{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T23:26:22Z","timestamp":1787268382443,"version":"build-2736575974"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"content-version":"vor","delay-in-days":73,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-57375-8","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:44:10Z","timestamp":1781023450000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient uncertainty aware human activity recognition on microcontrollers using hyperdimensional computing and conformal prediction"],"prefix":"10.1038","volume":"16","author":[{"given":"Ismail","family":"Lamaakal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaymae","family":"Yahyati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yassine","family":"Maleh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khalid","family":"El Makkaoui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ibrahim","family":"Ouahbi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"57375_CR1","doi-asserted-by":"publisher","first-page":"128379","DOI":"10.1109\/ACCESS.2025.3589938","volume":"13","author":"S Essahraui","year":"2025","unstructured":"Essahraui, S. et al. Human behavior analysis: a comprehensive survey on techniques, applications, challenges, and future directions. IEEE Access 13, 128379\u2013128419. https:\/\/doi.org\/10.1109\/ACCESS.2025.3589938 (2025).","journal-title":"IEEE Access"},{"issue":"16","key":"57375_CR2","doi-asserted-by":"publisher","first-page":"32419","DOI":"10.1109\/JIOT.2025.3565688","volume":"12","author":"I Lamaakal","year":"2025","unstructured":"Lamaakal, I. et al. A comprehensive survey on tiny machine learning for human behavior analysis. IEEE Internet of Things J. 12(16), 32419\u201332443. https:\/\/doi.org\/10.1109\/JIOT.2025.3565688 (2025).","journal-title":"IEEE Internet of Things J."},{"key":"57375_CR3","unstructured":"Banbury, C. R. et al. Benchmarking TinyML systems: challenges and direction. arXiv preprint arXiv:2003.04821 (2020)."},{"key":"57375_CR4","first-page":"800","volume":"3","author":"R David","year":"2021","unstructured":"David, R. et al. TensorFlow lite micro: embedded machine learning on TinyML systems. Proc. Mach. Learn. Syst. (MLSys) 3, 800\u2013811 (2021).","journal-title":"Proc. Mach. Learn. Syst. (MLSys)"},{"key":"57375_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3624283","author":"I Lamaakal","year":"2025","unstructured":"Lamaakal, I. et al. Tiny deep learning models with hybrid compression techniques for gesture-based air handwriting recognition of English alphabets on edge device. IEEE Internet Things J. https:\/\/doi.org\/10.1109\/JIOT.2025.3624283 (2025).","journal-title":"IEEE Internet Things J."},{"key":"57375_CR6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3625087","author":"I Lamaakal","year":"2025","unstructured":"Lamaakal, I. et al. An explainable tiny-fast Kolmogorov-Arnold network for gesture-based air handwriting recognition of Tifinagh letters in a resource-constrained IoT device. IEEE Internet Things J. https:\/\/doi.org\/10.1109\/JIOT.2025.3625087 (2025).","journal-title":"IEEE Internet Things J."},{"key":"57375_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2026.101889","volume":"36","author":"I Lamaakal","year":"2026","unstructured":"Lamaakal, I., Yahyati, C., Maleh, Y., El Makkaoui, K. & Ouahbi, I. TinyHAR-UQ: battery-aware, uncertainty-controlled TinyML for wearable activity recognition on IoT edge devices. Internet Things 36, 101889. https:\/\/doi.org\/10.1016\/j.iot.2026.101889 (2026).","journal-title":"Internet Things"},{"key":"57375_CR8","doi-asserted-by":"publisher","first-page":"76589","DOI":"10.1109\/ACCESS.2024.3406631","volume":"12","author":"I Lamaakal","year":"2024","unstructured":"Lamaakal, I. et al. A TinyDL model for gesture-based air handwriting Arabic numbers and simple Arabic letters recognition. IEEE Access 12, 76589\u201376605 (2024).","journal-title":"IEEE Access"},{"key":"57375_CR9","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","volume":"76","author":"M Abdar","year":"2021","unstructured":"Abdar, M. et al. A review of uncertainty quantification in deep learning: techniques, applications and challenges. Inf. Fusion 76, 243\u2013297. https:\/\/doi.org\/10.1016\/j.inffus.2021.05.008 (2021).","journal-title":"Inf. Fusion"},{"key":"57375_CR10","doi-asserted-by":"publisher","unstructured":"Yahyati, C., Lamaakal, I., Makkaoui, K. E., Ouahbi, I. & Maleh, Y. TinyML-based facial recognition for embedded systems. In 2025 International Conference on Circuit, Systems and Communication (ICCSC) 1\u20136. https:\/\/doi.org\/10.1109\/ICCSC66714.2025.11134957 (IEEE, 2025).","DOI":"10.1109\/ICCSC66714.2025.11134957"},{"issue":"10","key":"57375_CR11","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1145\/3736575","volume":"56","author":"X Zhou","year":"2025","unstructured":"Zhou, X., Chen, B., Gui, Y. & Cheng, L. Conformal prediction: a data perspective. ACM Comput. Surv. 56(10), 201. https:\/\/doi.org\/10.1145\/3736575 (2025).","journal-title":"ACM Comput. Surv."},{"key":"57375_CR12","first-page":"23920","volume":"34","author":"M Minderer","year":"2021","unstructured":"Minderer, M. et al. Revisiting the calibration of modern neural networks under distribution shift. Adv. Neural. Inf. Process. Syst. 34, 23920\u201323933 (2021).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"57375_CR13","unstructured":"Wang, C. (2023). Calibration in deep learning: a survey of the state of the art. Retrieved from arXiv preprint arXiv:2308.01222 (2025)."},{"key":"57375_CR14","unstructured":"Mozafari, A. S., Gomes, H. S., & Gagne, C. Unsupervised temperature scaling: robust post-processing calibration for domain shift. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview. Retrieved from https:\/\/openreview.net\/forum?id=Hyg5TRNtDH (2019)."},{"issue":"3","key":"57375_CR15","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3390\/make8030055","volume":"8","author":"I Lamaakal","year":"2026","unstructured":"Lamaakal, I., Yahyati, C., Maleh, Y., El Makkaoui, K. & Ouahbi, I. Explainable Kolmogorov\u2013Arnold networks for zero-shot human activity recognition on TinyML edge devices. Mach. Learn. Knowl. Extra. 8(3), 55. https:\/\/doi.org\/10.3390\/make8030055 (2026).","journal-title":"Mach. Learn. Knowl. Extra."},{"key":"57375_CR16","doi-asserted-by":"publisher","unstructured":"Lamaakal, I., Yahyati, C., Maleh, Y., El Makkaoui, K. & Ouahbi, I. TrustTiny-HAR: Selective, Open-Set, and Calibrated Activity Recognition on Microcontrollers. https:\/\/doi.org\/10.1109\/TAI.2026.3676723 (Advance online publication, IEEE Transactions on Artificial Intelligence, 2026).","DOI":"10.1109\/TAI.2026.3676723"},{"key":"57375_CR17","doi-asserted-by":"publisher","unstructured":"Miao, S., Chen, L., & Hu, R. (2024). Spatial\u2013temporal masked autoencoder for multi-device wearable human activity recognition. In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) 8(4), 1\u201325. https:\/\/doi.org\/10.1145\/3631415.","DOI":"10.1145\/3631415"},{"key":"57375_CR18","unstructured":"Redding, A., Yu, X., Hu, S., Pannuto, P., & Rosing, T. EmbHD: a library for embedded hyperdimensional computing. In Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems (SenSys) 610\u2013612. Retrieved from https:\/\/patpannuto.com\/pubs\/redding2023embHD.pdf (2023)."},{"key":"57375_CR19","doi-asserted-by":"publisher","unstructured":"Guo, Y., Zhan, Z. & Chen, X. CoR-FHD: communication-efficient and robust federated hyperdimensional learning for smartphone-based HAR. In Distributed Computing and Artificial Intelligence, LNCS15284, 92\u2013103. https:\/\/doi.org\/10.1007\/978-3-031-71467-2_8 (2024).","DOI":"10.1007\/978-3-031-71467-2_8"},{"issue":"4","key":"57375_CR20","doi-asserted-by":"publisher","first-page":"e2023-0093","DOI":"10.1175\/AIES-D-23-0093.1","volume":"3","author":"JS Schreck","year":"2024","unstructured":"Schreck, J. S. et al. Evidential deep learning: enhancing predictive uncertainty estimation for earth system science applications. AI for Earth Syst. 3(4), e2023-0093. https:\/\/doi.org\/10.1175\/AIES-D-23-0093.1 (2024).","journal-title":"AI for Earth Syst."},{"key":"57375_CR21","unstructured":"Lamaakal, I., Yahyati, C., Makkaoui, K. E., Ouahbi, I. & Maleh, Y. TCUQ: single-pass uncertainty quantification from temporal consistency with streaming conformal calibration for TinyML. arXiv preprint arXiv:2508.12905 (2025)."},{"key":"57375_CR22","doi-asserted-by":"crossref","unstructured":"Lamaakal, I., Yahyati, C., Makkaoui, K. E., Ouahbi, I. & Maleh, Y. SNAP-UQ: self-supervised next-activation prediction for single-pass uncertainty in TinyML. arXiv:2508.12907 arXiv preprint (2025).","DOI":"10.1201\/9781003544449-10"},{"issue":"1","key":"57375_CR23","doi-asserted-by":"publisher","first-page":"7414","DOI":"10.1038\/s41598-024-57912-3","volume":"14","author":"X Wei","year":"2024","unstructured":"Wei, X. & Wang, Z. TCN-attention-HAR: human activity recognition based on attention mechanism time convolutional network. Sci. Rep. 14(1), 7414 (2024).","journal-title":"Sci. Rep."},{"key":"57375_CR24","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.future.2024.06.016","volume":"160","author":"MA Al-qaness","year":"2024","unstructured":"Al-qaness, M. A., Dahou, A., Trouba, N. T., Abd Elaziz, M. & Helmi, A. M. TCN-inception: temporal convolutional network and inception modules for sensor-based human activity recognition. Futur. Gener. Comput. Syst. 160, 375\u2013388 (2024).","journal-title":"Futur. Gener. Comput. Syst."},{"key":"57375_CR25","doi-asserted-by":"publisher","first-page":"42335","DOI":"10.1038\/s41598-025-26297-2","volume":"15","author":"I Lamaakal","year":"2025","unstructured":"Lamaakal, I. et al. A tiny inertial transformer for human activity recognition via multimodal knowledge distillation and explainable AI. Sci. Rep. 15, 42335. https:\/\/doi.org\/10.1038\/s41598-025-26297-2 (2025).","journal-title":"Sci. Rep."},{"issue":"1","key":"57375_CR26","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s11831-023-09986-x","volume":"31","author":"P Kumar","year":"2024","unstructured":"Kumar, P., Chauhan, S. & Awasthi, L. K. Human activity recognition (HAR) using deep learning: review, methodologies, progress and future research directions. Archiv. Comput. Methods Eng. 31(1), 179\u2013219 (2024).","journal-title":"Archiv. Comput. Methods Eng."},{"key":"57375_CR27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3633575","author":"C Yahyati","year":"2025","unstructured":"Yahyati, C. et al. A systematic review of state-of-the-art TinyML applications in healthcare, education, and transportation. IEEE Access https:\/\/doi.org\/10.1109\/ACCESS.2025.3633575 (2025).","journal-title":"IEEE Access"},{"issue":"1","key":"57375_CR28","doi-asserted-by":"publisher","first-page":"13830","DOI":"10.1038\/s41598-025-98571-2","volume":"15","author":"H Zhou","year":"2025","unstructured":"Zhou, H., Zhang, X., Feng, Y., Zhang, T. & Xiong, L. Efficient human activity recognition on edge devices using DeepConv LSTM architectures. Sci. Rep. 15(1), 13830 (2025).","journal-title":"Sci. Rep."},{"key":"57375_CR29","doi-asserted-by":"crossref","unstructured":"Lamaakal, I., Yahyati, C., Ouahbi, I., El Makkaoui, K. & Maleh, Y. A survey of model compression techniques for TinyML applications. In 2025 International Conference on Circuit, Systems and Communication (ICCSC) 1\u20136 (IEEE, 2025).","DOI":"10.1109\/ICCSC66714.2025.11135279"},{"issue":"5","key":"57375_CR30","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.3390\/s25051318","volume":"25","author":"I Lamaakal","year":"2025","unstructured":"Lamaakal, I. et al. Tiny language models for automation and control: overview, potential applications, and future research directions. Sensors 25(5), 1318 (2025).","journal-title":"Sensors"},{"issue":"17","key":"57375_CR31","doi-asserted-by":"publisher","first-page":"28111","DOI":"10.1109\/JIOT.2024.3375337","volume":"11","author":"F Luo","year":"2024","unstructured":"Luo, F., Khan, S., Jiang, B. & Wu, K. Vision transformers for human activity recognition using WiFi channel state information. IEEE Internet Things J. 11(17), 28111\u201328122 (2024).","journal-title":"IEEE Internet Things J."},{"issue":"10","key":"57375_CR32","doi-asserted-by":"publisher","first-page":"5515","DOI":"10.1007\/s00521-023-09362-7","volume":"36","author":"G Pareek","year":"2024","unstructured":"Pareek, G., Nigam, S. & Singh, R. Modeling transformer architecture with attention layer for human activity recognition. Neural Comput. Appl. 36(10), 5515\u20135528 (2024).","journal-title":"Neural Comput. Appl."},{"issue":"12","key":"57375_CR33","doi-asserted-by":"publisher","first-page":"5635","DOI":"10.1007\/s11263-024-02117-4","volume":"132","author":"J Yang","year":"2024","unstructured":"Yang, J., Zhou, K., Li, Y. & Liu, Z. Generalized out-of-distribution detection: a survey. Int. J. Comput. Vis. 132(12), 5635\u20135662 (2024).","journal-title":"Int. J. Comput. Vis."},{"key":"57375_CR34","unstructured":"Gal, Y. & Ghahramani, Z. Dropout as a bayesian approximation: representing model uncertainty in deep learning. In International Conference on Machine Learning (PMLR) 1050\u20131059 (2016)."},{"key":"57375_CR35","unstructured":"Lakshminarayanan, B., Pritzel, A. & Blundell, C. Simple and scalable predictive uncertainty estimation using deep ensembles. In Advances in Neural Information Processing Systems 30 (2017)."},{"key":"57375_CR36","first-page":"20089","volume":"34","author":"E Daxberger","year":"2021","unstructured":"Daxberger, E. et al. Laplace redux-effortless Bayesian deep learning. Adv. Neural. Inf. Process. Syst. 34, 20089\u201320103 (2021).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"57375_CR37","unstructured":"Wang, H., Ji. & Q. Beyond dirichlet-based models: when Bayesian neural networks meet evidential deep learning. In The 40th Conference on Uncertainty in Artificial Intelligence (2024)."},{"issue":"1","key":"57375_CR38","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1109\/JETCAS.2023.3242767","volume":"13","author":"CY Chang","year":"2023","unstructured":"Chang, C. Y., Chuang, Y. C., Huang, C. T. & Wu, A. Y. Recent progress and development of hyperdimensional computing (HDC) for edge intelligence. IEEE J. Emerg. Sel. Top. Circuits Syst. 13(1), 119\u2013136 (2023).","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"issue":"6","key":"57375_CR39","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1038\/s41928-020-0410-3","volume":"3","author":"G Karunaratne","year":"2020","unstructured":"Karunaratne, G. et al. In-memory hyperdimensional computing. Nat. Electron. 3(6), 327\u2013337 (2020).","journal-title":"Nat. Electron."},{"key":"57375_CR40","doi-asserted-by":"publisher","first-page":"97651","DOI":"10.1109\/ACCESS.2021.3059762","volume":"10","author":"E Hassan","year":"2021","unstructured":"Hassan, E., Halawani, Y., Mohammad, B. & Saleh, H. Hyper-dimensional computing challenges and opportunities for AI applications. IEEE Access 10, 97651\u201397664 (2021).","journal-title":"IEEE Access"},{"key":"57375_CR41","doi-asserted-by":"crossref","unstructured":"Khaleghi, B., Yu, X., Kang, J., Wang, X. & Rosing, T. Private and efficient learning with hyperdimensional computing. In IEEE Transactions on Circuits and Systems for Artificial Intelligence (2024).","DOI":"10.1109\/TCASAI.2024.3481193"},{"issue":"549","key":"57375_CR42","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1080\/01621459.2024.2344700","volume":"120","author":"Y Yang","year":"2025","unstructured":"Yang, Y. & Kuchibhotla, A. K. Selection and aggregation of conformal prediction sets. J. Am. Stat. Assoc. 120(549), 435\u2013447 (2025).","journal-title":"J. Am. Stat. Assoc."},{"key":"57375_CR43","unstructured":"Oursland, A. Interpreting neural networks through Mahalanobis distance. arXiv:2410.19352 arXiv preprint (2024)."},{"key":"57375_CR44","doi-asserted-by":"crossref","unstructured":"Yu, Y., Zhu, Y., Wan, D., Liu, H. & Zhao, Q. A novel symbolic aggregate approximation for time series. In International Conference on Ubiquitous Information Management and Communication 805\u2013822 (Springer International Publishing, Cham, 2019).","DOI":"10.1007\/978-3-030-19063-7_65"},{"issue":"1","key":"57375_CR45","first-page":"3","volume":"3","author":"D Anguita","year":"2013","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X. & Reyes-Ortiz, J. L. A public domain dataset for human activity recognition using smartphones. ESANN 3(1), 3\u20134 (2013).","journal-title":"ESANN"},{"issue":"2","key":"57375_CR46","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1145\/1964897.1964918","volume":"12","author":"JR Kwapisz","year":"2011","unstructured":"Kwapisz, J. R., Weiss, G. M. & Moore, S. A. Activity recognition using cell phone accelerometers. ACM SIGKDD Explor. Newsl. 12(2), 74\u201382 (2011).","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"57375_CR47","doi-asserted-by":"crossref","unstructured":"Reiss, A. & Stricker, D. Introducing a new benchmarked dataset for activity monitoring. In 2012 16th International Symposium on Wearable Computers 108\u2013109 (IEEE, 2012).","DOI":"10.1109\/ISWC.2012.13"},{"key":"57375_CR48","doi-asserted-by":"crossref","unstructured":"Roggen, D. et al. Collecting complex activity datasets in highly rich networked sensor environments. In 2010 Seventh International Conference on Networked Sensing Systems (INSS) 233\u2013240. (IEEE, 2010).","DOI":"10.1109\/INSS.2010.5573462"},{"key":"57375_CR49","first-page":"380","volume":"5","author":"O Rodrigues","year":"1840","unstructured":"Rodrigues, O. Des lois g\u00e9om\u00e9triques qui r\u00e9gissent les d\u00e9placements d\u2019un syst\u00e8me solide dans l\u2019espace, et de la variation des coordonn\u00e9es provenant de ces d\u00e9placements consid\u00e9r\u00e9s ind\u00e9pendamment des causes qui peuvent les produire. Journal de math\u00e9matiques pures et appliqu\u00e9es 5, 380\u2013440 (1840).","journal-title":"Journal de math\u00e9matiques pures et appliqu\u00e9es"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57375-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57375-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57375-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T23:16:59Z","timestamp":1787267819000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57375-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["57375"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-57375-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,9]]},"assertion":[{"value":"27 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"26262"}}