{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T04:48:12Z","timestamp":1791607692530,"version":"4.3.4"},"reference-count":51,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the MOE (Ministry of Education in China) Project of Humanities and Social Sciences","award":["19YJC760158"],"award-info":[{"award-number":["19YJC760158"]}]},{"name":"the Zhejiang Provincial Natural Science Foundation of China","award":["LY20F020028"],"award-info":[{"award-number":["LY20F020028"]}]},{"name":"the Fundamental Research Funds for the Provincial Universities of Zhejiang","award":["GB201901006"],"award-info":[{"award-number":["GB201901006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Surface electromyogram (sEMG) signals are widely employed as a neural control source for lower-limb exoskeletons, in which gait recognition based on sEMG is particularly important. Many scholars have taken measures to improve the accuracy of gait recognition, but several real-time limitations affect its applicability, of which variation in the load styles is obvious. The purposes of this study are to (1) investigate the impact of different load styles on gait recognition; (2) study whether good gait recognition performance can be obtained when a convolutional neural network (CNN) is used to deal with the sEMG image from sparse multichannel sEMG (SMC-sEMG); and (3) explore whether the control system of the lower-limb exoskeleton trained by sEMG from part of the load styles still works efficiently in a real-time environment where multiload styles are required. In addition, we discuss an effective method to improve gait recognition at the levels of the load styles. In our experiment, fifteen able-bodied male graduate students with load (20% of body weight) and using three load styles (SBP = backpack, SCS = cross shoulder, SSS = straight shoulder) were asked to walk uniformly on a treadmill. Each subject performed 50 continuous gait cycles under three speeds (V3 = 3 km\/h, V5 = 5 km\/h, and V7 = 7 km\/h). A CNN was employed to deal with sEMG images from sEMG signals for gait recognition, and back propagation neural networks (BPNNs) and support vector machines (SVMs) were used for comparison by dealing with the same sEMG signal. The results indicated that (1) different load styles had remarkable impact on the gait recognition at three speeds under three load styles (p &lt; 0.001); (2) the performance of gait recognition from the CNN was better than that from the SVM and BPNN at each speed (84.83%, 81.63%, and 83.76% at V3; 93.40%, 88.48%, and 92.36% at V5; and 90.1%, 86.32%, and 85.42% at V7, respectively); and (3) when all the data from three load styles were pooled as testing sets at each speed, more load styles were included in the training set, better performance was obtained, and the statistical analysis suggested that the kinds of load styles included in training set had a significant effect on gait recognition (p = 0.002), from which it can be concluded that the control system of a lower-limb exoskeleton trained by sEMG using only some load styles is not sufficient in a real-time environment.<\/jats:p>","DOI":"10.3390\/s21248365","type":"journal-article","created":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T21:47:36Z","timestamp":1639604856000},"page":"8365","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["The Impact of Load Style Variation on Gait Recognition Based on sEMG Images Using a Convolutional Neural Network"],"prefix":"10.3390","volume":"21","author":[{"given":"Xianfu","family":"Zhang","sequence":"first","affiliation":[{"name":"Schlool of Jewelry and Art Design, Wuzhou University, Wuzhou 543002, China"},{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuping","family":"Hu","sequence":"additional","affiliation":[{"name":"Schlool of Jewelry and Art Design, Wuzhou University, Wuzhou 543002, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruimin","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4187-1510","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5841-288X","authenticated-orcid":false,"given":"Zhichuan","family":"Tang","sequence":"additional","affiliation":[{"name":"Industrial Design Institute, Zhejiang University of Technology, Hangzhou 310023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,12,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Joshi, C.D., Lahiri, U., and Thakor, N.V. (2013, January 16\u201318). Classification of gait phases from lower limb EMG: Application to exoskeleton orthosis. Proceedings of the 2013 IEEE Point-of-Care Healthcare Technologies (PHT), Bangalore, India.","DOI":"10.1109\/PHT.2013.6461326"},{"key":"ref_2","unstructured":"Yang, P., Chen, L., Guo, X., Wang, X., and Li, L. (2006, January 21\u201323). Artificial Lower Limb with Myoelectrical Control Based on Support Vector Machine. Proceedings of the 6th World Congress on Intelligent Control and Automation, Dalian, China."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ielpo, N., Calabrese, B., Cannataro, M., Palumbo, A., Ciliberti, S., Grillo, C., and Iocco, M. (2014, January 27\u201329). EMG-miner: Automatic acquisition and processing of electromyographic signals: First experimentation in a clinical context for gait disorders evaluation. Proceedings of the 2014 IEEE 27th International Symposium on Computer-Based Medical Systems, New York, NY, USA.","DOI":"10.1109\/CBMS.2014.41"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Park, K.H., and Lee, S.W. (2016, January 22\u201324). Movement intention decoding based on deep learning for multiuser myoelectric interfaces. Proceedings of the 2016 4th International Winter Conference on Brain-Computer Interface (BCI), Gangwon-do, Korea.","DOI":"10.1109\/IWW-BCI.2016.7457459"},{"key":"ref_5","unstructured":"Meng, M., Luo, Z., She, Q., and Ma, Y. (2010, January 30\u201331). Automatic recognition of gait mode from EMG signals of lower limb. Proceedings of the 2010 2nd International Conference on Industrial Mechatronics and Automation (ICIMA 2010), Wuhan, China."},{"key":"ref_6","unstructured":"Chen, L., Xu, X., Yang, P., Guo, X., and Zu, L. (2008, January 25\u201327). Stride recognition in the control concept of trans-femoral prosthesis. Proceedings of the 2008 7th World Congress on Intelligent Control and Automation, Chongqing, China."},{"key":"ref_7","first-page":"385","article-title":"Cooperative Intelligent Robot Control Method Using Leg Surface EMG Signals","volume":"4","author":"Xu","year":"2016","journal-title":"Chin. J. Biomed. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2255","DOI":"10.3390\/s120202255","article-title":"Gait analysis using wearable sensors","volume":"12","author":"Tao","year":"2012","journal-title":"Sensors"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Pham, H., Kawanishi, M., and Narikiyo, T. (2015, January 25\u201330). A LLE-HMM-based framework for recognizing human gait movement from EMG. Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA.","DOI":"10.1109\/ICRA.2015.7139610"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ryu, J., Lee, B.H., and Kim, D.H. (2016, January 16\u201320). EMG signal-based gait phase recognition using a GPES library and ISMF. Proceedings of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.","DOI":"10.1109\/EMBC.2016.7591118"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/j.gaitpost.2014.10.019","article-title":"Adaptive method for real-time gait phase detection based on ground contact forces","volume":"41","author":"Yu","year":"2015","journal-title":"Gait Posture"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/1743-0003-8-25","article-title":"Influence of the training set on the accuracy of surface EMG classification in dynamic contractions for the control of multifunction prostheses","volume":"8","author":"Lorrain","year":"2011","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1109\/TASE.2015.2477283","article-title":"Design of a gait phase recognition system that can cope with EMG electrode location variation","volume":"14","author":"Lee","year":"2015","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_14","first-page":"189","article-title":"Gait analysis of slope lateral walking: A preliminary study","volume":"24","author":"Lin","year":"2004","journal-title":"J. Med. Biol. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sun, S., Li, C., and Tang, Z. (2018). Impact of load variation on the accuracy of gait recognition from surface EMG signals. Appl. Sci., 8.","DOI":"10.3390\/app8091462"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"109","DOI":"10.3233\/BMR-150605","article-title":"Effect of single and double backpack strap loading on gait and perceived exertion of young adults","volume":"29","author":"Abaraogu","year":"2016","journal-title":"J. Musculoskelet. Rehabil."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.gaitpost.2016.01.012","article-title":"Load distribution and postural changes in young adults when wearing a traditional backpack versus the BackTpack","volume":"45","author":"Dahl","year":"2016","journal-title":"Gait Posture"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1080\/001401397187928","article-title":"Influence of carrying book bags on gait cycle and posture of youths","volume":"40","author":"Pascoe","year":"1997","journal-title":"Ergonomics"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1109\/TNSRE.2015.2502663","article-title":"Impact of load variation on joint angle estimation from surface EMG signals","volume":"24","author":"Tang","year":"2015","journal-title":"IEEE Trans. Neural. Syst. Rehabil. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Kavukcuoglu, K., Chintala, S., and Lecun, Y. (2013, January 25\u201327). Pedestrian detection with unsupervised multi-stage feature learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.465"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Fricke, C., Alizadeh, J., Zakhary, N., Woost, T.B., Bogdan, M., and Classen, J. (2021). Evaluation of Three Machine Learning Algorithms for the Automatic Classification of EMG Patterns in Gait Disorders. Front. Neurol., 12.","DOI":"10.3389\/fneur.2021.666458"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1007\/s42235-021-00083-y","article-title":"A Novel Gait Pattern Recognition Method Based on LSTM-CNN for Lower Limb Exoskeleton","volume":"18","author":"Chen","year":"2021","journal-title":"J Bionic. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8846021","DOI":"10.1155\/2020\/8846021","article-title":"Lw-CNN-based myoelectric signal recognition and real-time control of robotic arm for upper-limb rehabilitation","volume":"2020","author":"Guo","year":"2020","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_26","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":"Alonso","year":"2012","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_27","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_28","first-page":"18","article-title":"Surface EMG Topography and Pain Distribution in Pre-chronic Back","volume":"39","author":"Traue","year":"1992","journal-title":"Int. J. Psychosom."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hu, Y., Mak, J.N.F., and Luk, K.D.K. (2007, January 2\u20135). Application of surface EMG topography in low back pain rehabilitation assessment. Proceedings of the 2007 3rd International IEEE\/EMBS Conference on Neural Engineering, Kohala Coast, HI, USA.","DOI":"10.1109\/CNE.2007.369733"},{"key":"ref_30","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_31","doi-asserted-by":"crossref","unstructured":"Du, Y., Jin, W., Wei, W., Hu, Y., and Geng, W. (2017). Surface EMG-based inter-session gesture recognition enhanced by deep domain adaptation. Sensors, 17.","DOI":"10.3390\/s17030458"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: An overview and application in radiology","volume":"9","author":"Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Li, Y., Gao, F., Chen, H., and Xu, M. (2016, January 27\u201329). Gait recognition based on EMG with different individuals and sample sizes. Proceedings of the 2016 35th Chinese Control Conference (CCC), Chengdu, China.","DOI":"10.1109\/ChiCC.2016.7553988"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, H., and Kiguchi, K. (2007, January 8\u201311). A study on EMG-based control of exoskeleton robots for human lower-limb motion assist. Proceedings of the 6th IEEE International Special Topic Conference on Information Technology Applications in Biomedicine, Tokyo, Japan.","DOI":"10.1109\/ITAB.2007.4407405"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.clinbiomech.2008.08.003","article-title":"Surface electromyography and muscle force: Limits in sEMG\u2013force relationship and new approaches for applications","volume":"24","author":"Rau","year":"2009","journal-title":"Clin. Biomech."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1016\/j.ergon.2014.08.004","article-title":"An ergonomics evaluation of the vibration backpack harness system in walking","volume":"44","author":"Tang","year":"2014","journal-title":"Int. J. Ind. Ergonom."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"De Rossi, S.M.M., Crea, S., Donati, M., Reber\u0161ek, P., Novak, D., Vitiello, N., and Carrozza, M.C. (2012, January 24\u201327). Gait segmentation using bipedal foot pressure patterns. Proceedings of the 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob), Rome, Italy.","DOI":"10.1109\/BioRob.2012.6290278"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.gaitpost.2003.10.001","article-title":"Assessment and validation of a simple automated method for the detection of gait events and intervals","volume":"20","author":"Ghoussayni","year":"2004","journal-title":"Gait Posture"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.bspc.2007.07.009","article-title":"Myoelectric control systems\u2014A survey. Biomed","volume":"2","author":"Oskoei","year":"2007","journal-title":"Signal Process. Control"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"LeCun, Y.A., Bottou, L., Orr, G.B., and M\u00fcller, K.-R. (2012). Efficient backprop. Neural Networks: Tricks of the Trade, Springer.","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"ref_41","first-page":"1","article-title":"Motor Imagery Clasification Based on Deep Convolutional Neural Network and Its Application in Exoskeleton Controlled by EEG","volume":"2016","author":"Tang","year":"2016","journal-title":"Chin. J. Comput."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TPAMI.2010.125","article-title":"Convolutional neural networks for P300detection with application to brain-computer interfaces","volume":"33","author":"Cecotti","year":"2011","journal-title":"IEEE Trans. Patern Anal. Mach. Intel."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/10.204774","article-title":"A new strategy for multifunction myoelectric control","volume":"40","author":"Hudgins","year":"1993","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_44","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_45","doi-asserted-by":"crossref","first-page":"1722","DOI":"10.1080\/00140139.2013.835870","article-title":"Carrying and spine loading","volume":"56","author":"Rose","year":"2013","journal-title":"Ergonomics"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1080\/00140136508930774","article-title":"Carrying of school bags by children","volume":"8","author":"Malhotra","year":"1965","journal-title":"Ergonomics"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.jelekin.2016.03.008","article-title":"Use of a backpack alters gait initiation of high school students","volume":"28","author":"Vieira","year":"2016","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1080\/00140139.2010.489965","article-title":"Postural sway modifications induced by backpack carriage in primary school children: A case study in Italy","volume":"53","author":"Pau","year":"2010","journal-title":"Ergonomics"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Kuo, C.Y., and Lin, W.H. (2010, January 1\u20136). The Effects of Schoolbag Style on Muscle Activation in Lower Extremities during Level Walking and Hill Walking in Primary School Students. Proceedings of the 6th World Congress of Biomechanics (WCB 2010), Singapore.","DOI":"10.1007\/978-3-642-14515-5_82"},{"key":"ref_50","first-page":"188","article-title":"The effects of signal conditioning on the statistical analyses of gait EMG","volume":"93","author":"Gabel","year":"1994","journal-title":"Clin. Neurophysiol."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1002\/jor.1100070611","article-title":"Repeatability of kinematic, kinetic, and electromyographic data in normal adult gait","volume":"7","author":"Kadaba","year":"1989","journal-title":"J. Orthop. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/24\/8365\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:48:33Z","timestamp":1760168913000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/24\/8365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":51,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["s21248365"],"URL":"https:\/\/doi.org\/10.3390\/s21248365","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,15]]}}}