{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T19:00:46Z","timestamp":1785438046676,"version":"3.56.0"},"reference-count":21,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Agenia Nationala pentru Cercetare si Dezvoltare","award":["25.80013.5007.09RE"],"award-info":[{"award-number":["25.80013.5007.09RE"]}]},{"award":["25.80013.5007.09RE"],"award-info":[{"award-number":["25.80013.5007.09RE"]}],"id":[{"id":"https:\/\/ror.org\/04kp6rb84","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Electromyographic (EMG) signals are increasingly used in wearable cyber\u2013physical systems (CPS), where reliable movement recognition must be achieved under limited computational resources. In this study, we present a compact EMG processing framework that integrates signal acquisition, preprocessing, segmentation, and movement classification within a unified pipeline designed for embedded-oriented applications. The proposed approach combines a multi-channel EMG acquisition system with a lightweight one-dimensional convolutional neural network (1D CNN) developed according to TinyML principles, withprocessing input windows of size 32 \u00d7 3 and low computational complexity and memory requirements. Experimental evaluation was conducted on a dataset collected from 15 participants performing squat, walking, and running activities under realistic acquisition conditions. The proposed model achieved an accuracy of 0.9135, an F1-score of 0.9124, and a ROC AUC of approximately 0.96, demonstrating reliable classification performance. Following 8-bit quantization, the model size was reduced to approximately 2 KB, supporting deployment on resource-constrained embedded platforms. The results show that compact CNN architectures can effectively classify EMG-based movement patterns while maintaining a small computational footprint, providing a practical foundation for future wearable CPS and TinyML-enabled applications.<\/jats:p>","DOI":"10.3390\/s26123862","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T15:11:22Z","timestamp":1781709082000},"page":"3862","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Design and Evaluation of a Compact CNN for EMG-Based Wearable Systems Under Embedded Constraints"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1726-792X","authenticated-orcid":false,"given":"Valentina","family":"Tirsu","sequence":"first","affiliation":[{"name":"Department of Telecommunications and Electronic Systems, Faculty of Electronics and Telecommunications, Technical University of Moldova, 2004 Chisinau, Moldova"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0518-035X","authenticated-orcid":false,"given":"Andrei","family":"Dorogan","sequence":"additional","affiliation":[{"name":"Department of Telecommunications and Electronic Systems, Faculty of Electronics and Telecommunications, Technical University of Moldova, 2004 Chisinau, Moldova"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lilia","family":"Sava","sequence":"additional","affiliation":[{"name":"Department of Telecommunications and Electronic Systems, Faculty of Electronics and Telecommunications, Technical University of Moldova, 2004 Chisinau, Moldova"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5076-0695","authenticated-orcid":false,"given":"Larisa","family":"Dunai","sequence":"additional","affiliation":[{"name":"Department of Graphic Engineering, Universitat Polit\u00e8cnica de Val\u00e8ncia, 46022 Valencia, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandru","family":"Ilev","sequence":"additional","affiliation":[{"name":"Department of Telecommunications and Electronic Systems, Faculty of Electronics and Telecommunications, Technical University of Moldova, 2004 Chisinau, Moldova"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7651-8475","authenticated-orcid":false,"given":"Nelea","family":"Manin","sequence":"additional","affiliation":[{"name":"Department of Telecommunications and Electronic Systems, Faculty of Electronics and Telecommunications, Technical University of Moldova, 2004 Chisinau, Moldova"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Heydari, S., and Mahmoud, Q.H. (2025). Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions. Sensors, 25.","DOI":"10.3390\/s25103191"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ozdemir, M.A., Kisa, D.H., Guren, O., and Akan, A. (2022). Dataset for Multi-Channel Surface Electromyography (sEMG) Signals of Hand Gestures. Data Brief, 41.","DOI":"10.1016\/j.dib.2022.107921"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Atzori, M., Gijsberts, A., Castellini, C., Caputo, B., Mittaz Hager, A.-G., Elsig, S., Giatsidis, G., Bassetto, F., and M\u00fcller, H. (2014). Electromyography Data for Non-Invasive Naturally-Controlled Robotic Hand Prostheses. Sci. Data, 1.","DOI":"10.1038\/sdata.2014.53"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1038\/s41597-022-01836-y","article-title":"Multi-Day Dataset of Forearm and Wrist Electromyogram for Hand Gesture Recognition and Biometrics","volume":"9","author":"Pradhan","year":"2022","journal-title":"Sci. Data"},{"key":"ref_5","unstructured":"Banbury, C.R., Reddi, V.J., Lam, M., Fu, W., Fazel, A., Holleman, J., Huang, X., Hurtado, R., Kanter, D., and Lokhmotov, A. (2020). Benchmarking TinyML Systems: Challenges and Directions. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ramasamy, L.K., Khan, F., Shah, M., Prasad, B.V.V.S., Iwendi, C., and Biamba, C. (2022). Secure Smart Wearable Computing through Artificial Intelligence-Enabled Internet of Things and Cyber-Physical Systems for Health Monitoring. Sensors, 22.","DOI":"10.3390\/s22031076"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Perilli, S., Di Pietro, M., Mantini, E., Regazzetti, M., Kiper, P., Galliani, F., Panella, M., and Mantini, D. (2024). Development of a Wearable Electromyographic Sensor with Aerosol Jet Printing Technology. Bioengineering, 11.","DOI":"10.3390\/bioengineering11121283"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Qiu, F., Liu, X., and Ye, X. (2025). Influence of Electrode Placement on the Recognition of Different Gesture Categories Using High-Density sEMG. Front. Neurosci., 19.","DOI":"10.3389\/fnins.2025.1750792"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kim, E., Shin, J., Kwon, Y., and Park, B. (2023). EMG-Based Dynamic Hand Gesture Recognition Using Edge AI for Human\u2013Robot Interaction. Electronics, 12.","DOI":"10.3390\/electronics12071541"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Shin, S., Kang, M., Jung, J., and Kim, Y.T. (2021). Development of Miniaturized Wearable Wristband Type Surface EMG Measurement System for Biometric Authentication. Electronics, 10.","DOI":"10.3390\/electronics10080923"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Dunai, L. (2022). Active Lower Limb Exoskeleton for Walking and Stand Up. Proceedings of the IECON 2022\u201448th Annual Conference of the IEEE Industrial Electronics Society, Brussels, Belgium, 17\u201320 October 2022, IEEE.","DOI":"10.1109\/IECON49645.2022.9968354"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/TMRB.2020.3048255","article-title":"A Deep Learning Model for Automated Classification of Intraoperative Continuous EMG","volume":"3","author":"Zha","year":"2021","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, L., Fu, J., Wu, Y., Li, H., and Zheng, B. (2020). Hand Gesture Recognition Using Compact CNN via Surface Electromyography Signals. Sensors, 20.","DOI":"10.3390\/s20030672"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Prabhakar, S.K., and Won, D.-O. (2023). Efficient Strategies for Finger Movement Classification Using Surface Electromyogram Signals. Front. Neurosci., 17.","DOI":"10.3389\/fnins.2023.1168112"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1080\/10255842.2023.2287419","article-title":"Multi-Scale EMG Classification with Spatial-Temporal Attention for Prosthetic Hands","volume":"28","author":"Emimal","year":"2025","journal-title":"Comput. Methods Biomech. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sahnoun, S., Mnif, M., Ghoul, B., Jemal, M., Fakhfakh, A., and Kanoun, O. (2025). Hybrid Solution Through Systematic Electrical Impedance Tomography Data Reduction and CNN Compression for Efficient Hand Gesture Recognition on Resource-Constrained IoT Devices. Future Internet, 17.","DOI":"10.3390\/fi17020089"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bhamare, M., Kulkarni, P.V., Rane, R., Bobde, S., and Patankar, R. (2024). TinyML Applications and Use Cases for Healthcare. TinyML and Edge Intelligence for IoT Applications, Elsevier.","DOI":"10.1016\/B978-0-44-322202-3.00019-1"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yamashita, J.V.Y.B., Leite, J.P.R.R., and Machado, J.B. (2025). TinyML Implementation of CNN-Based Gait Analysis for Low-Cost Motorized Prosthetics: A Proof-of-Concept. Technologies, 13.","DOI":"10.20944\/preprints202509.2473.v1"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sul, J.-H., Piyathilaka, L., Moratuwage, D., Dunu Arachchige, S., Jayawardena, A., Kahandawa, G., and Preethichandra, D.M.G. (2025). Electromyography Signal Acquisition, Filtering, and Data Analysis for Exoskeleton Development. Sensors, 25.","DOI":"10.3390\/s25134004"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1016\/j.jksuci.2021.11.019","article-title":"A Review on TinyML: State-of-the-Art and Prospects","volume":"34","author":"Ray","year":"2022","journal-title":"J. King Saud Univ.\u2013Comput. Inf. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Phinyomark, A., Khushaba, R.N., and Scheme, E. (2018). Feature extraction and selection for myoelectric control based on wearable EMG sensors. Sensors, 18.","DOI":"10.3390\/s18051615"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3862\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T04:47:59Z","timestamp":1781844479000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3862"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":21,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123862"],"URL":"https:\/\/doi.org\/10.3390\/s26123862","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]}}}