A Machine Learning Framework for Classroom EEG Recording Classification: Unveiling Learning-Style Patterns

A Machine Learning Framework for Classroom EEG Recording Classification: Unveiling Learning-Style Patterns Rajamanickam Yuvaraj Office of Education Research, Science of Learning in Education Centre (SoLEC), National Institute of Education (NIE), Nanyang Technological University (NTU), Nanyang Walk, Singapore 637616, Singapore http://orcid.org/0000-0003-4526-0749 Shivam Chadha Department of Electrical and Electronics Engineering, BITS Pilani K k Birla Goa Campus, Sancoale 403726, Goa, India A. Amalin Prince Department of Electrical and Electronics Engineering, BITS Pilani K k Birla Goa Campus, Sancoale 403726, Goa, India http://orcid.org/0000-0002-4471-9979 M. Murugappan Intelligent Signal Processing (ISP) Research Laboratory, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Block 4, Doha 13133, Kuwait Department of Electronics and Communication Engineering, Faculty of Engineering, Vels Institute of Sciences, Technology, and Advanced Studies, Chennai 600117, Tamil Nadu, India http://orcid.org/0000-0002-5839-4589 Md. Sakib Bin Islam Department of Electrical Engineering, Qatar University, Doha 2713, Qatar http://orcid.org/0009-0005-6593-495X Md. Shaheenur Islam Sumon Department of Electrical Engineering, Qatar University, Doha 2713, Qatar http://orcid.org/0000-0001-5839-2826 Muhammad E. H. Chowdhury Department of Electrical Engineering, Qatar University, Doha 2713, Qatar http://orcid.org/0000-0003-0744-8206

Classroom EEG recordings classification has the capacity to significantly enhance comprehension and learning by revealing complex neural patterns linked to various cognitive processes. Electroencephalography (EEG) in academic settings allows researchers to study brain activity while students are in class, revealing learning preferences. The purpose of this study was to develop a machine learning framework to automatically classify different learning-style EEG patterns in real classroom environments. Method: In this study, a set of EEG features was investigated, including statistical features, fractal dimension, higher-order spectra, entropy, and a combination of all sets. Three different machine learning classifiers, random forest (RF), K-nearest neighbor (KNN), and multilayer perceptron (MLP), were used to evaluate the performance. The proposed framework was evaluated on the real classroom EEG dataset, involving EEG recordings featuring different teaching blocks: reading, discussion, lecture, and video. Results: The findings revealed that statistical features are the most sensitive feature metric in distinguishing learning patterns from EEG. The statistical features and RF classifier method tested in this study achieved an overall best average accuracy of 78.45% when estimated by fivefold cross-validation. Conclusions: Our results suggest that EEG time domain statistics have a substantial role and are more reliable for internal state classification. This study might be used to highlight the importance of using EEG signals in the education context, opening the path for educational automation research and development.
11 04 2024 503 a17110503 https://creativecommons.org/licenses/by/4.0/ 10.3390/a17110503 https://www.mdpi.com/1999-4893/17/11/503 https://www.mdpi.com/1999-4893/17/11/503/pdf Moioli Neurosciences and wireless networks: The potential of brain-type communications and their applications IEEE Commun. Surv. Tutor. 2021 10.1109/COMST.2021.3090778 23 1599 Baceviciute Remediating learning from non-immersive to immersive media: Using EEG to investigate the effects of environmental embeddedness on reading in Virtual Reality Comput. Educ. 2021 10.1016/j.compedu.2020.104122 164 104122 Janssen Opportunities and limitations of mobile neuroimaging technologies in educational neuroscience Mind Brain Educ. 2021 10.1111/mbe.12302 15 354 Gupta A machine learning-based decision support system for temporal human cognitive state estimation during online education using wearable physiological monitoring devices Decis. Anal. 2023 8 100280 10.3389/fnbeh.2019.00086 Jawed, S., Amin, H.U., Malik, A.S., and Faye, I. (2019). Classification of Visual and Non-visual Learners Using Electroencephalographic Alpha and Gamma Activities. Front. Behav. Neurosci., 13. 10.3390/brainsci11050613 Zhang, B., Chai, C., Yin, Z., and Shi, Y. (2021). Design and Implementation of an EEG-Based Learning-Style Recognition Mechanism. Brain Sci., 11. Rashid Learners’ Learning Style Classification related to IQ and Stress based on EEG Procedia Soc. Behav. Sci. 2011 10.1016/j.sbspro.2011.11.339 29 1061 Mendelsohn Real-life neuroscience: An ecological approach to brain and behavior research Perspect. Psychol. Sci. 2019 10.1177/1745691619856350 14 841 Salselas Sound design inducing attention in the context of audiovisual immersive environments Pers. Ubiquitous Comput. 2021 10.1007/s00779-020-01386-3 25 737 Sams Movies and narratives as naturalistic stimuli in neuroimaging Neuroimage 2021 10.1016/j.neuroimage.2020.117445 224 117445 10.3389/fnhum.2021.675068 Saarimäki, H. (2021). Naturalistic stimuli in affective neuroimaging: A review. Front. Hum. Neurosci., 15. Jawed Deep Learning-Based Assessment Model for Real-Time Identification of Visual Learners Using Raw EEG IEEE Trans. Neural Syst. Rehabil. Eng. 2024 10.1109/TNSRE.2024.3351694 32 378 10.21203/rs.3.rs-3370479/v1 Schwartz, L., Levy, J., Hayut, O., Netzer, O., Endevelt-Shapira, Y., and Feldman, R. (2023). Generation Whatsup: Inter-Brain Synchrony during Face-to-Face and Texting Communication. Sci. Rep., 14. Schwartz Technologically-assisted communication attenuates inter-brain synchrony Neuroimage 2022 10.1016/j.neuroimage.2022.119677 264 119677 Li Dynamic inter-brain synchrony in real-life inter-personal cooperation: A functional near-infrared spectroscopy hyperscanning study Neuroimage 2021 10.1016/j.neuroimage.2021.118263 238 118263 Smykovskyi Bridging the gap between emotion and joint action Neurosci. Biobehav. Rev. 2021 10.1016/j.neubiorev.2021.08.014 131 806 Wang Beyond classroom academics: A school-wide and multi-contextual perspective on student engagement in school Adolesc. Res. Rev. 2020 5 419 Havik Do teachers matter? Students’ perceptions of classroom interactions and student engagement Scand. J. Educ. Res. 2020 10.1080/00313831.2019.1577754 64 488 Bevilacqua Brain-to-brain synchrony and learning outcomes vary by student–teacher dynamics: Evidence from a real-world classroom electroencephalography study J. Cogn. Neurosci. 2019 10.1162/jocn_a_01274 31 401 Dikker Brain-to-Brain Synchrony Tracks Real-World Dynamic Group Interactions in the Classroom Curr. Biol. 2017 10.1016/j.cub.2017.04.002 27 1375 10.1016/j.compbiomed.2024.108555 Chowdhury, F.A., Hosain, M.K., Islam, M.S.B., Hossain, M.S., Basak, P., Mahmud, S., Murugappan, M., and Chowdhury, M.E.H. (2024). ECG waveform generation from radar signals: A deep learning perspective. Comput. Biol. Med., 176. 10.1016/j.bspc.2023.105687 Chowdhury, M.H., Chowdhury, M.E.H., Reaz, M.B.I., Ali, S.H.M., Rakhtala, S.M., Murugappan, M., Mahmud, S., Shuzan, N.I., Bakar, A.A.A., and Bin Shapiai, M.I. (2024). LGI-rPPG-Net: A shallow encoder-decoder model for rPPG signal estimation from facial video streams. Biomed. Signal Process. Control, 89. 10.1007/978-981-15-5558-9 Sengodan, T., Murugappan, M., and Misra, S. (2020). Performance Analysis of Wavelet Transform in the Removal of Baseline Wandering from ECG Signals in Children with Autism Spectrum Disorder (ASD). Advances in Electrical and Computer Technologies, Springer. Lecture Notes in Electrical Engineering. Hossain, M.S.A., Rahman, M.A., and Chakrabarty, A. (2021, January 26–27). MUSIC Model based Neural Information Processing for Emotion Recognition from Multichannel EEG Signal. Proceedings of the 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India. 10.3390/bioengineering10010099 Hossain, S.A., Rahman, M.A., Chakrabarty, A., Rashid, M.A., Kuwana, A., and Kobayashi, H. (2023). Emotional State Classification from MUSIC-Based Features of Multichannel EEG Signals. Bioengineering, 10. Koehler What is technological pedagogical content knowledge (TPACK)? Contemp. Issues Technol. Teach. Educ. 2009 9 60 Assessing a learning process with functional ANOVA estimators of EEG power spectral densities Cogn. Neurodyn. 2016 10.1007/s11571-015-9368-7 10 175 Ghali, R., Tato, A., and Nkambou, R. (2019, January 19–22). Using EEG features and machine learning to predict gifted children. Proceedings of the Thirty-Second International Florida Artificial Intelligence Research Society Conference (FLAIRS-32), Sarasota, FL, USA. Lo Cognitive performance, sleepiness, and mood in partially sleep deprived adolescents: The need for sleep study Sleep 2016 10.5665/sleep.5552 39 687 Carrell A’s from Zzzz’s? The causal effect of school start time on the academic achievement of adolescents Am. Econ. J.-Econ. Policy 2011 10.1257/pol.3.3.62 3 62 10.1038/s41598-021-89297-y Kalantari, S., Rounds, J.D., Kan, J., Tripathi, V., and Cruz-Garza, J.G. (2021). Comparing physiological responses during cognitive tests in virtual environments vs. in identical real-world environments. Sci. Rep., 11. Kalantari Virtual environments for design research: Lessons learned from use of fully immersive virtual reality in interior design research J. Inter. Des. 2020 45 27 Chen Effects of online synchronous instruction with an attention monitoring and alarm mechanism on sustained attention and learning performance Interact. Learn. Environ. 2018 10.1080/10494820.2017.1341938 26 427 10.1038/srep43916 Poulsen, A.T., Kamronn, S., Dmochowski, J., Parra, L.C., and Hansen, L.K. (2017). EEG in the classroom: Synchronised neural recordings during video presentation. Sci. Rep., 7. Wen Exploring resting-state functional connectivity with total interdependence Neuroimage 2012 10.1016/j.neuroimage.2012.01.079 60 1587 Sun The effects of attention monitoring with EEG biofeedback on university students’ attention and self-efficacy: The case of anti-phishing instructional materials Comput. Educ. 2017 10.1016/j.compedu.2016.12.003 106 73 10.3390/bioengineering10030372 Chiarion, G., Sparacino, L., Antonacci, Y., Faes, L., and Mesin, L. (2023). Connectivity Analysis in EEG Data: A Tutorial Review of the State of the Art and Emerging Trends. Bioengineering, 10. Campbell Monofractal analysis of functional magnetic resonance imaging: An introductory review Hum. Brain Mapp. 2022 10.1002/hbm.25801 43 2693 10.3390/s23020915 Yuvaraj, R., Thagavel, P., Thomas, J., Fogarty, J., and Ali, F. (2023). Comprehensive Analysis of Feature Extraction Methods for Emotion Recognition from Multichannel EEG Recordings. Sensors, 93. Greco Discriminative power of EEG-based biomarkers in major depressive disorder: A systematic review IEEE Access 2021 10.1109/ACCESS.2021.3103047 9 112850 10.1016/j.bspc.2020.101867 Sharma, R., Pachori, R.B., and Sircar, P. (2020). Automated emotion recognition based on higher order statistics and deep learning algorithm. Biomed. Signal Process. Control, 58. 10.3390/s23146434 Chaddad, A., Wu, Y., Kateb, R., and Bouridane, A. (2023). Electroencephalography signal processing: A comprehensive review and analysis of methods and techniques. Sensors, 23. 10.3390/ijerph18115838 Sharma, M., Rajput, J.S., Tan, R.S., and Acharya, U.R. (2021). Automated detection of hypertension using physiological signals: A review. Int. J. Environ. Res. Public Health, 18. Berraih Preliminary study in the analysis of the severity of cardiac pathologies using the higher-order spectra on the heart-beats signals Pol. J. Med. Phys. Eng. 2021 10.2478/pjmpe-2021-0010 27 73 Pappalettera Analysis of complexity in the EEG activity of Parkinson’s disease patients by means of approximate entropy GeroScience 2022 10.1007/s11357-022-00552-0 44 1599 Moorthy A novel optimal feature selection technique for medical data classification using ANOVA based whale optimization J. Ambient Intell. Humaniz. Comput. 2021 10.1007/s12652-020-02592-w 12 3527 Wold Analysis of variance (ANOVA) Chemom. Intell. Lab. Syst. 1989 10.1016/0169-7439(89)80095-4 6 259 Muhammad Enhancing Prognosis Accuracy for Ischemic Cardiovascular Disease Using K Nearest Neighbor Algorithm: A Robust Approach IEEE Access 2023 10.1109/ACCESS.2023.3312046 11 97879 Cinar Training feed-forward multi-layer perceptron artificial neural networks with a tree-seed algorithm Arab. J. Sci. Eng. 2020 10.1007/s13369-020-04872-1 45 10915 Dung, P., and Florea, A.M. (2012, January 5–6). An approach for detecting learning styles in learning management systems based on learners’ behaviors. Proceedings of the International Conference on Education and Management Innovation, Kuala Lumpur, Malaysia. Karagiannis An adaptive mechanism for Moodle based on automatic detection of learning styles Educ. Inf. Technol. 2017 10.1007/s10639-017-9663-5 23 1331 Liyanage Using Learning Styles to Enhance Learning Management Systems Int. J. Adv. ICT Emerg. Reg. 2014 7 1 Graf, S. (2007, January 2–5). Adaptivity in learning management systems focussing on learning styles. Proceedings of the IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, Silicon Valley, CA, USA. Noisy EEG signals classification based on entropy metrics. Performance assessment using first and second generation statistics Comput. Biol. Med. 2017 10.1016/j.compbiomed.2017.05.028 87 141