Real-Time Emotion Classification Using EEG Data Stream in E-Learning Contexts

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.

Improving Motor Imagery EEG Signals Classification Accuracy with CSP by Available Machine Learning Approach

“…This paper shows all the figures and table data when the frequency range was 10-30 Hz. Nandi et al (2021) mentioned that the classifier categorized the classes of one diagonal entry of confusion matrix accurately and other diagonal entries classified inaccurately for binary classification. Table 1 shows the confusion matrix for k=1 fold in case of SVM classifier.…”

Responsive Dashboard as a Component of Learning Analytics System for Evaluation in Emergency Remote Teaching Situations

“…The result of the present study can be compared with 10 of these relevant papers [68][69][70][71][72][73][74][75][76][77]. While other researchers have analyzed the effects of ERT on high school teachers [68], state universities [69], and the challenges faced by educational institutions [70], for the proposed model, the developed EvalMathI system was tested to be able to answer questions Q1-Q4, questions that support the development of the model for the evaluation system (LAEM), and also validate the software instrument called EvalMathI.…”

“…The authors answered Q1—How useful is EvalMathI in evaluating courses in an ERT situation?—by introducing and integrating the dashboard in a responsive panel to facilitate and streamline the evaluation process. In addition, other researchers have previously analyzed students’ performance in an ERT situation [ 71 ], the challenges faced by math teachers in an ERT situation [ 72 ], the level of emotions in the learning process [ 75 ], the factors influencing home learning [ 78 ], and students’ emotions and the perception of teachers in ERT [ 76 , 77 ]. In this context, the present study analyzed the methodology of evaluation in ERT conditions and proposed a tool called EvalMathI, which was tested in a case study of six courses conducted in ERT at our university.…”

Prediction And Detection In Change Of Cognitive Load For VIP's By A Machine Learning Approach

“…L(q, q) is a term used to describe the distinction between class labels predicted by a neural network and those viewed (considered as q ) and the actual class labels q. A family F of functions f k (p) is defined by a weight vector k. The function f ∈ F reduces the size of the error section Q(z, k) = L (f k (p), q)This was calculated by averaging the training samples [87].…”