The CLASSIFICATION of emotions using electroencephalography (EEG) signals is inherently challenging due to the intricate nature of brain activity. Overcoming inconsistencies in EEG signals and establishing a universally applicable sentiment analysis model are essential objectives. This study introduces an innovative approach to cross-subject emotion recognition, employing a genetic algorithm (GA) to eliminate non-informative frames. Then, the optimal frames identified by the GA undergo spatial feature extraction using common spatial patterns (CSP) and the logarithm of variance. Subsequently, these features are input into a Transformer network to capture spatial-temporal features, and the emotion CLASSIFICATION is executed using a fully connected (FC) layer with a Softmax activation function. Therefore, the innovations of this paper include using a limited number of channels for emotion CLASSIFICATION without sacrificing accuracy, selecting optimal signal segments using the GA, and employing the Transformer network for high-accuracy and high-speed CLASSIFICATION. The proposed method undergoes evaluation on two publicly accessible datasets, SEED and SEED-V, across two distinct scenarios. Notably, it attains mean accuracy rates of 99.96% and 99.51% in the cross-subject scenario, and 99.93% and 99.43% in the multi-subject scenario for the SEED and SEED-V datasets, respectively. Noteworthy is the outperformance of the proposed method over the state-of-the-art (SOTA) in both scenarios for both datasets, thus underscoring its superior efficacy. Additionally, comparing the accuracy of individual subjects with previous works in cross subject scenario further confirms the superiority of the proposed method for both datasets.

Brain Computer Interface (BCI) systems still suffer from lack of accuracy in real-time applications. This problem emerges from isolated optimization, and in some occasions from mismatching of feature extraction and CLASSIFICATION stages. To unify optimization of both stages, this paper presents a novel scheme to integrate them and simultaneously optimize under a unit criterion. The proposed method iteratively estimates both spatio-spectral filters and classifier weights under a non-linear form of Fisher criterion. In order to validate the introduced method, two standard EEG sets, one containing 118 EEG signals and the other 29, were employed to demonstrate its spatial resolution capability. Experimental results on both datasets reveal the superiority of the proposed scheme in terms of enhancing the CLASSIFICATION performance simultaneously with speeding up the optimization process, compared to the conventional methods.

This paper proposes a method for processing motor imagery-based Electroencephalography (EEG) signals to generate precise signals for Brain-Computer Interface (BCI) devices used in rehabilitation and physical treatments. BCI research is mainly used in neuroprosthetic applications to help improve disabilities. We analyze EEG data from seven healthy individuals using 59-channel caps. The signals are down-sampled to 100 Hz after pre-processing to remove artifacts and noise by using Filter Bank Common Spatial Patterns (FBCSP). EEG features are extracted using the Fisher Discriminant Ratio (FDR). A comprehensive comparison of CLASSIFICATION methods is conducted, encompassing statistical techniques, machine learning algorithms, and neural network-based models. Specifically, Linear Discriminant Analysis (LDA) and K-Nearest Neighbors (KNN) are evaluated as statistical classifiers; Support Vector Machine (SVM) is used for the machine learning approach; and Radial Basis Function (RBF), Probabilistic Neural Network (PNN), and Extreme Learning Machine (ELM) are explored as neural network models. Model performance is validated using K-fold cross-validation and confusion matrix analysis. Among all evaluated classifiers, the ELM model—implemented as a single-layer neural network—demonstrates superior CLASSIFICATION accuracy, suggesting its strong potential for real-time BCI applications in neurorehabilitation.

Background: Emotion recognition, as a subset of affective computing, has received considerable attention in recent years. Emotions are key to human-computer interactions. Electroencephalogram (EEG) is considered a valuable physiological source of information for classifying emotions. However, it has complex and chaotic behavior. Methods: In this study, an attempt is made to extract important nonlinear features from EEGs with the aim of emotion recognition. We also take advantage of machine learning methods such as evolutionary feature selection methods and committee machines to enhance the CLASSIFICATION performance. CLASSIFICATION performed concerning both arousal and valence factors. Results: Results suggest that the proposed method is successful and comparable to the previous works. A recognition rate equal to 90% achieved, and the most significant features reported. We apply the final CLASSIFICATION scheme to 2 different databases including our recorded EEGs and a benchmark dataset to evaluate the suggested approach. Conclusion: Our findings approve of the effectiveness of using nonlinear features and a combination of classifiers. Results are also discussed from different points of view to understand brain dynamics better while emotion changes. This study reveals useful insights about emotion CLASSIFICATION and brain-behavior related to emotion elicitation.