{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T12:24:08Z","timestamp":1787228648736,"version":"build-2736575974"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Egyptian Russian University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Human Activity Recognition (HAR) using wearable sensors is relevant to rehabilitation, assistive robotics, and mobile health applications. This study presents (i) SDALLE, a publicly available multimodal dataset integrating surface electromyography (EMG) and inertial measurement unit (IMU) signals acquired using a DELSYS Trigno wireless system; (ii) a harmonized, subject-dependent comparison with the public ENABL3S dataset; and (iii) an exploratory Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) augmentation strategy for class balancing. SDALLE contains recordings of nine healthy male subjects walking, jogging, climbing stairs and descending stairs. EMG and IMU signals were synchronized, standardized, and segmented using 75%-overlapping windows. In the implemented pipeline, feature standardization preceded segmentation, after which the windows were randomly divided into 70% training and 30% testing subsets without participant- or trial-level grouping. Consequently, overlapping windows, including windows from the same participant and trial, could occur in both subsets. Under this window-level protocol, attention-enhanced CNN\u2013LSTM models recorded approximately 98\u201399% accuracy on ENABL3S and approximately 99% on SDALLE. These values are protocol-specific and may be optimistic; they do not measure generalization to unseen participants or establish a portable model ranking. GAN augmentation increased the SDALLE row count by approximately 12% and changed average testing accuracy from 96.9% before augmentation to 96.5% afterward under the implemented protocol. The study therefore provides a dataset resource and an exploratory subject-dependent comparison of predictive and computational behavior. Participant-independent evaluation with training-fold-only normalization, model selection, and GAN training is required before drawing conclusions about cross-subject robustness or deployment readiness.<\/jats:p>","DOI":"10.1038\/s41598-026-64847-4","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T11:16:06Z","timestamp":1787224566000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A multimodal EMG\u2013IMU dataset and multi-dataset benchmark for deep learning-based human activity recognition"],"prefix":"10.1038","volume":"16","author":[{"given":"Mohamed Khaled","family":"Farouk","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed Fawzy","family":"El-Khatib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed I.","family":"Awad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mostafa R. A.","family":"Atia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A.","family":"Abdellatif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"64847_CR1","doi-asserted-by":"publisher","unstructured":"Banyai, A. D. & Bri\u0219an, C. Robotics in physical rehabilitation: Systematic review. Healthcare  12,  1720. https:\/\/doi.org\/10.3390\/HEALTHCARE12171720 (2024).","DOI":"10.3390\/HEALTHCARE12171720"},{"key":"64847_CR2","doi-asserted-by":"publisher","unstructured":"Aner, E. A., Shehata, O. M., Awad, M. I. & ElHady, N. E. A Decade of soft robotic manipulators: Advances in design, modeling, control, and emerging challenges. J. Bionic Eng.  23,  55\u201398. https:\/\/doi.org\/10.1007\/s42235-025-00819-0 (2025).","DOI":"10.1007\/s42235-025-00819-0"},{"key":"64847_CR3","doi-asserted-by":"publisher","unstructured":"Windrich, M., Grimmer, M., Christ, O., Rinderknecht, S. & Beckerle, P. Active lower limb prosthetics: A systematic review of design issues and solutions. Biomed. Eng. Online. 15(3), 5\u201319. https:\/\/doi.org\/10.1186\/S12938-016-0284-9\/TABLES\/3 (2016).","DOI":"10.1186\/S12938-016-0284-9\/TABLES\/3"},{"key":"64847_CR4","doi-asserted-by":"publisher","unstructured":"Kim, M., Simon, A. M. & Hargrove, L. J. Seamless and intuitive control of a powered prosthetic leg using deep neural network for transfemoral amputees. Wearable Technol. 3, e24. https:\/\/doi.org\/10.1017\/WTC.2022.19 (2022).","DOI":"10.1017\/WTC.2022.19"},{"key":"64847_CR5","doi-asserted-by":"publisher","unstructured":"D\u2019Onofrio, G. & Sancarlo, D. Assistive robots for healthcare and human-robot interaction. Sensors (Basel). 23(4). https:\/\/doi.org\/10.3390\/s23041883 (2023).","DOI":"10.3390\/s23041883"},{"key":"64847_CR6","doi-asserted-by":"publisher","unstructured":"Alim, A. & Imtiaz, M. H. Wearable sensors for the monitoring of maternal health: A systematic review. Sensors (Basel). 23(5). https:\/\/doi.org\/10.3390\/s23052411 (2023).","DOI":"10.3390\/s23052411"},{"key":"64847_CR7","doi-asserted-by":"publisher","unstructured":"Schrader, L. et al. Advanced sensing and human activity recognition in early intervention and rehabilitation of elderly people. J. Popul. Ageing 13,  139\u2013165. https:\/\/doi.org\/10.1007\/S12062-020-09260-Z\/TABLES\/4 (2020).","DOI":"10.1007\/S12062-020-09260-Z\/TABLES\/4"},{"key":"64847_CR8","doi-asserted-by":"publisher","unstructured":"Minh Dang, L. et al. Sensor-based and vision-based human activity recognition: A comprehensive survey. Pattern Recognit. 108, 107561. https:\/\/doi.org\/10.1016\/J.PATCOG.2020.107561 (2020).","DOI":"10.1016\/J.PATCOG.2020.107561"},{"key":"64847_CR9","doi-asserted-by":"publisher","unstructured":"Prakash, C., Kumar, R. & Mittal, N. Recent developments in human gait research: Parameters, approaches, applications, machine learning techniques, datasets and challenges. Artif. Intell. Rev. 49(1), 1\u201340. https:\/\/doi.org\/10.1007\/S10462-016-9514-6\/TABLES\/5 (2018).","DOI":"10.1007\/S10462-016-9514-6\/TABLES\/5"},{"key":"64847_CR10","doi-asserted-by":"publisher","unstructured":"Malesevic, N., Svensson, I., H\u00e4gglund, G. & Antfolk, C. An Integrated approach for real-time monitoring of knee dynamics with IMUs and multichannel EMG. Sensors. 23(21), 8955. https:\/\/doi.org\/10.3390\/S23218955 (2023).","DOI":"10.3390\/S23218955"},{"key":"64847_CR11","doi-asserted-by":"crossref","unstructured":"Dimitrov, H., Bull, A. M. J. & Farina, D. High-density EMG, IMU, kinetic, and kinematic open-source data for comprehensive locomotion activities. Sci. Data. 10(1), 1\u201310  (2023).","DOI":"10.1038\/s41597-023-02679-x"},{"key":"64847_CR12","doi-asserted-by":"publisher","unstructured":"Brambilla, C. et al. Combined use of EMG and EEG techniques for neuromotor assessment in rehabilitative applications: A systematic review. Sensors. 21(21), 7014. https:\/\/doi.org\/10.3390\/S21217014 (2021).","DOI":"10.3390\/S21217014"},{"key":"64847_CR13","doi-asserted-by":"publisher","unstructured":"Halim, A., Abdellatif, A., Awad, M. I. & Atia, M. R. A. Prediction of human gait activities using wearable sensors (2021). https:\/\/doi.org\/10.1177\/09544119211001238","DOI":"10.1177\/09544119211001238"},{"key":"64847_CR14","unstructured":"Deep Learning for Time Series Forecasting: Predict the Future with MLPs \u2026 Jason Brownlee - Google Books. Accessed: Dec. 07, 2024."},{"key":"64847_CR15","doi-asserted-by":"publisher","unstructured":"Haresamudram, H., Tang, C. I., Suh, S., Lukowicz, P. & Pl\u00f6tz, T. Past, present, and future of sensor-based human activity recognition using wearables: A surveying tutorial on a still challenging task. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. https:\/\/doi.org\/10.1145\/3729467 (2025).","DOI":"10.1145\/3729467"},{"key":"64847_CR16","doi-asserted-by":"publisher","unstructured":"Camacho Carlos, W. et al. Human activity recognition: An approach 2D CNN-LSTM to sequential image representation and processing of inertial sensor data  (2024). https:\/\/doi.org\/10.3934\/bioeng.2024024","DOI":"10.3934\/bioeng.2024024"},{"key":"64847_CR17","doi-asserted-by":"publisher","unstructured":"Pienaar, S. W. & Malekian, R. Human activity recognition using LSTM-RNN deep neural network architecture. 2019 IEEE 2nd Wireless Africa Conference, WAC 2019 - Proceedings  (2019). https:\/\/doi.org\/10.1109\/AFRICA.2019.8843403","DOI":"10.1109\/AFRICA.2019.8843403"},{"key":"64847_CR18","doi-asserted-by":"publisher","unstructured":"Kreuzer, D. & Munz, M. Deep convolutional and LSTM networks on multi-channel time series data for gait phase recognition. Sensors  21, 789. https:\/\/doi.org\/10.3390\/s21030789  (2021).","DOI":"10.3390\/s21030789"},{"key":"64847_CR19","doi-asserted-by":"publisher","unstructured":"Akter, M., Ansary, S., Khan, M. A. M. & Kim, D. Human Activity Recognition Using Attention-Mechanism-Based Deep Learning Feature Combination,Sensors, 23, 5715. https:\/\/doi.org\/10.3390\/S23125715 (2023).","DOI":"10.3390\/S23125715"},{"key":"64847_CR20","doi-asserted-by":"publisher","unstructured":"Farouk, M. K. Attention-enhanced CNN-LSTM models for sensor-based human activity recognition: A comparative study. Int. J. Mechatronics Appl. Mech. 2025 https:\/\/doi.org\/10.17683\/ijomam\/issue20 (2025).","DOI":"10.17683\/ijomam\/issue20"},{"key":"64847_CR21","doi-asserted-by":"publisher","unstructured":"Sikder, N. & Al Nahid, A. KU-HAR: An open dataset for heterogeneous human activity recognition. Pattern Recognit. Lett. 146, 46\u201354. https:\/\/doi.org\/10.1016\/j.patrec.2021.02.024 (2021).","DOI":"10.1016\/j.patrec.2021.02.024"},{"key":"64847_CR22","doi-asserted-by":"publisher","unstructured":"Nahid, A. A., Sikder, N. & Rafi, I. KU-HAR: An open dataset for human activity recognition (2021). https:\/\/doi.org\/10.17632\/45F952Y38R.5","DOI":"10.17632\/45F952Y38R.5"},{"key":"64847_CR23","unstructured":"Anguita, D., Ghio, A., Oneto, L., Parra, X. & Reyes-Ortiz, J. L. A public domain dataset for human activity recognition using smartphones. The European Symposium on Artificial Neural Networks  (2013)."},{"key":"64847_CR24","unstructured":"Human Activity Recognition Using Smartphones - UCI Machine Learning Repository. Accessed: Feb. 05, 2026. [Online]. https:\/\/archive.ics.uci.edu\/dataset\/240\/human+activity+recognition+using+smartphones"},{"key":"64847_CR25","doi-asserted-by":"publisher","unstructured":"Peppas, K., Tsolakis, A. C., Krinidis, S. & Tzovaras, D. Real-time physical activity recognition on smart mobile devices using convolutional neural networks. Appl. Sci.. 10(23), 8482. https:\/\/doi.org\/10.3390\/app10238482 (2020).","DOI":"10.3390\/app10238482"},{"key":"64847_CR26","unstructured":"Lab, W. I. S. D. M. Dataset. Accessed: Feb. 05, 2026. [Online].  https:\/\/www.cis.fordham.edu\/wisdm\/dataset.php"},{"key":"64847_CR27","unstructured":"PAMAP2 Physical Activity Monitoring - UCI Machine Learning Repository. Accessed: Feb. 05, 2026. [Online]. https:\/\/archive.ics.uci.edu\/dataset\/231\/pamap2+physical+activity+monitoring"},{"key":"64847_CR28","doi-asserted-by":"publisher","unstructured":"Hu, B., Rouse, E. & Hargrove, L. Benchmark datasets for Bilateral Lower-limb neuromechanical signals from wearable sensors during unassisted locomotion in able-bodied individuals. Front. Robot. AI. https:\/\/doi.org\/10.3389\/FROBT.2018.00014\/FULL (2018).","DOI":"10.3389\/FROBT.2018.00014\/FULL"},{"key":"64847_CR29","unstructured":"Item -. Benchmark datasets for bilateral lower limb neuromechanical signals from wearable sensors during unassisted locomotion in able-bodied individuals - figshare - Figshare. Accessed: Feb. 05, 2026. https:\/\/figshare.com\/articles\/dataset\/Benchmark_datasets_for_bilateral_lower_limb_neuromechanical_signals_from_wearable_sensors_during_unassisted_locomotion_in_able-bodied_individuals\/5362627?file=13035155"},{"key":"64847_CR30","unstructured":"Hu, Y. & Wang, Y. BSDGAN: Balancing sensor data generative adversarial networks for human activity recognition. Proceedings of the International Joint Conference on Neural Networks http:\/\/arxiv.org\/abs\/2208.03647"},{"key":"64847_CR31","doi-asserted-by":"publisher","unstructured":"Abdellatif Hamed Ibrahim, A.  et al. DATASET_SDALLE. https:\/\/doi.org\/10.5281\/ZENODO.14841611","DOI":"10.5281\/ZENODO.14841611"},{"key":"64847_CR32","doi-asserted-by":"publisher","unstructured":"Llaurad\u00f3, B. et al. Generative models for data augmentation on inertial measurement units data classification. Front. Artif. Intell. Appl. 390, 68\u201377. https:\/\/doi.org\/10.3233\/FAIA240412 (2024).","DOI":"10.3233\/FAIA240412"},{"key":"64847_CR33","unstructured":"Xiao, B. The Signature-Wasserstein GAN for Time Series Generation and Beyond, Doctoral thesis, UCL (University College London) (2023)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-64847-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-64847-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-64847-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T11:28:10Z","timestamp":1787225290000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-64847-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["64847"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-64847-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]},"assertion":[{"value":"28 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 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"}},{"value":"The study protocol involving human participants was reviewed and approved by the Scientific Research Ethical Committee, Faculty of Pharmacy, Egyptian Russian University (ERU), Cairo, Egypt (Reference No. ERUFE-MR-26-001; approval date: 13 May 2026). All experimental procedures were conducted in accordance with the relevant ethical guidelines and regulations for research involving human participants.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"26180"}}