Search Results (49)

Emotion recognition plays a crucial role in human–computer interaction and mental health applications. Traditional Electroencephalogram (EEG)-based emotion recognition methods are limited in classification accuracy due to their neglect of the spatiotemporal characteristics of the signals and individual differences. This study proposes a novel EEG emotion recognition framework that integrates spatiotemporal features to enhance performance through the following innovations: (1) the use of a Recurrence Plot (RP) to transform one-dimensional EEG signals into two-dimensional images, enhancing the representation of nonlinear dynamic features; (2) the design of a Spatiotemporal Channel Attention Module (TCSA), which combines temporal convolution, channel, and spatial attention mechanisms to optimize the capture of complex patterns; and (3) the integration of the lightweight and efficient network Efficientnet to construct the TCSA-Efficientnet classification model. On the Database for Emotion Analysis using Physiological Signals (DEAP) dataset, the proposed method achieves accuracy rates of 99.11% and 99.33% for valence and arousal classification tasks, respectively. On the Database for Emotion Recognition Using EEG and Physiological Signals (DREAMER) dataset, the method achieves accuracy rates of 98.08% and 97.49%, outperforming other EEG-based emotion classification models on both datasets. This demonstrates its advantages in accuracy, robustness, and generalization. Full article

Background/Objectives: Lucid dreaming—dreaming with the awareness that one is dreaming—has been explored from many perspectives, including those of cognitive neuroscience and various ancient cultural traditions. Lucid dreaming appears within the Tibetan-Buddhist literature together with dream yoga, a set of contemplative practices aimed at cultivating lucidity during dreams along with other qualities such as visual imagination, somatic awareness, and cognitive flexibility. These practices include deity visualization, which is the practice of bringing to mind a detailed image of a being whose qualities the practitioner wishes to cultivate. We examined whether it is possible to induce a lucid dream of Chenrezig, the ultimate embodiment of compassion in a Tibetan-Buddhist context. Methods: Five participants slept in the sleep laboratory for 7 overnight sessions with polysomnographic recording and auditory reminders to visualize Chenrezig during REM sleep. Results: Lucid dreams were reported by two participants. A frequent lucid dreamer with no prior Tibetan-Buddhist training experienced a lucid dream that included a visualization of Chenrezig following auditory cueing during REM sleep. A monastic participant with no prior history of lucid dreaming reported their first-ever lucid dream on the night following their laboratory session. Conclusions: This exploratory study illustrates, via collaborative research including monastic scholars trained in neuroscience, that dream content can be intentionally shaped using an approach that integrates contemplative visualization practices with modern techniques of dream engineering. Full article

To investigate the regulatory effects of emotional states on the evolution of fatigue in metro drivers, this study conducts an experimental investigation based on an urban rail transit driving simulation platform. A total of 21 participants complete a 90 min simulated driving task, during which electroencephalogram (EEG) and electrocardiogram (ECG) signals are synchronously collected from drivers for fatigue assessment and emotion recognition, respectively. An emotion recognition model based on a multi-scale convolutional neural network (MSCNN) combined with an attention mechanism is constructed. The proposed model uses ECG signals to classify three emotional states—neutral, positive, and negative—where the neutral state is defined as an emotionally undefined baseline that is neither positive nor negative. The model achieves a classification accuracy of 86.96% on the DREAMER dataset. By temporally aligning the emotion recognition results with EEG frequency-domain fatigue indicators, the results show that fatigue exhibits the highest growth and largest fluctuation in amplitude under negative emotions, demonstrating a pronounced fatigue-accelerating effect. Under positive emotions, fatigue decreases considerably and has smaller fluctuations, indicating a certain buffering and restorative effect. In contrast, the neutral emotional state exhibits intermediate and transitional fatigue characteristics. This study innovatively integrates ECG-based emotion recognition with EEG-based fatigue assessment to reveal the mechanisms based on which emotions influence fatigue in metro driving tasks from a physiological perspective. This work provides a basis for emotion-aware fatigue monitoring and safety intervention strategies. Full article

Cross-subject emotion recognition using EEG remains challenging due to substantial inter-individual variability. To address this, we propose a Multi-scale Spatio-Temporal Convolution and Multi-order Gated Spatial-Channel Aggregation Network (MCF-SCA). The model leverages multi-scale spatio-temporal convolution to capture rich temporal and spatial features and applies Fast Fourier Transform to transform EEG signals into the frequency domain, enhancing emotion-related representations. A multi-order spatial-channel aggregation module is then introduced, which adaptively integrates features across spatial and channel dimensions through a gating mechanism, enabling dynamic feature weighting and more expressive emotional representations. Experiments on the DEAP dataset show accuracy gains of up to 11–30% for arousal and 12–31% for valence compared with TSception, CNN, LSTM, EEGNet, and MLP. On the DREAMER dataset, improvements reach 5–33% and 3.7–34%, respectively. These results confirm that MCF-SCA achieves superior accuracy and cross-subject adaptability, providing strong support for emotion-based brain–computer interface applications. Full article

Emotions are classified into the valence dimension (positive and negative) and the arousal dimension (low and high). Using electrocardiogram (ECG) phase space diagrams and a deep learning approach, emotional states were identified in this study. The DREAMER database was utilized for training and testing the classification model developed. We examined different ECG phase space parameters and compared different deep learning models, including the Visual Geometry Group and Residual networks, and a simple convolutional neural network (CNN) with attention modules. Among the models, a simple four-layer CNN integrated with a convolutional block attention module showed the best performance. Experimental results indicate that the model achieved an accuracy of 87.89% for the valence dimension and 91.79% for the arousal dimension. Compared with existing models, the developed model demonstrates superior performance in emotion recognition. Emotional changes produce noticeable variations in the trajectory patterns of ECG phase space diagrams, which enhance the model’s ability to recognize emotions, even when using relatively simple networks. Full article

Affective computing has emerged as a pivotal field in human–computer interaction. Recognizing human emotions through electroencephalogram (EEG) signals can advance our understanding of cognition and support healthcare. This study introduces a novel subject-independent emotion recognition framework by integrating multiple EEG emotion databases (DEAP, MAHNOB HCI-Tagging, DREAMER, AMIGOS and REFED) into a unified dataset. EEG segments were transformed into feature vectors capturing statistical, spectral, and entropy-based measures. Standardized pre-processing, analysis of variance (ANOVA) F-test feature selection, and six machine learning models were applied to the extracted features. Classification models such as Decision Tree, Discriminant Analysis, Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Naive Bayes, and Artificial Neural Networks (ANN) were considered. Experimental results demonstrate that SVM achieved the best performance for arousal classification (70.43%), while ANN achieved the highest accuracy for valence classification (68.07%), with both models exhibiting strong generalization across subjects. The results highlight the feasibility of developing biomimetic brain–computer interface (BCI) systems for objective assessment of emotional intelligence and its cognitive underpinnings, enabling scalable applications in affective computing and adaptive human–machine interaction. Full article

Background: Studies on the organization and structure of dreams before and after acute myocardial infarction (AMI) are lacking. Methods: We retrospectively studied dream patterns before and after AMI in the STEP-IN-AMI trial (Short-TErm Psychotherapy IN Acute Myocardial Infarction). We also performed an analysis to describe how this pattern may change during ontopsychological short-term psychotherapy (STP) performed after AMI. Forty-seven patients (pts) aged 31–70 were studied. Results: At baseline, 21/47 (45%) pts remembered dreams, which increased to 43/47 (91%) with psychotherapy (p < 0.0001). Recurring dreams, described as a state of anguish, despair, perceived inability to complete an action, or grief over one’s mother’s early death, occurred before AMI in 16/47 pts (24%). After the third psychotherapy session, no pts reported recurring dreams (p < 0.001). In dreams that occurred during the year before AMI, 12 of 25 symbols referred to people known to pts and who had died of a cardiac disease; 9 of 25 symbols referred to an accident, danger, or distressing events. Overall, 21 of 25 symbols were associated with danger to an individual’s life (84%). The incidence of “negative” symbols was sharply reduced during psychotherapy, from 84% to 32% during the first three psychotherapy sessions and to 9% in the last phase of psychotherapy (p < 0.0001). Conclusions: Our study is the very first on dreams in pts with AMI, and it also examines how STP may change dream patterns in this cohort of pts. AMI pts frequently do not remember dreams that occurred before AMI or report distressing dreams. STP after AMI significantly increased their ability to remember dreams and sharply reduced the incidence of negative/distressing dreams. The results suggest that (1) dream symbols may be connected to the biological status of the dreamer, warning the dreamer of their cardiac condition; (2) ontopsychological STP may act as a stimulus for inner personal change for AMI pts. Full article

This study proposes 4D-MRSimNet, a framework that employs attention mechanisms to focus on distinct dimensions. The approach applies enhancements to key responses in the spatial and spectral domains and provides a characterization of dynamic evolution in temporal domain, which extracts and integrates complementary emotional features to facilitate final classification. At the feature level, differential entropy (DE) and power spectral density (PSD) are combined within four core frequency bands ($\theta$, $\alpha$, $\beta$, and $\gamma$). These bands are recognized as closely related to emotional processing. This integration constructs a complementary feature representation that preserves both energy distribution and entropy variability. These features are organized into a 4D representation that integrates electrode topology, frequency characteristics, and temporal dependencies inherent in EEG signals. At the network level, a multi-resolution convolutional module embedded with SimAM attention extracts spatial and spectral features at different scales and adaptively emphasizes key information. A bidirectional GRU (BiGRU) integrated with temporal attention further emphasizes critical time segments and strengthens the modeling of temporal dependencies. Experiments show that our method achieves an accuracy of 97.68% for valence and 97.61% for arousal on the DEAP dataset and 99.60% for valence and 99.46% for arousal on the DREAMER dataset. The results demonstrate the effectiveness of complementary feature fusion, multidimensional feature representation, and the complementary dual attention enhancement strategy for EEG emotion recognition. Full article

This essay argues that Jeremy Bentham’s experience of the 1780 Gordon Riots and 1787 sojourn to White Russia inspired his conception of several projects for managing unruly populations. Bentham’s devotion to speculative enterprise informs his Defence of Usury, which vindicates schemers and dreamers from the criticism of Adam Smith, whose Wealth of Nations caricatured projectors as “riotous” con-artists who threatened domestic peace. Bentham’s Defence, I show, resuscitated early modern debates over the efficacy of free-lance enterprise to authorize his own efforts to improve society. A projector and theorist of projection, Bentham reveals how residents of the late eighteenth century described riot so that they could suppress it. Full article

Objective. Consumer-grade EEG devices have the potential for widespread brain–computer interface deployment but pose significant challenges for emotion recognition due to reduced spatial coverage and the variable signal quality encountered in uncontrolled deployment environments. While deep learning approaches have employed increasingly complex architectures, their efficacy in noisy consumer-grade signals and cross-system generalizability remains unexplored. We present a comprehensive systematic comparison of EEGNet architecture, which has become a benchmark model for consumer-grade EEG analysis versus traditional machine learning, examining when and why domain-specific feature engineering outperforms end-to-end learning in resource constrained scenarios. Approach. We conducted comprehensive within-dataset evaluation using the DREAMER dataset (23 subjects, Emotiv EPOC 14-channel) and challenging cross-dataset validation (DREAMER→SEED-VII transfer). Traditional ML employed domain-specific feature engineering (statistical, frequency-domain, and connectivity features) with random forest classification. Deep learning employed both optimized and enhanced EEGNet architectures, specifically designed for low channel consumer EEG systems. For cross-dataset validation, we implemented progressive domain adaptation combining anatomical channel mapping, CORAL adaptation, and TCA subspace learning. Statistical validation included 345 comprehensive evaluations with fivefold cross-validation × 3 seeds × 23 subjects, Wilcoxon signed-rank tests, and Cohen’s d effect size calculations. Main results. Traditional ML achieved superior within-dataset performance (F1 = 0.945 ± 0.034 versus 0.567 for EEGNet architectures, p < 0.000001, Cohen’s d = 3.863, 67% improvement) across 345 evaluations. Cross-dataset validation demonstrated good performance (F1 = 0.619 versus 0.007) through systematic domain adaptation. Progressive improvements included anatomical channel mapping (5.8× improvement), CORAL domain adaptation (2.7× improvement), and TCA subspace learning (4.5× improvement). Feature analysis revealed inter-channel connectivity patterns contributed 61% of the discriminative power. Traditional ML demonstrated superior computational efficiency (95% faster training, 10× faster inference) and excellent stability (CV = 0.036). Fairness validation experiments supported the advantage of traditional ML in its ability to persist even with minimal feature engineering (F1 = 0.842 vs. 0.646 for enhanced EEGNet), and robustness analysis revealed that deep learning degrades more under consumer-grade noise conditions (17% vs. <1% degradation). Significance. These findings challenge the assumption that architectural complexity universally improves biosignal processing performance in consumer-grade applications. Through the comparison of traditional ML against the EEGNet consumer-grade architecture, we highlight the potential that domain-specific feature engineering and lightweight adaptation techniques can provide superior accuracy, stability, and practical deployment capabilities for consumer-grade EEG emotion recognition. While our empirical comparison focused on EEGNet, the underlying principles regarding data efficiency, noise robustness, and the value of domain expertise could extend to comparisons with other complex architectures facing similar constraints in further research. This comprehensive domain adaptation framework enables robust cross-system deployment, addressing critical gaps in real-world BCI applications. Full article

Autonomous racing serves as a challenging testbed that exposes the limitations of perception-decision-control algorithms in extreme high-speed environments, revealing safety gaps not addressed in existing autonomous driving research. However, traditional control techniques (e.g., FGM and MPC) and reinforcement learning-based approaches (including model-free and Dreamer variants) struggle to simultaneously satisfy sample efficiency, prediction reliability, and real-time control performance, making them difficult to apply in actual high-speed racing environments. To address these challenges, we propose LiDAR Dreamer, a novel world model specialized for LiDAR sensor data. LiDAR Dreamer introduces three core techniques: (1) efficient point cloud preprocessing and encoding via Cartesian Polar Bar Charts, (2) Light Structured State-Space Cells (LS3C) that reduce RSSM parameters by 14.2% while preserving key dynamic information, and (3) a Displacement Covariance Distance divergence function, which enhances both learning stability and expressiveness. Experiments in PyBullet F1TENTH simulation environments demonstrate that LiDAR Dreamer achieves competitive performance across different track complexities. On the Austria track with complex corners, it reaches 90% of DreamerV3’s performance (1.14 vs. 1.27 progress) while using 81.7% fewer parameters. On the simpler Columbia track, while model-free methods achieve higher absolute performance, LiDAR Dreamer shows improved sample efficiency compared to baseline Dreamer models, converging faster to stable performance. The Treitlstrasse environment results demonstrate comparable performance to baseline methods. Furthermore, beyond the 14.2% RSSM parameter reduction, reward loss converged more stably without spikes, improving overall training efficiency and stability. Full article

Background/Objectives: Lucid dreaming (LD), during which the dreamer becomes aware of the dream state, offers a unique opportunity for a variety of applications, including motor practice, personal well-being, and nightmare therapy. However, these applications largely depend on the dreamer’s ability to control their dreams. While LD research has traditionally focused on induction techniques to increase dream frequency, the equally important skill of dream control remains largely underexplored. This study provides an exploration into the mechanisms of LD motor practice, dream control, and its potential influencing factors. We specifically examined whether a complex motor skill—juggling—could be performed during LD, calling for relatively high levels of dream control and access to procedural memory. Methods: Four healthy participants underwent overnight polysomnography (PSG), provided detailed dream reports, and completed questionnaires assessing dream control and self-efficacy. Dream-task success was assessed using predefined in-dream motor performance criteria. Differences between high and low LD control participants were examined, and two detailed case reports of lucid dream juggling attempts provide insight into the challenges of executing complex motor tasks during LD. Results: Dream control varied between and within participants. Both dream control and self-efficacy seemed to predict participants’ ability to execute the LD motor task. Conclusions: Despite the low sample size, this study highlights the potential roles of individual traits like self-efficacy in shaping dream control abilities and motor performance during LD. By using empirical, task-based measures, this study helps build the foundation for future research aimed at optimizing LD applications in clinical and non-clinical fields. Full article

Sleep paralysis (SP), an REM parasomnia, can be characterized as one of the symptoms of narcolepsy. The SP phenomenon involves regaining meta-consciousness by the dreamer during REM, when the physiological atonia of skeletal muscles is accompanied by visual and auditory hallucinations that are perceived as vivid and distressing nightmares. Sensory impressions include personification of an unknown presence, strong chest pressure sensation, and intense fear resulting from subjective interaction with the unfolding nightmare. While the mechanism underlying skeletal muscle atonia is known, the physiology of hallucinations remains unclear. Their complex etiology involves interactions among various membrane receptor systems and neurotransmitters, which leads to altered neuronal functionality and disruptions in sensory perception. According to current knowledge, serotonergic activation of 5-hydroxytryptamine-receptor-2A (5-HT2A)-associated pathways plays a critical role in promoting hallucinogenesis during SP. Furthermore, they share similarities with psychedelic-substance-induced ones (i.e., LSD, psilocybin, and 2,5-dimethoxy-4-iodoamphetamine). These compounds also target the 5-HT2A receptor; however, their molecular mechanism varies from serotonin-induced ones. The current review discusses the intracellular signaling pathways responsible for promoting hallucinations in SP, highlighting the critical role of β-arrestin-2. We propose that the β-arrestin-2 signaling pathway does not directly induce hallucinations but creates a state of network susceptibility that facilitates their abrupt emergence in sensory areas. Understanding the molecular basis of serotonergic hallucinations and gaining better insight into 5-HT2A-receptor-dependent pathways may prove crucial in the treatment of multifactorial neuropsychiatric disorders associated with the dysfunctional activity of serotonin receptors. Full article

EEG-based emotion recognition (EEG-ER) through deep learning models has gained more attention in recent years, with more researchers focusing on architecture, feature extraction, and generalisability. This paper presents a novel end-to-end deep learning framework for EEG-ER, combining temporal feature extraction, self-attention mechanisms, and adversarial domain adaptation. The architecture entails a multi-stage 1D CNN for spatiotemporal features from raw EEG signals, followed by a transformer-based attention module for long-range dependencies, and a domain-adversarial neural network (DANN) module with gradient reversal to enable a powerful subject-independent generalisation by learning domain-invariant features. Experiments on benchmark datasets (DEAP, SEED, DREAMER) demonstrate that our approach achieves a state-of-the-art performance, with a significant improvement in cross-subject recognition accuracy compared to non-adaptive frameworks. The architecture tackles key challenges in EEG emotion recognition, including generalisability, inter-subject variability, and temporal dynamics modelling. The results highlight the effectiveness of combining convolutional feature learning with adversarial domain adaptation for robust EEG-ER. Full article

In the current context, the use of technologies in applications for multimodal dialogue systems with computers and emotion recognition through artificial intelligence continues to grow rapidly. Consequently, it is challenging for researchers to identify gaps, propose new models, and increase user satisfaction. The objective of this study is to explore and analyze potential applications based on artificial intelligence for multimodal dialogue systems incorporating emotion recognition. The methodology used in selecting papers is in accordance with PRISMA and identifies 13 scientific articles whose research proposals are generally focused on convolutional neural networks (CNNs), Long Short-Term Memory (LSTM), GRU, and BERT. The research results identify the proposed models as Mindlink-Eumpy, RHPRnet, Emo Fu-Sense, 3FACRNNN, H-MMER, TMID, DKMD, and MatCR. The datasets used are DEAP, MAHNOB-HCI, SEED-IV, SEDD-V, AMIGOS, and DREAMER. In addition, the metrics achieved by the models are presented. It is concluded that emotion recognition models such as Emo Fu-Sense, 3FACRNNN, and H-MMER obtain outstanding results, with their accuracy ranging from 92.62% to 98.19%, and multimodal dialogue models such as TMID and the scene-aware model with BLEU4 metrics obtain values of 51.59% and 29%, respectively. Full article