{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T08:06:35Z","timestamp":1784102795025,"version":"3.55.0"},"reference-count":37,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"EPSRC Standard Mode Grant \u2018KNOT\u2019","award":["EP\/Z533841\/1"],"award-info":[{"award-number":["EP\/Z533841\/1"]}]},{"name":"EPSRC Programme Grant \u2018SONNETS\u2019","award":["EP\/X036006\/1"],"award-info":[{"award-number":["EP\/X036006\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human activity recognition (HAR) based on smartphone and wearable sensor data is commonly addressed using statistical learning methods and deep neural networks that often provide strong predictive performance, but at the expense of limited interpretability and substantial computational and energy requirements. Such limitations reduce their suitability for deployment in practical sensing environments where model decisions must be transparent, verifiable and executable on resource-constrained devices. In this work, we investigate the Convolutional Tsetlin Machine (CTM) for multimodal HAR using only the raw inertial signals (9 \u00d7 128) of the UCI-HAR dataset, rather than its pre-computed 561-feature representation. The Tsetlin Machine is a novel neuro-symbolic machine learning approach that offers two important advantages over many conventional machine learning methods: (i) it learns logic-based decision rules that support human inspection and provide a transparent basis for analyzing model decisions, and (ii) it operates with comparatively low computational complexity, making it well suited to efficient and low-power on-device learning. The proposed study systematically analyses the contribution of different feature modalities by decomposing the inertial signals space into semantically defined subsets according to: (i) sensor source: accelerometer and gyroscope; (ii) signal group: gyroscope angular velocity, body and total acceleration (including gravity); (iii) coordinate axis: x, y and z. A separate CTM classifier was trained for each modality and its combinations in order to determine the relative discriminative value of each modality group for activity classification. In addition to predictive performance, the study emphasizes the interpretability of the CTM model ensured by expressing each decision in the form of propositional clauses, thereby enabling visualization and direct inspection of the modality-specific patterns supporting each activity class. Owing to its symbolic structure and modest computational demands, the CTM provides a principled framework for the design of explainable, resource-efficient and deployable HAR systems. The proposed work therefore contributes toward trustworthy multimodal sensing by jointly addressing predictive performance, interpretability and suitability for embedded and mobile platforms.<\/jats:p>","DOI":"10.3390\/s26144482","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:29:39Z","timestamp":1784100579000},"page":"4482","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sensor-Modality-Aware Human Activity Recognition with the Convolutional Tsetlin Machine: Interpretable and Resource-Efficient Neuro-Symbolic Learning"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5991-8631","authenticated-orcid":false,"given":"Olga","family":"Tarasyuk","sequence":"first","affiliation":[{"name":"School of Engineering, Newcastle University, Newcastle upon Tyne NE1 7RU, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6757-1797","authenticated-orcid":false,"given":"Anatoliy","family":"Gorbenko","sequence":"additional","affiliation":[{"name":"School of Built Environment, Engineering and Computing, Leeds Beckett University, Leeds LS1 3HE, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2517-9388","authenticated-orcid":false,"given":"Oleksandr","family":"Gordieiev","sequence":"additional","affiliation":[{"name":"School of Built Environment, Engineering and Computing, Leeds Beckett University, Leeds LS1 3HE, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2105-1603","authenticated-orcid":false,"given":"Artem","family":"Akulynichev","sequence":"additional","affiliation":[{"name":"Department of Infocommunication Engineering, Kharkiv National University of Radio Electronics, 61166 Kharkiv, Ukraine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5444-537X","authenticated-orcid":false,"given":"Rishad","family":"Shafik","sequence":"additional","affiliation":[{"name":"School of Engineering, Newcastle University, Newcastle upon Tyne NE1 7RU, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0826-9330","authenticated-orcid":false,"given":"Alex","family":"Yakovlev","sequence":"additional","affiliation":[{"name":"School of Engineering, Newcastle University, Newcastle upon Tyne NE1 7RU, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"842","DOI":"10.3390\/make6020040","article-title":"A Comprehensive Survey on Deep Learning Methods in Human Activity Recognition","volume":"6","author":"Kaseris","year":"2024","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., and Alshurafa, N. (2022). Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances. Sensors, 22.","DOI":"10.3390\/s22041476"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1007\/s10462-025-11275-x","article-title":"A Systematic Literature Review on Human Activity Recognition Using Smart Devices: Advances, Challenges, and Future Directions","volume":"58","author":"Qureshi","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e13680","DOI":"10.1111\/exsy.13680","article-title":"Human Activity Recognition: A Comprehensive Review","volume":"41","author":"Kaur","year":"2024","journal-title":"Expert Syst."},{"key":"ref_5","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_6","doi-asserted-by":"crossref","first-page":"111146","DOI":"10.1016\/j.asoc.2023.111146","article-title":"Human Activity Recognition through Deep Learning: Leveraging Unique and Common Feature Fusion in Wearable Multi-Sensor Systems","volume":"151","author":"Liu","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"130911","DOI":"10.1016\/j.neucom.2025.130911","article-title":"Machine Learning Models for Wearable-Based Human Activity Recognition: A Comparative Study","volume":"650","author":"Ciortuz","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ins.2021.04.062","article-title":"Continual Learning in Sensor-Based Human Activity Recognition: An Empirical Benchmark Analysis","volume":"575","author":"Jha","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"101817","DOI":"10.1016\/j.pmcj.2023.101817","article-title":"Online Continual Learning for Human Activity Recognition","volume":"93","author":"Schiemer","year":"2023","journal-title":"Pervasive Mob. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Liu, M., Bian, S., Fortes Rey, V., Gei\u00dfler, D., Kang, P., Zhou, B., and Lukowicz, P. (2026). COOL: Continual Online on-Device Learning for Human Activity Recognition Enhanced by KANs. CCF Trans. Pervasive Comput. Interact.","DOI":"10.1007\/s42486-026-00229-z"},{"key":"ref_11","unstructured":"Granmo, O.-C., Glimsdal, S., Jiao, L., Goodwin, M., Omlin, C.W., and Berge, G.T. (2019). The Convolutional Tsetlin Machine. arXiv."},{"key":"ref_12","unstructured":"Granmo, O.-C. (2021). The Tsetlin Machine\u2014A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic. arXiv."},{"key":"ref_13","unstructured":"Anguita, D., Chio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J.-L. (2013, January 24). A Public Domain Dataset for Human Activity Recognition Using Smartphones. Proceedings of the 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Bruges, Belgium."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Reiss, A., and Stricker, D. (2012). Introducing a New Benchmarked Dataset for Activity Monitoring. Proceedings of the 2012 16th International Symposium on Wearable Computers, IEEE.","DOI":"10.1109\/ISWC.2012.13"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"133190","DOI":"10.1109\/ACCESS.2019.2940729","article-title":"Smartphone and Smartwatch-Based Biometrics Using Activities of Daily Living","volume":"7","author":"Weiss","year":"2019","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1016\/j.neucom.2015.07.085","article-title":"Transition-Aware Human Activity Recognition Using Smartphones","volume":"171","author":"Oneto","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Tarasyuk, O., Gorbenko, A., Rahman, T., Shafik, R., and Yakovlev, A. (2023). Logic-Based Machine Learning with Reproducible Decision Model Using the Tsetlin Machine. Proceedings of the 2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), IEEE.","DOI":"10.1109\/IDAACS58523.2023.10348711"},{"key":"ref_18","unstructured":"Tsetlin, M.L. (1973). Automata Theory and Modeling of Biological Systems, Academic Press."},{"key":"ref_19","first-page":"327","article-title":"On the Behavior of Stochastic Automata with Variable Structure","volume":"24","author":"Varshavskii","year":"1963","journal-title":"Autom. Remote Control"},{"key":"ref_20","unstructured":"Narendra, K., and Thathachar, M. (2012). Learning Automata: An Introduction, Dover Publications."},{"key":"ref_21","unstructured":"(2026, June 28). Centre for Artificial Intelligence Research TsetlinMachine: Code and Datasets for the Tsetlin Machine. Available online: https:\/\/github.com\/cair\/TsetlinMachine."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"20190593","DOI":"10.1098\/rsta.2019.0593","article-title":"Learning Automata Based Energy-Efficient AI Hardware Design for IoT Applications","volume":"378","author":"Wheeldon","year":"2020","journal-title":"Philos. Trans. R. Soc. A Math. Phys. Eng. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1109\/TCSI.2025.3586698","article-title":"An All-Digital 8.6-NJ\/Frame 65-Nm Tsetlin Machine Image Classification Accelerator","volume":"73","author":"Tunheim","year":"2025","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_24","unstructured":"Buckman, J., Roy, A., Raffel, C., and Goodfellow, I. (May, January 30). Thermometer Encoding: One Hot Way to Resist Adversarial Examples. Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tarasyuk, O., Rahman, T., Shafik, R., Yakovlev, A., Gorbenko, A., Granmo, O.-C., and Jiao, L. (2023). Systematic Search for Optimal Hyper-Parameters of the Tsetlin Machine on MNIST Dataset. Proceedings of the 2023 International Symposium on the Tsetlin Machine (ISTM), IEEE.","DOI":"10.1109\/ISTM58889.2023.10454969"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"11152","DOI":"10.1109\/TPAMI.2023.3268415","article-title":"REDRESS: Generating Compressed Models for Edge Inference Using Tsetlin Machines","volume":"45","author":"Maheshwari","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"\u017byczkowski, K., and S\u0142omczy\u0144ski, W. (2013). Square Root Voting System, Optimal Threshold and \u03c0. Power, Voting, and Voting Power: 30 Years After, Springer.","DOI":"10.1007\/978-3-642-35929-3_30"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"53","DOI":"10.2307\/2981392","article-title":"The Elementary Statistics of Majority Voting","volume":"109","author":"Penrose","year":"1946","journal-title":"J. R. Stat. Soc."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"113028","DOI":"10.1016\/j.patcog.2025.113028","article-title":"Learning Dynamics, Pattern Recognition Capability and Interpretability of the Tsetlin Machine","volume":"174","author":"Tarasyuk","year":"2026","journal-title":"Pattern Recognit."},{"key":"ref_30","first-page":"130","article-title":"1D Convolution Approach to Human Activity Recognition Using Sensor Data and Comparison with Machine Learning Algorithms","volume":"2","author":"Muralidharan","year":"2021","journal-title":"Int. J. Cogn. Comput. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.eswa.2016.04.032","article-title":"Human Activity Recognition with Smartphone Sensors Using Deep Learning Neural Networks","volume":"59","author":"Ronao","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3101","DOI":"10.1109\/JSEN.2019.2956901","article-title":"Human Action Recognition Using Deep Learning Methods on Limited Sensory Data","volume":"20","author":"Tufek","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_33","unstructured":"Arigbabu, O.A. (2020). Entropy Decision Fusion for Smartphone Sensor Based Human Activity Recognition. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"468","DOI":"10.28991\/ESJ-2025-09-01-026","article-title":"HSTCN-NuSVC: A Homogeneous Stacked Deep Ensemble Learner for Classifying Human Actions Using Smartphones","volume":"9","author":"Raja","year":"2025","journal-title":"Emerg. Sci. J."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3834","DOI":"10.1109\/JBHI.2021.3092396","article-title":"The Convolutional Neural Networks Training with Channel-Selectivity for Human Activity Recognition Based on Sensors","volume":"25","author":"Huang","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"10146","DOI":"10.3390\/s140610146","article-title":"Fusion of Smartphone Motion Sensors for Physical Activity Recognition","volume":"14","author":"Shoaib","year":"2014","journal-title":"Sensors"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"16979","DOI":"10.1109\/JSEN.2021.3079883","article-title":"Human Activity Recognition with Accelerometer and Gyroscope: A Data Fusion Approach","volume":"21","author":"Webber","year":"2021","journal-title":"IEEE Sens. J."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4482\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:30:57Z","timestamp":1784100657000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":37,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144482"],"URL":"https:\/\/doi.org\/10.3390\/s26144482","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]}}}