{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T18:10:38Z","timestamp":1759947038118,"version":"build-2065373602"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071143"],"award-info":[{"award-number":["62071143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3579732","type":"journal-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T13:29:45Z","timestamp":1751549385000},"page":"18765-18779","source":"Crossref","is-referenced-by-count":0,"title":["Utilizing TOP2 Class for Hybrid Decision-Making to Enhance TOP1 Accuracy of Ensemble Models"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4415-366X","authenticated-orcid":false,"given":"Jiqing","family":"Li","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7567-9084","authenticated-orcid":false,"given":"Zhendong","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4747-0486","authenticated-orcid":false,"given":"Dasen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8913-6032","authenticated-orcid":false,"given":"Yanlong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.3389\/fpubh.2022.858282","article-title":"Improving the accuracy of ensemble machine learning classification models using a novel bit-fusion algorithm for healthcare AI systems","volume":"10","author":"Mishra","year":"2022","journal-title":"Frontiers Public Health"},{"issue":"4","key":"ref3","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1080\/08839514.2021.1877481","article-title":"Classifier selection and ensemble model for multi-class imbalance learning in education grants prediction","volume":"35","author":"Sun","year":"2021","journal-title":"Appl. Artif. Intell."},{"issue":"12","key":"ref4","doi-asserted-by":"crossref","first-page":"8240","DOI":"10.1109\/TPAMI.2024.3432812","article-title":"Stimulating diffusion model for image denoising via adaptive embedding and ensembling","volume":"46","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"11","key":"ref5","doi-asserted-by":"crossref","first-page":"7205","DOI":"10.1109\/TPAMI.2024.3388097","article-title":"Ensemble predictors: Possibilistic combination of conformal predictors for multivariate time series classification","volume":"46","author":"Campagner","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"11","key":"ref6","doi-asserted-by":"crossref","first-page":"15896","DOI":"10.1109\/TNNLS.2023.3290203","article-title":"Interpretability diversity for decision-tree-initialized dendritic neuron model ensemble","volume":"35","author":"Luo","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"1","key":"ref7","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1109\/TNNLS.2023.3282809","article-title":"Semi-supervised detection model based on adaptive ensemble learning for medical images","volume":"36","author":"Li","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"9","key":"ref8","doi-asserted-by":"crossref","first-page":"12186","DOI":"10.1109\/TNNLS.2023.3252586","article-title":"Active clustering ensemble with self-paced learning","volume":"35","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref9","first-page":"13329","article-title":"Eliciting thinking hierarchy without a prior","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kong"},{"issue":"1","key":"ref10","first-page":"24851","article-title":"Optimization of SVR and CatBoost models using metaheuristic algorithms to assess landslide susceptibility","volume-title":"Sci. Rep.","volume":"14","author":"Ajin","year":"2024"},{"issue":"14","key":"ref11","doi-asserted-by":"crossref","first-page":"2595","DOI":"10.3390\/rs16142595","article-title":"Enhancing the performance of machine learning and deep learning-based flood susceptibility models by integrating grey wolf optimizer (GWO) algorithm","volume":"16","author":"Mabdeh","year":"2024","journal-title":"Remote Sens."},{"issue":"2","key":"ref12","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1023\/A:1007607513941","article-title":"An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization","volume":"40","author":"Dietterich","year":"2000","journal-title":"Mach. Learn."},{"issue":"4","key":"ref13","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1109\/TSMCC.2011.2161285","article-title":"A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches","volume":"42","author":"Galar","year":"2012","journal-title":"IEEE Trans. Syst. Man, Cybern., C"},{"issue":"4","key":"ref14","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.ijar.2011.12.011","article-title":"The impact of diversity on the accuracy of evidential classifier ensembles","volume":"53","author":"Bi","year":"2012","journal-title":"Int. J. Approx. Reasoning"},{"issue":"2","key":"ref15","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.12363","article-title":"Credit scoring for a microcredit data set using the synthetic minority oversampling technique and ensemble classifiers","volume":"36","author":"Gici\u0107","year":"2019","journal-title":"Expert Syst."},{"key":"ref16","first-page":"90","article-title":"A comparative evaluation of voting and meta-learning on partitioned data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chan"},{"key":"ref17","first-page":"1","article-title":"A comprehensive survey on ensemble methods","volume-title":"Proc. IEEE 7th Int. Conf. Converg. Technol. (I2CT)","author":"Kumar"},{"key":"ref18","first-page":"16464","article-title":"Boosting ensemble accuracy by revisiting ensemble diversity metrics","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Wu"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2019.105434","article-title":"Random balance ensembles for multiclass imbalance learning","volume":"193","author":"Rodr\u00edguez","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"ref20","first-page":"1621","article-title":"Managing diversity in regression ensembles","volume":"6","author":"Brown","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/978-3-642-03999-7_7","article-title":"Disturbing neighbors diversity for decision forests","volume":"245","author":"Maudes","year":"2009","journal-title":"Appl. Supervised Unsupervised Ensemble Methods"},{"issue":"1","key":"ref22","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/s00500-011-0734-z","article-title":"Parameter determination and feature selection for C4.5 algorithm using scatter search approach","volume":"16","author":"Lin","year":"2012","journal-title":"Soft Comput."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.105"},{"issue":"5","key":"ref24","doi-asserted-by":"crossref","first-page":"2284","DOI":"10.1109\/TNNLS.2021.3106306","article-title":"Adaptive subspace optimization ensemble method for high-dimensional imbalanced data classification","volume":"34","author":"Xu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"5","key":"ref25","doi-asserted-by":"crossref","first-page":"2308","DOI":"10.1109\/TNNLS.2021.3106391","article-title":"MGML: Multigranularity multilevel feature ensemble network for remote sensing scene classification","volume":"34","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"5","key":"ref26","doi-asserted-by":"crossref","first-page":"2670","DOI":"10.1109\/TNNLS.2021.3107354","article-title":"From ensemble clustering to subspace clustering: Cluster structure encoding","volume":"34","author":"Tao","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"ref27","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1023\/A:1022648800760","article-title":"The strength of weak learnability","volume":"5","author":"Schapire","year":"1990","journal-title":"Mach. Learn."},{"issue":"2","key":"ref28","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1023\/A:1018054314350","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"issue":"2","key":"ref29","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Netw."},{"issue":"10","key":"ref30","doi-asserted-by":"crossref","first-page":"6015","DOI":"10.1109\/TSMC.2019.2958647","article-title":"Formulating ensemble learning of SVMs into a single SVM formulation by negative agreement learning","volume":"51","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Syst. Man, Cybern. Syst."},{"key":"ref31","first-page":"119","article-title":"A decision-theoretic generalization of on-line learning and an application to boosting","volume-title":"Proc. Eur. Conf. Comput. Learn. Theory","volume":"55","author":"Freund"},{"key":"ref32","first-page":"785","article-title":"XGBoost: A scalable tree boosting system","volume-title":"Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining","author":"Chen"},{"key":"ref33","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv:1701.06538"},{"key":"ref34","article-title":"Mixture-of-experts with expert choice routing","author":"Zhou","year":"2022","journal-title":"arXiv:2202.09368"},{"key":"ref35","first-page":"26068","article-title":"Collaboration of experts: Achieving 80% top-1 accuracy on ImageNet with 100M FLOPs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref36","first-page":"1","article-title":"Ensemble deep learning for regression and time series forecasting","volume-title":"Proc. IEEE Symp. Comput. Intell. Ensemble Learn. (CIEL)","author":"Qiu"},{"issue":"1","key":"ref37","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","first-page":"5338","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lakshminarayanan"},{"key":"ref39","first-page":"1467","article-title":"Deep neural decision forests","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Kontschieder"},{"issue":"5","key":"ref40","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1007\/s12559-017-9472-6","article-title":"Ensemble of deep neural networks with probability-based fusion for facial expression recognition","volume":"9","author":"Wen","year":"2017","journal-title":"Cogn. Comput."},{"issue":"3","key":"ref41","doi-asserted-by":"crossref","first-page":"3780","DOI":"10.1109\/TNNLS.2022.3198142","article-title":"Robust self-ensembling network for hyperspectral image classification","volume":"35","author":"Xu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref42","doi-asserted-by":"crossref","first-page":"2901","DOI":"10.1109\/TIP.2023.3263109","article-title":"Learning a deep ensemble network with band importance for hyperspectral object tracking","volume":"32","author":"Li","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109449","article-title":"ECM-EFS: An ensemble feature selection based on enhanced co-association matrix","volume":"139","author":"Wu","year":"2023","journal-title":"Pattern Recognit."},{"issue":"3","key":"ref44","doi-asserted-by":"crossref","first-page":"3912","DOI":"10.1109\/TNNLS.2022.3201198","article-title":"A deep ensemble dynamic learning network for corona virus disease 2019 diagnosis","volume":"35","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"6","key":"ref45","doi-asserted-by":"crossref","first-page":"7923","DOI":"10.1109\/TNNLS.2022.3222263","article-title":"Inverse adversarial diversity learning for network ensemble","volume":"35","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref46","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. Comput. Vis. Pattern Recognit.","author":"He"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref48","first-page":"1314","article-title":"Searching for MobileNetV3","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Howard"},{"key":"ref49","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"arXiv:1905.11946"},{"issue":"7","key":"ref50","first-page":"3","article-title":"Tiny ImageNet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"volume-title":"Learning Multiple Layers of Features From Tiny Images","year":"2009","author":"Krizhevsky","key":"ref51"},{"key":"ref52","first-page":"213","article-title":"Adapting visual category models to new domains","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Saenko"},{"key":"ref53","first-page":"249","article-title":"PlantDoc: A dataset for visual plant disease detection","volume-title":"Proc. 7th ACM IKDD CoDS 25th COMAD","author":"Singh"},{"key":"ref54","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Song"},{"key":"ref55","first-page":"1137","article-title":"A study of cross-validation and bootstrap for accuracy estimation and model selection","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","volume":"2","author":"Kohavi"},{"volume-title":"Automatic Differentiation in Pytorch","year":"2017","author":"Paszke et al","key":"ref56"},{"key":"ref57","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11068155.pdf?arnumber=11068155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:45Z","timestamp":1759945125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11068155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":57,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3579732","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}