Recently, emotion classification from electroencephalogram (EEG) data has attracted much attention. As EEG is an unsteady and rapidly changing voltage signal, the features extracted from EEG usually change dramatically, whereas emotion states change gradually. Most existing feature extraction approaches do not consider these differences between EEG and emotion. Microstate analysis could capture important spatio-temporal properties of EEG signals. At the same time, it could reduce the fast-changing EEG signals to a sequence of prototypical topographical maps. While microstate analysis has been widely used to study brain function, few studies have used this method to analyze how brain responds to emotional auditory stimuli. In this study, the authors proposed a novel feature extraction method based on EEG microstates for emotion recognition. Determining the optimal number of microstates automatically is a challenge for applying microstate analysis to emotion. This research proposed dual-threshold-based atomize and agglomerate hierarchical clustering (DTAAHC) to determine the optimal number of microstate classes automatically. By using the proposed method to model the temporal dynamics of auditory emotion process, we extracted microstate characteristics as novel temporospatial features to improve the performance of emotion recognition from EEG signals. We evaluated the proposed method on two datasets. For public music-evoked EEG Dataset for Emotion Analysis using Physiological signals, the microstate analysis identified 10 microstates which together explained around 86% of the data in global field power peaks. The accuracy of emotion recognition achieved 75.8% in valence and 77.1% in arousal using microstate sequence characteristics as features. Compared to previous studies, the proposed method outperformed the current feature sets. For the speech-evoked EEG dataset, the microstate analysis identified nine microstates which together explained around 85% of the data. The accuracy of emotion recognition achieved 74.2% in valence and 72.3% in arousal using microstate sequence characteristics as features. The experimental results indicated that microstate characteristics can effectively improve the performance of emotion recognition from EEG signals.
19 October 2018 in International Journal of Machine Learning and Cybernetics
Introduction: Recently, the microstate analysis method has been widely used to investigate the temporal and spatial dynamics of electroencephalogram (EEG) signals. However, most studies have focused on EEG at resting state, and few use microstate analysis to study emotional EEG. This paper aims to investigate the temporal and spatial patterns of EEG in emotional states, and the specific neurophysiological significance of microstates during the emotion cognitive process, and further explore the feasibility and effectiveness of applying the microstate analysis to emotion recognition.Methods: We proposed a KLGEV-criterion-based microstate analysis method, which can automatically and adaptively identify the optimal number of microstates in emotional EEG. The extracted temporal and spatial microstate features then served as novel feature sets to improve the performance of EEG emotion recognition. We evaluated the proposed method on two publicly available emotional EEG datasets: the SJTU Emotion EEG Dataset (SEED) and the Database for Emotion Analysis using Physiological Signals (DEAP).Results: For the SEED dataset, 10 microstates were identified using the proposed method. These temporal and spatial features were fed into AutoGluon, an open-source automatic machine learning model, yielding an average three-class accuracy of 70.38% (±8.03%) in subject-dependent emotion recognition. For the DEAP dataset, the method identified 9 microstates. The average accuracy in the arousal dimension was 74.33% (±5.17%) and 75.49% (±5.70%) in the valence dimension, which were competitive performance compared to some previous machine-learning-based studies. Based on these results, we further discussed the neurophysiological relationship between specific microstates and emotions, which broaden our knowledge of the interpretability of EEG microstates. In particular, we found that arousal ratings were positively correlated with the activity of microstate C (anterior regions of default mode network) and negatively correlated with the activity of microstate D (dorsal attention network), while valence ratings were positively correlated with the activity of microstate B (visual network) and negatively correlated with the activity of microstate D (dorsal attention network).Discussion: In summary, the findings in this paper indicate that the proposed KLGEV-criterion-based method can be employed to research emotional EEG signals effectively, and the microstate features are promising feature sets for EEG-based emotion recognition.
Introduction: Scalp electroencephalogram (EEG) analysis and interpretation are crucial for tracking and analyzing brain activity. The collected scalp EEG signals, however, are weak and frequently tainted with various sorts of artifacts. The models based on deep learning provide comparable performance with that of traditional techniques. However, current deep learning networks applied to scalp EEG noise reduction are large in scale and suffer from overfitting.Methods: Here, we propose a dual-pathway autoencoder modeling framework named DPAE for scalp EEG signal denoising and demonstrate the superiority of the model on multi-layer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN), respectively. We validate the denoising performance on benchmark scalp EEG artifact datasets.Results: The experimental results show that our model architecture not only significantly reduces the computational effort but also outperforms existing deep learning denoising algorithms in root relative mean square error (RRMSE)metrics, both in the time and frequency domains.Discussion: The DPAE architecture does not require a priori knowledge of the noise distribution nor is it limited by the network layer structure, which is a general network model oriented toward blind source separation.
Introduction: Emotion recognition based on electroencephalogram (EEG) signals has shown increasing application potential in fields such as brain-computer interfaces and affective computing. However, current graph neural network models rely on predefined fixed adjacency matrices during training, which imposes certain limitations on the model's adaptability and feature expressiveness.Methods: In this study, we propose a novel EEG emotion recognition framework known as the Dynamic Graph Attention Network (DGAT). This framework dynamically learns the relationships between different channels by utilizing dynamic adjacency matrices and a multi-head attention mechanism, allowing for the parallel computation of multiple attention heads. This approach reduces reliance on specific adjacency structures while enabling the model to learn information in different subspaces, significantly improving the accuracy of emotion recognition from EEG signals.Results: Experiments conducted on the EEG emotion datasets SEED and DEAP demonstrate that DGAT achieves higher emotion classification accuracy in both subject-dependent and subject-independent scenarios compared to other models. These results indicate that the proposed model effectively captures dynamic changes, thereby enhancing the accuracy and practicality of emotion recognition.Discussion: DGAT holds significant academic and practical value in the analysis of emotional EEG signals and applications related to other physiological signal data.
Cognitive control has been extensively studied from Event-Related Potential (ERP) point of view in visual modality using Stroop paradigms. Little work has been done in auditory Stroop paradigms, and inconsistent conclusions have been reported, especially on the conflict detection stage of cognitive control. This study investigated the early ERP components in an auditory Stroop paradigm, during which participants were asked to identify the volume of spoken words and ignore the word meanings. A series of significant ERP components were revealed that distinguished incongruent and congruent trials: two declined negative polarity waves (the N1 and the N2) and three declined positive polarity wave (the P1, the P2 and the P3) over the fronto-central area for the incongruent trials. These early ERP components imply that both a perceptual stage and an identification stage exist in the auditory Stroop effect. A 3-stage cognitive control model was thus proposed for a more detailed description of the human cognitive control mechanism in the auditory Stroop tasks.