{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:31:34Z","timestamp":1773793894185,"version":"3.50.1"},"reference-count":30,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"content-version":"vor","delay-in-days":253,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001317","name":"Swansea University","doi-asserted-by":"publisher","award":["RS718"],"award-info":[{"award-number":["RS718"]}],"id":[{"id":"10.13039\/501100001317","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/W020408\/1"],"award-info":[{"award-number":["EP\/W020408\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Electrical and Computer Engineering"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Face recognition is a key technique in modern image processing, yet it faces challenges such as achieving high accuracy, reducing computational time, and optimizing memory usage. This research proposes a hybrid model that integrates an enhanced State\u2010Action\u2010Reward\u2010State\u2010Action (SARSA) reinforcement learning (RL) framework to address these challenges in face recognition tasks. The model utilizes principal component analysis (PCA) for dimensionality reduction and initial feature extraction, followed by a SARSA\u2010based online Q\u2010learning algorithm to refine classification accuracy and resolve state overlap issues. During training, facial datasets are processed to extract critical features, and a state\u2010action value table is constructed to guide decision\u2010making during testing. This reinforcement\u2010driven learning enables the system to dynamically update its policy based on the most rewarding actions, improving adaptability and performance. Experimental results demonstrate that the proposed approach enhanced traditional models in terms of recognition accuracy, classification efficiency, and training speed. Integrating optimized feature selection and policy learning mechanisms makes the model a promising solution for real\u2010time and resource\u2010efficient face recognition applications.<\/jats:p>","DOI":"10.1155\/jece\/3305430","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T10:34:36Z","timestamp":1757586876000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4027-8229","authenticated-orcid":false,"given":"Anil Kumar","family":"Yadav","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8037-7152","authenticated-orcid":false,"given":"Purushottam","family":"Sharma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0371-9646","authenticated-orcid":false,"given":"Xiaochun","family":"Cheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8893-9458","authenticated-orcid":false,"given":"Nirmal Kumar","family":"Gupta","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"e_1_2_10_1_2","unstructured":"AugensteinS. McMahanH. B. RamageD.et al. Generative Models for Effective ML on Private Decentralized Datasets 2019."},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"e_1_2_10_3_2","first-page":"1","article-title":"Reinforcement Learning and Optimal Control","volume":"1","author":"Bertsekas D.","year":"2019","journal-title":"Athena Scientific"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2011.06.014"},{"key":"e_1_2_10_5_2","doi-asserted-by":"crossref","unstructured":"GuoY. ZhangL. HuY. HeX. andGaoJ. Ms-celeb-1m: A Dataset and Benchmark for Large-Scale Face Recognition Computer Vision\u2013ECCV:14th European Conference 2016 Amsterdam The Netherlands 87\u2013102.","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"e_1_2_10_6_2","unstructured":"BonsorK.andJohnsonR. How Facial Recognition Systems Work Howstuffworks. Com Np 2001."},{"key":"e_1_2_10_7_2","doi-asserted-by":"publisher","DOI":"10.4103\/0256-4602.110546"},{"key":"e_1_2_10_8_2","unstructured":"HuangG. B. MattarM. BergT. andLearned-MillerE. Labeled Faces in the Wild: a Database for Studying Face Recognition in Unconstrained Environments Workshop on Faces in Real-Life Images: Detection Alignment and Recognition 2008 1\u201314."},{"key":"e_1_2_10_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-020-00716-8"},{"key":"e_1_2_10_10_2","doi-asserted-by":"crossref","unstructured":"AngelovaA. Abu-MostafaY. andPeronaP. Pruning Training Sets for Learning of Object Categories IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2005 no. 1 494\u2013501 https:\/\/doi.org\/10.1109\/cvpr.2005.283 2-s2.0-24644505329.","DOI":"10.1109\/CVPR.2005.283"},{"key":"e_1_2_10_11_2","doi-asserted-by":"crossref","unstructured":"PitisS. Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach Proceedings of the AAAI Conference on Artificial Intelligence 2019 7949\u20137956 https:\/\/doi.org\/10.1609\/aaai.v33i01.33017949.","DOI":"10.1609\/aaai.v33i01.33017949"},{"key":"e_1_2_10_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.12.026"},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.14257\/ijsia.2016.10.3.08"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"ShenL. BaiL. andJiZ. A SVM Face Recognition Method Based on Optimized Gabor Features Advances in Visual Information Systems: 9th International Conference 2007 165\u2013174.","DOI":"10.1007\/978-3-540-76414-4_17"},{"key":"e_1_2_10_15_2","doi-asserted-by":"crossref","unstructured":"Ayd\u0131nA.andS\u00fcrerE. Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning 28th Signal Processing and Communications Applications Conference 2020 1\u20134 https:\/\/doi.org\/10.1109\/siu49456.2020.9302454.","DOI":"10.1109\/SIU49456.2020.9302454"},{"key":"e_1_2_10_16_2","doi-asserted-by":"crossref","unstructured":"KlareB. F. KleinB. andTaborskyE. Pushing the Frontiers of Unconstrained Face Detection and Recognition IEEE Conference on Computer Vision and Pattern Recognition 2015.","DOI":"10.1109\/CVPR.2015.7298803"},{"key":"e_1_2_10_17_2","doi-asserted-by":"crossref","unstructured":"LiuZ. LuoP. WangX. andTangX. Deep Learning Face Attributes in the Wild Proceedings of the IEEE International Conference on Computer Vision 2015 3730\u20133738 https:\/\/doi.org\/10.1109\/iccv.2015.425 2-s2.0-84973917446.","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"HasanbeigM. AbateA. andKroeningD. Cautious Reinforcement Learning With Logical Constraints 2020.","DOI":"10.65109\/RTAS4039"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"MazeB. AdamsJ. DuncanJ. A. KalkaN. MillerT. andOttoC. Iarpa Janus Benchmark-c: Face Dataset and Protocol IEEE International Conference on Biometrics 2018 158\u2013165.","DOI":"10.1109\/ICB2018.2018.00033"},{"key":"e_1_2_10_20_2","unstructured":"McMahanB. MooreE. RamageD. HampsonS. andArcasB. A. Communication-Efficient Learning of Deep Networks From Decentralized Data Proceedings of the 20th International Conference on Artificial Intelligence and Statistics 2017 1273\u20131282."},{"key":"e_1_2_10_21_2","doi-asserted-by":"crossref","unstructured":"WangH. WangY. andZhouZ Cosface: Large Margin Cosine Loss for Deep Face Recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018 5265\u20135274 https:\/\/doi.org\/10.1109\/cvpr.2018.00552 2-s2.0-85062873611.","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_2_10_22_2","unstructured":"ZhangX. GuanY. WangS. LiangJ. andQuanT. Face Recognition in Color Images Using Principal Component Analysis and Fuzzy Support Vector Machines IEEE 1st International Symposium on Systems and Control in Aerospace and Astronautics 2006 1\u20134."},{"key":"e_1_2_10_23_2","unstructured":"YiD. LeiZ. LiaoS. andLiS. Z. Learning Face Representation from Scratch 2014."},{"key":"e_1_2_10_24_2","doi-asserted-by":"crossref","unstructured":"WangH. YangS. andLiaoW. An Improved PCA Face Recognition Algorithm Based on the Discrete Wavelet Transform and the Support Vector Machines International Conference on Computational Intelligence and Security Workshops 2007 308\u2013311 https:\/\/doi.org\/10.1109\/cisw.2007.4425498.","DOI":"10.1109\/CISW.2007.4425498"},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"LiX. MaJ. andLiS. A Novel Face Recognition Method Based on Principal Component Analysis and Kernel Partial Least Squares IEEE International Conference on Robotics and Biomimetics 2007 1773\u20131777.","DOI":"10.1109\/ROBIO.2007.4522434"},{"key":"e_1_2_10_26_2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6157"},{"key":"e_1_2_10_27_2","unstructured":"RiouxR.andSimonT. Class Redundancy for Face Recognition by SVM 50th International Symposium 2008 no. 1 117\u2013120."},{"key":"e_1_2_10_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13290-4"},{"key":"e_1_2_10_29_2","first-page":"2698","article-title":"Hybrid Machine Learning Model for Face Recognition Using SVM","author":"Yadav A. K.","year":"2022","journal-title":"Computers, Materials & Continua"},{"key":"e_1_2_10_30_2","doi-asserted-by":"crossref","unstructured":"YadavA. K.andShrivastavaS. Evaluation of Reinforcement Learning Techniques Proceedings of the First International Conference on Intelligent Interactive Technologies and Multimedia 2010 88\u201392.","DOI":"10.1145\/1963564.1963578"}],"container-title":["Journal of Electrical and Computer Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/jece\/3305430","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/jece\/3305430","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/jece\/3305430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:37:26Z","timestamp":1773779846000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/jece\/3305430"}},"subtitle":[],"editor":[{"given":"Arpan","family":"Hazra","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/jece\/3305430"],"URL":"https:\/\/doi.org\/10.1155\/jece\/3305430","archive":["Portico"],"relation":{},"ISSN":["2090-0147","2090-0155"],"issn-type":[{"value":"2090-0147","type":"print"},{"value":"2090-0155","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-01-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3305430"}}