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.

Multi-robot navigation is a challenging task, especially for many robots, since individual gains may more often than not adversely affect the global gain. This paper investigates the problem of multiple robots moving towards individual goals within a common workspace whereas the motion of every individual robot is deduced by a novel Particle Swarm Optimization (PSO) tuned Feed Forward Neural Network (FFNN). Motion coordination among the robots is implemented using a cooperative coordination algorithm that identifies critical robots and maintains cooperation count while actuating deviation in select robots. The contribution of this paper is twofold; firstly in hybridizing the Artificial Neural Network(ANN) by employing PSO, an evolutionary algorithm, to find optimal values of deviation for every critical robot using velocity and acceleration constraints, secondly ensuing the convergence of the PSO by carrying first and second order stability analysis. Experiments have been carried out to evaluate and validate the efficacy of the proposed coordination schemes by changing the number of robots under hundred different scenarios each, and the founded results demonstrate the efficacy of the proposed schemes.

Activation functions in the neural networks play an important role by introducing non-linear properties to the neural networks. Thus it is considered as one of the essential ingredients among other building blocks of a neural network. But the selection of the appropriate activation function for the enhancement of model accuracy is strenuous in a sense; the performance of the NN-model is influenced by a proper selection of activation function for a dataset. Proper activation function selection is still a trial and error method for which the model accuracy improves for classification. As a solution to this problem, we have proposed an activation function ensembling by majority voting that has significantly improved the model accuracy in a classification context. The proposed model is tested on four benchmark datasets such as MNIST, Fashion MNIST, Semeion, and ARDIS IV datasets. The result shows that the performance of the proposed model is appreciably better than other traditional methods such as Convolutional Neural Network (CNN), Support Vector Machine (SVM), Recurrent Neural Network (RNN).

Emotions play a crucial role in learning. To improve and optimize electronic learning (e-Learning) outcomes, many researchers have investigated the role of emotions. Also, researchers have come up with many approaches to utilize one or many data modalities to achieve this goal, and they have been successful. But the recent advancements in technology and the internet of things (IoT) devices have brought a new dimension in e-Learning, with many input devices (such as webcams, fit-bands etc.) for interacting with e-Learners. This new dimension brings not only massive amounts of data with volume, variety, and velocity called multimodal data streams but also more challenges of mining those data in real-time. In this work, we have focused on state-of-the-art emotion recognition in e-Learning utilizing the multimodal data streams of learners. Also, we have thoroughly investigated the past research and surveys on emotion recognition methods in e-Learning to find the affecting emotions and their relations with the emotion measurement channels; and we have compared several data-stream classifiers for emotion recognition by utilizing multimodal physiological data streams. Finally, the future research opportunities to be addressed are also discussed.