{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:07:52Z","timestamp":1777486072395,"version":"3.51.4"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T00:00:00Z","timestamp":1677542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>With the development of signal analysis technology and artificial intelligence, surface electromyography (sEMG) signal gesture recognition is widely used in rehabilitation therapy, human-computer interaction, and other fields. Deep learning has gradually become the mainstream technology for gesture recognition. It is necessary to consider the characteristics of the surface EMG signal when constructing the deep learning model. The surface electromyography signal is an information carrier that can reflect neuromuscular activity. Under the same circumstances, a longer signal segment contains more information about muscle activity, and a shorter segment contains less information about muscle activity. Thus, signals with longer segments are suitable for recognizing gestures that mobilize complex muscle activity, and signals with shorter segments are suitable for recognizing gestures that mobilize simple muscle activity. However, current deep learning models usually extract features from single-length signal segments. This can easily cause a mismatch between the amount of information in the features and the information needed to recognize gestures, which is not conducive to improving the accuracy and stability of recognition. Therefore, in this article, we develop a long short-term transformer feature fusion network (referred to as LST-EMG-Net) that considers the differences in the timing lengths of EMG segments required for the recognition of different gestures. LST-EMG-Net imports multichannel sEMG datasets into a long short-term encoder. The encoder extracts the sEMG signals\u2019 long short-term features. Finally, we successfully fuse the features using a feature cross-attention module and output the gesture category. We evaluated LST-EMG-Net on multiple datasets based on sparse channels and high density. It reached 81.47, 88.24, and 98.95% accuracy on Ninapro DB2E2, DB5E3 partial gesture, and CapgMyo DB-c, respectively. Following the experiment, we demonstrated that LST-EMG-Net could increase the accuracy and stability of various gesture identification and recognition tasks better than existing networks.<\/jats:p>","DOI":"10.3389\/fnbot.2023.1127338","type":"journal-article","created":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T17:04:10Z","timestamp":1678122250000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":27,"title":["LST-EMG-Net: Long short-term transformer feature fusion network for sEMG gesture recognition"],"prefix":"10.3389","volume":"17","author":[{"given":"Wenli","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Tingsong","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jianyi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yufei","family":"Wang","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,2,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102172","article-title":"Deep learning for motor imagery EEG-based classification: A review.","volume":"63","author":"Al-Saegh","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU56188.2022.9925273","article-title":"Machine learning-enabled classification of forearm sEMG signals to control robotic hands prostheses","author":"Alseed","year":"2022","journal-title":"Proceedings of the 2022 innovations in intelligent systems and applications conference (ASYU)"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2016.00009","article-title":"Deep learning with convolutional neural networks applied to electromyography data: A resource for the classification of movements for prosthetic hands.","volume":"10","author":"Atzori","year":"2016","journal-title":"Front. Neurorobot."},{"key":"B4","first-page":"1","article-title":"Electromyography data for non-invasive naturally-controlled robotic hand prostheses.","volume":"1","author":"Atzori","year":"","journal-title":"Sci. Data"},{"key":"B5","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/TNSRE.2014.2328495","article-title":"Characterization of a benchmark database for myoelectric movement classification.","volume":"23","author":"Atzori","year":"","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1258","DOI":"10.1109\/BioRob.2012.6290287","article-title":"Building the Ninapro database: A resource for the biorobotics community","author":"Atzori","year":"2012","journal-title":"Proceedings of the 2012 4th IEEE RAS &amp; EMBS international conference on biomedical robotics and biomechatronics (BioRob)"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3390\/s22052007","article-title":"A hand-modeled feature extraction-based learning network to detect grasps using sEMG signal.","volume":"22","author":"Baygin","year":"2022","journal-title":"Sensors"},{"key":"B8","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1109\/IC_ASET53395.2022.9765856","article-title":"EMG signal classification for human hand rehabilitation via two machine learning techniques: KNN and SVM","author":"Briouza","year":"2022","journal-title":"Proceedings of the 2022 5th international conference on advanced systems and emergent technologies (IC_ASET)"},{"key":"B9","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-981-33-4932-2_30","article-title":"Improving gesture recognition by bidirectional temporal convolutional netwoks","author":"Chen","year":"2020","journal-title":"Proceedings of the international conference on robotics and rehabilitation intelligence"},{"key":"B10","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1109\/TRO.2007.910708","article-title":"On the shared control of an EMG-controlled prosthetic hand: Analysis of user\u2013prosthesis interaction.","volume":"24","author":"Cipriani","year":"2008","journal-title":"IEEE Trans. Robot."},{"key":"B11","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/TNN.2004.826380","author":"Comon","year":"1992","journal-title":"Independent component analysis. J-L.Lacoume. Higher-order statistics"},{"key":"B12","first-page":"2017","author":"Du","year":"2017","journal-title":"CapgMyo: A high density surface electromyography database for gesture recognition."},{"key":"B13","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1109\/RBME.2022.3164797","article-title":"A review of techniques for surface electromyography signal quality analysis.","volume":"16","author":"Farago","year":"2022","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"B14","article-title":"Measuring movement classification performance with the movement error rate.","author":"Gijsberts","year":"2014","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B15","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B16","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1145\/3438872.3439060","article-title":"A comprehensive evaluation of hidden Markov model for hand movement recognition with surface electromyography","author":"Hu","year":"2020","journal-title":"Proceedings of the 2020 2nd international conference on robotics, intelligent control and artificial intelligence"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0206049","article-title":"A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition.","volume":"13","author":"Hu","year":"2018","journal-title":"PLoS One"},{"key":"B18","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1109\/ROBIO.2009.4913110","article-title":"Objective and quantitative assessment methodology of hand functions for rehabilitation","author":"Huang","year":"2009","journal-title":"Proceedings of the 2008 IEEE international conference on robotics and biomimetics"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.3389\/fnhum.2022.911204","article-title":"Gestures recognition of sEMG signal based on Random Forest","author":"Jia","year":"2021","journal-title":"Proceedings of the 2021 IEEE 16th conference on industrial electronics and applications (ICIEA)"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.2174\/1573405618666220519144358","article-title":"Hyperspectral imaging: A review and trends towards medical imaging.","author":"Karim","year":"2022","journal-title":"Curr. Med. Imaging."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.2174\/1573405619666221228094228","article-title":"How to collect and interpret medical pictures captured in highly challenging environments that range from nanoscale to hyperspectral imaging.","author":"Laghari","year":"2022","journal-title":"Curr. Med. Imaging."},{"key":"B22","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1109\/TOH.2015.2417570","article-title":"An EMG-controlled robotic hand exoskeleton for bilateral rehabilitation.","volume":"8","author":"Leonardis","year":"2015","journal-title":"IEEE Trans. Haptics"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/mi13081205","article-title":"Human motion pattern recognition and feature extraction: An approach using multi-information fusion.","volume":"13","author":"Li","year":"2022","journal-title":"Micromachines"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.1109\/CVPR.2017.106","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B25","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1109\/TNSRE.2016.2560906","article-title":"Development of an EMG-ACC-based upper limb rehabilitation training system.","volume":"25","author":"Liu","year":"2016","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.09516","article-title":"Learning spatial fusion for single-shot object detection.","author":"Liu","year":"2019","journal-title":"arXiv"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1832","DOI":"10.1109\/TNSRE.2017.2687761","article-title":"Study on interaction between temporal and spatial information in classification of EMG signals for myoelectric prostheses.","volume":"25","author":"Menon","year":"2017","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.10060","article-title":"ViT-HGR: Vision transformer-based hand gesture recognition from high density surface EMG signals.","author":"Montazerin","year":"2022","journal-title":"arXiv"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/app11094164","article-title":"Real-time hand gesture recognition based on deep learning YOLOv3 model.","volume":"11","author":"Mujahid","year":"2021","journal-title":"Appl. Sci."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/477\/1\/012041","article-title":"Virtual reality upper limb model controlled by EMG signals.","volume":"477","author":"Muri","year":"2013","journal-title":"J. Phys. Conf. Ser."},{"key":"B31","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/JBHI.2014.2326660","article-title":"Nonnegative matrix factorization for the identification of EMG finger movements: Evaluation using matrix analysis.","volume":"19","author":"Naik","year":"2014","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"B32","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/DICTA.2007.4426772","article-title":"Subtle hand gesture identification for HCI using temporal decorrelation source separation BSS of surface EMG","author":"Naik","year":"2007","journal-title":"Proceedings of the 9th biennial conference of the Australian pattern recognition society on digital image computing techniques and applications (DICTA 2007)"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1142\/S0218348X19500221","article-title":"Decoding of hand gestures by fractal analysis of electromyography (EMG) signal.","volume":"27","author":"Namazi","year":"","journal-title":"Fractals"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1142\/S0218348X19500506","article-title":"Fractal-based classification of electromyography (EMG) signal between fingers and hand\u2019s basic movements, functional movements, and force patterns.","volume":"27","author":"Namazi","year":"","journal-title":"Fractals"},{"key":"B35","doi-asserted-by":"crossref","first-page":"3226","DOI":"10.1016\/j.matpr.2020.09.091","article-title":"Hb vsEMG signal classification with time domain and frequency domain features using LDA and ANN classifier.","volume":"37","author":"Narayan","year":"2021","journal-title":"Mater. Today Proc."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3390\/app7101050","article-title":"Assessment on stationarity of EMG signals with different windows size during isotonic contractions.","volume":"7","author":"Nazmi","year":"2017","journal-title":"Appl. Sci."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6080073","article-title":"Hand gesture recognition based on computer vision: A review of techniques.","volume":"6","author":"Oudah","year":"2020","journal-title":"J. Imaging"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3390\/s19204596","article-title":"Real-time EMG based pattern recognition control for hand prostheses: A review on existing methods, challenges and future implementation.","volume":"19","author":"Parajuli","year":"2019","journal-title":"Sensors"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0186132","article-title":"Comparison of six electromyography acquisition setups on hand movement classification tasks.","volume":"12","author":"Pizzolato","year":"2017","journal-title":"PLoS One"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.12379","article-title":"TEMGNet: Deep transformer-based decoding of Upperlimb sEMG for hand gestures recognition.","author":"Rahimian","year":"2021","journal-title":"arXiv"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3390\/s20040969","article-title":"Deep learning in physiological signal data: A survey.","volume":"20","author":"Rim","year":"2020","journal-title":"Sensors"},{"key":"B42","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1682\/JRRD.2010.09.0177","article-title":"Electromyogram pattern recognition for control of powered upper-limb prostheses: State of the art and challenges for clinical use.","volume":"48","author":"Scheme","year":"2011","journal-title":"J. Rehabil. Res. Dev."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2202.05170","article-title":"Efficacy of transformer networks for classification of raw EEG data.","author":"Siddhad","year":"2022","journal-title":"arXiv"},{"key":"B44","first-page":"5998","article-title":"Attention is all you need.","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"B45","doi-asserted-by":"publisher","first-page":"3903","DOI":"10.1109\/WCICA.2012.6359124","article-title":"Human-machine interfaces based on EMG and Kinect applied to teleoperation of a mobile humanoid robot","author":"Wang","year":"2012","journal-title":"Proceedings of the 10th world congress on intelligent control and automation"},{"key":"B46","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.patrec.2017.12.005","article-title":"A multi-stream convolutional neural network for sEMG-based gesture recognition in muscle-computer interface.","volume":"119","author":"Wei","year":"2019","journal-title":"Pattern Recogn. Lett."},{"key":"B47","doi-asserted-by":"publisher","first-page":"E67","DOI":"10.1111\/aor.13004","article-title":"EMG-based estimation of limb movement using deep learning with recurrent convolutional neural networks.","volume":"42","author":"Xia","year":"2018","journal-title":"Artif. Organs"},{"key":"B48","doi-asserted-by":"publisher","first-page":"176448","DOI":"10.1109\/ACCESS.2019.2957668","article-title":"SEMG-based human in-hand motion recognition using nonlinear time series analysis and random forest.","volume":"7","author":"Xue","year":"2019","journal-title":"IEEE Access"},{"key":"B49","doi-asserted-by":"publisher","first-page":"31","DOI":"10.6180\/jase.202003_23(1).0004","article-title":"Dynamic gesture recognition based on deep learning in human-to-computer interfaces.","volume":"23","author":"Yu","year":"2020","journal-title":"J. Appl. Sci. Eng."},{"key":"B50","doi-asserted-by":"publisher","first-page":"15","DOI":"10.5815\/ijmsc.2020.06.03","article-title":"Action recognition based on the modified twostream CNN.","volume":"6","author":"Zheng","year":"2020","journal-title":"Int. J. Math. Sci. Comp."},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.11886","article-title":"Deepvit: Towards deeper vision transformer.","author":"Zhou","year":"2021","journal-title":"arXiv"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1127338\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T17:04:19Z","timestamp":1678122259000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1127338\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,28]]},"references-count":51,"alternative-id":["10.3389\/fnbot.2023.1127338"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1127338","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,28]]},"article-number":"1127338"}}