{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T17:20:38Z","timestamp":1771003238418,"version":"3.50.1"},"reference-count":11,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"published-print":{"date-parts":[[2022,12,19]]},"abstract":"<jats:p>MFF-Net (a multi-scale feature fusion convolutional neural network) was designed to improve the recognition rate of handwritten digits. The low-level, middle-level and high-level features of the image were first extracted through the convolution operation, and then the low-level and intermediate features were further extracted through different convolutional layers, later directly fused with the high-level features of the image with a certain weight, and then processed by the full connection layer. By adding a batch normalization layer before the activation layer, and a dropout layer between the full connection layers, the accuracy and generalization capacity of the network are improved. At the same time, a dynamic learning rate algorithm was designed, with which, the trained network accuracy was significantly improved as shown in the experiments on the MNIST data set. The accurate rate could reach 99.66% through only 30 epochs training. The comparison indicated that the accuracy of the network model is significantly higher than that of others.<\/jats:p>","DOI":"10.3233\/jcm-226356","type":"journal-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T11:31:31Z","timestamp":1661254291000},"page":"2217-2225","source":"Crossref","is-referenced-by-count":0,"title":["A convolutional neural network model of multi-scale feature fusion: MFF-Net"],"prefix":"10.1177","volume":"22","author":[{"given":"Yunyun","family":"Yi","sequence":"first","affiliation":[{"name":"School of Computer and Information, Anhui Polytechnic University, Wuhu, Anhui, China"}]},{"given":"Jinbao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Anhui Normal University, Wuhu, Anhui, China"}]},{"given":"Xingtao","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Anhui Normal University, Wuhu, Anhui, China"}]},{"given":"Chenlong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Anhui Polytechnic University, Wuhu, Anhui, China"}]}],"member":"179","reference":[{"issue":"11","key":"10.3233\/JCM-226356_ref1","first-page":"22","article-title":"Application of multi-scale features based on CNN in handwritten digit recognition","volume":"38","author":"Zhong","year":"2019","journal-title":"J Mianyang Norm Univ."},{"issue":"4","key":"10.3233\/JCM-226356_ref2","first-page":"382","article-title":"Research on handwritten digit recognition based on KNN algorithm","volume":"36","author":"Zhao","year":"2017","journal-title":"J Chengdu Univ (Nat Sci Ed)."},{"issue":"11","key":"10.3233\/JCM-226356_ref3","first-page":"187","article-title":"Handwritten digit recognition based on fusion convolutional neural network model","volume":"43","author":"Chen","year":"2017","journal-title":"Comput Eng."},{"issue":"4","key":"10.3233\/JCM-226356_ref4","first-page":"1239","article-title":"Research on handwritten digit recognition based on deep convolutional autoencoding neural network","volume":"37","author":"Zeng","year":"2020","journal-title":"Comput Appl Res."},{"issue":"3","key":"10.3233\/JCM-226356_ref5","first-page":"47","article-title":"Handwritten digit recognition based on deep ensemble learning","volume":"36","author":"Zhou","year":"2020","journal-title":"J Shaanxi Univ Technol (Nat Sci Ed)."},{"key":"10.3233\/JCM-226356_ref7","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.inffus.2018.12.005","article-title":"On improving CNNs performance: The case of MNIST","volume":"52","author":"Alvear-Sandoval","year":"2019","journal-title":"Inf Fusion."},{"issue":"2","key":"10.3233\/JCM-226356_ref8","doi-asserted-by":"crossref","first-page":"126","DOI":"10.5391\/IJFIS.2018.18.2.126","article-title":"Comparisons of deep learning algorithms for MNIST in real-time environment","volume":"18","author":"Palvanov","year":"2018","journal-title":"Int J Fuzzy Logic Intell Syst."},{"issue":"15","key":"10.3233\/JCM-226356_ref9","doi-asserted-by":"crossref","first-page":"3169","DOI":"10.3390\/app9153169","article-title":"A survey of handwritten character. Recognition with MNIST and EMNIST","volume":"9","author":"Baldominos","year":"2019","journal-title":"Appl Sci-Basel."},{"issue":"12","key":"10.3233\/JCM-226356_ref12","first-page":"3548","article-title":"Handwritten digit recognition under the background of edge intelligence","volume":"39","author":"Wang","year":"2019","journal-title":"Comput Appl."},{"key":"10.3233\/JCM-226356_ref13","first-page":"73","article-title":"MNIST-NET10: A heterogeneous deep networks fusion based on the degree of certainty to reach 0.1% error rate","volume":"62","author":"Tabik","year":"2020","journal-title":"Ensembles Overview Proposal."},{"issue":"6","key":"10.3233\/JCM-226356_ref14","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1103\/PhysRevA.101.062327","article-title":"Classification of the MNIST data set with quantum slow feature analysis","volume":"101","author":"Kerenidis","year":"2020","journal-title":"Phys Review A."}],"container-title":["Journal of Computational Methods in Sciences and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JCM-226356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T16:31:44Z","timestamp":1771000304000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JCM-226356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,19]]},"references-count":11,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/jcm-226356","relation":{},"ISSN":["1472-7978","1875-8983"],"issn-type":[{"value":"1472-7978","type":"print"},{"value":"1875-8983","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,19]]}}}