No Cover Image

Journal article 202 views 56 downloads

Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems

Anil Kumar Yadav Orcid Logo, Purushottam Sharma Orcid Logo, Cheng Cheng Orcid Logo, Nirmal Kumar Gupta Orcid Logo

Journal of Electrical and Computer Engineering, Volume: 2025, Issue: 1

Swansea University Author: Cheng Cheng Orcid Logo

  • 70224.VoR.pdf

    PDF | Version of Record

    Copyright © 2025 Anil Kumar Yadav et al. This is an open access article under the terms of the Creative Commons Attribution License.

    Download (592.7KB)

Check full text

DOI (Published version): 10.1155/jece/3305430

Abstract

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-Action-Reward-State-Action (SARSA) reinforcement...

Full description

Published in: Journal of Electrical and Computer Engineering
ISSN: 2090-0147 2090-0155
Published: Wiley 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa70224
first_indexed 2025-08-26T09:16:36Z
last_indexed 2025-10-03T05:57:39Z
id cronfa70224
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-10-02T16:36:13.0986116</datestamp><bib-version>v2</bib-version><id>70224</id><entry>2025-08-26</entry><title>Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems</title><swanseaauthors><author><sid>11ddf61c123b99e59b00fa1479367582</sid><ORCID>0000-0003-0371-9646</ORCID><firstname>Cheng</firstname><surname>Cheng</surname><name>Cheng Cheng</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-08-26</date><deptcode>MACS</deptcode><abstract>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-Action-Reward-State-Action (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-based online Q-learning algorithm to refine classification accuracy and resolve state overlap issues. During training, facial datasets are processed to extract critical features, and a state-action value table is constructed to guide decision-making during testing. This reinforcement-driven 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-time and resource-efficient face recognition applications.</abstract><type>Journal Article</type><journal>Journal of Electrical and Computer Engineering</journal><volume>2025</volume><journalNumber>1</journalNumber><paginationStart/><paginationEnd/><publisher>Wiley</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2090-0147</issnPrint><issnElectronic>2090-0155</issnElectronic><keywords>classification; face recognition; feature extraction; learning agent; reward; SARSA</keywords><publishedDay>11</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-09-11</publishedDate><doi>10.1155/jece/3305430</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Swansea University. Grant Number: RS718; Engineering and Physical Sciences Research Council. Grant Number: EP/W020408/1</funders><projectreference/><lastEdited>2025-10-02T16:36:13.0986116</lastEdited><Created>2025-08-26T10:01:26.9445778</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Anil Kumar</firstname><surname>Yadav</surname><orcid>0000-0003-4027-8229</orcid><order>1</order></author><author><firstname>Purushottam</firstname><surname>Sharma</surname><orcid>0000-0002-8037-7152</orcid><order>2</order></author><author><firstname>Cheng</firstname><surname>Cheng</surname><orcid>0000-0003-0371-9646</orcid><order>3</order></author><author><firstname>Nirmal Kumar</firstname><surname>Gupta</surname><orcid>0000-0001-8893-9458</orcid><order>4</order></author></authors><documents><document><filename>70224__35128__403d52faed6d43fc9f95b1d4924ee7ed.pdf</filename><originalFilename>70224.VoR.pdf</originalFilename><uploaded>2025-09-18T12:50:23.1570881</uploaded><type>Output</type><contentLength>606926</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright &#xA9; 2025 Anil Kumar Yadav et al. This is an open access article under the terms of the Creative Commons Attribution License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-10-02T16:36:13.0986116 v2 70224 2025-08-26 Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems 11ddf61c123b99e59b00fa1479367582 0000-0003-0371-9646 Cheng Cheng Cheng Cheng true false 2025-08-26 MACS 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-Action-Reward-State-Action (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-based online Q-learning algorithm to refine classification accuracy and resolve state overlap issues. During training, facial datasets are processed to extract critical features, and a state-action value table is constructed to guide decision-making during testing. This reinforcement-driven 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-time and resource-efficient face recognition applications. Journal Article Journal of Electrical and Computer Engineering 2025 1 Wiley 2090-0147 2090-0155 classification; face recognition; feature extraction; learning agent; reward; SARSA 11 9 2025 2025-09-11 10.1155/jece/3305430 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University SU Library paid the OA fee (TA Institutional Deal) Swansea University. Grant Number: RS718; Engineering and Physical Sciences Research Council. Grant Number: EP/W020408/1 2025-10-02T16:36:13.0986116 2025-08-26T10:01:26.9445778 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Anil Kumar Yadav 0000-0003-4027-8229 1 Purushottam Sharma 0000-0002-8037-7152 2 Cheng Cheng 0000-0003-0371-9646 3 Nirmal Kumar Gupta 0000-0001-8893-9458 4 70224__35128__403d52faed6d43fc9f95b1d4924ee7ed.pdf 70224.VoR.pdf 2025-09-18T12:50:23.1570881 Output 606926 application/pdf Version of Record true Copyright © 2025 Anil Kumar Yadav et al. This is an open access article under the terms of the Creative Commons Attribution License. true eng http://creativecommons.org/licenses/by/4.0/
title Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems
spellingShingle Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems
Cheng Cheng
title_short Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems
title_full Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems
title_fullStr Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems
title_full_unstemmed Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems
title_sort Hybrid Reinforcement Learning With Optimized SARSA for Improved Face Recognition Systems
author_id_str_mv 11ddf61c123b99e59b00fa1479367582
author_id_fullname_str_mv 11ddf61c123b99e59b00fa1479367582_***_Cheng Cheng
author Cheng Cheng
author2 Anil Kumar Yadav
Purushottam Sharma
Cheng Cheng
Nirmal Kumar Gupta
format Journal article
container_title Journal of Electrical and Computer Engineering
container_volume 2025
container_issue 1
publishDate 2025
institution Swansea University
issn 2090-0147
2090-0155
doi_str_mv 10.1155/jece/3305430
publisher Wiley
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description 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-Action-Reward-State-Action (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-based online Q-learning algorithm to refine classification accuracy and resolve state overlap issues. During training, facial datasets are processed to extract critical features, and a state-action value table is constructed to guide decision-making during testing. This reinforcement-driven 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-time and resource-efficient face recognition applications.
published_date 2025-09-11T12:37:23Z
_version_ 1850853077841608704
score 11.08895

Similar Items