LGGNet: Learning From Local-Global-Graph Representations for Brain-Computer Interface

Joint disentangled representation and domain adversarial training for EEG-based cross-session biometric recognition in single-task protocols

The increasing adoption of wearable technologies highlights the potential of electroencephalogram (EEG) signals for biometric recognition. However, the intrinsic variability in cross-session EEG data presents substantial challenges in maintaining model stability and reliability. Moreover, the diversity within single-task protocols complicates achieving consistent and generalized model performance. To address these issues, we propose the Joint Disentangled Representation with Domain Adversarial Training (JDR-DAT) framework for EEG-based cross-session biometric recognition within single-task protocols. The JDR-DAT framework disentangles identity-specific features through mutual information estimation and incorporates domain adversarial training to enhance longitudinal robustness. Extensive experiments on longitudinal EEG data from two publicly available single-task protocol datasets-RSVP-based (Rapid Serial Visual Presentation) and MI-based (Motor Imagery)-demonstrate the efficacy of the JDR-DAT framework, with the proposed method achieving average accuracies of 85.83% and 96.72%, respectively.

A multidimensional adaptive transformer network for fatigue detection

Variations in information processing patterns induced by operational directives under varying fatigue conditions within the cerebral cortex can be identified and analyzed through electroencephalogram (EEG) signals. The inherent complexity of EEG signals poses significant challenges in the effective detection of driver fatigue across diverse task scenarios. Recent advancements in deep learning, particularly the Transformer architecture, have shown substantial benefits in the retrieval and integration of multi-dimensional information. Nevertheless, the majority of current research primarily focuses on the application of Transformers for temporal information extraction, often overlooking other dimensions of EEG data. In response to this gap, the present study introduces a Multidimensional Adaptive Transformer Recognition Network specifically tailored for the identification of driving fatigue states. This network features a multidimensional Transformer architecture for feature extraction that adaptively assigns weights to various information dimensions, thereby facilitating feature compression and the effective extraction of structural information. This methodology ultimately enhances the model's accuracy and generalization capabilities. The experimental results indicate that the proposed methodology outperforms existing research methods when utilized with the SEED-VIG and SFDE datasets. Additionally, the analysis of multidimensional and frequency band features highlights the ability of the proposed network framework to elucidate differences in various multidimensional features during the identification of fatigue states.

Uncertainty-Aware Graph Contrastive Fusion Network for multimodal physiological signal emotion recognition

Graph Neural Networks (GNNs) have been widely adopted to mine topological patterns contained in physiological signals for emotion recognition. However, since physiological signals are non-stationary and susceptible to various noises, there exists inter-sensor connectivity uncertainty in each modality. Such intra-modal connectivity uncertainty may further lead to inter-modal semantic gap uncertainty, which will cause the unimodal bias problem and greatly affect the fusion effectiveness. While, such issue has never been fully considered in existing multimodal fusion models. To this end, we proposed an Uncertainty-Aware Graph Contrastive Fusion Network (UAGCFNet) to fuse multimodal physiological signals effectively for emotion recognition. Firstly, a probabilistic model-based Uncertainty-Aware Graph Convolutional Network (UAGCN), which can estimate and quantify the inter-sensor connectivity uncertainty, is constructed for each modality to extract its uncertainty-aware graph representation. Secondly, a Transitive Contrastive Fusion (TCF) module, which combines the Criss-Cross Attention (CCA)-based fusion mechanism and Transitive Contrastive Learning (TCL)-based calibration strategy organically, is designed to achieve effective fusion of multimodal graph representations by eliminating the unimodal bias problem resulting from the inter-modal semantic gap uncertainty. Extensive experimental results on DEAP, DREAMER, and MPED datasets under both subject-dependent and subject-independent scenarios demonstrate that (i) the proposed model outperforms State-Of-The-Art (SOTA) multimodal fusion models with fewer parameters and lower computational complexity; (ii) each key module and loss function contributes significantly to the performance enhancement of the proposed model; (iii) the proposed model can eliminate the unimodal bias problem effectively.

Neurophysiological data augmentation for EEG-fNIRS multimodal features based on a denoising diffusion probabilistic model

BACKGROUND AND OBJECTIVE

The hybrid brain computer interfaces (BCI) combining electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) have attracted extensive attention for overcoming the decoding limitations of the single-modality BCI. With the deepening application of deep learning approaches in BCI systems, its significant performance improvement has become apparent. However, the scarcity of brain signal data limits the performance of deep learning models.

METHODS

In this study, we proposed an EEG-fNIRS data augmentation framework based on the combination of denoising diffusion probabilistic model (DDPM) and adding Gaussian noise (EFDA-CDG), for enhancing the performance of hybrid BCI systems. Firstly, we unified the temporal and spatial dimensions of EEG and fNIRS by manually extracting features and spatial mapping interpolation to create EEG-fNIRS joint distribution samples. Then, the DDPM generative model was combined with the traditional method of adding Gaussian noise to provide richer training data for the classifier. Finally, we constructed a classification module that applies EEG feature attention and fNIRS terrain attention to improve classification accuracy.

RESULTS

In order to evaluate the effectiveness of EFDA-CDG framework, experiments were conducted and fully validated on three publicly available databases and one self-collected database. In the context of a participant-dependent training approach, our method achieves accuracy rates of 82.02% for motor imagery, 91.93% for mental arithmetic, and 90.54% for n-back tasks on public databases. Additionally, our method boasts an accuracy rate of 97.82% for drug addiction discrimination task on the self-collected database.

CONCLUSIONS

EFDA-CDG framework successfully facilitates data augmentation, thereby enhancing the performance of EEG-fNIRS hybrid BCI systems.

EEG-Deformer: A Dense Convolutional Transformer for Brain-Computer Interfaces

Effectively learning the temporal dynamics in electroencephalogram (EEG) signals is challenging yet essential for decoding brain activities using brain-computer interfaces (BCIs). Although Transformers are popular for their long-term sequential learning ability in the BCI field, most methods combining Transformers with convolutional neural networks (CNNs) fail to capture the coarse-to-fine temporal dynamics of EEG signals. To overcome this limitation, we introduce EEG-Deformer, which incorporates two main novel components into a CNN-Transformer: (1) a Hierarchical Coarse-to-Fine Transformer (HCT) block that integrates a Fine-grained Temporal Learning (FTL) branch into Transformers, effectively discerning coarse-to-fine temporal patterns; and (2) a Dense Information Purification (DIP) module, which utilizes multi-level, purified temporal information to enhance decoding accuracy. Comprehensive experiments on three representative cognitive tasksâcognitive attention, driving fatigue, and mental workload detectionâconsistently confirm the generalizability of our proposed EEG-Deformer, demonstrating that it either outperforms or performs comparably to existing state-of-the-art methods. Visualization results show that EEG-Deformer learns from neurophysiologically meaningful brain regions for the corresponding cognitive tasks.

FLANet: A multiscale temporal convolution and spatial-spectral attention network for EEG artifact removal with adversarial training

Objective.Denoising artifacts, such as noise from muscle or cardiac activity, is a crucial and ubiquitous concern in neurophysiological signal processing, particularly for enhancing the signal-to-noise ratio in electroencephalograph (EEG) analysis. Novel methods based on deep learning demonstrate a notably prominent effect compared to traditional denoising approaches. However, those still suffer from certain limitations. Some methods often neglect the multi-domain characteristics of the artifact signal. Even among those that do consider these, there are deficiencies in terms of efficiency, effectiveness and computation cost.Approach.In this study, we propose a multiscale temporal convolution and spatial-spectral attention network with adversarial training for automatically filtering artifacts, named filter artifacts network (FLANet). The multiscale convolution module can extract sufficient temporal information and the spatial-spectral attention network can extract not only non-local similarity but also spectral dependencies. To make data denoising more efficient and accurate, we adopt adversarial training with novel loss functions to generate outputs that are closer to pure signals.Main results.The results show that the method proposed in this paper achieves great performance in artifact removal and valid information preservation on EEG signals contaminated by different types of artifacts. This approach enables a more optimal trade-off between denoising efficacy and computational overhead.Significance.The proposed artifact removal framework facilitates the implementation of an efficient denoising method, contributing to the advancement of neural analysis and neural engineering, and can be expected to be applied to clinical research and to realize novel human-computer interaction systems.

Graph convolution network-based eeg signal analysis: a review

With the advancement of artificial intelligence technology, more and more effective methods are being used to identify and classify Electroencephalography (EEG) signals to address challenges in healthcare and brain-computer interface fields. The applications and major achievements of Graph Convolution Network (GCN) techniques in EEG signal analysis are reviewed in this paper. Through an exhaustive search of the published literature, a module-by-module discussion is carried out for the first time to address the current research status of GCN. An exhaustive classification of methods and a systematic analysis of key modules, such as brain map construction, node feature extraction, and GCN architecture design, are presented. In addition, we pay special attention to several key research issues related to GCN. This review enhances the understanding of the future potential of GCN in the field of EEG signal analysis. At the same time, several valuable development directions are sorted out for researchers in related fields, such as analysing the applicability of different GCN layers, building task-oriented GCN models, and improving adaptation to limited data.

Non-Invasive Brain-Computer Interfaces: State of the Art and Trends

Brain-computer interface (BCI) is a rapidly evolving technology that has the potential to widely influence research, clinical and recreational use. Non-invasive BCI approaches are particularly common as they can impact a large number of participants safely and at a relatively low cost. Where traditional non-invasive BCIs were used for simple computer cursor tasks, it is now increasingly common for these systems to control robotic devices for complex tasks that may be useful in daily life. In this review, we provide an overview of the general BCI framework as well as the various methods that can be used to record neural activity, extract signals of interest, and decode brain states. In this context, we summarize the current state-of-the-art of non-invasive BCI research, focusing on trends in both the application of BCIs for controlling external devices and algorithm development to optimize their use. We also discuss various open-source BCI toolboxes and software, and describe their impact on the field at large.

Model-agnostic meta-learning for EEG-based inter-subject emotion recognition

Objective. Developing an efficient and generalizable method for inter-subject emotion recognition from neural signals is an emerging and challenging problem in affective computing. In particular, human subjects usually have heterogeneous neural signal characteristics and variable emotional activities that challenge the existing recognition algorithms from achieving high inter-subject emotion recognition accuracy.Approach. In this work, we propose a model-agnostic meta-learning algorithm to learn an adaptable and generalizable electroencephalogram-based emotion decoder at the subject's population level. Different from many prior end-to-end emotion recognition algorithms, our learning algorithms include a pre-training step and an adaptation step. Specifically, our meta-decoder first learns on diverse known subjects and then further adapts it to unknown subjects with one-shot adaptation. More importantly, our algorithm is compatible with a variety of mainstream machine learning decoders for emotion recognition.Main results. We evaluate the adapted decoders obtained by our proposed algorithm on three Emotion-EEG datasets: SEED, DEAP, and DREAMER. Our comprehensive experimental results show that the adapted meta-emotion decoder achieves state-of-the-art inter-subject emotion recognition accuracy and outperforms the classical supervised learning baseline across different decoder architectures.Significance. Our results hold promise to incorporate the proposed meta-learning emotion recognition algorithm to effectively improve the inter-subject generalizability in designing future affective brain-computer interfaces.

Hybrid Network Using Dynamic Graph Convolution and Temporal Self-Attention for EEG-Based Emotion Recognition

The electroencephalogram (EEG) signal has become a highly effective decoding target for emotion recognition and has garnered significant attention from researchers. Its spatial topological and time-dependent characteristics make it crucial to explore both spatial information and temporal information for accurate emotion recognition. However, existing studies often focus on either spatial or temporal aspects of EEG signals, neglecting the joint consideration of both perspectives. To this end, this article proposes a hybrid network consisting of a dynamic graph convolution (DGC) module and temporal self-attention representation (TSAR) module, which concurrently incorporates the representative knowledge of spatial topology and temporal context into the EEG emotion recognition task. Specifically, the DGC module is designed to capture the spatial functional relationships within the brain by dynamically updating the adjacency matrix during the model training process. Simultaneously, the TSAR module is introduced to emphasize more valuable time segments and extract global temporal features from EEG signals. To fully exploit the interactivity between spatial and temporal information, the hierarchical cross-attention fusion (H-CAF) module is incorporated to fuse the complementary information from spatial and temporal features. Extensive experimental results on the DEAP, SEED, and SEED-IV datasets demonstrate that the proposed method outperforms other state-of-the-art methods.

Multi-Domain Based Dynamic Graph Representation Learning for EEG Emotion Recognition

Graph neural networks (GNNs) have demonstrated efficient processing of graph-structured data, making them a promising method for electroencephalogram (EEG) emotion recognition. However, due to dynamic functional connectivity and nonlinear relationships between brain regions, representing EEG as graph data remains a great challenge. To solve this problem, we proposed a multi-domain based graph representation learning (MD 2GRL) framework to model EEG signals as graph data. Specifically, MD 2GRL leverages gated recurrent units (GRU) and power spectral density (PSD) to construct node features of two subgraphs. Subsequently, the self-attention mechanism is adopted to learn the similarity matrix between nodes and fuse it with the intrinsic spatial matrix of EEG to compute the corresponding adjacency matrix. In addition, we introduced a learnable soft thresholding operator to sparsify the adjacency matrix to reduce noise in the graph structure. In the downstream task, we designed a dual-branch GNN and incorporated spatial asymmetry for graph coarsening. We conducted experiments using the publicly available datasets SEED and DEAP, separately for subject-dependent and subject-independent, to evaluate the performance of our model in emotion classification. Experimental results demonstrated that our method achieved state-of-the-art (SOTA) classification performance in both subject-dependent and subject-independent experiments. Furthermore, the visualization analysis of the learned graph structure reveals EEG channel connections that are significantly related to emotion and suppress irrelevant noise. These findings are consistent with established neuroscience research and demonstrate the potential of our approach in comprehending the neural underpinnings of emotion.

Convolutional neural networks can identify brain interactions involved in decoding spatial auditory attention

Human listeners have the ability to direct their attention to a single speaker in a multi-talker environment. The neural correlates of selective attention can be decoded from a single trial of electroencephalography (EEG) data. In this study, leveraging the source-reconstructed and anatomically-resolved EEG data as inputs, we sought to employ CNN as an interpretable model to uncover task-specific interactions between brain regions, rather than simply to utilize it as a black box decoder. To this end, our CNN model was specifically designed to learn pairwise interaction representations for 10 cortical regions from five-second inputs. By exclusively utilizing these features for decoding, our model was able to attain a median accuracy of 77.56% for within-participant and 65.14% for cross-participant classification. Through ablation analysis together with dissecting the features of the models and applying cluster analysis, we were able to discern the presence of alpha-band-dominated inter-hemisphere interactions, as well as alpha- and beta-band dominant interactions that were either hemisphere-specific or were characterized by a contrasting pattern between the right and left hemispheres. These interactions were more pronounced in parietal and central regions for within-participant decoding, but in parietal, central, and partly frontal regions for cross-participant decoding. These findings demonstrate that our CNN model can effectively utilize features known to be important in auditory attention tasks and suggest that the application of domain knowledge inspired CNNs on source-reconstructed EEG data can offer a novel computational framework for studying task-relevant brain interactions.

MASA-TCN: Multi-Anchor Space-Aware Temporal Convolutional Neural Networks for Continuous and Discrete EEG Emotion Recognition

Emotion recognition from electroencephalogram (EEG) signals is a critical domain in biomedical research with applications ranging from mental disorder regulation to human-computer interaction. In this paper, we address two fundamental aspects of EEG emotion recognition: continuous regression of emotional states and discrete classification of emotions. While classification methods have garnered significant attention, regression methods remain relatively under-explored. To bridge this gap, we introduce MASA-TCN, a novel unified model that leverages the spatial learning capabilities of Temporal Convolutional Networks (TCNs) for EEG emotion regression and classification tasks. The key innovation lies in the introduction of a space-aware temporal layer, which empowers TCN to capture spatial relationships among EEG electrodes, enhancing its ability to discern nuanced emotional states. Additionally, we design a multi-anchor block with attentive fusion, enabling the model to adaptively learn dynamic temporal dependencies within the EEG signals. Experiments on two publicly available datasets show that MASA-TCN achieves higher results than the state-of-the-art methods for both EEG emotion regression and classification tasks.

EEG Emotion Recognition Network Based on Attention and Spatiotemporal Convolution

Human emotions are complex psychological and physiological responses to external stimuli. Correctly identifying and providing feedback on emotions is an important goal in human-computer interaction research. Compared to facial expressions, speech, or other physiological signals, using electroencephalogram (EEG) signals for the task of emotion recognition has advantages in terms of authenticity, objectivity, and high reliability; thus, it is attracting increasing attention from researchers. However, the current methods have significant room for improvement in terms of the combination of information exchange between different brain regions and time-frequency feature extraction. Therefore, this paper proposes an EEG emotion recognition network, namely, self-organized graph pesudo-3D convolution (SOGPCN), based on attention and spatiotemporal convolution. Unlike previous methods that directly construct graph structures for brain channels, the proposed SOGPCN method considers that the spatial relationships between electrodes in each frequency band differ. First, a self-organizing map is constructed for each channel in each frequency band to obtain the 10 most relevant channels to the current channel, and graph convolution is employed to capture the spatial relationships between all channels in the self-organizing map constructed for each channel in each frequency band. Then, pseudo-three-dimensional convolution combined with partial dot product attention is implemented to extract the temporal features of the EEG sequence. Finally, LSTM is employed to learn the contextual information between adjacent time-series data. Subject-dependent and subject-independent experiments are conducted on the SEED dataset to evaluate the performance of the proposed SOGPCN method, which achieves recognition accuracies of 95.26% and 94.22%, respectively, indicating that the proposed method outperforms several baseline methods.

TASA: Temporal Attention With Spatial Autoencoder Network for Odor-Induced Emotion Classification Using EEG

The olfactory system enables humans to smell different odors, which are closely related to emotions. The high temporal resolution and non-invasiveness of Electroencephalogram (EEG) make it suitable to objectively study human preferences for odors. Effectively learning the temporal dynamics and spatial information from EEG is crucial for detecting odor-induced emotional valence. In this paper, we propose a deep learning architecture called Temporal Attention with Spatial Autoencoder Network (TASA) for predicting odor-induced emotions using EEG. TASA consists of a filter-bank layer, a spatial encoder, a time segmentation layer, a Long Short-Term Memory (LSTM) module, a multi-head self-attention (MSA) layer, and a fully connected layer. We improve upon the previous work by utilizing a two-phase learning framework, using the autoencoder module to learn the spatial information among electrodes by reconstructing the given input with a latent representation in the spatial dimension, which aims to minimize information loss compared to spatial filtering with CNN. The second improvement is inspired by the continuous nature of the olfactory process; we propose to use LSTM-MSA in TASA to capture its temporal dynamics by learning the intercorrelation among the time segments of the EEG. TASA is evaluated on an existing olfactory EEG dataset and compared with several existing deep learning architectures to demonstrate its effectiveness in predicting olfactory-triggered emotional responses. Interpretability analyses with DeepLIFT also suggest that TASA learns spatial-spectral features that are relevant to olfactory-induced emotion recognition.

Cross-modal credibility modelling for EEG-based multimodal emotion recognition

Objective.The study of emotion recognition through electroencephalography (EEG) has garnered significant attention recently. Integrating EEG with other peripheral physiological signals may greatly enhance performance in emotion recognition. Nonetheless, existing approaches still suffer from two predominant challenges: modality heterogeneity, stemming from the diverse mechanisms across modalities, and fusion credibility, which arises when one or multiple modalities fail to provide highly credible signals.Approach.In this paper, we introduce a novel multimodal physiological signal fusion model that incorporates both intra-inter modality reconstruction and sequential pattern consistency, thereby ensuring a computable and credible EEG-based multimodal emotion recognition. For the modality heterogeneity issue, we first implement a local self-attention transformer to obtain intra-modal features for each respective modality. Subsequently, we devise a pairwise cross-attention transformer to reveal the inter-modal correlations among different modalities, thereby rendering different modalities compatible and diminishing the heterogeneity concern. For the fusion credibility issue, we introduce the concept of sequential pattern consistency to measure whether different modalities evolve in a consistent way. Specifically, we propose to measure the varying trends of different modalities, and compute the inter-modality consistency scores to ascertain fusion credibility.Main results.We conduct extensive experiments on two benchmarked datasets (DEAP and MAHNOB-HCI) with the subject-dependent paradigm. For the DEAP dataset, our method improves the accuracy by 4.58%, and the F1 score by 0.63%, compared to the state-of-the-art baseline. Similarly, for the MAHNOB-HCI dataset, our method improves the accuracy by 3.97%, and the F1 score by 4.21%. In addition, we gain much insight into the proposed framework through significance test, ablation experiments, confusion matrices and hyperparameter analysis. Consequently, we demonstrate the effectiveness of the proposed credibility modelling through statistical analysis and carefully designed experiments.Significance.All experimental results demonstrate the effectiveness of our proposed architecture and indicate that credibility modelling is essential for multimodal emotion recognition.

Graph Neural Network-Based EEG Classification: A Survey

Graph neural networks (GNN) are increasingly used to classify EEG for tasks such as emotion recognition, motor imagery and neurological diseases and disorders. A wide range of methods have been proposed to design GNN-based classifiers. Therefore, there is a need for a systematic review and categorisation of these approaches. We exhaustively search the published literature on this topic and derive several categories for comparison. These categories highlight the similarities and differences among the methods. The results suggest a prevalence of spectral graph convolutional layers over spatial. Additionally, we identify standard forms of node features, with the most popular being the raw EEG signal and differential entropy. Our results summarise the emerging trends in GNN-based approaches for EEG classification. Finally, we discuss several promising research directions, such as exploring the potential of transfer learning methods and appropriate modelling of cross-frequency interactions.

Exploring Adaptive Graph Topologies and Temporal Graph Networks for EEG-Based Depression Detection

In recent years, Graph Neural Networks (GNNs) based on deep learning techniques have achieved promising results in EEG-based depression detection tasks but still have some limitations. Firstly, most existing GNN-based methods use pre-computed graph adjacency matrices, which ignore the differences in brain networks between individuals. Additionally, methods based on graph-structured data do not consider the temporal dependency information of brain networks. To address these issues, we propose a deep learning algorithm that explores adaptive graph topologies and temporal graph networks for EEG-based depression detection. Specifically, we designed an Adaptive Graph Topology Generation (AGTG) module that can adaptively model the real-time connectivity of the brain networks, revealing differences between individuals. In addition, we designed a Graph Convolutional Gated Recurrent Unit (GCGRU) module to capture the temporal dynamical changes of brain networks. To further explore the differential features between depressed and healthy individuals, we adopt Graph Topology-based Max-Pooling (GTMP) module to extract graph representation vectors accurately. We conduct a comparative analysis with several advanced algorithms on both public and our own datasets. The results reveal that our final model achieves the highest Area Under the Receiver Operating Characteristic Curve (AUROC) on both datasets, with values of 83% and 99%, respectively. Furthermore, we perform extensive validation experiments demonstrating our proposed method's effectiveness and advantages. Finally, we present a comprehensive discussion on the differences in brain networks between healthy and depressed individuals based on the outputs of our final model's AGTG and GTMP modules.

AutoEER: automatic EEG-based emotion recognition with neural architecture search

Objective.Emotion recognition based on electroencephalography (EEG) is garnering increasing attention among researchers due to its wide-ranging applications and the rise of portable devices. Deep learning-based models have demonstrated impressive progress in EEG-based emotion recognition, thanks to their exceptional feature extraction capabilities. However, the manual design of deep networks is time-consuming and labour-intensive. Moreover, the inherent variability of EEG signals necessitates extensive customization of models, exacerbating these challenges. Neural architecture search (NAS) methods can alleviate the need for excessive manual involvement by automatically discovering the optimal network structure for EEG-based emotion recognition.Approach.In this regard, we propose AutoEER (AutomaticEEG-basedEmotionRecognition), a framework that leverages tailored NAS to automatically discover the optimal network structure for EEG-based emotion recognition. We carefully design a customized search space specifically for EEG signals, incorporating operators that effectively capture both temporal and spatial properties of EEG. Additionally, we employ a novel parameterization strategy to derive the optimal network structure from the proposed search space.Main results.Extensive experimentation on emotion classification tasks using two benchmark datasets, DEAP and SEED, has demonstrated that AutoEER outperforms state-of-the-art manual deep and NAS models. Specifically, compared to the optimal model WangNAS on the accuracy (ACC) metric, AutoEER improves its average accuracy on all datasets by 0.93%. Similarly, compared to the optimal model LiNAS on the F1 Ssore (F1) metric, AutoEER improves its average F1 score on all datasets by 4.51%. Furthermore, the architectures generated by AutoEER exhibit superior transferability compared to alternative methods.Significance.AutoEER represents a novel approach to EEG analysis, utilizing a specialized search space to design models tailored to individual subjects. This approach significantly reduces the labour and time costs associated with manual model construction in EEG research, holding great promise for advancing the field and streamlining research practices.

GIGN: Learning Graph-in-graph Representations of EEG Signals for Continuous Emotion Recognition

Effectively learning the spatial topology information of EEG channels as well as the temporal contextual information underlying emotions is crucial for EEG emotion regression tasks. In this paper, we represent EEG signals as spatial graphs in a temporal graph (SGTG). A graph-in-graph neural network (GIGN) is proposed to learn the spatial-temporal information from the proposed SGTG for continuous EEG emotion recognition. A spatial graph neural network (GCN) with a learnable adjacency matrix is utilized to capture the dynamical relations among EEG channels. To learn the temporal contextual information, we propose to use GCN to combine the short-time emotional states of each spatial graph embeddings with the help of a learnable adjacency matrix. Experiments on a public dataset, MAHNOB-HCI, show the proposed GIGN achieves better regression results than recently published methods for the same task. The code of GIGN is available at: https://github.com/yi-ding-cs/GIGN.