{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:34:44Z","timestamp":1782315284821,"version":"3.54.5"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>The integration of artificial intelligence in education has shown great potential to improve student\u2019s learning experience through emotion detection and the personalization of learning. Many educational settings lack adequate mechanisms to dynamically adapt to students\u2019 emotions, which can negatively impact their academic performance and engagement. This study addresses this problem by implementing a deep reinforcement learning model to detect emotions in real-time and personalize teaching strategies in a hybrid educational environment. Using data from 500 students, captured through cameras, microphones, and biometric sensors and pre-processed with advanced techniques such as histogram equalization and noise reduction, the deep reinforcement learning model was trained and validated to improve the detection accuracy of emotions and the personalization of learning. The results showed a significant improvement in the accuracy of emotion detection, going from 72.4% before the implementation of the system to 89.3% after. Real-time adaptability also increased from 68.5 to 87.6%, while learning personalization rose from 70.2 to 90.1%. K-fold cross-validation with k\u2009=\u200910 confirmed the robustness and generalization of the model, with consistently high scores in all evaluated metrics. This study demonstrates that integrating reinforcement learning models for emotion detection and learning personalization can transform education, providing a more adaptive and student-centered learning experience. These findings identify the potential of these technologies to improve academic performance and student engagement, offering a solid foundation for future research and implementation.<\/jats:p>","DOI":"10.3389\/frai.2024.1458230","type":"journal-article","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T06:35:14Z","timestamp":1732775714000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Implementation of deep reinforcement learning models for emotion detection and personalization of learning in hybrid educational environments"],"prefix":"10.3389","volume":"7","author":[{"given":"Jaime","family":"Govea","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandra Maldonado","family":"Navarro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Santiago","family":"S\u00e1nchez-Viteri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Villegas-Ch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"105884","DOI":"10.1016\/j.bspc.2023.105884","article-title":"A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection","volume":"90","author":"Alamatsaz","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"12844","DOI":"10.48084\/etasr.6675","article-title":"Empowering learning through intelligent data-driven systems","volume":"14","author":"Aldriwish","year":"2024","journal-title":"Eng. Technol. Appl. Sci. Res."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1230","DOI":"10.3390\/s23031230","article-title":"Intelligent feature selection for ECG-based personal authentication using deep reinforcement learning","volume":"23","author":"Baek","year":"2023","journal-title":"Sensors"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1021\/acs.jpclett.3c02771","article-title":"Reinforcement learning for traversing chemical structure space: optimizing transition states and minimum energy paths of molecules","volume":"15","author":"Barrett","year":"2024","journal-title":"J. Phys. Chem. Lett."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"237","DOI":"10.48550\/arXiv.cs\/9605103","article-title":"Research on spiking reinforcement learning algorithms: a survey","volume":"46","author":"Chen","year":"2023","journal-title":"Chin. J. Comput."},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1145\/3636555.3636875","article-title":"Exploring confusion and frustration as non-linear dynamical systems","volume-title":"ACM international conference proceeding series","author":"Cloude","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"120598","DOI":"10.1016\/j.apenergy.2022.120598","article-title":"Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings","volume":"333","author":"Coraci","year":"2023","journal-title":"Appl. Energy"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"18382","DOI":"10.1021\/acs.est.3c00353","article-title":"Systematic performance evaluation of reinforcement learning algorithms applied to wastewater treatment control optimization","volume":"57","author":"Croll","year":"2023","journal-title":"Environ. Sci. Technol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1007\/s13177-023-00346-4","article-title":"Deep reinforcement Q-learning for intelligent traffic signal control with partial detection","volume":"21","author":"Ducrocq","year":"2023","journal-title":"Int. J. Intell. Transp. Syst. Res."},{"key":"ref10","first-page":"38","article-title":"Facial recognition using OpenCV","volume":"4","author":"Emami","year":"2012","journal-title":"J. Mobile Embed. Distrib. Syst."},{"key":"ref11","article-title":"For SALE: state-action representation learning for deep reinforcement learning","volume-title":"Proceedings of the 37th international conference on neural information processing systems","author":"Fujimoto","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2024.3474169","article-title":"Practical probabilistic model-based reinforcement learning by integrating dropout uncertainty and trajectory sampling","author":"Huang","year":"2024","journal-title":"IEEE Trans. Neural. Netw. Learn. Syst."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e0280071","DOI":"10.1371\/journal.pone.0280071","article-title":"Reinforcement learning approach to control an inverted pendulum: a general framework for educational purposes","volume":"18","author":"Israilov","year":"2023","journal-title":"PLoS One"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1109\/TBIOM.2022.3143569","article-title":"Domain-specific adaptation of CNN for detecting face presentation attacks in NIR","volume":"4","author":"Kotwal","year":"2022","journal-title":"IEEE Trans. Biom. Behav. Identity Sci."},{"key":"ref15","first-page":"722","article-title":"Machine learning based speech emotions recognition system","volume":"8","author":"Kumar","year":"2019","journal-title":"Int. J. Sci. Technol. Res."},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1145\/3411681.3411684","article-title":"Deep learning of facial embeddings and facial landmark points for the detection of academic emotions","volume-title":"ACM international conference proceeding series","author":"Leong","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"534","DOI":"10.3390\/agriculture13030534","article-title":"Research on winter wheat growth stages recognition based on Mobile edge computing","volume":"13","author":"Li","year":"2023","journal-title":"Agriculture (Switzerland)"},{"key":"ref18","first-page":"1","article-title":"A reverse path planning approach for enhanced performance of multi-degree-of-freedom industrial manipulators","volume":"139","author":"Lin","year":"2024","journal-title":"Comput. Model. Eng. Sci."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1685","DOI":"10.3390\/electronics10141685","article-title":"Deep convolutional neural network with rnns for complex activity recognition using wrist-worn wearable sensor data","volume":"10","author":"Mekruksavanich","year":"2021","journal-title":"Electronics (Switzerland)"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"227","DOI":"10.14257\/ijmue.2014.9.4.24","article-title":"Development of pallet recognition system using kinect camera","volume":"9","author":"Oh","year":"2014","journal-title":"Int. J. Multimed. Ubiquitous Eng."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"100798","DOI":"10.1109\/ACCESS.2023.3314750","article-title":"Deep adversarial reinforcement learning method to generate control policies robust against worst-case value predictions","volume":"11","author":"Ohashi","year":"2023","journal-title":"IEEE Access"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"100020","DOI":"10.1016\/j.caeai.2021.100020","article-title":"Artificial intelligence in education: the three paradigms. Computers and education","volume":"2","author":"Ouyang","year":"2021","journal-title":"Artif. Intell."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"108232","DOI":"10.1016\/j.compchemeng.2023.108232","article-title":"A practical reinforcement learning implementation approach for continuous process control","volume":"174","author":"Patel","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3329\/dujbs.v30i1.51812","article-title":"Teacher-student interactions and academic performance of students. Dhaka university","volume":"30","author":"Pervin","year":"2021","journal-title":"J. Biol. Sci."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"4516","DOI":"10.1038\/s41598-024-55110-9","article-title":"Optimizing warfarin dosing for patients with atrial fibrillation using machine learning","volume":"14","author":"Petch","year":"2024","journal-title":"Sci. Rep."},{"key":"ref26","article-title":"Non-invasive technology on a classroom chair for detection of emotions used for the personalization of learning resources","volume":"66","author":"Ramirez","year":"2010","journal-title":"World Acad. Sci. Eng. Technol."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2023.3329513","article-title":"Relative entropy regularized sample-efficient reinforcement learning with continuous actions","author":"Shang","year":"2023","journal-title":"IEEE Trans. Neural. Netw. Learn. Syst."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2313","DOI":"10.1140\/epjst\/e2019-900046-x","article-title":"A survey on LSTM memristive neural network architectures and applications","volume":"228","author":"Smagulova","year":"2019","journal-title":"Eur. Phys. J. Spec. Top."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1109\/JOE.2022.3152519","article-title":"Underwater image enhancement with reinforcement learning","volume":"49","author":"Sun","year":"2024","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"2810","DOI":"10.3390\/ijerph16162810","article-title":"Influence of emotional intelligence, motivation and resilience on academic performance and the adoption of healthy lifestyle habits among adolescents","volume":"16","author":"Trigueros","year":"2019","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"38010","DOI":"10.1109\/ACCESS.2023.3267007","article-title":"Identification of emotions from facial gestures in a teaching environment with the use of machine learning techniques","volume":"11","author":"Villegas-Ch","year":"2023","journal-title":"IEEE Access"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"33061","DOI":"10.1109\/ACCESS.2023.3263670","article-title":"Multimodal emotion recognition from EEG signals and facial expressions","volume":"11","author":"Wang","year":"2023","journal-title":"IEEE Access"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.1109\/JAS.2023.123684","article-title":"Adaptive multi-step evaluation design with stability guarantee for discrete-time optimal learning control","volume":"10","author":"Wang","year":"2023","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"120430","DOI":"10.1016\/j.applthermaleng.2023.120430","article-title":"Comparison of reinforcement learning and model predictive control for building energy system optimization","volume":"228","author":"Wang","year":"2023","journal-title":"Appl. Therm. Eng."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"197","DOI":"10.14733\/cadaps.2024.S5.197-210","article-title":"Research on data-driven college English teaching model based on reinforcement learning and virtual reality through online gaming","volume":"21","author":"Yan","year":"2024","journal-title":"Comput. Aided Des. Appl."},{"key":"ref36","first-page":"949","article-title":"Deep reinforcement learning based bi-layer optimal scheduling for microgrids considering flexible load control","volume":"9","author":"Zhang","year":"2023","journal-title":"CSEE J. Power Energy Syst."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"120561","DOI":"10.1016\/j.apenergy.2022.120561","article-title":"Deep reinforcement learning towards real-world dynamic thermal management of data centers","volume":"333","author":"Zhang","year":"2023","journal-title":"Appl. Energy"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TITS.2022.3207011","article-title":"Learning to solve multiple-TSP with time window and rejections via deep reinforcement learning","volume":"24","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1016\/j.ins.2022.07.111","article-title":"Proximal policy optimization via enhanced exploration efficiency","volume":"609","author":"Zhang","year":"2022","journal-title":"Inf. Sci."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1458230\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T06:35:21Z","timestamp":1732775721000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1458230\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"references-count":39,"alternative-id":["10.3389\/frai.2024.1458230"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1458230","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"article-number":"1458230"}}