{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T05:17:08Z","timestamp":1788499028392,"version":"build-2803163510"},"reference-count":32,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University of Wollongong in Dubai","award":["URC25017"],"award-info":[{"award-number":["URC25017"]}]},{"award":["URC25017"],"award-info":[{"award-number":["URC25017"]}],"id":[{"id":"https:\/\/ror.org\/0447ajy94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper presents a wearable soft strain sensor based on a commercially available conductive thermoplastic polyurethane (cTPU) 3D-printed as an auxetic soft metamaterial for human activity recognition. The growing demand for flexible and wearable electronics, driven by advances in artificial intelligence, highlights the importance of such sensors in healthcare, medical rehabilitation, soft robotics, and human\u2013machine interfaces. The auxetic cTPU sensor was mechanically and electrically characterized through empirical measurements and validated against numerical simulations. A single sensor mounted on a knee brace was used to collect gait signals across four activities: running, walking, standing, and sitting. Two classification approaches were investigated. A Long Short-Term Memory (LSTM) network was trained directly on the raw time-series signal, with the best configuration achieving 96% accuracy using Relative Standard Deviation Normalization with 50 hidden units. Traditional machine learning models, namely Random Forest and XGBoost, were trained on 30 extracted time-domain and frequency-domain features per motion cycle, achieving 100% and 97.33% accuracy, respectively, under five-fold cross-validation. To enhance model transparency, explainability analysis using SHAP identified power spectral density and the first harmonic frequency as the most consistently influential features across both models, with dynamic activities driven by frequency characteristics and stationary activities distinguished by signal mean amplitude. The results demonstrate that auxetic cTPU soft strain sensors combined with machine learning and explainable artificial intelligence provide an accurate and interpretable solution for wearable human activity recognition, highlighting their potential for applications in robotics, healthcare, and human\u2013robot interfaces.<\/jats:p>","DOI":"10.3390\/s26175548","type":"journal-article","created":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T03:19:26Z","timestamp":1788232766000},"page":"5548","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Machine Learning for Human Activity Recognition Using Auxetic cTPU Knee-Worn Sensors"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5142-379X","authenticated-orcid":false,"given":"Abeer","family":"Elkhouly","sequence":"first","affiliation":[{"name":"School of Engineering, University of Wollongong in Dubai, Dubai 20183, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1011-2826","authenticated-orcid":false,"given":"Umar","family":"Asghar","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Wollongong in Dubai, Dubai 20183, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6887-7761","authenticated-orcid":false,"given":"Ganga","family":"Raj","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Wollongong in Dubai, Dubai 20183, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"ref_1","unstructured":"Ni, J., Tang, H., Haque, S.T., Yan, Y., and Ngu, A.H.H. (2024). A Survey on Multimodal Wearable Sensor-Based Human Action Recognition. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Rajasekaran, P., Hemanth, A.K., Jayaseeli, J.D.D., Robert, P., and Suryah, S.S. (2025). Wearable Sensors in Human Activity Recognition: A Survey. Proceedings of the International Conference on Innovative Computing and Communication (ICICC 2024), Springer.","DOI":"10.2139\/ssrn.5195561"},{"key":"ref_3","first-page":"2548208","article-title":"Recent developments of auxetic metamaterials","volume":"10","author":"Islam","year":"2025","journal-title":"Adv. Phys. X"},{"key":"ref_4","first-page":"2572830","article-title":"Auxetic mechanical metamaterials for resistive tactile sensors: A review","volume":"10","author":"Kang","year":"2025","journal-title":"Adv. Phys. X"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Alemayoh, T.T., Lee, J.H., and Okamoto, S. (2023). Leg-Joint Angle Estimation from a Single Inertial Sensor Attached to Various Lower-Body Links during Walking Motion. Appl. Sci., 13.","DOI":"10.3390\/app13084794"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ni\u00f1o-Tejada, K., Salda\u00f1a-Aristiz\u00e1bal, L., Rivas-Caicedo, J.L., and Patarroyo-Montenegro, J.F. (2025). Upper Limb Joint Angle Estimation Using a Reduced Number of IMU Sensors and Recurrent Neural Networks. Electronics, 14.","DOI":"10.3390\/electronics14153039"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1109\/THMS.2021.3086017","article-title":"A Novel Application of Flexible Inertial Sensors for Ambulatory Measurement of Gait Kinematics","volume":"51","author":"Yin","year":"2021","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"36559","DOI":"10.1109\/ACCESS.2021.3062978","article-title":"Biomechanical Ambulatory Assessment of 3D Knee Angle Using Novel Inertial Sensor-Based Technique","volume":"9","author":"Tham","year":"2021","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2829","DOI":"10.1109\/JBHI.2023.3262164","article-title":"Estimation of Lower Extremity Joint Moments and 3D Ground Reaction Forces Using IMU Sensors in Multiple Walking Conditions: A Deep Learning Approach","volume":"27","author":"Hossain","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Becker, E., Khaksar, S., Booker, H., Hill, K., Ren, Y., Tan, T., Watson, C., Wordsworth, E., and Harrold, M. (2025). Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed. Sensors, 25.","DOI":"10.3390\/s25020499"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"18086","DOI":"10.1038\/s41598-023-45375-x","article-title":"Wearable sensor and machine learning estimate tendon load and walking speed during immobilizing boot ambulation","volume":"13","author":"Kwon","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Raj, G., Al-Khatib, O., Afsari, K., and ElKhouly, A. (2026, January 20\u201322). Non-Invasive Estimation of Achilles Tendon Load in Fast Bowlers Using IMUs and Machine Learning for Tendinitis Prevention. Proceedings of the 2026 12th International Conference on Communication and Signal Processing (ICCSP), Melmaruvathur, India.","DOI":"10.1109\/ICCSP68173.2026.11539234"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"22053","DOI":"10.1109\/JSEN.2022.3205363","article-title":"Analysis of Front Leg Kinematics of Cricket Bowler Using Wearable Sensors and Machine Learning","volume":"22","author":"Rana","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1109\/JSEN.2024.3488898","article-title":"Advanced Kinematic Analysis of Cricket Bowlers Using Wearable Sensors and Machine Learning","volume":"25","author":"Rana","year":"2025","journal-title":"IEEE Sens. J."},{"key":"ref_15","unstructured":"Jaya, I.G.P., Dharmmesta, R.A., Rizal, A. (2022, January 9\u201310). Application Foot Kick Classification in Taekwondo with Inertia Sensor and Machine Learning. Proceedings of the 2022 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob), Bandung, Indonesia."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sonalcan, H., Bilen, E., Ate\u015f, B., and Se\u00e7kin, A.\u00c7. (2025). Action Recognition in Basketball with Inertial Measurement Unit-Supported Vest. Sensors, 25.","DOI":"10.3390\/s25020563"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2950","DOI":"10.1038\/s41467-021-23207-8","article-title":"Sensing of joint and spinal bending or stretching via a retractable and wearable badge reel","volume":"12","author":"Li","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1038\/s44328-026-00101-1","article-title":"Interdigitated capacitive strain sensor enables precise yoga-inspired motion tracking","volume":"3","author":"Papaefstathiou","year":"2026","journal-title":"npj Biosens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100053","DOI":"10.1016\/j.nwnano.2024.100053","article-title":"Self-powered highly stretchable ferroelectret nanogenerator towards intelligent sports","volume":"8","author":"Wang","year":"2024","journal-title":"Nano Trends"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, T., Chen, X., and Wang, F. (2025). A Novel Fabric Strain Sensor Array with Hybrid Deep Learning for Accurate Knee Movement Recognition. Micromachines, 17.","DOI":"10.3390\/mi17010056"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"107768","DOI":"10.1016\/j.nanoen.2022.107768","article-title":"Flexible, stretchable, breathable and sweatproof all-nanofiber iontronic tactile sensor for continuous and comfortable knee joint motion monitoring","volume":"103","author":"Wang","year":"2022","journal-title":"Nano Energy"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102438","DOI":"10.1016\/j.xcrp.2025.102438","article-title":"Intelligent wearable system design for personalized knee motion and swelling monitoring in osteoarthritis care","volume":"6","author":"Ma","year":"2025","journal-title":"Cell Rep. Phys. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"49845","DOI":"10.1021\/acsami.4c13402","article-title":"High-Performance Stretchable Strain Sensors Based on Auxetic Fabrics for Human Motion Detection","volume":"16","author":"Zhang","year":"2024","journal-title":"ACS Appl. Mater. Interfaces"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"159539","DOI":"10.1016\/j.cej.2025.159539","article-title":"Machine learning-enhanced low-hysteresis conductive auxetic strain sensors with curved re-entrant honeycomb structures based on MXene\/graphene for human rehabilitation training","volume":"505","author":"Zhu","year":"2025","journal-title":"Chem. Eng. J."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mutlu, R., Elkhouly, A., Asghar, U., and O\u2019Driscoll, C. (2025, January 26\u201328). Auxetic cTPU Soft Strain Sensor Augmented with Artificial Intelligence for Human Gait Analytics. Proceedings of the 2025 IEEE 5th International Conference on Human-Machine Systems (ICHMS), Abu Dhabi, United Arab Emirates.","DOI":"10.1109\/ICHMS65439.2025.11154316"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"42335","DOI":"10.1038\/s41598-025-26297-2","article-title":"A tiny inertial transformer for human activity recognition via multimodal knowledge distillation and explainable AI","volume":"15","author":"Lamaakal","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Navakauskas, D., and Dumpis, M. (2025). Wearable Sensor-Based Human Activity Recognition: Performance and Interpretability of Dynamic Neural Networks. Sensors, 25.","DOI":"10.3390\/s25144420"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1108\/SR-02-2020-0027","article-title":"Human activity detection using machine learning methods from wearable sensors","volume":"40","author":"Randhawa","year":"2020","journal-title":"Sens. Rev."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Raju, V.G., Lakshmi, K.P., Jain, V.M., Kalidindi, A., and Padma, V. (2020, January 20\u201322). Study the influence of normalization\/transformation process on the accuracy of supervised classification. Proceedings of the 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India.","DOI":"10.1109\/ICSSIT48917.2020.9214160"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3717","DOI":"10.1016\/j.camwa.2012.02.049","article-title":"Modelling global temperature changes with genetic programming","volume":"64","author":"Stanislawska","year":"2012","journal-title":"Comput. Math. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"020042","DOI":"10.1063\/1.4975275","article-title":"Analysis of feature selection with probabilistic neural network (PNN) to classify sources influencing indoor air quality","volume":"1808","author":"Saad","year":"2017","journal-title":"AIP Conf. Proc."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1854","DOI":"10.1038\/s41598-022-25411-y","article-title":"Data-driven audiogram classifier using data normalization and multi-stage feature selection","volume":"13","author":"Elkhouly","year":"2023","journal-title":"Sci. Rep."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5548\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T04:29:49Z","timestamp":1788496189000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5548"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":32,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26175548"],"URL":"https:\/\/doi.org\/10.3390\/s26175548","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]}}}