{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T13:22:10Z","timestamp":1791379330969,"version":"4.3.2"},"reference-count":41,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:00:00Z","timestamp":1750291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Recovery and Resilience Plan (NRRP)","award":["ECS00000041"],"award-info":[{"award-number":["ECS00000041"]}]},{"name":"National Recovery and Resilience Plan (NRRP)","award":["CUP I33C22001330007"],"award-info":[{"award-number":["CUP I33C22001330007"]}]},{"name":"National Recovery and Resilience Plan (NRRP)","award":["0001057.23-06-2022"],"award-info":[{"award-number":["0001057.23-06-2022"]}]},{"name":"European Union\u2014NextGenerationEU","award":["ECS00000041"],"award-info":[{"award-number":["ECS00000041"]}]},{"name":"European Union\u2014NextGenerationEU","award":["CUP I33C22001330007"],"award-info":[{"award-number":["CUP I33C22001330007"]}]},{"name":"European Union\u2014NextGenerationEU","award":["0001057.23-06-2022"],"award-info":[{"award-number":["0001057.23-06-2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accelerometers are nowadays included in almost any portable or mobile device, including smartphones, smartwatches, wrist-bands, and even smart rings. The data collected from them is therefore an ideal candidate to tackle human motion recognition, as it can easily and unobtrusively be acquired. In this work we analyze the performance of a hand-gesture classification system implemented using LSTM neural networks on a resource-constrained microcontroller platform, which required trade-offs between network accuracy and resource utilization. Using a publicly available dataset, which includes data for 20 different hand gestures recorded from 10 subjects using a wrist-worn device with a 3-axial accelerometer, we achieved nearly 90.25% accuracy while running the model on an STM32L4-series microcontroller, with an inference time of 418 ms for 4 s sequences, corresponding to an average CPU usage of about 10% for the recognition task.<\/jats:p>","DOI":"10.3390\/s25123831","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T03:05:27Z","timestamp":1750388727000},"page":"3831","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Microcontroller Implementation of LSTM Neural Networks for Dynamic Hand Gesture Recognition"],"prefix":"10.3390","volume":"25","author":[{"given":"Kevin","family":"Di Leo","sequence":"first","affiliation":[{"name":"DII\u2014Dipartimento di Ingegneria dell\u2019Informazione, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche 12, I-60131 Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6601-0039","authenticated-orcid":false,"given":"Giorgio","family":"Biagetti","sequence":"additional","affiliation":[{"name":"DII\u2014Dipartimento di Ingegneria dell\u2019Informazione, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche 12, I-60131 Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3183-7682","authenticated-orcid":false,"given":"Laura","family":"Falaschetti","sequence":"additional","affiliation":[{"name":"DII\u2014Dipartimento di Ingegneria dell\u2019Informazione, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche 12, I-60131 Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4504-7550","authenticated-orcid":false,"given":"Paolo","family":"Crippa","sequence":"additional","affiliation":[{"name":"DII\u2014Dipartimento di Ingegneria dell\u2019Informazione, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche 12, I-60131 Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1186\/s12938-018-0567-4","article-title":"Human activity monitoring system based on wearable sEMG and accelerometer wireless sensor nodes","volume":"17","author":"Biagetti","year":"2018","journal-title":"Biomed. Eng. Online"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3473","DOI":"10.1016\/j.procs.2022.09.406","article-title":"ECG-Based Arrhythmia Classification using Recurrent Neural Networks in Embedded Systems","volume":"207","author":"Falaschetti","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.1109\/TETC.2020.3027454","article-title":"Online Fall Detection Using Recurrent Neural Networks on Smart Wearable Devices","volume":"9","author":"Musci","year":"2021","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Alessandrini, M., Biagetti, G., Crippa, P., Falaschetti, L., and Turchetti, C. (2021). Recurrent Neural Network for Human Activity Recognition in Embedded Systems Using PPG and Accelerometer Data. Electronics, 10.","DOI":"10.3390\/electronics10141715"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1355","DOI":"10.1007\/s00779-020-01472-6","article-title":"Continuous touch gesture recognition based on RNNs for capacitive proximity sensors","volume":"26","author":"Carrabina","year":"2022","journal-title":"Pers. Ubiquitous Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1007\/978-981-19-3444-5_40","article-title":"A Lightweight and Accurate RNN in Wearable Embedded Systems for Human Activity Recognition","volume":"309","author":"Falaschetti","year":"2022","journal-title":"Smart Innov. Syst. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"35394","DOI":"10.1109\/JSEN.2024.3450499","article-title":"MHCNLS-HAR: Multiheaded CNN-LSTM-Based Human Activity Recognition Leveraging a Novel Wearable Edge Device for Elderly Health Care","volume":"24","author":"Gaud","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/LES.2024.3410024","article-title":"Wireless Tag Sensor Network for Apnea Detection and Posture Recognition Using LSTM","volume":"16","author":"Saddaoui","year":"2024","journal-title":"IEEE Embed. Syst. Lett."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yu, X., Qiu, H., and Xiong, S. (2020). A Novel Hybrid Deep Neural Network to Predict Pre-impact Fall for Older People Based on Wearable Inertial Sensors. Front. Bioeng. Biotechnol., 8.","DOI":"10.3389\/fbioe.2020.00063"},{"key":"ref_11","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2025, April 03). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: https:\/\/zenodo.org\/records\/15009305."},{"key":"ref_12","unstructured":"STMicroelectronics (2025, April 03). X-CUBE-AI\u2014AI Expansion Pack for STM32CubeMX\u2014STMicroelectronics. Available online: https:\/\/www.st.com\/en\/embedded-software\/x-cube-ai.html."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sinkevych, O., Boyko, Y., Rechynskyi, O., Sokolovskii, B., and Monastyrskii, L. (2021, January 19\u201321). Embedding Sequence Model in STM32 Based Neuro-Controller. Proceedings of the 2021 IEEE 12th International Conference on Electronics and Information Technologies (ELIT), Lviv, Ukraine.","DOI":"10.1109\/ELIT53502.2021.9501132"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1016\/j.procs.2018.07.255","article-title":"A comparative study of machine learning algorithms for physiological signal classification","volume":"126","author":"Biagetti","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3878","DOI":"10.1109\/JBHI.2023.3276629","article-title":"An End-to-End Energy-Efficient Approach for Intake Detection With Low Inference Time Using Wrist-Worn Sensor","volume":"27","author":"Wei","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kumari, N., Yadagani, A., Behera, B., Semwal, V.B., and Mohanty, S. (2024). Human motion activity recognition and pattern analysis using compressed deep neural networks. Comput. Methods Biomech. Biomed. Eng. Imaging Vis., 12.","DOI":"10.1080\/21681163.2024.2331052"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"145003","DOI":"10.1109\/ACCESS.2024.3472469","article-title":"AI-Based Sensory Glove System to Recognize Bengali Sign Language (BaSL)","volume":"12","author":"Begum","year":"2024","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s11554-024-01435-7","article-title":"Real-time attention-based embedded LSTM for dynamic sign language recognition on edge devices","volume":"21","author":"Sharma","year":"2024","journal-title":"J. Real-Time Image Process."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"10589","DOI":"10.1109\/LRA.2022.3191232","article-title":"A Wearable Smart Glove and Its Application of Pose and Gesture Detection to Sign Language Classification","volume":"7","author":"DelPreto","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Makaussov, O., Krassavin, M., Zhabinets, M., and Fazli, S. (2020, January 11\u201314). A Low-Cost, IMU-Based Real-Time On Device Gesture Recognition Glove. Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada.","DOI":"10.1109\/SMC42975.2020.9283231"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"15065","DOI":"10.1109\/JSEN.2021.3074642","article-title":"Gesture Recognition Using Wearable Sensors With Bi-Long Short-Term Memory Convolutional Neural Networks","volume":"21","author":"Vu","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3103","DOI":"10.1016\/j.procs.2020.09.178","article-title":"Machine Learning and Data Fusion Techniques Applied to Physical Activity Classification Using Photoplethysmographic and Accelerometric Signals","volume":"176","author":"Biagetti","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"ref_23","unstructured":"Chevalier, G. (2021, April 16). LSTMs for humAn Activity Recognition. Available online: https:\/\/github.com\/guillaume-chevalier\/LSTM-Human-Activity-Recognition."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Aklah, Z.T., Hassan, H.T., Al-Safi, A., and Aljabery, K. (2024). Fall Detection in Q-eBall: Enhancing Gameplay Through Sensor-Based Solutions. J. Sens. Actuator Netw., 13.","DOI":"10.3390\/jsan13060077"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Coffen, B., and Mahmud, M. (2021, January 1\u20132). TinyDL: Edge Computing and Deep Learning Based Real-time Hand Gesture Recognition Using Wearable Sensor. Proceedings of the 2020 IEEE International Conference on E-health Networking, Application & Services (HEALTHCOM), Shenzhen, China.","DOI":"10.1109\/HEALTHCOM49281.2021.9399005"},{"key":"ref_26","unstructured":"Costante, G., Porzi, L., Lanz, O., Valigi, P., and Ricci, E. (2014, January 1\u20135). Personalizing a smartwatch-based gesture interface with transfer learning. Proceedings of the 2014 22nd European Signal Processing Conference (EUSIPCO), Lisbon, Portugal."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.cviu.2019.01.008","article-title":"Heterogeneous hand gesture recognition using 3D dynamic skeletal data","volume":"181","author":"Wannous","year":"2019","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/TMM.2014.2374357","article-title":"Superpixel-Based Hand Gesture Recognition With Kinect Depth Camera","volume":"17","author":"Wang","year":"2015","journal-title":"IEEE Trans. Multimed."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Gupta, S., Kim, K., and Kautz, J. (2015, January 7\u201312). Hand gesture recognition with 3D convolutional neural networks. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, MA, USA.","DOI":"10.1109\/CVPRW.2015.7301342"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, X., Guo, H., Wang, G., and Zhang, L. (2017, January 17\u201320). Motion feature augmented recurrent neural network for skeleton-based dynamic hand gesture recognition. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), IEEE, Beijing, China.","DOI":"10.1109\/ICIP.2017.8296809"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.patcog.2017.10.033","article-title":"Convolutional neural networks and long short-term memory for skeleton-based human activity and hand gesture recognition","volume":"76","author":"Cabido","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Reifinger, S., Wallhoff, F., Ablassmeier, M., Poitschke, T., and Rigoll, G. (2007, January 22\u201327). Static and dynamic hand-gesture recognition for augmented reality applications. Proceedings of the Human-Computer Interaction, HCI Intelligent Multimodal Interaction Environments: 12th International Conference, HCI International 2007, Beijing, China. Proceedings, Part III 12.","DOI":"10.1007\/978-3-540-73110-8_79"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chavan, S., Yu, X., and Saniie, J. (2021, January 14\u201315). Convolutional neural network hand gesture recognition for American sign language. Proceedings of the 2021 IEEE International Conference on Electro Information Technology (EIT), Mt. Pleasant, MI, USA.","DOI":"10.1109\/EIT51626.2021.9491897"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Singh, A., Hashmi, F.E., Tyagi, N., and Jayswal, A.K. (2024, January 18\u201319). Impact of colour image and skeleton plotting on sign language recognition using convolutional neural networks (CNN). Proceedings of the 2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence), Noida, India.","DOI":"10.1109\/Confluence60223.2024.10463239"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"18043","DOI":"10.1109\/JSEN.2024.3389055","article-title":"Accurate and Real-time Variant Hand Pose Estimation Based on Gray Code Bounding Box Representation","volume":"24","author":"Wang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhang, P., and Kong, D. (2024, January 4\u20138). Handformer2T: A Lightweight Regression-based Model for Interacting Hands Pose Estimation from A Single RGB Image. Proceedings of the 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00613"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s00371-024-03307-4","article-title":"Dyhand: Dynamic hand gesture recognition using BiLSTM and soft attention methods","volume":"41","author":"Singh","year":"2025","journal-title":"Vis. Comput."},{"key":"ref_38","first-page":"1","article-title":"A wearable sensor-based dynamic gesture recognition model via broad attention learning","volume":"19","author":"Liu","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Rafiq, R.B., Shi, W., and Albert, M.V. (2024). Wearable sensor-based few-shot continual learning on hand gestures for motor-impaired individuals via latent embedding exploitation. arXiv.","DOI":"10.24963\/ijcai.2024\/823"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Porzi, L., Messelodi, S., Modena, C.M., and Ricci, E. (2013, January 22). A smart watch-based gesture recognition system for assisting people with visual impairments. Proceedings of the 3rd ACM International Workshop on Interactive Multimedia on Mobile & Portable Devices  (IMMPD \u201913), Barcelona, Spain.","DOI":"10.1145\/2505483.2505487"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Shin, S., and Sung, W. (2016, January 22\u201325). Dynamic hand gesture recognition for wearable devices with low complexity recurrent neural networks. Proceedings of the 2016 IEEE International Symposium on Circuits and Systems (ISCAS), Montreal, QC, Canada.","DOI":"10.1109\/ISCAS.2016.7539037"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/12\/3831\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:16Z","timestamp":1760032516000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/12\/3831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,19]]},"references-count":41,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["s25123831"],"URL":"https:\/\/doi.org\/10.3390\/s25123831","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,19]]}}}