Cross-subject EEG emotion recognition is crucial yet challenged by limited fine-grained alignment and label scarcity in Semi-Supervised Domain Adaptation (SSDA). We propose EPM-AAC-TSLA, a framework addressing these issues. The Emotion Pattern Matching (EPM) module uses a bidirectional similarity and diversity-based greedy strategy to aggregate source subjects, effectively mitigating negative transfer. The Adversarial Adaptive Clustering (AAC) module performs robust, cluster-level cross-domain feature alignment. Finally, the Target-aware Source Label Adjustment (TSLA) module refines source knowledge by leveraging scarce target labels. Evaluated in a 3-shot setting on SEED and SEED-IV datasets, EPM-AAC-TSLA achieved peak average accuracies of 94.46% and 85.55%, respectively. These results confirm the framework's effectiveness and superior data efficiency in the few-shot setting for cross-subject EEG-based emotion recognition.

Electroencephalography (EEG) has seen rapidly growing applications in healthcare and brain-computer interfaces, yet cross-subject generalization remains a critical challenge. Unsupervised Domain Adaptation (UDA) techniques are widely employed to mitigate domain shift, but the strong constraints introduced during adaptation often lead to feature space collapse and loss of information. Moreover, relying on empirical risk minimization with cross-entropy (CE) loss fails to effectively prevent such collapse. To address this issue, we propose a novel regularizer, Dynamic Log-Determinant Gating Loss (Dyn-LogDet). This strategy introduces a history-adaptive gating mechanism based on the log-determinant of the feature Gram matrix, such that the penalty is applied only when the current feature diversity drops below a historical baseline. This ultimately contributing to better generalization performance. We validate Dyn-LogDet on two representative categories of UDA approaches: (i) explicit distribution alignment, represented by the maximum mean discrepancy (MMD)-based regularization method, and (ii) adversarial distribution alignment, represented by adversarial learning approaches(ADV), and conduct experiments on the SEED and SEED-IV datasets. In both cases, Dyn-LogDet yields consistent and improvements in performance, demonstrating its efficacy in enhancing cross-subject generalization.

Emotion plays a crucial role in information exchange and decision-making processes. Emotion recognition based on electroencephalography (EEG) captures and analyzes brain electrical activity, effectively reflecting emotional characteristics and providing unique advantages for constructing intelligent emotional systems. However, due to significant differences in feature distribution between the source and target domains, traditional models struggle with generalization in cross-subject tasks. To address this issue, this paper proposes a new model for EEG-based emotion analysis that employs the Pseudo-Label Distance-aware Dual-Classifier (PL-DDC) strategy, which relies on a Residual Temporal-Frequency Analysis (RTFA) structure. We name this model Residual Pseudo-Label Distance-aware Dual-Classifier (RPL-DDC). The RTFA module effectively captures mixed dependencies in complex time-frequency signals, while the PL-DDC strategy introduces a distance loss between the source and target domains. By combining classifier output discrepancies and a pseudo-label mechanism, it progressively reduces the feature distribution gap between the two domains, thereby enhancing the model’s classification performance. Experimental results on the SEED and SEED-IV datasets show that the proposed model achieves accuracy of 89.03% ± 5.03 on the SEED dataset and 75.49% ± 10.44 on the SEED-IV dataset. Compared to traditional baseline models, these results validate the effectiveness of the proposed model in cross-subject emotion recognition.

In recent years, deep learning has exhibited significant prowess in the field of EEG-based affective recognition. The attention mechanism has always been a focal point of interest within the domain of deep learning. However, existing EEG analysis techniques still face challenges in accurately pinpointing emotion-related signals across both spatial and temporal scales. We propose a novel model, named MDAC, which is based on a multi-scale dual attention and a capsule network tuned for EEG data, to address the aforementioned issue. Initially, the MDA module applies varying scales of perceptual fields to the data and integrates them to simultaneously obtain attention weights at the pixel level and the sampling rate level, achieving precise weighting of EEG signals in both spatial and temporal resolutions. Furthermore, we have increased the number of convolutional channels and the dimensionality of the primary capsules in CapsNet to better align with the characteristics of EEG data, proposing a structural configuration more apt for EEG-based affective recognition. We conducted subject-dependent and subject-independent experiments on the DEAP dataset to validate our model. In the subject-dependent experiments, the accuracy rates for both the valence and arousal dimensions were 99.58%. In the subject-independent experiments, the accuracy rates for the valence and arousal dimensions were 98.15% and 98.04%, respectively. The experimental results corroborate the efficacy of the method we proposed in this paper for the task of emotion recognition.

Emotion recognition from electroencephalogram (EEG) signals is a key application in brain-computer interfaces (BCIs), but the high dimensionality and noise in EEG data pose significant challenges. Many existing approaches fail to adequately filter irrelevant information or fully capture complex inter-channel relationships and temporal dynamics, leading to suboptimal emotional representation.To address these challenges, we propose ST-GCN, a novel model that integrates spectral and temporal domain features using graph convolution for robust EEG emotion recognition. ST-GCN employs a channel information reconstruction layer, channel aggregation, and temporal feature extraction to learn discriminative representations across EEG channels and time. Evaluated on the DEAP dataset with a cross-validation setup, ST-GCN achieves state-of-the-art performance, with 98.43% accuracy for valence and 98.69% for arousal, demonstrating its effectiveness in EEG-based emotion recognition.