{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:55:47Z","timestamp":1783526147620,"version":"3.55.0"},"reference-count":49,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T00:00:00Z","timestamp":1628467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Surface electromyogram (sEMG) signals have been used in human motion intention recognition, which has significant application prospects in the fields of rehabilitation medicine and cognitive science. However, some valuable dynamic information on upper-limb motions is lost in the process of feature extraction for sEMG signals, and there exists the fact that only a small variety of rehabilitation movements can be distinguished, and the classification accuracy is easily affected. To solve these dilemmas, first, a multiscale time\u2013frequency information fusion representation method (MTFIFR) is proposed to obtain the time\u2013frequency features of multichannel sEMG signals. Then, this paper designs the multiple feature fusion network (MFFN), which aims at strengthening the ability of feature extraction. Finally, a deep belief network (DBN) was introduced as the classification model of the MFFN to boost the generalization performance for more types of upper-limb movements. In the experiments, 12 kinds of upper-limb rehabilitation actions were recognized utilizing four sEMG sensors. The maximum identification accuracy was 86.10% and the average classification accuracy of the proposed MFFN was 73.49%, indicating that the time\u2013frequency representation approach combined with the MFFN is superior to the traditional machine learning and convolutional neural network.<\/jats:p>","DOI":"10.3390\/s21165385","type":"journal-article","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T21:41:46Z","timestamp":1628545306000},"page":"5385","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Fusion Learning for sEMG Recognition of Multiple Upper-Limb Rehabilitation Movements"],"prefix":"10.3390","volume":"21","author":[{"given":"Tianyang","family":"Zhong","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donglin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhui","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacan","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zida","family":"An","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3191","DOI":"10.1109\/TIE.2010.2051931","article-title":"A New Control Method for Power-Assisted Wheelchair Based on the Surface Myoelectric Signal","volume":"57","author":"Oonishi","year":"2010","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_2","unstructured":"Giho, J., and Choi, Y. (2014, January 14\u201318). EMG-based continuous control method for electric wheelchair. Proceedings of the 2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems, Chicago, IL, USA."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1109\/TNSRE.2007.903919","article-title":"Design and Evaluation of the LOPES Exoskeleton Robot for Interactive Gait Rehabilitation","volume":"15","author":"Veneman","year":"2007","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1064","DOI":"10.1109\/TSMCB.2012.2185843","article-title":"An EMG-Based Control for an Upper-Limb Power-Assist Exoskeleton Robot","volume":"42","author":"Kiguchi","year":"2012","journal-title":"IEEE Trans. Syst. Man. Cyber."},{"key":"ref_5","unstructured":"(2014, February 20). Clearpath Robotics Drives Robot with Arm Motions. Available online: http:\/\/www.clearpathrobotics.com\/press_release\/drive-robot-with-arm-motion\/."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1109\/TNSRE.2013.2291322","article-title":"A Multi-Classifier Approach to MUAP Classification for Diagnosis of Neuromuscular Disorders","volume":"22","author":"Kamali","year":"2014","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1109\/TNSRE.2009.2032638","article-title":"The application of machine learning algorithms to the analysis of electromyographic patterns from arthritic patients","volume":"18","author":"Nair","year":"2010","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"61998","DOI":"10.1109\/ACCESS.2021.3072781","article-title":"Human-Exoskeleton Coupling Dynamics of a Multi-Mode Therapeutic Exoskeleton for Upper Limb Rehabilitation Training","volume":"9","author":"Xie","year":"2021","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1109\/TNSRE.2016.2532478","article-title":"Assistive Control System for Upper Limb Rehabilitation Robot","volume":"24","author":"Chen","year":"2016","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1109\/TSMC.2016.2531653","article-title":"Toward Patients\u2019 Motion Intention Recognition: Dynamics Modeling and Identification of iLeg-An LLRR Under Motion Constraints","volume":"46","author":"Wang","year":"2016","journal-title":"IEEE Trans. Syst. Man Cyber. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1109\/TMECH.2007.897262","article-title":"A Supervised Feature-Projection-Based Real-Time EMG Pattern Recognition for Multifunction Myoelectric Hand Control","volume":"12","author":"Chu","year":"2007","journal-title":"IEEE\/ASME Trans. Mecha."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4276","DOI":"10.1109\/TIE.2016.2593693","article-title":"Recognizing the Gradual Changes in sEMG Characteristics Based on Incremental Learning of Wavelet Neural Network Ensemble","volume":"64","author":"Duan","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"13121","DOI":"10.1109\/ACCESS.2019.2892780","article-title":"Motion Estimation from Surface Electromyogram Using Adaboost Regression and Average Feature Values","volume":"7","author":"Xiao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1109\/JSTARS.2013.2293343","article-title":"Nonlinear Compressed Sensing-Based LDA Topic Model for Polarimetric SAR Image Classification","volume":"7","author":"He","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_15","first-page":"126","article-title":"A bionic hand controlled by hand gesture recognition based on surface EMG signals: A preliminary study","volume":"38","author":"Shi","year":"2017","journal-title":"Biocyber. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.patrec.2017.01.012","article-title":"Motion intent recognition of individual fingers based on mechanomyogram","volume":"88","author":"Ding","year":"2017","journal-title":"Patt. Recog. Lett."},{"key":"ref_17","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_18","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.1109\/TBME.2006.883695","article-title":"A Real-Time EMG Pattern Recognition System Based on Linear-Nonlinear Feature Projection for a Multifunction Myoelectric Hand","volume":"53","author":"Chu","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_19","first-page":"297","article-title":"Genetic reasoning for finger sign identification based on forearm electromyogram","volume":"7","author":"Tsujimura","year":"2014","journal-title":"Int. Conf. Appl. Electron."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1109\/TNSRE.2005.847357","article-title":"A heuristic fuzzy logic approach to EMG pattern recognition for multifunctional prosthesis control","volume":"13","author":"Ajiboye","year":"2005","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TNSRE.2007.908376","article-title":"Real-Time Classification of Forearm Electromyographic Signals Corresponding to User-Selected Intentional Movements for Multifunction Prosthesis Control","volume":"15","author":"Momen","year":"2007","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1948","DOI":"10.1109\/TMECH.2014.2360119","article-title":"A Low-Cost Real-Time Research Platform for EMG Pattern Recognition-Based Prosthetic Hand","volume":"20","author":"Geethanjali","year":"2015","journal-title":"IEEE\/ASME Trans. Mech."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1109\/TFUZZ.2004.832525","article-title":"Neuro-fuzzy control of a robotic exoskeleton with EMG signals","volume":"12","author":"Kiguchi","year":"2004","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/TCDS.2020.2969297","article-title":"Performance Comparison of Gesture Recognition System Based on Different Classifiers","volume":"13","author":"Yang","year":"2021","journal-title":"IEEE Trans. Cognit. Dev. Syst."},{"key":"ref_25","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_26","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":"Patt. Recog. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1016\/j.jare.2014.03.004","article-title":"An intelligent approach for variable size segmentation of non-stationary signals","volume":"6","author":"Azami","year":"2015","journal-title":"J. Adv. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.bspc.2014.12.005","article-title":"Comparison of decision tree algorithms for EMG signal classification using DWT","volume":"18","author":"Ercan","year":"2015","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zheng, B., and Zhao, Y. (December, January 30). Dynamic Gesture Recognition Based on LSTM-CNN. Proceedings of the 2018 Chinese Automation Congress (CAC), Xi\u2019an, China.","DOI":"10.1109\/CAC.2018.8623035"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.eswa.2011.06.043","article-title":"Identification of EMG signals using discriminant analysis and SVM classifier","volume":"39","author":"Alkan","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/TNSRE.2009.2023284","article-title":"A Continuous Wavelet Transform and Classification Method for Delirium Motoric Subtyping","volume":"17","author":"Godfrey","year":"2009","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"132882","DOI":"10.1109\/ACCESS.2020.3008901","article-title":"Feature Extraction and Classification of Lower Limb Motion Based on sEMG Signals","volume":"8","author":"Shi","year":"2020","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1016\/j.jbiomech.2010.01.027","article-title":"Filtering the surface EMG signal: Movement artifact and baseline noise contamination","volume":"43","author":"De","year":"2010","journal-title":"J. Biomech."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/j.jelekin.2003.10.005","article-title":"Less is more: High pass filtering, to remove up to 99% of the surface EMG signal power, improves EMG-based biceps brachii muscle force estimates","volume":"14","author":"Potvin","year":"2004","journal-title":"J. Electromyogr. Kinesi."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"132720","DOI":"10.1109\/ACCESS.2019.2941867","article-title":"Densely Feature Fusion Based on Convolutional Neural Networks for Motor Imagery EEG Classification","volume":"7","author":"Li","year":"2019","journal-title":"IEEE Access"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"6036","DOI":"10.1109\/TSP.2012.2210890","article-title":"Generalized Morse Wavelets as a Superfamily of Analytic Wavelets","volume":"60","author":"Lilly","year":"2012","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1109\/TSP.2008.2007607","article-title":"Higher-Order Properties of Analytic Wavelets","volume":"57","author":"Lilly","year":"2009","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_38","unstructured":"Gao, H., Liu, Z., Laurens, V., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the 30th IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1109\/TASLP.2014.2303296","article-title":"Application of Deep Belief Networks for Natural Language Understanding","volume":"22","author":"Sarikaya","year":"2014","journal-title":"IEEE\/ACM Trans. Aud. Spe. Lan. Process."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A Fast Learning Algorithm for Deep Belief Nets","volume":"18","author":"Hinton","year":"2006","journal-title":"Neural Comput."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2381","DOI":"10.1109\/JSTARS.2015.2388577","article-title":"Spectral-Spatial Classification of Hyperspectral Data Based on Deep Belief Network","volume":"8","author":"Chen","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Ear. Obser. Rem. Sens."},{"key":"ref_42","first-page":"1","article-title":"A Hierarchical Hand Gesture Recognition Framework for Sports Referee Training-Based EMG and Accelerometer Sensors","volume":"10","author":"Pan","year":"2020","journal-title":"IEEE Trans. Cyber."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2895781","article-title":"Training Faster by Separating Modes of Variation in Batch-Normalized Models","volume":"42","author":"Kalayeh","year":"2020","journal-title":"IEEE Trans. Patt. Analy. Mach. Intelli."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1109\/TNNLS.2020.2978753","article-title":"Effective and Efficient Batch Normalization Using a Few Uncorrelated Data for Statistics Estimation","volume":"32","author":"Chen","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"102","DOI":"10.26599\/BDMA.2019.9020024","article-title":"Feature representations using the reflected rectified linear unit (RReLU) activation","volume":"3","author":"Banerjee","year":"2020","journal-title":"Big Data Min. Anal."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"38630","DOI":"10.1109\/ACCESS.2019.2903354","article-title":"Relative Depth Order Estimation Using Multiscale Densely Connected Convolutional Networks","volume":"7","author":"Deng","year":"2019","journal-title":"IEEE Access"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"58056","DOI":"10.1109\/ACCESS.2018.2874307","article-title":"A Parameter Efficient Human Pose Estimation Method Based on Densely Connected Convolutional Module","volume":"6","author":"Wang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1109\/TBME.2013.2250502","article-title":"Bilinear Modeling of EMG Signals to Extract User-Independent Features for Multiuser Myoelectric Interface","volume":"60","author":"Matsubara","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Ye, Q., Chu, M., and Grethler, M. (2021, January 22\u201324). Upper Limb Motion Recognition Using Gated Convolution Neural Network via Multi-Channel sEMG. Proceedings of the 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA), Shenyang, China.","DOI":"10.1109\/ICPECA51329.2021.9362522"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/16\/5385\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:43:09Z","timestamp":1760164989000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/16\/5385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,9]]},"references-count":49,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["s21165385"],"URL":"https:\/\/doi.org\/10.3390\/s21165385","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,9]]}}}