Real-Time Emotion Classification Using EEG Data Stream in E-Learning Contexts - PubMed
- ️Fri Jan 01 2021
Real-Time Emotion Classification Using EEG Data Stream in E-Learning Contexts
Arijit Nandi et al. Sensors (Basel). 2021.
Abstract
In face-to-face and online learning, emotions and emotional intelligence have an influence and play an essential role. Learners' emotions are crucial for e-learning system because they promote or restrain the learning. Many researchers have investigated the impacts of emotions in enhancing and maximizing e-learning outcomes. Several machine learning and deep learning approaches have also been proposed to achieve this goal. All such approaches are suitable for an offline mode, where the data for emotion classification are stored and can be accessed infinitely. However, these offline mode approaches are inappropriate for real-time emotion classification when the data are coming in a continuous stream and data can be seen to the model at once only. We also need real-time responses according to the emotional state. For this, we propose a real-time emotion classification system (RECS)-based Logistic Regression (LR) trained in an online fashion using the Stochastic Gradient Descent (SGD) algorithm. The proposed RECS is capable of classifying emotions in real-time by training the model in an online fashion using an EEG signal stream. To validate the performance of RECS, we have used the DEAP data set, which is the most widely used benchmark data set for emotion classification. The results show that the proposed approach can effectively classify emotions in real-time from the EEG data stream, which achieved a better accuracy and F1-score than other offline and online approaches. The developed real-time emotion classification system is analyzed in an e-learning context scenario.
Keywords: e-learning; emotion classification; logistic regression; online training; real-time emotion classification; stochastic gradient descent.
Conflict of interest statement
The authors declare no conflict of interest.
Figures

Online emotion classification from a data stream.

The Russel 2D valence–arousal (VA) space emotion model.

The framework of our proposed work.

Learning rate vs model error.

Valence classification comparison among different online classifiers. In (a) shows the accuracy and (b) shows the F1-score comparison.

Arousal classification comparison among different online classifiers. In (a) is shown the accuracy and (b) shows the F1-score comparison.

Confusion matrix comparison among different online classifiers for valence classification with our proposed RECS.

Confusion matrix comparison among different online classifiers for arousal classification with our proposed RECS.

New generation of EEG head bands.

An application scenario.

Confusion matrix for discrete emotion mapping based on valence–arousal status.
Similar articles
-
Online Learning for Wearable EEG-Based Emotion Classification.
Moontaha S, Schumann FEF, Arnrich B. Moontaha S, et al. Sensors (Basel). 2023 Feb 21;23(5):2387. doi: 10.3390/s23052387. Sensors (Basel). 2023. PMID: 36904590 Free PMC article.
-
Fused CNN-LSTM deep learning emotion recognition model using electroencephalography signals.
Ramzan M, Dawn S. Ramzan M, et al. Int J Neurosci. 2023 Jun;133(6):587-597. doi: 10.1080/00207454.2021.1941947. Epub 2021 Aug 27. Int J Neurosci. 2023. PMID: 34121598
-
Li Z, Qiu L, Li R, He Z, Xiao J, Liang Y, Wang F, Pan J. Li Z, et al. Sensors (Basel). 2020 May 27;20(11):3028. doi: 10.3390/s20113028. Sensors (Basel). 2020. PMID: 32471047 Free PMC article.
-
Recognition of human emotions using EEG signals: A review.
Rahman MM, Sarkar AK, Hossain MA, Hossain MS, Islam MR, Hossain MB, Quinn JMW, Moni MA. Rahman MM, et al. Comput Biol Med. 2021 Sep;136:104696. doi: 10.1016/j.compbiomed.2021.104696. Epub 2021 Aug 3. Comput Biol Med. 2021. PMID: 34388471 Review.
-
EEG-Based Emotion Recognition: A State-of-the-Art Review of Current Trends and Opportunities.
Suhaimi NS, Mountstephens J, Teo J. Suhaimi NS, et al. Comput Intell Neurosci. 2020 Sep 16;2020:8875426. doi: 10.1155/2020/8875426. eCollection 2020. Comput Intell Neurosci. 2020. PMID: 33014031 Free PMC article. Review.
Cited by
-
Shen X, Bao J, Tao X, Li Z. Shen X, et al. Sensors (Basel). 2022 Sep 27;22(19):7321. doi: 10.3390/s22197321. Sensors (Basel). 2022. PMID: 36236416 Free PMC article.
-
SSTM-IS: simplified STM method based on instance selection for real-time EEG emotion recognition.
Ran S, Zhong W, Duan D, Ye L, Zhang Q. Ran S, et al. Front Hum Neurosci. 2023 Jun 1;17:1132254. doi: 10.3389/fnhum.2023.1132254. eCollection 2023. Front Hum Neurosci. 2023. PMID: 37323929 Free PMC article.
-
Ma X, Jiang M, Nong L. Ma X, et al. Front Psychol. 2023 Jan 30;14:1076552. doi: 10.3389/fpsyg.2023.1076552. eCollection 2023. Front Psychol. 2023. PMID: 36794084 Free PMC article.
-
Wei J, Yun Z, Zhang Y, Mei X, Ba L, Peng H, Li N, Li M, Liu Z, Liu H. Wei J, et al. Front Psychiatry. 2023 Sep 25;14:1239583. doi: 10.3389/fpsyt.2023.1239583. eCollection 2023. Front Psychiatry. 2023. PMID: 37817833 Free PMC article.
-
Online Learning for Wearable EEG-Based Emotion Classification.
Moontaha S, Schumann FEF, Arnrich B. Moontaha S, et al. Sensors (Basel). 2023 Feb 21;23(5):2387. doi: 10.3390/s23052387. Sensors (Basel). 2023. PMID: 36904590 Free PMC article.
References
-
- Pekrun R. The Impact of Emotions on Learning and Achievement: Towards a Theory of Cognitive/Motivational Mediators. Appl. Psychol. 1992;41:359–376. doi: 10.1111/j.1464-0597.1992.tb00712.x. - DOI
-
- Krithika L., Lakshmi P.G.G. Student Emotion Recognition System (SERS) for e-learning Improvement Based on Learner Concentration Metric. Procedia Comput. Sci. 2016;85:767–776. doi: 10.1016/j.procs.2016.05.264. - DOI
-
- Giannakos M., Sharma K., Martinez-Maldonado R., Dillenbourg P., Rogers Y. Learner-Computer Interaction; Proceedings of the 10th Nordic Conference on Human-Computer Interaction, NordiCHI ’18; Oslo, Norway. 29 September–3 October 2018; New York, NY, USA: Association for Computing Machinery; 2018. pp. 968–971. - DOI
-
- Ekman P. An argument for basic emotions. Cogn. Emot. 1992;6:169–200. doi: 10.1080/02699939208411068. - DOI
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources