSS modeler 18.3\n          \n          \n          2022"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.1109\/LRA.2021.3059624","article-title":"Multi-GAT: a graphical attention-based hierarchical multimodal representation learning approach for human activity recognition","volume":"6","author":"Islam","year":"2021","journal-title":"IEEE Robotics Automation Lett."},{"key":"B16","doi-asserted-by":"publisher","first-page":"106060","DOI":"10.1016\/j.compbiomed.2022.106060","article-title":"Human activity recognition using tools of convolutional neural networks: a state of the art review, data sets, challenges, and future prospects","volume":"149","author":"Islam","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B17","doi-asserted-by":"publisher","first-page":"109726","DOI":"10.1016\/j.compag.2024.109726","article-title":"High-resolution UAV-Based blueberry scorch virus mapping utilizing a deep vision transformer algorithm","volume":"229","author":"Jamali","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TSMC.2018.2850149","article-title":"Deep convolutional neural networks for human action recognition using depth maps and postures","volume":"49","author":"Kamel","year":"2019","journal-title":"IEEE Trans. Syst. Man, Cybern. Syst."},{"key":"B19","doi-asserted-by":"publisher","first-page":"107671","DOI":"10.1016\/j.asoc.2021.107671","article-title":"Attention induced multi-head convolutional neural network for human activity recognition","volume":"110","author":"Khan","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1109\/TITB.2010.2051955","article-title":"A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer","volume":"14","author":"Khan","year":"2010","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"B26","first-page":"1","article-title":"From wrist to ankle: understanding imu sensor placement in human activity recognition","volume-title":"2025 Emerging Technologies for Intelligent Systems (ETIS)","author":"Lakshmi","year":"2025"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1907","DOI":"10.32604\/iasc.2022.027233","article-title":"Sport-related activity recognition from wearable sensors using bidirectional GRU network","volume":"34","author":"Mekruksavanich","year":"2022","journal-title":"Intelligent Automation and Soft Comput."},{"key":"B22","first-page":"682","article-title":"A comparative analysis of deep learning neural networks for human activity recognition using wrist-worn inertial sensor","volume-title":"2026 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering (ECTI DAMT and NCON) (IEEE)","author":"Mekruksavanich","year":"2026"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3789688","article-title":"Wonderwall: a virtual-to-real foundation model for imu-based har","volume":"10","author":"Miao","year":"2026","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"199601","DOI":"10.1109\/ACCESS.2020.3035026","article-title":"A cnn-lstm approach to human activity recognition using wearable sensors","volume":"8","author":"Mutegeki","year":"2020","journal-title":"IEEE Access"},{"key":"B25","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1007\/s42107-023-00826-8","article-title":"Compressive strength prediction of PET fiber-reinforced concrete using dolphin echolocation optimized decision tree-based machine learning algorithms","volume":"25","author":"Parhi","year":"2024","journal-title":"Asian J. Civ. Eng."},{"key":"B27","doi-asserted-by":"publisher","first-page":"106953","DOI":"10.1016\/j.cie.2020.106953","article-title":"Hybrid domain adaptation with deep network architecture for end-to-end cross-domain human activity recognition","volume":"151","author":"Prabono","year":"2021","journal-title":"Comput. and Industrial Eng."},{"key":"B28","doi-asserted-by":"publisher","first-page":"e0262181","DOI":"10.1371\/journal.pone.0262181","article-title":"A deep neural network model for multi-view human activity recognition","volume":"17","author":"Putra","year":"2022","journal-title":"PLOS ONE"},{"key":"B29","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.inffus.2021.11.006","article-title":"Multi-sensor information fusion based on machine learning for real applications in human activity recognition: state-of-the-art and research challenges","volume":"80","author":"Qiu","year":"2022","journal-title":"Inf. Fusion"},{"key":"B30","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1108\/IJICC-07-2023-0174","article-title":"Evaluation of predicted fault tolerance based on C5.0 decision tree algorithm in irrigation system of paddy fields","volume":"17","author":"Rahi","year":"2024","journal-title":"Int. J. Intelligent Comput. Cybern."},{"key":"B31","first-page":"19","article-title":"Chapter 10, multivariate regression\u2013section 10.1, introduction","volume":"709","author":"Rencher","year":"2012","journal-title":"Methods Multivariate Analysis"},{"key":"B32","doi-asserted-by":"publisher","first-page":"68985","DOI":"10.1109\/access.2021.3078184","article-title":"Isplinception: an inception-resnet deep learning architecture for human activity recognition","volume":"9","author":"Ronald","year":"2021","journal-title":"IEEE Access"},{"key":"B33","doi-asserted-by":"publisher","first-page":"32","DOI":"10.37134\/jsml.vol10.1.4.2022","article-title":"Comparative study of ensemble method vs deep learning on human activity recognition for elderly care","volume":"10","author":"Saudi","year":"2022","journal-title":"J. Sci. Math. Lett."},{"key":"B34","doi-asserted-by":"publisher","first-page":"298","DOI":"10.18178\/ijmlc.2021.11.4.1051","article-title":"Smartphone sensor accelerometer data for human activity recognition using spiking neural network","volume":"11","author":"Suriani","year":"2021","journal-title":"Int. J. Mach. Learn. Comput."},{"key":"B35","doi-asserted-by":"publisher","first-page":"4137","DOI":"10.1109\/ACCESS.2022.3140373","article-title":"ConvAE-LSTM: convolutional autoencoder long short-term memory network for smartphone-based human activity recognition","volume":"10","author":"Thakur","year":"2022","journal-title":"IEEE Access"},{"key":"B36","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1001\/jama.2016.7653","article-title":"Logistic regression: relating patient characteristics to outcomes","volume":"316","author":"Tolles","year":"2016","journal-title":"JAMA"},{"key":"B37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICCC64910.2025.11077308","article-title":"Optimizing machine learning models for human activity recognition via feature engineering and selection","volume-title":"2025 6th International Conference on Control, Communication and Computing (ICCC)","author":"Viswalal","year":"2025"},{"key":"B38","doi-asserted-by":"publisher","first-page":"458","DOI":"10.3390\/s19030458","article-title":"Human physical activity recognition using smartphone sensors","volume":"19","author":"Voicu","year":"2019","journal-title":"Sensors"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1109\/TPAMI.2016.2565479","article-title":"Super normal vector for human activity recognition with depth cameras","volume":"39","author":"Yang","year":"2017","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B40","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/s10462-024-10934-9","article-title":"A survey of video-based human action recognition in team sports","volume":"57","author":"Yin","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2017\/3090343","article-title":"A review on human activity recognition using vision-based method","volume":"2017","author":"Zhang","year":"2017","journal-title":"J. Healthc. Eng."},{"key":"B42","doi-asserted-by":"publisher","first-page":"2146","DOI":"10.3390\/s18072146","article-title":"Comparison of data preprocessing approaches for applying deep learning to human activity recognition in the context of industry 4.0","volume":"18","author":"Zheng","year":"2018","journal-title":"Sensors"},{"key":"B43","doi-asserted-by":"publisher","first-page":"5001","DOI":"10.3390\/s19225001","article-title":"Sport-related human activity detection and recognition using a smartwatch","volume":"19","author":"Zhuang","year":"2019","journal-title":"Sensors"}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1926076\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T22:10:40Z","timestamp":1789942240000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1926076\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":43,"alternative-id":["10.3389\/fbioe.2026.1926076"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2026.1926076","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]},"article-number":"1926076"}}