The human attention system, similar to other networks in the brain, is of a complex nature. At any moment, our attention can shift between external and internal stimuli. In this study, we aimed to assess three EEG-based measures of attention (Power Spectral Density, Connectivity, and Spectral Entropy) in decision-making situations involving goal-directed and stimulus-driven attention using a Virtual Reality supermarket. We collected the EEG data of 29 participants in 2 shopping phases, planned and unplanned purchases. The three mentioned features were extracted and a statistical analysis was conducted. We evaluated the discriminatory power of these features using an SVM classifier. The results showed a significant (p-value < 0.001) increase in theta power over frontal, central, and temporal lobes for the planned purchase phase. There was also a significant decrease in alpha power over frontal and parietal lobes in the unplanned purchase phase. A significant increase in the frontoparietal connectivity during the planned purchase was observed. Additionally, an increase in spectral entropy was observed in the frontoparietal region for the unplanned purchase phase. The classification results showed that spectral entropy has the highest discriminatory power. This study can provide further insights into the attentional behaviors of consumers and how their type of attentional control can affect their decision-making processes.

The main drawback of SSVEP-based BCIs is the lack of a classifier that categorizes SSVEPs with high accuracy and Information Transfer Rate (ITR). Addressing this, we proposed a deep convolutional neural network (CNN) for classifying a 40-class SSVEP. Time windows of length 2 and 3.5 seconds were used for training and testing the model by leave-one-subject-out cross-validation, using nine, three, and single-channel EEG. The proposed model reached 88.5% average accuracy for the nine-channel EEG with the mean and max ITR of 72 and 91.23 bpm, respectively. It outperformed the previous deep learning methods for SSVEP-based BCIs, in terms of accuracy and ITR. In the three-channel experiment the mean accuracy and ITR were 76.02% and 40.1 bpm. In single-channel implementation, O₁ channel achieved 77.38 % average accuracy (highest) and the mean ITR was 57.51 bpm. The model showed promising performance to put this technology forward and make it more practical.

Detecting human emotional states, crucial in research for human-machine interaction and affective computing, often relies on objective and spontaneous physiological signals such as Electroencephalogram (EEG). Despite the wealth of stateof-the-art methods for emotion recognition, lingering challenges in terms of generalization power persist. Addressing this issue, we introduce an approach employing a transformer-based autoencoder for the emotion classification using EEG. An autoencoder is applied to connectivity matrices to distil essential features and reduce data dimensionality. Additionally, a multihead attention transformer directs attention to pertinent features for emotion recognition which subsequently added to a fully connected network for classification. Extensive experiments have been conducted on DEAP and DREAMER datasets. In subjectdependent evaluation on the DEAP dataset, the model achieves an accuracy of 99.68% and 99.47% for valence and arousal, respectively. In the subject-independent scheme, the model demonstrates an accuracy of 94.08% and 94.98% for valence and arousal. In the DREAMER experiment, subject-dependent evaluation results in an accuracy of 99.54% and 99.30% for valence and arousal prediction. For the subject-independent experiment, the model accurately predicts valence and arousal levels with 98.38% and 97.32%, respectively. The results are further elucidated through ablation experiments and the visualization of learned features.