{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T12:37:29Z","timestamp":1781181449025,"version":"3.54.1"},"reference-count":25,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T00:00:00Z","timestamp":1715904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Liaoning Provincial Department of Education\u2019s Higher Education Foundation Research Project (General Project), Shenyang University of Technology","award":["LJKZ0159"],"award-info":[{"award-number":["LJKZ0159"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Higher Education Foundation Research Project (General Project), Shenyang University of Technology","award":["JG22DB488"],"award-info":[{"award-number":["JG22DB488"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Higher Education Foundation Research Project (General Project), Shenyang University of Technology","award":["202200209"],"award-info":[{"award-number":["202200209"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Higher Education Foundation Research Project (General Project), Shenyang University of Technology","award":["JYTMS20231160"],"award-info":[{"award-number":["JYTMS20231160"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Higher Education Foundation Research Project (General Project), Shenyang University of Technology","award":["22-319-2-26"],"award-info":[{"award-number":["22-319-2-26"]}]},{"name":"Liaoning Provincial Department of Education Science \u201c14th Five-Year Plan\u201d","award":["LJKZ0159"],"award-info":[{"award-number":["LJKZ0159"]}]},{"name":"Liaoning Provincial Department of Education Science \u201c14th Five-Year Plan\u201d","award":["JG22DB488"],"award-info":[{"award-number":["JG22DB488"]}]},{"name":"Liaoning Provincial Department of Education Science \u201c14th Five-Year Plan\u201d","award":["202200209"],"award-info":[{"award-number":["202200209"]}]},{"name":"Liaoning Provincial Department of Education Science \u201c14th Five-Year Plan\u201d","award":["JYTMS20231160"],"award-info":[{"award-number":["JYTMS20231160"]}]},{"name":"Liaoning Provincial Department of Education Science \u201c14th Five-Year Plan\u201d","award":["22-319-2-26"],"award-info":[{"award-number":["22-319-2-26"]}]},{"name":"Ministry of Education\u2019s \u201cChunhui Plan\u201d","award":["LJKZ0159"],"award-info":[{"award-number":["LJKZ0159"]}]},{"name":"Ministry of Education\u2019s \u201cChunhui Plan\u201d","award":["JG22DB488"],"award-info":[{"award-number":["JG22DB488"]}]},{"name":"Ministry of Education\u2019s \u201cChunhui Plan\u201d","award":["202200209"],"award-info":[{"award-number":["202200209"]}]},{"name":"Ministry of Education\u2019s \u201cChunhui Plan\u201d","award":["JYTMS20231160"],"award-info":[{"award-number":["JYTMS20231160"]}]},{"name":"Ministry of Education\u2019s \u201cChunhui Plan\u201d","award":["22-319-2-26"],"award-info":[{"award-number":["22-319-2-26"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Basic Research Project \u201cTraining and Application of Vertical Field Multi-Mode Deep Neural Network Model\u201d","award":["LJKZ0159"],"award-info":[{"award-number":["LJKZ0159"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Basic Research Project \u201cTraining and Application of Vertical Field Multi-Mode Deep Neural Network Model\u201d","award":["JG22DB488"],"award-info":[{"award-number":["JG22DB488"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Basic Research Project \u201cTraining and Application of Vertical Field Multi-Mode Deep Neural Network Model\u201d","award":["202200209"],"award-info":[{"award-number":["202200209"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Basic Research Project \u201cTraining and Application of Vertical Field Multi-Mode Deep Neural Network Model\u201d","award":["JYTMS20231160"],"award-info":[{"award-number":["JYTMS20231160"]}]},{"name":"Liaoning Provincial Department of Education\u2019s Basic Research Project \u201cTraining and Application of Vertical Field Multi-Mode Deep Neural Network Model\u201d","award":["22-319-2-26"],"award-info":[{"award-number":["22-319-2-26"]}]},{"name":"Shenyang Science and Technology Plan \u201cSpecial Mission for Leech Breeding and Traditional Chinese Medicine Planting in Dengshibao Town, Faku County\u201d","award":["LJKZ0159"],"award-info":[{"award-number":["LJKZ0159"]}]},{"name":"Shenyang Science and Technology Plan \u201cSpecial Mission for Leech Breeding and Traditional Chinese Medicine Planting in Dengshibao Town, Faku County\u201d","award":["JG22DB488"],"award-info":[{"award-number":["JG22DB488"]}]},{"name":"Shenyang Science and Technology Plan \u201cSpecial Mission for Leech Breeding and Traditional Chinese Medicine Planting in Dengshibao Town, Faku County\u201d","award":["202200209"],"award-info":[{"award-number":["202200209"]}]},{"name":"Shenyang Science and Technology Plan \u201cSpecial Mission for Leech Breeding and Traditional Chinese Medicine Planting in Dengshibao Town, Faku County\u201d","award":["JYTMS20231160"],"award-info":[{"award-number":["JYTMS20231160"]}]},{"name":"Shenyang Science and Technology Plan \u201cSpecial Mission for Leech Breeding and Traditional Chinese Medicine Planting in Dengshibao Town, Faku County\u201d","award":["22-319-2-26"],"award-info":[{"award-number":["22-319-2-26"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>This paper introduces an enhanced variant of the Adam optimizer\u2014the BGE-Adam optimization algorithm\u2014that integrates three innovative technologies to augment the adaptability, convergence, and robustness of the original algorithm under various training conditions. Firstly, the BGE-Adam algorithm incorporates a dynamic \u03b2 parameter adjustment mechanism that utilizes the rate of gradient variations to dynamically adjust the exponential decay rates of the first and second moment estimates (\u03b21 and \u03b22), the adjustment of \u03b21 and \u03b22 is symmetrical, which means that the rules that the algorithm considers when adjusting \u03b21 and \u03b22 are the same. This design helps to maintain the consistency and balance of the algorithm, allowing the optimization algorithm to adaptively capture the trending movements of gradients. Secondly, it estimates the direction of future gradients by a simple gradient prediction model, combining historic gradient information with the current gradient. Lastly, entropy weighting is integrated into the gradient update step. This strategy enhances the model\u2019s exploratory nature by introducing a certain amount of noise, thereby improving its adaptability to complex loss surfaces. Experimental results on classical datasets, MNIST and CIFAR10, and gastrointestinal disease medical datasets demonstrate that the BGE-Adam algorithm has improved convergence and generalization capabilities. In particular, on the specific medical image gastrointestinal disease test dataset, the BGE-Adam optimization algorithm achieved an accuracy of 69.36%, a significant improvement over the 67.66% accuracy attained using the standard Adam algorithm; on the CIFAR10 test dataset, the accuracy of the BGE-Adam algorithm reached 71.4%, which is higher than the 70.65% accuracy of the Adam optimization algorithm; and on the MNIST dataset, the BGE-Adam algorithm\u2019s accuracy was 99.34%, surpassing the Adam optimization algorithm\u2019s accuracy of 99.23%. The BGE-Adam optimization algorithm exhibits better convergence and robustness. This research not only demonstrates the effectiveness of the combination of these three technologies but also provides new perspectives for the future development of deep learning optimization algorithms.<\/jats:p>","DOI":"10.3390\/sym16050623","type":"journal-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T04:26:29Z","timestamp":1715919989000},"page":"623","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["An Improved BGE-Adam Optimization Algorithm Based on Entropy Weighting and Adaptive Gradient Strategy"],"prefix":"10.3390","volume":"16","author":[{"given":"Yichuan","family":"Shao","sequence":"first","affiliation":[{"name":"School of Intelligent Science Engineering, Shenyang University, Shenyang 110044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2049-1829","authenticated-orcid":false,"given":"Jiantao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Shenyang University, Shenyang 110044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5168-6145","authenticated-orcid":false,"given":"Haijing","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Intelligent Science Engineering, Shenyang University, Shenyang 110044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3475-1056","authenticated-orcid":false,"given":"Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Shenyang University, Shenyang 110044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xing","sequence":"additional","affiliation":[{"name":"School of Chemistry and Chemical Engineering, University of Surrey, Guildford GU2 7XH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Science, Shenyang University of Technology, Shenyang 110044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5533-7645","authenticated-orcid":false,"given":"Le","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Intelligent Science Engineering, Shenyang University, Shenyang 110044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,5,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Anjum, M., and Shahab, S. (2023). Improving Autonomous Vehicle Controls and Quality Using Natural Language Processing-Based Input Recognition Model. Sustainability, 15.","DOI":"10.3390\/su15075749"},{"key":"ref_2","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_3","unstructured":"Kashyap, R. (2023). A survey of deep learning optimizers\u2013First and second order methods. arXiv."},{"key":"ref_4","unstructured":"Zhang, Z., Ma, L., Li, Z., and Wu, C. (2018). Normalized Direction-preserving Adam. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"17095","DOI":"10.1007\/s00521-023-08568-z","article-title":"A modified Adam algorithm for deep neural network optimization","volume":"35","author":"Reyad","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_6","unstructured":"Zhuang, J., Tang, T., Ding, Y., Tatikonda, S., Dvornek, N., Papademetris, X., and Duncan, J.S. (2020, January 6\u201312). Adabelief optimizer: Adapting stepsizes by the belief in observed gradients. Proceedings of the Advances in Neural Information Processing Systems, NeurIPS, Online."},{"key":"ref_7","first-page":"2121","article-title":"Adaptive Subgradient Methods for Online Learning and Stochastic Optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_8","first-page":"10665","article-title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","volume":"35","author":"Yao","year":"2021","journal-title":"Proc. Aaai Conf. Artif. Intell."},{"key":"ref_9","unstructured":"Luo, L., Xiong, Y., Liu, Y., and Sun, X. (2019). Adaptive Gradient Methods with Dynamic Bound of Learning Rate. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gill, K., Sharma, A., Anand, V., and Gupta, R. (2022, January 1\u20133). Brain Tumor Detection using VGG19 model on Adadelta and SGD Optimizer. Proceedings of the 2022 6th International Conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India.","DOI":"10.1109\/ICECA55336.2022.10009496"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, J., and Cao, Z. (2017, January 27\u201330). Chinese text sentiment analysis using LSTM network based on L2 and Nadam. Proceedings of the 2017 IEEE 17th International Conference on Communication Technology (ICCT), Chengdu, China.","DOI":"10.1109\/ICCT.2017.8359958"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhang, Y., Shao, Y., Liu, M., Li, J., Yuan, J., and Wang, R. (2023). Boosting Adversarial Attacks with Nadam Optimizer. Electronics, 12.","DOI":"10.3390\/electronics12061464"},{"key":"ref_13","unstructured":"Landro, N., Gallo, I., and La Grassa, R. (2020). Mixing ADAM and SGD: A Combined Optimization Method. arXiv."},{"key":"ref_14","unstructured":"Woodworth, B., Patel, K., Stich, S., Dai, Z., Bullins, B., Mcmahan, B., Shamir, O., and Srebro, N. (2020, January 13\u201318). Is Local SGD Better than Minibatch SGD?. Proceedings of the 37th International Conference on Machine Learning, Online."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yi, D., Ahn, J., and Ji, S. (2020). An Effective Optimization Method for Machine Learning Based on ADAM. Appl. Sci., 10.","DOI":"10.3390\/app10031073"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.3934\/mbe.2024054","article-title":"The WuC-Adam algorithm based on joint improvement of Warmup and cosine annealing algorithms","volume":"21","author":"Zhang","year":"2024","journal-title":"Math. Biosci. Eng."},{"key":"ref_17","unstructured":"Chen, X., Liu, S., Sun, R., and Hong, M. (2018). On the Convergence of A Class of Adam-type Algorithms for Non-Convex Optimization. arXiv."},{"key":"ref_18","unstructured":"Reddi, S.J., Kale, S., and Kumar, S. (2019, January 6\u20139). On the Convergence of Adam and Beyond. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_19","unstructured":"Jimenez Rezende, D., and Mohamed, S. (2015, January 7\u201312). Variational information maximisation for intrinsically motivated reinforcement learning. Proceedings of the Advances in Neural Information Processing Systems, NeurIPS, Montreal, QC, Canada."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lhermitte, E., Hilal, M., Furlong, R., O\u2019Brien, V., and Humeau-Heurtier, A. (2022). Deep Learning and Entropy-Based Texture Features for Color Image Classification. Entropy, 24.","DOI":"10.3390\/e24111577"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"129308","DOI":"10.1016\/j.physa.2023.129308","article-title":"On the theory of deep learning: A theoretical physics perspective (Part I)","volume":"632","year":"2023","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"100349","DOI":"10.1016\/j.egyai.2024.100349","article-title":"A new dust detection method for photovoltaic panel surface based on Pytorch and its economic benefit analysis","volume":"16","author":"Shao","year":"2024","journal-title":"Energy AI"},{"key":"ref_23","first-page":"872","article-title":"Effect of filter sizes on image classification in CNN: A case study on CFIR10 and Fashion-MNIST datasets","volume":"10","author":"Khanday","year":"2021","journal-title":"IAES Int. J. Artif. Intell. (IJ-AI)"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2748","DOI":"10.1038\/s41598-022-06726-2","article-title":"Artificial intelligence enabled automated diagnosis and grading of ulcerative colitis endoscopy images","volume":"12","author":"Sutton","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Shao, Y., Fan, S., Sun, H., Tan, Z., Cai, Y., Zhang, C., and Zhang, L. (2023). Multi-Scale Lightweight Neural Network for Steel Surface Defect Detection. Coatings, 13.","DOI":"10.3390\/coatings13071202"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/16\/5\/623\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:43:45Z","timestamp":1760107425000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/16\/5\/623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,17]]},"references-count":25,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["sym16050623"],"URL":"https:\/\/doi.org\/10.3390\/sym16050623","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,17]]}}}