{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T14:21:16Z","timestamp":1784816476233,"version":"3.55.0"},"reference-count":36,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T00:00:00Z","timestamp":1582243200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1813214"],"award-info":[{"award-number":["U1813214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Basic Research Projects Foundation","award":["JCYJ 20160429161539298"],"award-info":[{"award-number":["JCYJ 20160429161539298"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>High-density surface electromyography (HD-sEMG) and deep learning technology are becoming increasingly used in gesture recognition. Based on electrode grid data, information can be extracted in the form of images that are generated with instant values of multi-channel sEMG signals. In previous studies, image-based, two-dimensional convolutional neural networks (2D CNNs) have been applied in order to recognize patterns in the electrical activity of muscles from an instantaneous image. However, 2D CNNs with 2D kernels are unable to handle a sequence of images that carry information concerning how the instantaneous image evolves with time. This paper presents a 3D CNN with 3D kernels to capture both spatial and temporal structures from sequential sEMG images and investigates its performance on HD-sEMG-based gesture recognition in comparison to the 2D CNN. Extensive experiments were carried out on two benchmark datasets (i.e., CapgMyo DB-a and CSL-HDEMG). The results show that, where the same network architecture is used, 3D CNN can achieve a better performance than 2D CNN, especially for CSL-HDEMG, which contains the dynamic part of finger movement. For CapgMyo DB-a, the accuracy of 3D CNN was 1% higher than 2D CNN when the recognition window length was equal to 40 ms, and was 1.5% higher when equal to 150 ms. For CSL-HDEMG, the accuracies of 3D CNN were 15.3% and 18.6% higher than 2D CNN when the window length was equal to 40 ms and 150 ms, respectively. Furthermore, 3D CNN achieves a competitive performance in comparison to the baseline methods.<\/jats:p>","DOI":"10.3390\/s20041201","type":"journal-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T10:49:16Z","timestamp":1582282156000},"page":"1201","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":86,"title":["High-Density Surface EMG-Based Gesture Recognition Using a 3D Convolutional Neural Network"],"prefix":"10.3390","volume":"20","author":[{"given":"Jiangcheng","family":"Chen","sequence":"first","affiliation":[{"name":"Shenzhen Academy of Robotics, Shenzhen 518057, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Bi","sequence":"additional","affiliation":[{"name":"Shenzhen Academy of Robotics, Shenzhen 518057, China"},{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Academy of Robotics, Shenzhen 518057, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5595-7155","authenticated-orcid":false,"given":"Guangzhong","family":"Cao","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Electromagnetic Control, Shenzhen University, Shenzhen 518060, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,2,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.bspc.2015.02.009","article-title":"Current state of digital signal processing in myoelectric interfaces and related applications","volume":"18","author":"Hakonen","year":"2015","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.neucom.2013.12.010","article-title":"A real-time EMG pattern recognition method for virtual myoelectric hand control","volume":"136","author":"Xing","year":"2014","journal-title":"Neurocomputing"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.bspc.2014.12.001","article-title":"Improved pattern recognition classification accuracy for surface myoelectric signals using spectral enhancement","volume":"18","author":"Mccool","year":"2015","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1109\/TIE.2015.2497212","article-title":"sEMG-based identification of hand motion commands using wavelet neural network combined with discrete wavelet transform","volume":"63","author":"Duan","year":"2016","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"140053","DOI":"10.1038\/sdata.2014.53","article-title":"Electromyography data for non-invasive naturally-controlled robotic hand prostheses","volume":"1","author":"Atzori","year":"2014","journal-title":"Sci. Data"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1801","DOI":"10.1007\/s11771-015-2698-0","article-title":"Multi-channel electromyography pattern classification using deep belief networks for enhanced user experience","volume":"22","author":"Shim","year":"2015","journal-title":"J. Cent. South Univ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1186\/1743-0003-9-85","article-title":"High-density surface EMG maps from upper-arm and forearm muscles","volume":"9","author":"Monica","year":"2012","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9","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":"ref_9","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.jelekin.2014.11.008","article-title":"Alteration of Surface EMG amplitude levels of five major trunk muscles by defined electrode location displacement","volume":"25","author":"Huebner","year":"2015","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.jelekin.2012.06.009","article-title":"Identification of isometric contractions based on high density EMG maps","volume":"23","author":"Alonso","year":"2013","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"36571","DOI":"10.1038\/srep36571","article-title":"Gesture recognition by instantaneous surface EMG images","volume":"6","author":"Geng","year":"2016","journal-title":"Sci. Rep."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Amma, C., Krings, T., B\u00f6er, J., and Schultz, T. (2015, January 18\u201323). Advancing muscle-computer interfaces with high-density electromyography. Proceedings of the 33rd annual ACM Conference on Human Factors in Computing Systems, Seoul, Korea.","DOI":"10.1145\/2702123.2702501"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1109\/TBME.2016.2603463","article-title":"Muscle activity map reconstruction from high density surface EMG signals with missing channels using image inpainting and surface reconstruction methods","volume":"64","author":"Ghaderi","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"7420","DOI":"10.1016\/j.eswa.2012.01.102","article-title":"Feature reduction and selection for EMG signal classification","volume":"39","author":"Angkoon","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4832","DOI":"10.1016\/j.eswa.2013.02.023","article-title":"EMG feature evaluation for improving myoelectric pattern recognition robustness","volume":"40","author":"Angkoon","year":"2013","journal-title":"Expert Syst. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1186\/1743-0003-7-21","article-title":"Study of stability of time-domain features for electromyographic pattern recognition","volume":"7","author":"Tkach","year":"2010","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/TBME.2004.836492","article-title":"Continuous myoelectric control for powered prostheses using hidden markov models","volume":"52","author":"Chan","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1109\/TBME.2008.919734","article-title":"Support vector machine-based classification scheme for myoelectric control applied to upper limb","volume":"55","author":"Oskoei","year":"2008","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1952","DOI":"10.1109\/TIE.2010.2053334","article-title":"A neuro-fuzzy inference system for sEMG-based identification of hand motion commands","volume":"58","author":"Khezri","year":"2011","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"53040","DOI":"10.1109\/ACCESS.2019.2912200","article-title":"Review of deep learning algorithms and architectures","volume":"7","author":"Shrestha","year":"2019","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"21","DOI":"10.3390\/bdcc2030021","article-title":"EMG pattern recognition in the era of big data and deep learning","volume":"2","author":"Angkoon","year":"2018","journal-title":"Big Data Cogn. Comput."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"101669","DOI":"10.1016\/j.bspc.2019.101669","article-title":"An experimental study on upper limb position invariant EMG signal classification based on deep neural network","volume":"55","author":"Mukhopadhyay","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"5775","DOI":"10.1109\/JSEN.2019.2904595","article-title":"Cooperative sensing and wearable computing for sequential hand gesture recognition","volume":"19","author":"Zhang","year":"2019","journal-title":"IEEE Sens. J."},{"key":"ref_25","unstructured":"Allard, U.C., Nougarou, F., Fall, C.L., Gigu\u00e8re, P., Gosselin, C., Laviolette, F., and Gosselin, B. (2016, January 9\u201314). A convolutional neural network for robotic arm guidance using sEMG based frequency-features. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"279","DOI":"10.3389\/fnins.2017.00379","article-title":"Self-recalibrating surface EMG pattern recognition for neuroprosthesis control based on convolutional neural network","volume":"11","author":"Zhai","year":"2017","journal-title":"Front. Neurosci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hu, Y., Wong, Y., Wei, W., Du, Y., Kankanhalli, M., and Geng, W. (2018). A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0206049"},{"key":"ref_28","doi-asserted-by":"crossref","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 Recognit. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1109\/MCE.2019.2941464","article-title":"Hand gesture recognition using 3D-CNN model","volume":"9","author":"Muhammad","year":"2020","journal-title":"IEEE Consum. Electron. Mag."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.bspc.2017.10.002","article-title":"Surface EMG based continuous estimation of human lower limb joint angles by using deep belief networks","volume":"40","author":"Chen","year":"2018","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1522","DOI":"10.1109\/TMI.2018.2832217","article-title":"3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network","volume":"37","author":"Shan","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015, January 7\u201313). Learning spatiotemporal features with 3D convolutional networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref_34","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_35","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1016\/j.patcog.2017.12.002","article-title":"Deep convolutional neural networks for mental load classification based on EEG data","volume":"76","author":"Jiao","year":"2018","journal-title":"Pattern Recognit."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/4\/1201\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:59:54Z","timestamp":1760173194000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/4\/1201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,21]]},"references-count":36,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,2]]}},"alternative-id":["s20041201"],"URL":"https:\/\/doi.org\/10.3390\/s20041201","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,21]]}}}