Active-Reflective Learning Style Detection Using EEG and Abrupt Change Detection
Article Sidebar
Main Article Content
Abstract
Recognizing the varying learning styles of students is vital to creating customized educational approaches and maximizing academic success. While commonly used, conventional evaluation methods such as self-report surveys are frequently characterized by subjective biases and inconsistent accuracy. To address this limitation, this present study proposes an EEG-driven approach for learning style classification, specifically targeting the Active and Reflective dimensions of the Felder-Silverman Learning Style Model (FSLSM). Data was acquired from 14 participants using an 8-channel OpenBCI headset, with cognitive engagement stimulated through Raven’s Advanced Progressive Matrices (RAPM). Initially, the raw EEG data underwent bandpass filtering process purposely to remove noise. Subsequently, the data was divided into consecutive 1-second segments. For feature extraction, the CUSUM algorithm was employed, with an aim to effectively capture significant signal variations. These features were then fed into an LDA classifier for style discrimination. The performance evaluation revealed impressive results—98.26% accuracy in standard Train-Test validation, and an even higher 99.29% under LOOCV testing. Notably, our approach consistently outperformed existing techniques including 1-DCNN and TSMG across all metrics. Notably, computational efficiency and reliability were improved, with the "Odd-only" subset yielding peak accuracy (99.24%). These findings demonstrate that integrating EEG signals with conventional machine learning enables real-time, high-precision learning style detection. Additionally, this work addresses the computational constraints and dataset limitations observed in recent studies, providing a robust foundation for adaptive learning systems. It is recommended that future research explore larger, more diverse datasets and additional FSLSM dimensions to enhance generalizability and practical implementation of the research.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
2. Z. Mehenaoui, Y. Lafifi, dan L. Zemmouri, Learning behavior analysis to identify learner’s learning style based on machine learning techniques, J. Univers. Comput. Sci. 28 (2022) 1193–1220.
3. W. Waam dan P. Hks, Identifying the learning style of students using machine learning techniques: an approach of Felder Silverman learning style model (FSLSM), Asian J. Res. Comput. Sci. 17 (2024) 15–37.
4. A. B. Rashid, R. R. Raja Ikram, Y. Thamilarasan, L. Salahuddin, N. F. A. Yusof, dan Z. B. Rashid, A student learning style auto-detection model in a learning management system, Eng. Technol. Appl. Sci. Res. 13 (2023) 11000–11005.
5. A. Wijaya, N. A. Setiawan, dan M. I. Shapiai, Mapping research themes and future directions in learning style detection research: a bibliometric and content analysis, Electron. J. E-Learn. 21 (2023) 274–285.
6. R. Yuvaraj, et al., A machine learning framework for classroom EEG recording classification: unveiling learning-style patterns, Algorithms 17 (2024) 503.
7. B. Zhang, Y. Shi, L. Hou, Z. Yin, dan C. Chai, TSMG: a deep learning framework for recognizing human learning style using EEG signals, Brain Sci. 11 (2021) 1397.
8. S. Chen, Z. Hu, S. Li, X. Hu, G. Liu, dan W. Wen, Autonomic nervous pattern recognition of students’ learning states in real classroom situation, IEEE Trans. Comput. Soc. Syst. 10 (2023) 220–233.
9. L. Cao, M. He, dan H. Wang, Effects of attention level and learning style based on electroencephalograph analysis for learning behavior in immersive virtual reality, IEEE Access 11 (2023) 53429–53438.
10. A. Wijaya, T. B. Adji, dan N. A. Setiawan, Improving multi-class EEG-motor imagery classification using two-stage detection on one-versus-one approach, Commun. Sci. Technol. 5 (2020) 85–92.
11. M. M. El-Bishouty, et al., Use of Felder and Silverman learning style model for online course design, Educ. Technol. Res. Dev. 67 (2019) 161–177.
12. A. Chuderski, J. Jastrzębski, B. Kroczek, H. Kucwaj, dan M. Ociepka, Metacognitive experience on Raven’s matrices versus insight problems, Metacognition Learn. 16 (2021) 15–35.
13. S. J. Cheyette dan S. T. Piantadosi, Response to difficulty drives variation in IQ test performance, Open Mind 8 (2024) 265–277.
14. M. V. Konstantinova, V. N. Anisimov, dan A. V. Latanov, EEG spectral power in the beta frequency band reflects the subjective estimation of the Go/NoGo task performance time, Hum. Physiol. 46 (2020) 8–15.
15. S. A. Schapkin, J. Raggatz, M. Hillmert, dan I. Böckelmann, EEG correlates of cognitive load in a multiple-choice reaction task, Acta Neurobiol. Exp. 80 (2020) 76–89.
16. B. Zhang dan L. Wang, Evaluating abstract reasoning and problem-solving abilities of large language models using Raven’s progressive matrices, In Review (2024).
17. B. Zhang, C. Chai, Z. Yin, dan Y. Shi, Design and implementation of an EEG-based learning-style recognition mechanism, Brain Sci. 11 (2021) 613.
18. S. Pattisapu dan S. Ray, Stimulus-induced narrow-band gamma oscillations in humans can be recorded using open-hardware low-cost EEG amplifier, PLOS ONE 18 (2023) e0279881.
19. T. Lee, M. K. Kim, H. J. Lee, dan M. Je, A multimodal neural-recording IC with reconfigurable analog front-ends for improved availability and usability for recording channels, IEEE Trans. Biomed. Circuits Syst. 16 (2022) 185–199.
20. J. Ghosh dan S. B. Shuvo, Improving classification model’s performance using linear discriminant analysis on linear data, Int. Conf. Comput. Commun. Netw. Technol., 10th ed., Kanpur, India, 2019, pp. 1–5.
21. N. Trendafilov dan M. Gallo, Linear discriminant analysis, Multivariate Data Analysis on Matrix Manifolds, Cham, Switzerland: Springer, 2021, pp. 229–268.
22. M. Lundqvist, E. K. Miller, J. Nordmark, J. Liljefors, dan P. Herman, Beta: bursts of cognition, Trends Cogn. Sci. 28 (2024) 662–676.
23. L. Rier, et al., Tracking the neurodevelopmental trajectory of beta band oscillations with optically pumped magnetometer-based magnetoencephalography, eLife 13 (2024) RP94561.
24. Z. Zhang, W. Wu, C. Sun, dan C. Wang, Seizure detection via deterministic learning feature extraction, Pattern Recognit. 153 (2024) 110466.
25. X. Yu and Y. Cheng, A Comprehensive Review and Comparison of CUSUM and Change-Point-Analysis Methods to Detect Test Speededness, Multivar. Behav. Res. 57 (2022) 112–133.
26. W. Ren and M. Han, “Classification of EEG Signals Using Hybrid Feature Extraction and Ensemble Extreme Learning Machine, Neural Process. Lett. 50 (2019) 1281–1301.
27. S. Kunjan et al., The Necessity of Leave One Subject Out (LOSO) Cross Validation for EEG Disease Diagnosis, in Brain Informatics, vol. 12960, M. Mahmud, M. S. Kaiser, S. Vassanelli, Q. Dai, and N. Zhong, Eds., in Lecture Notes in Computer Science, vol. 12960., Cham: Springer International Publishing, (2021) 558–567.
28. M. Aljalal, S. A. Aldosari, M. Molinas, and F. A. Alturki, Selecting EEG channels and features using multi-objective optimization for accurate MCI detection: validation using leave-one-subject-out strategy, Sci. Rep. 14 (2024) 12483.
29. R. Yuvaraj et al., A Machine Learning Framework for Classroom EEG Recording Classification: Unveiling Learning-Style Patterns, Algorithms, 17 (2024) 503.