{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T09:32:07Z","timestamp":1761989527906,"version":"3.37.3"},"reference-count":45,"publisher":"World Scientific Pub Co Pte Ltd","issue":"02","funder":[{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ20F020016"],"award-info":[{"award-number":["LQ20F020016"]}]},{"DOI":"10.13039\/100011199","name":"FP7 Ideas: European Research Council","doi-asserted-by":"publisher","award":["600915"],"award-info":[{"award-number":["600915"]}],"id":[{"id":"10.13039\/100011199","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Human. Robot."],"published-print":{"date-parts":[[2021,4]]},"abstract":"<jats:p> The learning of inter-day representation of electromyographic (EMG) signals across multiple days remains a challenging topic and not fully accommodated yet. This study aims to improve the inter-day hand motion classification accuracy via convolutional neural network (CNN)-based data feature fusion. An EMG database (ISRMyo-I) was recorded from six subjects on 10 days via a low density electrode setting. This study investigated CNNs\u2019 capability of feature learning, and found that the output of the first fully connected layer (CNNFeats) was a decent supplement feature set to the most prevalent Hudgins\u2019 time domain features in combination with fourth-order autoregressive coefficients (TDAR). Through adding the automatically learned CNNFeats to the handcrafted TDAR feature set, both linear discriminant analysis (LDA) and support vector machine (SVM) classifiers received [Formula: see text]3% accuracy improvement. Similarly, taking TDAR as additional input to the CNN improved the accuracy by [Formula: see text]1% in the comparison with the basic CNN.\u00a0Our results also demonstrated that the CNN approach outperformed conventional approaches when multiple subjects\u2019 data were available for training, while traditional approaches were more adept at presenting motion patterns for single subject. A preliminary conclusion is drawn that substantial \u201ccommon knowledge\/features\u201d can be learned by CNNs from the raw EMG signals across multiple days and multiple subjects, and thus it is believed that a pre-trained CNN model would contribute to higher accuracy as well as the reduction of learning burden. <\/jats:p>","DOI":"10.1142\/s0219843620500255","type":"journal-article","created":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T07:17:07Z","timestamp":1607930227000},"page":"2050025","source":"Crossref","is-referenced-by-count":21,"title":["Improve Inter-day Hand Gesture Recognition Via Convolutional Neural Network-based Feature Fusion"],"prefix":"10.1142","volume":"18","author":[{"given":"Yinfeng","family":"Fang","sequence":"first","affiliation":[{"name":"College of Telecommunication, Hangzhou Dianzi University, 1158, No. 2 Avenue, Xiasha, Hangzhou 310018, P. R. China"}]},{"given":"Xuguang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Telecommunication, Hangzhou Dianzi University, 1158, No. 2 Avenue, Xiasha, Hangzhou 310018, P. R. China"}]},{"given":"Dalin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Intelligent Systems and Biomedical Robotics Group, School of Computing, University of Portsmouth, Portsmouth PO1 3HE, UK"}]},{"given":"Honghai","family":"Liu","sequence":"additional","affiliation":[{"name":"Intelligent Systems and Biomedical Robotics Group, School of Computing, University of Portsmouth, Portsmouth PO1 3HE, UK"},{"name":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2021,1,25]]},"reference":[{"key":"S0219843620500255BIB001","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2003.813539"},{"key":"S0219843620500255BIB002","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2014.2305111"},{"key":"S0219843620500255BIB003","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2012.6346923"},{"key":"S0219843620500255BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2011.2159216"},{"key":"S0219843620500255BIB005","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2017.2766360"},{"key":"S0219843620500255BIB006","doi-asserted-by":"publisher","DOI":"10.1097\/JPO.0b013e31827af7c1"},{"key":"S0219843620500255BIB007","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2013.2279737"},{"key":"S0219843620500255BIB008","doi-asserted-by":"publisher","DOI":"10.1186\/1743-0003-7-21"},{"key":"S0219843620500255BIB009","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2007.11.005"},{"key":"S0219843620500255BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2013.2296274"},{"key":"S0219843620500255BIB011","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2015.2492619"},{"key":"S0219843620500255BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2006.260681"},{"key":"S0219843620500255BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2015.2450211"},{"key":"S0219843620500255BIB014","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.53"},{"key":"S0219843620500255BIB015","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702501"},{"key":"S0219843620500255BIB016","doi-asserted-by":"publisher","DOI":"10.3390\/s17030458"},{"key":"S0219843620500255BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2012.6485374"},{"key":"S0219843620500255BIB018","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00379"},{"key":"S0219843620500255BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.477"},{"key":"S0219843620500255BIB020","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc2030021"},{"key":"S0219843620500255BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/10.204774"},{"key":"S0219843620500255BIB022","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759384"},{"key":"S0219843620500255BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122854"},{"key":"S0219843620500255BIB024","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2019.101574"},{"key":"S0219843620500255BIB025","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2016.00009"},{"key":"S0219843620500255BIB026","doi-asserted-by":"publisher","DOI":"10.1038\/srep36571"},{"issue":"10","key":"S0219843620500255BIB027","first-page":"1","volume":"13","author":"Geng W.","year":"2018","journal-title":"PLoS One"},{"key":"S0219843620500255BIB028","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941977"},{"key":"S0219843620500255BIB029","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-019-00966-x"},{"key":"S0219843620500255BIB030","doi-asserted-by":"publisher","DOI":"10.3390\/s20143994"},{"key":"S0219843620500255BIB031","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2925191"},{"key":"S0219843620500255BIB032","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40852-6_41"},{"key":"S0219843620500255BIB033","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2014.6974252"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow I.","key":"S0219843620500255BIB034"},{"key":"S0219843620500255BIB035","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790388"},{"key":"S0219843620500255BIB036","first-page":"1929","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"S0219843620500255BIB038","first-page":"625","volume":"11","author":"Erhan D.","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"S0219843620500255BIB039","first-page":"153","volume-title":"Proc. Artificial Intelligence and Statistics","author":"Erhan D.","year":"2009"},{"key":"S0219843620500255BIB040","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2263288"},{"key":"S0219843620500255BIB041","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2014.2366752"},{"key":"S0219843620500255BIB042","doi-asserted-by":"publisher","DOI":"10.3390\/s17071597"},{"key":"S0219843620500255BIB043","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/12\/4\/046005"},{"key":"S0219843620500255BIB044","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2013.02.023"},{"key":"S0219843620500255BIB045","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2011.2177662"},{"key":"S0219843620500255BIB046","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2015.2420654"}],"container-title":["International Journal of Humanoid Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0219843620500255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,5]],"date-time":"2021-08-05T09:35:27Z","timestamp":1628156127000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0219843620500255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,25]]},"references-count":45,"journal-issue":{"issue":"02","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["10.1142\/S0219843620500255"],"URL":"https:\/\/doi.org\/10.1142\/s0219843620500255","relation":{},"ISSN":["0219-8436","1793-6942"],"issn-type":[{"type":"print","value":"0219-8436"},{"type":"electronic","value":"1793-6942"}],"subject":[],"published":{"date-parts":[[2021,1,25]]}}}