Search Results (394)

Quantitative EEG features such as frontal alpha asymmetry, spectral ratios and signal-complexity measures are often presented as interpretable biomarkers of emotion. Such claims require the markers to generalize across individuals, yet common evaluation protocols allow overlapping epochs and recordings from the same participants to appear in both training and test sets. We re-evaluated qEEG-based valence and arousal recognition on DEAP and DREAMER under trial-grouped, participant-independent, within-participant and cross-dataset protocols. Epoch-pooled evaluation on DEAP gave ROC-AUC values of 0.689 for valence and 0.711 for arousal, whereas participant-independent evaluation of the same features and model returned 0.493 and 0.447. Grouping epochs by trial accounted for about 0.06 of that difference and separating participants for a further 0.13 to 0.17. The same features identified participants with accuracy of 0.998 on DEAP and 0.891 on DREAMER, and a predictor that used no EEG, assigning each trial its participant’s training-set positive rate, accounted for 42 to 84 percent of the above-chance discrimination of the epoch-pooled model. Emotion-related effects were reproducible within participants on DEAP but close to zero on DREAMER, and their direction reversed for about 40 percent of features across participants. In a matched participant-level comparison using a single fixed estimator in both arms, training on a participant’s own data improved DEAP valence by 0.092 AUC (95% CI 0.029 to 0.157, Holm-adjusted $p=0.042$) and gave no reliable benefit for DEAP arousal or for either DREAMER target. Across the channels shared by the two datasets, per-feature arousal effect sizes correlated moderately, although no individual feature reached false-discovery-rate significance in both datasets. Pooled qEEG emotion-recognition scores can therefore reflect participant-specific recording structure rather than transferable affective information. Population-level claims require participant-independent evaluation, while personalization should be considered only where stable within-person effects are demonstrated. Full article

Music is used during exercise to enhance psychological and physiological responses, including increased motivation, improved affective valence, optimized arousal, and reduced perceived exertion. Although researchers have identified several musical elements that may moderate these effects, the contribution of lyrics remains poorly understood. The present study examined the effects of lyrics on motivation, affective valence, arousal, and perceived exertion during moderate-intensity cycling. Thirty college students (M_age = 21.0 ± 2.9 years) completed 8-min bouts of moderate-intensity cycling under three counterbalanced conditions: music with lyrics (ML), music without lyrics (MNL; an instrumental version of the same track), and a no-music metronome control (MC). Motivation, affective valence, arousal, and perceived exertion were sampled at the end of a 6-min warm-up and at four in-task time points (8, 10, 12, and 14 min). Both music conditions produced significantly higher motivation, affective valence, and arousal than the metronome control at the in-task time points (8–14 min), with no differences between ML and MNL at any time point. Significant Condition × Time interactions indicate that these condition differences did not apply uniformly across the analytic window. Perceived exertion increased over time but did not differ across conditions. Under these specific conditions (a single, highly familiar popular track, an 8-min moderate-intensity cycling bout, and a metronome overlaid across all conditions), no additional psychological benefit of lyrical content was detected beyond that provided by the music itself. These results should not be generalized as evidence that lyrics have no effect on exercise-related psychological responses. Full article

Virtual reality (VR) survival horror is often discussed in terms of heightened fear and immersion, yet less attention has been paid to how fear is organized across different atmospheric conditions and how this organization differs from non-VR gameplay. This study approaches immersive fear as a process emerging from the interaction among atmospheric configuration, embodied regulation, and post-play interpretation. A sequential mixed-methods design was employed using Resident Evil Village as the empirical context. Study 1 combined scene-based observation, synchronized gameplay recordings, and post-play interviews with eight participants to examine how fear was enacted across three contrasted atmospheric configurations: combat pressure, psychological ambiguity, and spatial disorientation. Study 2 extended this analysis through a within-subject experiment with 30 participants who completed both VR and non-VR versions of the same gameplay content under standardized conditions. The findings show that immersive fear is not a uniform increase in emotional intensity. In Study 1, different atmospheric configurations elicited distinct modes of embodied regulation, including defensive retreat, hesitant exposure, and cautious reorientation, while behavioral responses and retrospective accounts often diverged in systematic ways. In Study 2, paired-samples tests showed that VR produced lower valence, higher arousal, reduced perceived control, higher fear ratings, stronger immersion, and greater motion sickness than non-VR gameplay. Although VR increased fear ratings across all scenes, the display mode × scene interaction was not significant; descriptively, psychologically ambiguous environments produced the highest absolute fear ratings under VR. Across both studies, prior VR and genre experience appeared to shape how players interpreted and narrated threat, while short-term residual effects suggested that fear may extend beyond gameplay. These results suggest that VR modifies not only the intensity but also the organization of fear, while the scene-level and experience-related patterns should be interpreted cautiously. More broadly, the study reframes immersive fear as a temporally distributed process linking atmospheric configuration, embodied regulation, and post-play interpretation in survival horror gameplay. Full article

Although electroencephalography (EEG)-based emotion recognition is a promising approach for affective brain–computer interface (BCI) applications, substantial inter-subject variability continues to limit its generalizability. This study proposed an EEG-based framework to recognize emotions within a valence–arousal model using auditory stimulation. Predefined emotional states were established using validated affective video clips and subsequently evaluated through EEG responses elicited by instrumental melodies. Three EEG features, which include discrete wavelet transform (DWT), functional connectivity (FC), and effective connectivity (EC), together with their combined feature set, were systematically evaluated using five machine learning classifiers. Performance was assessed under subject-dependent, subject-independent (leave-one-subject-out, LOSO), and few-shot subject-adaptation protocols. The results showed that DWT achieved the highest subject-dependent classification accuracy (0.88), followed by the combined feature set (0.84). In contrast, the subject-independent LOSO evaluation yielded near-chance performance across all feature domains (0.23–0.30), highlighting substantial inter-subject variability. Few-shot subject adaptation using 25–75% subject-specific calibration data substantially improved subject-independent performance, with the highest accuracy of 0.77 achieved by FC at 75% calibration. In conclusion, these findings demonstrate the feasibility of EEG-based emotion recognition using auditory stimulation under predefined affective conditions and provide a foundation for the future development of personalized affective brain–computer interface systems. Full article

Electroencephalography (EEG)-based emotion recognition is an important biosensing technique for affective brain-computer interfaces (BCIs), mental-state assessment, and physiological monitoring. Existing methods often rely on a single spectral descriptor or regular two-dimensional brain maps, which makes it difficult to jointly model local spatial representations, global spatial relations, and temporal dynamics. This paper proposes GLSTNet, a global-local spatial relations and temporal dynamics network for EEG emotion recognition. EEG trials are divided into short windows, from which multi-band spectral features are extracted and arranged into compact spatial maps. The local spatial encoder (LSE) learns local spatial and spatial–spectral representations from these compact multi-band spatial maps. The global spatial-relation encoder (GSRE) models long-range spatial relations between non-adjacent electrodes using a Pearson correlation prior and a learnable residual adjacency matrix. After local and global representations are integrated through gated fusion, the temporal dynamics encoder (TDE) models consecutive EEG windows using a gated recurrent unit with temporal attention. Comprehensive validation is conducted on two public EEG emotion datasets, the Database for Emotion Analysis using Physiological Signals (DEAP) and the SJTU Emotion EEG Dataset (SEED). In the subject-dependence setting, GLSTNet achieves 93.50 ± 3.22% accuracy for valence and 93.79 ± 3.64% accuracy for arousal on DEAP, and 92.48 ± 3.30% accuracy on SEED. In the subject-independence setting with target-subject calibration, GLSTNet obtains 75.61 ± 6.19% and 79.57 ± 5.99% accuracy for DEAP valence and arousal, respectively, and 88.22 ± 4.70% accuracy on SEED. These results indicate that integrating global-local spatial relations with temporal dynamics provides an effective representation strategy for EEG-based emotion recognition. Full article

Wearable and intelligent bioelectronic systems are emerging as a key enabling technology for continuous, non-invasive health monitoring, coupling physiological sensing with data-driven inference. Within this paradigm, electroencephalography (EEG) provides a wearable-compatible biosensing modality for capturing the pre-sleep neurophysiological dynamics linked to emotional regulation and sleep onset. Insomnia affects approximately 10–15% of adults worldwide and is often associated with dysregulated emotions and pre-sleep hyperarousal. Existing EEG-based affective and sleep-onset processing pipelines often rely either on deep-learning architectures with limited interpretability or on hand-crafted spectral descriptors with weak theoretical motivation. This study presents an exploratory proof-of-principle bioelectronic processing framework in which EEG sensing features are organized according to ANT-7 (artificial neurotransmitter seven-dimensional model), a neurotransmitter-inspired computational taxonomy introduced as a heuristic feature-design prior rather than as a validated neurochemical theory. The proposed feature set includes the alpha/theta power ratio, sample entropy, Higuchi fractal dimension, and phase-locking value extracted from the public DREAMER and DEAP datasets (23 and 32 subjects, respectively). SVM, Random Forest, and 1D-CNN classifiers are trained under subject-independent leave-one-subject-out cross-validation with strict within-fold normalization to prevent data leakage, and interpretability is assessed through SHAP values and permutation importance (PI). To stress-test whether this feature organization transfers beyond the affective benchmarks on which it is trained, classifier outputs are then related to sleep-onset latency in Sleep-EDF Expanded through a deliberately cautious cross-dataset transfer analysis. Within this protocol, the best model reaches 88.4% accuracy in three-class affective-state recognition (stress/neutral/relaxed; AUC-ROC = 0.93). As an exploratory secondary analysis, classifier-derived relaxation estimates show a statistically significant negative association with polysomnographic sleep-onset latency and improve over a single alpha/theta-ratio baseline; this cross-dataset result is reported as a proof of concept, not as a validated sleep-onset predictor. Interpretability analyses (SHAP and permutation importance) indicate that the learned feature rankings are internally consistent with the neurotransmitter-inspired feature design, a property we interpret as internal coherence rather than as independent confirmation of the taxonomy. Together, these elements outline a complete sensor-to-AI processing chain—from EEG biosensing, through neurotransmitter-inspired signal-feature extraction, to interpretable and computationally lightweight inference—designed for compatibility with low-density wearable EEG devices and edge deployment. However, EEG does not measure neurotransmitter concentrations, the study does not benchmark ANT-7 directly against competing taxonomies such as valence-arousal/circumplex or RDoC-inspired feature organizations, and the Sleep-EDF analysis should not be interpreted as evidence that the model measures a validated latent construct of sleep readiness. Accordingly, the manuscript should be read as a framework-validation study of one interpretable feature taxonomy, not as a theory-validation study of ANT-7 or as a clinical validation study. Full article

Redundant channels, sparse electrode topology, and insufficient cross-layer feature fusion limit electroencephalography (EEG)-based emotion recognition. This study proposes the Topology-Aware Dual-Bridge Fusion Network (TDBF-Net), a compact framework that integrates adaptive channel selection, topology-aware sparse convolution, and bidirectional bridge fusion. First, sample entropy, dispersion entropy, and fuzzy entropy are fused to estimate channel importance, while particle swarm optimization (PSO) learns the entropy weights and an elbow-based criterion determines the retained channel subset. Second, differential entropy (DE) features from the $\theta$, $\alpha$, $\beta$, and $\gamma$ bands are mapped to an $8\times 9$ sparse topological tensor according to electrode locations. A fixed spatial validity mask is applied before and after convolution to suppress invalid responses from zero-padded regions and preserve real electrode topology. Third, a dual-bridge fusion module recalibrates shallow and deep features in both directions through channel attention and gated fusion, and a bidirectional long short-term memory network (BiLSTM) further captures short-term temporal dependencies. Subject-dependent experiments on the SJTU Emotion EEG Dataset (SEED) and the Database for Emotion Analysis using Physiological Signals (DEAP) show that TDBF-Net achieves $97.62\%$ ± $1.59\%$ accuracy on SEED and $98.46\%$ ± $0.94\%$ and $98.14\%$ ± $0.77\%$ on DEAP valence and arousal, respectively. Paired DEAP ablations support topology and bridge contributions for valence, whereas the corresponding arousal differences are not significant. Selector controls, robustness tests, computational profiling, and held-out visualizations further characterize the method’s compression, cost, and interpretability. The evidence supports TDBF-Net as an effective subject-dependent framework while leaving subject-independent and cross-dataset generalization for future validation. Full article

In this paper we study how external affective information should be integrated into a compact transformer-based text classifier. Rather than treating affective features as signals to be appended directly to the representation, we examine whether their contribution should be controlled through lightweight fusion mechanisms. The comparison focuses on scalar-gated fusion versus plain concatenation, using DistilBERT as the textual backbone and four affective resources: the NRC VAD Lexicon, VAD-BERT, Ekman-style emotion scores, and SenticNet. The evaluation is conducted on two English corpora with different label structures: a seven-class MentalHealth dataset and the fine-grained GoEmotions benchmark. Across both corpora, scalar gating consistently matches or outperforms concatenation in terms of Macro-F1. On MentalHealth, scalar gating improves all directly comparable configurations. On GoEmotions, it achieves the best overall Macro-F1 and improves most matched comparisons. Beyond static feature integration, we introduce affective flow (EmoFlow) representations derived from VAD-BERT, which model the evolution of valence, arousal, and dominance across segments of a text. These dynamic representations do not surpass the strongest static lexical resources in absolute performance, but they provide consistent improvements within the VAD-BERT family, particularly when combined with scalar gating or cross-attention. Our contribution is twofold. First, we show that a lightweight scalar gate provides an effective and interpretable mechanism for adaptively integrating low-dimensional affective side information into transformer-based classifiers. Second, we introduce affective flow representations that explicitly model how affect evolves within a document, enabling the analysis of both adaptive resource selection and intra-document affective dynamics. Together, these results suggest that the key issue is not only which affective resources to use, but also when and how they should influence the model. Full article

Background/Objectives: Electroencephalography (EEG) is widely applied in emotion recognition. Integrating diverse frequency and spatial features to improve performance remains a major challenge. Methods: This paper proposes two preprocessing methods to map EEG signals into image-style representations. These methods preserve the spatial topology and enable effective feature extraction using convolutional neural networks. The first method is a spatial concatenation method (SCM). It projects three feature types onto color channels, providing a structural prior that encourages the network to learn the three feature types within local spatial windows. It differs from traditional spectral mixing, which maps frequency bands to color channels. The second method is a band-wise stacking method (BSM). It treats frequency bands as independent depth frames to form a three-dimensional tensor. This structure is designed to facilitate the learning of inter-band relationships while preserving band-specific information. Dedicated convolutional neural network architectures are designed for these tensor structures, aligned with the spatial and spectral organization of the proposed SCM and BSM. Results: Experiments on the DEAP and DREAMER datasets for binary Arousal and Valence classification show that both representations achieve competitive results. The BSM achieves higher accuracy than the SCM on the DREAMER dataset, while both methods perform comparably on the DEAP dataset. Conclusions: The proposed strategies offer efficient convolutional neural network approaches for EEG emotion recognition systems. Full article

Understanding the neural dynamics underlying expressive musical performance remains a major challenge at the intersection of neuroscience, music cognition, and computational modeling. While Electroencephalogram (EEG) studies of emotion have largely focused on passive exposure to affective stimuli, comparatively little research has examined oscillatory brain activity during active musical expression. The present single-subject study investigated whether band-limited EEG activity recorded during expressive piano performance by a professional concert pianist contains sufficient discriminative structure to support supervised multi-class classification of musically defined emotional categories. EEG was recorded from 128 scalp sites while a professional concert pianist performed emotionally characterized excerpts from Bach, Beethoven, and Chopin in a continuous naturalistic session. Musical excerpts had been previously categorized and perceptually validated according to emotional valence, tempo, energy/arousal, and tonal structure. From the continuous EEG recording, 180 non-overlapping 2 s artifact-free segments were extracted, yielding 30 segments for each emotional category. Mean spectral power was computed within theta (3.5–7.5 Hz), alpha (7.5–12.5 Hz), and high-beta (24–30 Hz) frequency bands across selected centro-parietal and posterior electrodes, resulting in 24 EEG-derived features per segment. Linear Support Vector Machine, Random Forest, and Gradient Boosting classifiers were evaluated using an 80/20 train-test split combined with five-fold cross-validation. EEG-only classification achieved above-chance performance across models, with Random Forest yielding the highest accuracy (0.42), macro F1-score (0.414), and Cohen’s κ (0.30), exceeding the theoretical chance level of 0.167. Feature importance analysis revealed distributed contributions across theta, alpha, and high-beta oscillatory activity, particularly over parietal and occipital regions, without evidence for a single dominant neural marker. Inclusion of an additional binary arousal-related feature substantially improved Random Forest performance (accuracy = 0.58; macro F1 = 0.579; κ = 0.50), indicating that arousal organization contributed strongly to category separability within the classification framework. These findings suggest that oscillatory EEG activity accompanying expressive musical action contains measurable statistical structure associated with emotionally differentiated performance states. Rather than identifying discrete neural correlates of emotion, the present results provide a computational characterization of distributed oscillatory dynamics emerging during expressive motor-acoustic interaction, extending affective EEG research beyond passive perception paradigms toward ecologically grounded musical performance contexts. Full article

Urbanization underscores the critical role of the built environment in shaping human health outcomes. Recently, technology-driven assessment enables a more precise, dynamic, and objective evaluation of individuals’ biobehavioral responses to built environments and their health. However, existing reviews are limited to single technologies, single health outcomes, or specific environmental features. As a result, this narrative review summarizes 269 studies (2003–2025) to examine how such technology-driven methodologies capture the effects of built environments on psychophysiological well-being. Findings reveal a four-stage evolution in methodology from subjective evaluations and single-device monitoring to integrated subjective-objective measures and, more recently, multimodal synergistic frameworks. Accordingly, based on a technology-driven assessment of biobehavioral responses, this review synthesizes a dual-pathway framework linking the built environment to health: (1) psychological responses are mediated through emotion-arousal mechanisms, encompassing 22 key emotions across both positive and negative valences; and (2) physiological outcomes are influenced by behavioral–psychological mediation and direct environmental exposure, encompassing six categories that span from subclinical dysfunction to clinical disease risk. This review thereby provides a framework derived from the reviewed evidence that connects built environments to health through measurable biobehavioral pathways, directly supporting human-centered urban design and assessment. Full article

While the influence of the urban built environment on public emotions has garnered extensive attention, existing studies predominantly focus on temperate climates or warmer seasons. As a result, they rarely extend their scope to winter-specific emotions in cold-region cities, thereby overlooking the complex human–environment emotional interactions under extreme climates. To bridge this seasonal research gap, this study develops an innovative analytical framework integrating Large Language Models (LLMs) with Multiscale Geographically Weighted Regression (MGWR). Drawing on social media data, this framework leverages the powerful zero-shot reasoning capabilities of LLMs to precisely quantify the two-dimensional emotional characteristics of Valence and Arousal. Concurrently, by incorporating the multi-scale spatial modeling strengths of MGWR, it thoroughly investigates the spatial patterns and driving mechanisms of public emotions within the winter context of typical cold-region cities. The results indicate that, first, extreme climates do not lead to urban emotional suppression; instead, frozen rivers transform into vibrant emotional corridors, with the public demonstrating a high degree of thermal-psychological adaptability. Second, by incorporating winter-specific environmental variables, the research reveals a cold-region paradox of emotional valence. Specifically, under snow cover, lower winter Land Surface Temperature (LST) and winter Normalized Difference Vegetation Index (NDVI) paradoxically evoke positive emotions by reconstructing the aesthetic experience of ice-snow landscapes. Furthermore, the impact of urban service facilities on emotional arousal exhibits a significant pattern of diminishing marginal utility. Overall, the LLMs-MGWR framework achieves a closed loop of high-throughput, multi-dimensional semantic decoding and multi-scale spatial interpretation, demonstrating exceptional cross-regional generalizability. Ultimately, this study not only provides a novel paradigm for understanding human–environment interactions in complex environments but also offers transferable planning guidelines for microclimate design, facility decentralization, and the reshaping of winter blue-green infrastructure in global cold-region cities. Full article

Facial emotion recognition (FER) in real-world settings is limited by the semantic mismatch between discrete emotion categories and continuous Valence–Arousal–Dominance (V-A-D) dimensions and the lack of reliable uncertainty estimates under incomplete facial evidence. Existing uncertainty-aware FER studies mainly address annotation ambiguity or training-time reliability, leaving the behavior of predictive uncertainty under progressive input degradation insufficiently examined. This paper proposes BGDC (Bayesian Gaussian-mixture Distributional Consistency), a multi-task FER framework that integrates a GMM-based soft consistency module with a context-conditioned Bayesian regression head and explicitly models aleatoric and epistemic uncertainty. To evaluate predictive reliability, a controlled masking protocol is introduced to remove facial information under different spatial configurations. On FER2013-VAD, BGDC attains the highest classification accuracy of 0.6943 and the highest mean V-A-D CCC of 0.6079 among the compared configurations, and it yields a stronger epistemic uncertainty-error correspondence than MC Dropout in a single-model setting. Controlled masking further shows that the epistemic uncertainty of BGDC tracks task-relevant facial information loss rather than masking ratio alone: it rises with regression error when diagnostically important regions are removed, and it contracts when the masked region is largely task-irrelevant. Combining Bayesian uncertainty with the GMM-based distributional prior thus enables reliability-aware multi-task FER, in which controlled masking serves as a diagnostic intervention rather than as a benchmark of accuracy degradation alone. Full article

Classifying cognitive workload (CWL) from neurophysiological signals remains a central challenge in affective computing. We present a multi-stage pipeline fusing EEG Slope Entropy (SlpEn; $M=3$, $\delta =0.001$, $\gamma =1.0$, 1-s window) on the DEAP corpus, evaluating five affective dimensions (Valence, Arousal, Dominance, Liking, Familiarity) individually and across all ten pairwise combinations. Random Forest (RF) and XGBoost classifiers were assessed with 5-fold stratified cross-validation on a binary HIGH/LOW CWL task derived from a disjunctive threshold rule over Arousal and Dominance. Results are, therefore, reported separately for rule-constituentand non-constituent features. Arousal (RF: 81.48%, AUC: 0.896) and Dominance (71.64%, AUC: 0.811) attain the highest apparent accuracies but largely reconstruct the labelling rule. Among non-constituent dimensions, Valence is the strongest legitimate predictor (RF: 64.14%, AUC: 0.684), followed by Liking (58.75%) and Familiarity (57.93%). Slope entropy adds 3.6–4.1 pp over the strongest affective baselines and up to 23.4 pp over the SlpEn-alone baseline, with complete insensitivity to blend weighting. The Arousal + Dominance pair (RF: 99.84%, AUC: 1.000) fully reconstructs the rule and is excluded from substantive interpretation. Valence + Arousal reaches 87.27% but remains partially rule-inflated. All results are reported as mean with 95%. Full article

This study examines how auditory contexts, or soundscapes, shape chocolate taste perception, affective response, hedonic liking, and the extent to which emotion mediates these effects. Using a within-subjects design with 120 participants aged 18–25 years, four auditory conditions were compared: silence, natural soundscape, relatively low-pitched soundscape, and relatively high-pitched soundscape. Participants evaluated perceived bitterness, sweetness, acidity, emotional valence, arousal, and overall liking after tasting the same 65% dark chocolate under each auditory condition. The results showed that auditory context significantly modulated taste perception, affective response, and liking. The natural soundscape produced the most favorable profile, increasing liking and emotional valence while reducing arousal. In contrast, the relatively high-pitched condition increased arousal and enhanced perceived acidity (Δ ≈ 6.77 VAS points). Effect sizes indicated stronger effects on arousal (partial η² ≈ 0.46), liking (partial η² ≈ 0.29), acidity (partial η² ≈ 0.28), and valence (partial η² ≈ 0.26) than on sweetness perception (partial η² ≈ 0.05). Mediation analysis showed that emotional valence partially explained the relationship between the natural soundscape and liking, whereas arousal did not play a significant mediating role. These findings suggest that auditory environments influence chocolate evaluation through both affective and crossmodal pathways. Overall, the study provides controlled evidence that sound can function as a relevant contextual variable in multisensory chocolate-tasting experiences, with implications for sensory evaluation, gastronomy, and experience design. Full article