{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:42:58Z","timestamp":1771702978506,"version":"3.50.1"},"reference-count":51,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T00:00:00Z","timestamp":1603238400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Optical character recognition is gaining immense importance in the domain of deep learning. With each passing day, handwritten digits (0\u20139) data are increasing rapidly, and plenty of research has been conducted thus far. However, there is still a need to develop a robust model that can fetch useful information and investigate self-build handwritten digit data efficiently and effectively. The convolutional neural network (CNN) models incorporating a sigmoid activation function with a large number of derivatives have low efficiency in terms of feature extraction. Here, we designed a novel CNN model integrated with the extreme learning machine (ELM) algorithm. In this model, the sigmoid activation function is upgraded as the rectified linear unit (ReLU) activation function, and the CNN unit along with the ReLU activation function are used as a feature extractor. The ELM unit works as the image classifier, which makes the perfect symmetry for handwritten digit recognition. A deeplearning4j (DL4J) framework-based CNN-ELM model was developed and trained using the Modified National Institute of Standards and Technology (MNIST) database. Validation of the model was performed through self-build handwritten digits and USPS test datasets. Furthermore, we observed the variation of accuracies by adding various hidden layers in the architecture. Results reveal that the CNN-ELM-DL4J approach outperforms the conventional CNN models in terms of accuracy and computational time.<\/jats:p>","DOI":"10.3390\/sym12101742","type":"journal-article","created":{"date-parts":[[2020,10,23]],"date-time":"2020-10-23T02:01:42Z","timestamp":1603418502000},"page":"1742","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["An Effective and Improved CNN-ELM Classifier for Handwritten Digits Recognition and Classification"],"prefix":"10.3390","volume":"12","author":[{"given":"Saqib","family":"Ali","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1545-9204","authenticated-orcid":false,"given":"Yan","family":"Pei","sequence":"additional","affiliation":[{"name":"Computer Science Division, University of Aizu, Aizu-wakamatsu, Fukushima 965-8580, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Saqlain","family":"Aslam","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Central University, Taoyuan 32001, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7901-6712","authenticated-orcid":false,"given":"Zeeshan","family":"Shaukat","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0373-6112","authenticated-orcid":false,"given":"Muhammad","family":"Azeem","sequence":"additional","affiliation":[{"name":"Department of Information Technology, University of Sialkot, Punjab 51040, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Billah, M., Ruman, M.K., Sadat, N., and Islam, M.M. (2019, January 7\u20139). Bangladeshi Post Office Automation System Using Neural Network. Proceedings of the 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE), Cox\u2019s Bazar, Bangladesh.","DOI":"10.1109\/ECACE.2019.8679350"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Dansena, P., Bag, S., and Pal, R. (2017, January 5\u20138). Differentiating pen inks in handwritten bank cheques using multi-layer perceptron. Proceedings of the 2017 International Conference on Pattern Recognition and Machine Intelligence, Kolkata, India.","DOI":"10.1007\/978-3-319-69900-4_83"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Selmi, Z., Halima, M.B., and Alimi, A.M. (2017, January 9\u201315). Deep learning system for automatic license plate detection and recognition. Proceedings of the 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.187"},{"key":"ref_4","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201326). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), San Diego, CA, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1142\/S021962201841002X","article-title":"A new approach for stock price analysis and prediction based on SSA and SVM","volume":"18","author":"Xiao","year":"2019","journal-title":"Int. J. Inf. Technol. Decis. Mak."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3815","DOI":"10.1109\/TNNLS.2017.2741349","article-title":"Dissipativity and synchronization of generalized BAM neural networks with multivariate discontinuous activations","volume":"29","author":"Wang","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1007\/s00500-014-1332-7","article-title":"A novel SVM by combining kernel principal component analysis and improved chaotic particle swarm optimization for intrusion detection","volume":"19","author":"Kuang","year":"2015","journal-title":"Soft Comput."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Li, Y.-H., Aslam, M.S., Yang, K.-L., Kao, C.-A., and Teng, S.-Y. (2020). Classification of Body Constitution Based on TCM Philosophy and Deep Learning. Symmetry, 12.","DOI":"10.3390\/sym12050803"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: A review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.aci.2015.05.001","article-title":"Novel feature extraction technique for the recognition of handwritten digits","volume":"13","author":"Boukharouba","year":"2017","journal-title":"Appl. Comput. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.neunet.2014.08.001","article-title":"A convolutional recursive modified Self Organizing Map for handwritten digits recognition","volume":"60","author":"Mohebi","year":"2014","journal-title":"Neural Netw."},{"key":"ref_13","first-page":"1101","article-title":"Handwritten digit recognition using convolutional neural networks","volume":"4","author":"Alwzwazy","year":"2016","journal-title":"Int. J. Innov. Res. Comput. Commun. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jain, A., Subrahmanyam, G.R.S., and Mishra, D. (2018, January 16\u201318). Rotation invariant digit recognition using convolutional neural network. Proceedings of the 2018 2nd International Conference on Computer Vision & Image Processing, Chengdu, China.","DOI":"10.1007\/978-981-10-7895-8_8"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"700","DOI":"10.18517\/ijaseit.9.2.6809","article-title":"High-quality wavelets features extraction for handwritten arabic numerals recognition","volume":"9","author":"Akhtar","year":"2019","journal-title":"Int. J. Adv. Sci. Eng. Inf. Technol."},{"key":"ref_16","unstructured":"Krizhevsky, A., and Hinton, G. (2010). Convolutional deep belief networks on cifar-10. 40, 1\u20139. Unpublished Work."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Arora, S., and Bhatia, M.S. (2018, January 12\u201313). Handwriting recognition using Deep Learning in Keras. Proceedings of the 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), Greater Noida (UP), India.","DOI":"10.1109\/ICACCCN.2018.8748540"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Malik, H., and Roy, N. (2019). Extreme Learning Machine-Based Image Classification Model Using Handwritten Digit Database. Applications of Artificial Intelligence Techniques in Engineering, Springer.","DOI":"10.1007\/978-981-13-1822-1_57"},{"key":"ref_19","first-page":"195","article-title":"Sindhi Handwritten-Digits Recognition Using Machine Learning Techniques","volume":"19","author":"Ali","year":"2019","journal-title":"Int. J. Comput. Sci. Netw. Secur."},{"key":"ref_20","first-page":"45","article-title":"Advanced approaches of handwritten digit recognition using hybrid algorithm","volume":"1","author":"Bishnoi","year":"2012","journal-title":"Int. J. Commun. Comput. Technol."},{"key":"ref_21","unstructured":"Cruz, R.M., Cavalcanti, G.D., and Ren, T.I. (2010, January 17\u201319). Handwritten digit recognition using multiple feature extraction techniques and classifier ensemble. Proceedings of the 2010 17th International Conference on Systems, Signals and Image Processing, Rio de Janeiro, Brazil."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kochura, Y., Stirenko, S., Alienin, O., Novotarskiy, M., and Gordienko, Y. (2017, January 5\u20138). Comparative analysis of open source frameworks for machine learning with use case in single-threaded and multi-threaded modes. Proceedings of the 2017 12th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT), Lviv, Ukraine.","DOI":"10.1109\/STC-CSIT.2017.8098808"},{"key":"ref_23","unstructured":"Huang, G.-B., Zhu, Q.-Y., and Siew, C.-K. (2004, January 25\u201329). Extreme learning machine: A new learning scheme of feedforward neural networks. Proceedings of the 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541), Budapest, Hungary."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Tan, H.H., Lim, K.H., and Harno, H.G. (2017, January 14\u201319). Stochastic diagonal approximate greatest descent in neural networks. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.","DOI":"10.1109\/IJCNN.2017.7966081"},{"key":"ref_25","unstructured":"Hamid, N.A., and Sjarif, N.N.A. (2017). Handwritten recognition using SVM, KNN and neural network. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1049\/el.2017.2621","article-title":"SparseConnect: Regularising CNNs on fully connected layers","volume":"53","author":"Xu","year":"2017","journal-title":"Electron. Lett."},{"key":"ref_27","unstructured":"Ghosh, M.M.A., and Maghari, A.Y. (2017, January 16\u201317). A comparative study on handwriting digit recognition using neural networks. Proceedings of the 2017 International Conference on Promising Electronic Technologies (ICPET), Deir El-Balah, Palestine."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"4538","DOI":"10.1109\/TSP.2017.2712128","article-title":"Exploiting restricted Boltzmann machines and deep belief networks in compressed sensing","volume":"65","author":"Polania","year":"2017","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_29","first-page":"1","article-title":"A tutorial survey of architectures, algorithms, and applications for deep learning","volume":"3","author":"Deng","year":"2014","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Teow, M.Y. (2017, January 21). Understanding convolutional neural networks using a minimal model for handwritten digit recognition. Proceedings of the 2017 IEEE 2nd International Conference on Automatic Control and Intelligent Systems (I2CACIS), Kota Kinabalu, Malaysia.","DOI":"10.1109\/I2CACIS.2017.8239052"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2521","DOI":"10.1109\/TMM.2017.2697824","article-title":"Compact hash codes for efficient visual descriptors retrieval in large scale databases","volume":"19","author":"Ercoli","year":"2017","journal-title":"IEEE Trans. Multimed."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Abouelnaga, Y., Ali, O.S., Rady, H., and Moustafa, M. (2016, January 15\u201317). CIFAR-10: KNN-based Ensemble of Classifiers. Proceedings of the 2016 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA.","DOI":"10.1109\/CSCI.2016.0225"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3218","DOI":"10.1109\/TCYB.2016.2633552","article-title":"Building correlations between filters in convolutional neural networks","volume":"47","author":"Wang","year":"2016","journal-title":"IEEE Trans. Cybern."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2825","DOI":"10.1109\/TCYB.2015.2490165","article-title":"Feature set evaluation for offline handwriting recognition systems: Application to the recurrent neural network model","volume":"46","author":"Chherawala","year":"2015","journal-title":"IEEE Trans. Cybern."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Katayama, N., and Yamane, S. (2018, January 9\u201312). Recognition of rotated images by angle estimation using feature map with CNN. Proceedings of the 2017 IEEE 6th Global Conference on Consumer Electronics (GCCE), Nagoya, Japan.","DOI":"10.1109\/GCCE.2017.8229445"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2016\/3049632","article-title":"Deep convolutional extreme learning machine and its application in handwritten digit classification","volume":"2016","author":"Pang","year":"2016","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"8309","DOI":"10.3934\/mbe.2019420","article-title":"An effective classifier based on convolutional neural network and regularized extreme learning machine","volume":"16","author":"He","year":"2019","journal-title":"Math. Biosci. Eng. MBE"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.neucom.2019.10.013","article-title":"Sample selection-based hierarchical extreme learning machine","volume":"377","author":"Xu","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"19495","DOI":"10.1007\/s11042-019-7330-0","article-title":"An empirical evaluation of extreme learning machine: Application to handwritten character recognition","volume":"78","author":"Das","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1975","DOI":"10.1007\/s00521-015-2170-y","article-title":"Extreme learning machine with kernel model based on deep learning","volume":"28","author":"Ding","year":"2017","journal-title":"Neural Comput. Appl."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Sukittanon, S., Surendran, A.C., Platt, J.C., and Burges, C.J. (2004, January 4\u20138). Convolutional networks for speech detection. Proceedings of the 2004 Eighth International Conference on Spoken Language Processing, Jeju Island, Korea.","DOI":"10.21437\/Interspeech.2004-376"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1016\/j.patcog.2006.10.011","article-title":"A trainable feature extractor for handwritten digit recognition","volume":"40","author":"Lauer","year":"2007","journal-title":"Pattern Recognit."},{"key":"ref_44","first-page":"1","article-title":"A Method Combining CNN and ELM for Feature Extraction and Classification of SAR Image","volume":"2019","author":"Wang","year":"2019","journal-title":"J. Sens."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1318","DOI":"10.1016\/j.patcog.2011.09.021","article-title":"A novel hybrid CNN-SVM classifier for recognizing handwritten digits","volume":"45","author":"Niu","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_46","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). Imagenet classification with deep convolutional neural networks. Proceedings of the 2012 Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_47","unstructured":"Maji, S., and Malik, J. (2009). Fast and Accurate Digit Classification, Electrical Engineering and Computer Sciences Department, University of California at Berkeley. Available online: http:\/\/www2.eecs.berkeley.edu\/Pubs\/TechRpts\/2009\/EECS-2009-159.pdf."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Kusetogullari, H., Yavariabdi, A., Cheddad, A., Grahn, H., and Hall, J. (2019). ARDIS: A Swedish historical handwritten digit dataset. Neural Comput. Appl., 1\u201314.","DOI":"10.1007\/s00521-019-04163-3"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1007\/s42452-019-1161-5","article-title":"An efficient and improved scheme for handwritten digit recognition based on convolutional neural network","volume":"1","author":"Ali","year":"2019","journal-title":"SN Appl. Sci."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13042-019-01054-w","article-title":"Homo-ELM: Fully homomorphic extreme learning machine","volume":"11","author":"Wang","year":"2020","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/s41066-019-00158-6","article-title":"Multiple classifiers fusion and CNN feature extraction for handwritten digits recognition","volume":"5","author":"Zhao","year":"2020","journal-title":"Granul. Comput."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/12\/10\/1742\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:25:12Z","timestamp":1760178312000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/12\/10\/1742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,21]]},"references-count":51,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2020,10]]}},"alternative-id":["sym12101742"],"URL":"https:\/\/doi.org\/10.3390\/sym12101742","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,21]]}}}