{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:46:04Z","timestamp":1760147164269,"version":"build-2065373602"},"reference-count":57,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T00:00:00Z","timestamp":1673827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61720106005"],"award-info":[{"award-number":["61720106005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>In this paper, we focus on the redesign of the output layer for the weighted regularized extreme learning machine (WRELM). For multi-classification problems, the conventional method of the output layer setting, named \u201cone-hot method\u201d, is as follows: Let the class of samples be r; then, the output layer node number is r and the ideal output of s-th class is denoted by the s-th unit vector in Rr (1\u2264s\u2264r). Here, in this article, we propose a \u201cbinarymethod\u201d to optimize the output layer structure: Let 2p\u22121&lt;r\u22642p, where p\u22652, and p output nodes are utilized and, simultaneously, the ideal outputs are encoded in binary numbers. In this paper, the binary method is employed in WRELM. The weights are updated through iterative calculation, which is the most important process in general neural networks. While in the extreme learning machine, the weight matrix is calculated in least square method. That is, the coefficient matrix of the linear equations we solved is symmetric. For WRELM, we continue this idea. And the main part of the weight-solving process is a symmetry matrix. Compared with the one-hot method, the binary method requires fewer output layer nodes, especially when the number of sample categories is high. Thus, some memory space can be saved when storing data. In addition, the number of weights connecting the hidden and the output layer will also be greatly reduced, which will directly reduce the calculation time in the process of training the network. Numerical experiments are conducted to prove that compared with the one-hot method, the binary method can reduce the output nodes and hidden-output weights without damaging the learning precision.<\/jats:p>","DOI":"10.3390\/sym15010244","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T03:40:34Z","timestamp":1673840434000},"page":"244","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Output Layer Structure Optimization for Weighted Regularized Extreme Learning Machine Based on Binary Method"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2301-3803","authenticated-orcid":false,"given":"Sibo","family":"Yang","sequence":"first","affiliation":[{"name":"School of Science, Dalian Maritime University, Dalian 116026, China"}]},{"given":"Shusheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science, Dalian Maritime University, Dalian 116026, China"}]},{"given":"Lanyin","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Xinyang Normal University, Xinyang 464000, China"}]},{"given":"Zhongxuan","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Software, Dalian University of Technology, Dalian 116620, China"}]},{"given":"Yuan","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1007\/s10489-016-0767-1","article-title":"Training feedforward neural networks using multi-verse optimizer for binary classification problems","volume":"45","author":"Faris","year":"2016","journal-title":"Appl. Intell."},{"key":"ref_2","unstructured":"Eldan, R., and Shamir, O. (2016, January 23\u201326). The power of depth for feedforward neural networks. Proceedings of the Conference on Learning Theory, New York, NY, USA."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1109\/TSMCB.2011.2168604","article-title":"Extreme learning machine for regression and multiclass classification","volume":"42","author":"Huang","year":"2011","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s00521-017-2987-7","article-title":"Extreme learning machine model for water network management","volume":"31","author":"Sattar","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.neunet.2019.03.004","article-title":"Multilayer one-class extreme learning machine","volume":"115","author":"Dai","year":"2019","journal-title":"Neural Netw."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/j.jhydrol.2018.11.069","article-title":"An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction","volume":"569","author":"Yaseen","year":"2019","journal-title":"J. Hydrol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1016\/j.future.2018.04.085","article-title":"User behavior prediction in social networks using weighted extreme learning machine with distribution optimization","volume":"93","author":"Luo","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1016\/j.enconman.2018.10.089","article-title":"A novel wind speed forecasting based on hybrid decomposition and online sequential outlier robust extreme learning machine","volume":"180","author":"Zhang","year":"2019","journal-title":"Energy Convers. Manag."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5580","DOI":"10.1109\/TGRS.2019.2900509","article-title":"Local block multilayer sparse extreme learning machine for effective feature extraction and classification of hyperspectral images","volume":"57","author":"Cao","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/s11063-013-9326-5","article-title":"A rough RBF neural network based on weighted regularized extreme learning machine","volume":"40","author":"Ding","year":"2014","journal-title":"Neural Process. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Huang, N., Yuan, C., Cai, G., and Xing, E. (2016). Hybrid short term wind speed forecasting using variational mode decomposition and a weighted regularized extreme learning machine. Energies, 9.","DOI":"10.3390\/en9120989"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1016\/j.asr.2022.08.075","article-title":"Optimization of One versus All-SVM using AdaBoost algorithm for rainfall classification and estimation from multispectral MSG data","volume":"71","author":"Belghit","year":"2023","journal-title":"Adv. Space Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"107528","DOI":"10.1016\/j.patcog.2020.107528","article-title":"One-vs-One classification for deep neural networks","volume":"108","author":"Pawara","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"109122","DOI":"10.1016\/j.patcog.2022.109122","article-title":"A novel soft-coded error-correcting output codes algorithm","volume":"134","author":"Liu","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1016\/j.neucom.2014.07.039","article-title":"Neural network for multi-class classification by boosting composite stumps","volume":"149","author":"Nie","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2995","DOI":"10.1109\/TIT.2019.2893916","article-title":"Data-dependent generalization bounds for multi-class classification","volume":"65","author":"Lei","year":"2019","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/j.ins.2018.12.026","article-title":"A novel perspective on multiclass classification: Regular simplex support vector machine","volume":"480","author":"Tang","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_18","unstructured":"Dong, Q., Zhu, X., and Gong, S. (February, January 27). Single-label multi-class image classification by deep logistic regression. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.ins.2019.04.045","article-title":"A perfect solution to the parity problem with elementary cellular automaton 150 under asynchronous update","volume":"493","author":"Ruivo","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"109884","DOI":"10.1016\/j.knosys.2022.109884","article-title":"Dual regularized unsupervised feature selection based on matrix factorization and minimum redundancy with application in gene selection","volume":"256","author":"Rostami","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"104210","DOI":"10.1016\/j.engappai.2021.104210","article-title":"Review of swarm intelligence-based feature selection methods","volume":"100","author":"Rostami","year":"2021","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_22","first-page":"1","article-title":"Structure-Guided L1\/2 Minimization for Stable Multichannel Seismic Attenuation Compensation","volume":"60","author":"Wang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"103348","DOI":"10.1016\/j.dsp.2021.103348","article-title":"Improved multiband structured subband adaptive filter algorithm with L0-norm regularization for sparse system identification","volume":"122","author":"Heydari","year":"2022","journal-title":"Digit. Signal Process."},{"key":"ref_24","unstructured":"Courbariaux, M., and Bengio, Y. (2015). BinaryConnect: Training Deep Neural Networks with Binary Weights during Propagations, MIT Press."},{"key":"ref_25","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., and Bengio, Y. (2016). Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or \u22121. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., and Farhadi, A. (2016). XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks, Springer.","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chitrakar, P., Zhang, C., Warner, G., and Liao, X. (2016, January 11\u201313). Social Media Image Retrieval Using Distilled Convolutional Neural Network for Suspicious e-Crime and Terrorist Account Detection. Proceedings of the 2016 IEEE International Symposium on Multimedia (ISM), San Jose, CA, USA.","DOI":"10.1109\/ISM.2016.0110"},{"key":"ref_28","unstructured":"Lu, H., Yao, Q., and Kwok, J.T. (2017, January 24\u201326). Loss-aware Binarization of Deep Networks. Proceedings of the 5th International Conference on Learning Representations (ICLR 2017), Toulon, France."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hartmann, M., Farooq, H., and Imran, A. (July, January 29). Distilled Deep Learning based Classification of Abnormal Heartbeat Using ECG Data through a Low Cost Edge Device. Proceedings of the 2019 IEEE Symposium on Computers and Communications (ISCC), Barcelona, Spain.","DOI":"10.1109\/ISCC47284.2019.8969657"},{"key":"ref_30","unstructured":"Darabi, S., Belbahri, M., Courbariaux, M., and Nia, V.P. (2018). BNN+: Improved Binary Network Training. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, W., Xia, X., Zhang, B., Gu, J., Liu, J., Ji, R., and Doermann, D. (2019, January 16\u201317). Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00280"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1007\/s11265-017-1255-5","article-title":"Efficient Object Detection Using Embedded Binarized Neural Networks","volume":"90","author":"Kung","year":"2017","journal-title":"J. Signal Process. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Leng, C., Li, H., Zhu, S., and Jin, R. (2017, January 4\u20139). Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v32i1.11713"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, R., Wang, Y., Liang, F., Qin, H., and Fan, R. (2019, January 15\u201320). Fully Quantized Network for Object Detection. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00292"},{"key":"ref_35","first-page":"985","article-title":"Extreme learning machine: A new learning scheme of feedforward neural networks","volume":"2","author":"Huang","year":"2004","journal-title":"Neural Netw."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","article-title":"Extreme learning machine: Theory and applications","volume":"70","author":"Huang","year":"2006","journal-title":"Neurocomputing"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s13042-011-0019-y","article-title":"Extreme learning machines: A survey","volume":"2","author":"Huang","year":"2011","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1137\/S0895479897329692","article-title":"The Moore\u2013Penrose Generalized Inverse for Sums of Matrices","volume":"21","author":"Fill","year":"2000","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.amc.2003.09.004","article-title":"On the Moore\u2013Penrose generalized inverse matrix","volume":"158","author":"Rakha","year":"2004","journal-title":"Appl. Math. Comput."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1109\/LSP.2019.2895543","article-title":"Multiple Sequential Regularized Extreme Learning Machines for Single Image Super Resolution","volume":"26","author":"Cosmo","year":"2019","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.neucom.2012.02.040","article-title":"Regularized extreme learning machine for regression with missing data","volume":"102","author":"Yu","year":"2013","journal-title":"Neurocomputing"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"12589","DOI":"10.1007\/s10586-017-1685-7","article-title":"Short-term load forecasting based on multivariate time series prediction and weighted neural network with random weights and kernels","volume":"22","author":"Lang","year":"2019","journal-title":"Clust. Comput."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Seferbekov, S.S., Iglovikov, V., Buslaev, A., and Shvets, A. (2018, January 18\u201322). Feature Pyramid Network for Multi-Class Land Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00051"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.procs.2017.12.041","article-title":"Selection of important features and predicting wine quality using machine learning techniques","volume":"125","author":"Gupta","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Yang, L., Luo, P., Change Loy, C., and Tang, X. (2015, January 7\u201312). A large-scale car dataset for fine-grained categorization and verification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.measurement.2017.07.039","article-title":"Rotor resistance estimation using Extended Kalman filter and spectral analysis for rotor bar fault diagnosis of sensorless vector control induction motor","volume":"111","author":"Ameid","year":"2017","journal-title":"Measurement"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"16481","DOI":"10.1109\/JSEN.2022.3190387","article-title":"Map-Assisted Seamless Localization Using Crowdsourced Trajectories Data and Bi-LSTM Based Quality Control Criteria","volume":"22","author":"Yu","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Sankara Babu, B., Nalajala, S., Sarada, K., Muniraju Naidu, V., Yamsani, N., and Saikumar, K. (2022). Machine Learning Based Online Handwritten Telugu Letters Recognition for Different Domains. A Fusion of Artificial Intelligence and Internet of Things for Emerging Cyber Systems, Springer.","DOI":"10.1007\/978-3-030-76653-5_12"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"2417","DOI":"10.1109\/TKDE.2017.2740926","article-title":"Dependency analysis of accuracy estimates in k-fold cross validation","volume":"29","author":"Wong","year":"2017","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.neucom.2015.08.118","article-title":"Displacement prediction of landslide based on generalized regression neural networks with K-fold cross-validation","volume":"198","author":"Jiang","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1080\/10705511.2018.1500140","article-title":"Evaluating the Performance of the K-fold Cross-Validation Approach for Model Selection in Growth Mixture Modeling","volume":"26","author":"He","year":"2019","journal-title":"Struct. Equ. Model. A Multidiscip. J."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11222-009-9153-8","article-title":"Estimation of prediction error by using K-fold cross-validation","volume":"21","author":"Fushiki","year":"2011","journal-title":"Stat. Comput."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.yebeh.2010.03.011","article-title":"Seizure prediction and recall","volume":"18","author":"DuBois","year":"2010","journal-title":"Epilepsy Behav."},{"key":"ref_55","unstructured":"Wang, R., and Li, J. (August, January 28). Bayes Test of Precision, Recall, and F1 Measure for Comparison of Two Natural Language Processing Models. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"2037","DOI":"10.1007\/s11517-017-1647-5","article-title":"Refined multiscale fuzzy entropy based on standard deviation for biomedical signal analysis","volume":"55","author":"Azami","year":"2017","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3354\/cr030079","article-title":"Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance","volume":"30","author":"Willmott","year":"2005","journal-title":"Clim. Res."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/1\/244\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:07:04Z","timestamp":1760119624000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/15\/1\/244"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,16]]},"references-count":57,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["sym15010244"],"URL":"https:\/\/doi.org\/10.3390\/sym15010244","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2023,1,16]]}}}