{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:58:24Z","timestamp":1777705104395,"version":"3.51.4"},"reference-count":23,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2021,9,15]]},"abstract":"<jats:p>Deep convolutional neural networks (DCNNs), with their complex network structure and powerful feature learning and feature expression capabilities, have been remarkable successes in many large-scale recognition tasks. However, with the expectation of memory overhead and response time, along with the increasing scale of data, DCNN faces three non-rival challenges in a big data environment: excessive network parameters, slow convergence, and inefficient parallelism. To tackle these three problems, this paper develops a deep convolutional neural networks optimization algorithm (PDCNNO) in the MapReduce framework. The proposed method first pruned the network to obtain a compressed network in order to effectively reduce redundant parameters. Next, a conjugate gradient method based on modified secant equation (CGMSE) is developed in the Map phase to further accelerate the convergence of the network. Finally, a load balancing strategy based on regulate load rate (LBRLA) is proposed in the Reduce phase to quickly achieve equal grouping of data and thus improving the parallel performance of the system. We compared the PDCNNO algorithm with other algorithms on three datasets, including SVHN, EMNIST Digits, and ISLVRC2012. The experimental results show that our algorithm not only reduces the space and time overhead of network training but also obtains a well-performing speed-up ratio in a big data environment.<\/jats:p>","DOI":"10.3233\/jifs-201790","type":"journal-article","created":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T13:12:51Z","timestamp":1627391571000},"page":"2603-2615","source":"Crossref","is-referenced-by-count":6,"title":["A novel MapReduce-based deep convolutional neural network algorithm"],"prefix":"10.1177","volume":"41","author":[{"given":"Xiang-Min","family":"Liu","sequence":"first","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deborah Simon","family":"Mwakapesa","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Y.A.","family":"Nanehkaran","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Min","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui-Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi-Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computing, Central South University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-201790_ref1","first-page":"106","article-title":"Image recognition with deep learning","volume":"3","author":"Islam","year":"2018","journal-title":"International Conference on Intelligent Informatics and Biomedical Sciences"},{"key":"10.3233\/JIFS-201790_ref2","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.ecoinf.2018.10.002","article-title":"Deep convolution neural network for image recognition","volume":"48","author":"Traore","year":"2018","journal-title":"Ecological Informatics"},{"issue":"2","key":"10.3233\/JIFS-201790_ref3","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1109\/JSAC.2020.3020598","article-title":"An open IoHT-based deep learning framework for online medical image recognition","volume":"39","author":"Dourado","year":"2020","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"10.3233\/JIFS-201790_ref4","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.neunet.2020.01.018","article-title":"Theory of deep convolutional neural networks: Downsampling","volume":"124","author":"Zhou","year":"2020","journal-title":"Neural Networks"},{"key":"10.3233\/JIFS-201790_ref5","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.compeleceng.2019.03.004","article-title":"Modified Alexnet architecture for classification of diabetic retinopathy images","volume":"76","author":"Shanthi","year":"2019","journal-title":"Computers & Electrical Engineering"},{"issue":"1","key":"10.3233\/JIFS-201790_ref7","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s11416-018-0324-z","article-title":"Analysis of ResNet and GoogleNet models for malware detection","volume":"15","author":"Khan","year":"2019","journal-title":"Journal of Computer Virology and Hacking Techniques"},{"issue":"2","key":"10.3233\/JIFS-201790_ref8","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1109\/JBHI.2019.2928369","article-title":"Thorax-Net: an attention regularized deep neural network for classification of thoracic disease on chest radiography","volume":"24","author":"Wang","year":"2020","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.3233\/JIFS-201790_ref9","doi-asserted-by":"crossref","first-page":"4121","DOI":"10.1109\/JSTARS.2020.3009352","article-title":"Channel-attention-based DenseNet network for remote sensing image scene classification","volume":"13","author":"Han","year":"2020","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"issue":"6","key":"10.3233\/JIFS-201790_ref10","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1038\/s41583-020-0277-3","article-title":"Backpropagation and the brain","volume":"21","author":"Lillicrap","year":"2020","journal-title":"Nature Reviews Neuroscience"},{"issue":"3","key":"10.3233\/JIFS-201790_ref11","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1080\/23270012.2020.1728403","article-title":"Big data analytics for retail industry using MapReduce-Apriori framework","volume":"7","author":"Verma","year":"2020","journal-title":"Journal of Management Analytics"},{"issue":"5","key":"10.3233\/JIFS-201790_ref13","first-page":"187","article-title":"Convergence analysis of a new coefficient conjugate gradient method under exact line search","volume":"29","author":"Malik","year":"2020","journal-title":"International Journal of Advanced Science and Technology"},{"issue":"3","key":"10.3233\/JIFS-201790_ref14","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1109\/TPAMI.2018.2886192","article-title":"Deep neural network compression by in-parallel pruning-quantization","volume":"42","author":"Tung","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"10.3233\/JIFS-201790_ref15","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TNNLS.2019.2906563","article-title":"Toward compact convNets via structure-sparsity regularized filter pruning","volume":"31","author":"Lin","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.3233\/JIFS-201790_ref17","first-page":"117","article-title":"A spectral conjugate gradient method for unconstrained optimization","volume":"43","author":"Birgin","year":"2016","journal-title":"Journal of Yulin Normal University"},{"issue":"3","key":"10.3233\/JIFS-201790_ref18","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1080\/10556788.2016.1225213","article-title":"A new spectral conjugate gradient method for large-scale unconstrained optimization","volume":"32","author":"Jian","year":"2017","journal-title":"Optimization Methods and Software"},{"issue":"2","key":"10.3233\/JIFS-201790_ref19","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1007\/s10957-019-01527-6","article-title":"A modified spectral conjugate gradient method with global convergence","volume":"182","author":"Faramarzi","year":"2019","journal-title":"Journal of Optimization Theory and Applications"},{"issue":"2019","key":"10.3233\/JIFS-201790_ref22","first-page":"292","article-title":"Single image super-resolution using a polymorphic parallel CNN","volume":"49","author":"Zeng","journal-title":"Applied Intelligence"},{"key":"10.3233\/JIFS-201790_ref23","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1007\/s13042-018-0811-z","article-title":"Towards improving the convolutional neural networks for deep learning using the distributed artificial bee colony method","volume":"10","author":"Banharnsakun","year":"2019","journal-title":"International journal of machine learning and cybernetics"},{"issue":"2020","key":"10.3233\/JIFS-201790_ref25","first-page":"360","article-title":"Some modified Hestenes-Stiefel conjugate gradient algorithms with application in image restoration","volume":"158","author":"Hu","journal-title":"Applied Numerical Mathematics"},{"issue":"3","key":"10.3233\/JIFS-201790_ref27","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1007\/s10589-020-00256-1","article-title":"Secant Update generalized version of PSB: a new approach","volume":"78","author":"Boutet","year":"2021","journal-title":"Computational Optimization and Applications"},{"issue":"2019","key":"10.3233\/JIFS-201790_ref28","first-page":"525","article-title":"Improved Fletcher\u2013Reeves and Dai\u2013Yuan conjugate gradient methods with the strong Wolfe line search","volume":"348","author":"Jiang","journal-title":"Journal of Computational and Applied Mathematics"},{"issue":"9","key":"10.3233\/JIFS-201790_ref29","doi-asserted-by":"crossref","first-page":"3061","DOI":"10.1007\/s00500-017-2561-3","article-title":"Implementation of scalable fuzzy relational operations in MapReduce","volume":"22","author":"Khorasani","year":"2018","journal-title":"Soft Computing"},{"key":"10.3233\/JIFS-201790_ref32","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-201790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:42:54Z","timestamp":1777455774000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-201790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,15]]},"references-count":23,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-201790","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,15]]}}}