Search Results (2,509)

Road safety has emerged as a global issue, driven by the rapid rise in vehicle ownership and traffic congestion. Human error, like distraction, drowsiness, and panic, is the leading cause of road accidents. Conventional driver monitoring systems (DMSs) frequently fail to detect these emotional and cognitive states, limiting their potential to prevent accidents. To overcome these challenges, this work proposes a robust deep learning-based DMS framework capable of real-time detection and response to emotion-driven driver behaviors that pose safety risks. The proposed system employs convolutional neural networks (CNNs), specifically the Inception module and a Caffe-based ResNet-10 with a Single Shot Detector (SSD), to achieve efficient, accurate facial detection and classification. The DMS is trained on a comprehensive and diverse dataset from various public and private sources, ensuring robustness across a wide range of emotions and real-world driving scenarios. This approach enables the model to achieve an overall accuracy of 98.6%, an F1 score of 0.979, a precision of 0.980, and a recall of 0.979 across the four emotional states. Compared with existing techniques, the proposed model strikes an effective balance between computational efficiency and complexity, enabling the precise recognition of driving-relevant emotions, making it a practical and high-performing solution for real-world in-car driver monitoring systems. Full article

Accurate understanding of a mental disorder’s symptomatology is essential for valid diagnosis, differential assessment, and treatment planning. It is therefore remarkable that failure to speak is defined as the only symptom in the diagnostic criteria of selective mutism (SM) in current classification systems. This narrow definition may not reflect the full range of difficulties experienced by affected children. This systematic review aimed to synthesize empirical findings on the broader symptomatology of SM across diverse study designs, informants, and assessment methods. Following PRISMA guidelines, we searched PubMed, Web of Science, and APA PsycNet, leading to 82 studies with participant samples (beyond single case reports) included in the final analysis. Results indicated that social and unspecific anxiety were the most frequently assessed and consistently identified symptoms. However, additional features—including withdrawal, depressive symptoms, social skill deficits, and, in qualitative accounts, externalizing and oppositional behaviors—were also documented. The observed symptom diversity varied notably across assessment methods and informants. Our findings support a multisymptomatic understanding of SM and suggest that failure to speak alone do not fully account for its clinical presentation. A more differentiated conceptualization may enhance diagnostic precision, inform individualized intervention strategies, and contribute to discussions on refining diagnostic frameworks. Full article

Supernovae (SNe) are among the most energetic and transient events in the universe, offering crucial insights into stellar evolution, nucleosynthesis, and cosmic expansion. Optical observations have historically played a central role in the discovery, classification, and physical interpretation of SNe. In this review, we summarize recent progress in the optical study of SNe, with a focus on advancements in time-domain surveys and photometric and spectroscopic follow-up strategies. High-cadence optical monitoring is pivotal in capturing the diverse behaviors of SNe, from early-time emission to late-phase decline. Leveraging data from ARIES telescopes and national/international collaborations, we systematically investigate various SN types, including Type Iax, IIP/L, IIb, IIn/Ibn and Ib/c events. Our analysis includes light curve evolution and spectral diagnostics, providing insights into early emission signatures (e.g., shock breakout), progenitor systems, explosion mechanisms, and circumstellar medium (CSM) interactions. Through detailed case studies, we demonstrate the importance of both early-time and nebular-phase observations in constraining progenitor and CSM properties. This comprehensive approach underscores the importance of coordinated global efforts in time-domain astronomy to deepen our understanding of SN diversity. We conclude by discussing the challenges and opportunities for future optical studies in the era of wide-field observatories such as the Vera C. Rubin Observatory (hereafter Rubin), with an emphasis on detection strategies, automation, and rapid-response capabilities. Full article

Understanding luxury tourists required a more comprehensive approach than traditional expenditure-based segmentation, which often overlooked travelers’ financial capacity. This study therefore aimed to develop and validate a new typology of luxury tourists by jointly analyzing income and expenditure patterns using the International Visitor Survey of South Korea. The study addressed the need to capture both tourists’ economic capability and consumption behavior to enhance the precision of market segmentation and support sustainable destination management. Using the Jenks natural breaks classification and logistic regression, four distinct tourist types were identified: economy, spurious, scrooge, and premier, each reflecting unique combinations of income and expenditure. The results revealed that age, nationality, occupation, and trip purpose significantly influenced tourists’ classification. Younger and middle-aged professionals from East Asia were more likely to belong to high-income and high-expenditure groups, whereas Western tourists tended to spend more relative to their income. This income–expenditure typology advanced theoretical understanding of luxury tourism segmentation and provided practical insights for destination marketing organizations. The findings offered new insights for understanding how the alignment between tourists’ financial capacity and spending behavior can redefine strategies for sustainable and inclusive tourism development. Full article

Live fuel moisture content (LFMC) is a critical variable influencing wildfire behavior, ignition potential, and suppression difficulty, yet it remains challenging to monitor consistently across landscapes due to sparse field observations, rapid temporal changes, and vegetation heterogeneity. This study presents a comprehensive review of satellite-based approaches for estimating LFMC, with emphasis on methods applicable to New Zealand, where wildfire risk is increasing due to climate change. We assess the suitability of different remote sensing data sources, including multispectral, thermal, and microwave sensors, and evaluate their integration for characterizing both LFMC and fuel types. Particular attention is given to the trade-offs between data resolution, revisit frequency, and spectral sensitivity. As knowledge of fuel type and structure is critical for understanding wildfire behavior and LFMC, the review also outlines key limitations in existing land cover products for fuel classification and highlights opportunities for improving fuel mapping using remotely sensed data. This review lays the groundwork for the development of an operational LFMC prediction system in New Zealand, with broader relevance to fire-prone regions globally. Such a system would support real-time wildfire risk assessment and enhance decision-making in fire management and emergency response. Full article

Autism diagnosis remains a critical healthcare challenge, with current assessments contributing to average diagnostic ages of 5 and extending to 8 in underserved populations. With the FDA approval of CanvasDx in 2021, the paradigm of human-in-the-loop AI diagnostics entered the pediatric market as the first medical device for clinically precise autism diagnosis at scale, while fully automated deep learning approaches have remained underdeveloped. However, the importance of early autism detection, ideally before 3 years of age, underscores the value of developing even more automated AI approaches, due to their potentials for scale, reach, and privacy. We present the first systematic evaluation of multimodal LLMs as direct replacements for human annotation in AI-based autism detection. Evaluating seven Gemini model variants (1.5–2.5 series) on 50 YouTube videos shows clear generational progression: version 1.5 models achieve 72–80% accuracy, version 2.0 models reach 80%, and version 2.5 models attain 85–90%, with the best model (2.5 Pro) achieving 89.6% classification accuracy using validated autism detection AI models (LR5)—comparable to the 88% clinical baseline and approaching crowdworker performance of 92–98%. The 24% improvement across two generations suggests the gap is closing. LLMs demonstrate high within-model consistency versus moderate human agreement, with distinct assessment strategies: LLMs focus on language/behavioral markers, crowdworkers prioritize social-emotional engagement, clinicians balance both. While LLMs have yet to match the highest-performing subset of human annotators in their ability to extract behavioral features that are useful for human-in-the-loop AI diagnosis, their rapid improvement and advantages in consistency, scalability, cost, and privacy position them as potentially viable alternatives for aiding diagnostic processes in the future. Full article

The detection of abnormal behavior has consistently garnered significant attention. Conventional methods employ vision-based dual-stream networks or 3D convolutions to represent spatio-temporal information in video sequences to identify normal and pathological behaviors. Nonetheless, these methodologies generally employ datasets balanced across data categories and consist solely of two classifications. In actuality, anomalous behaviors frequently display multi-category characteristics, with each category’s distribution demonstrating a pronounced long-tail phenomenon. This paper presents a video-based technique for detecting multi-category abnormal behavior, termed the Spatio-Temporal Fusion–Temporal Difference Network (STF-TDN). The system first employs a temporal difference network (TDN) model to encapsulate movie temporal dynamics via local and global modeling. To enhance recognition performance, this study develops a feature fusion module—Spatial-Temporal Fusion (STF)—which augments the model’s representational capacity by amalgamating spatial and temporal data. Furthermore, given the long-tailed distribution characteristics of the datasets, this study employs focused loss rather than the conventional cross-entropy loss function to enhance the model’s recognition capability for under-represented categories. We perform comprehensive experiments and ablation studies on two datasets. Precision is 96.3% for the Violence5 dataset and 87.5% for the RWF-2000 dataset. The results of the experiment indicate the enhanced efficacy of the proposed strategy in detecting anomalous behavior. Full article

This study presents an advanced signal analysis model for internal defect identification in bridge decks using impact echo field testing data designed to mitigate signal noise and the variability encountered during real-world inspections. Field tests were conducted on a concrete bridge deck utilizing an automated inspection system, systematically capturing impact-echo signals across multiple scanning paths. The large volume of field-acquired data poses significant challenges, particularly in identifying defects and isolating clean signals and suppressing noise under variable environmental conditions. To enhance the accuracy of defect detection, a deep learning framework was designed to refine critical signal parameters, such as signal duration and the starting point in relation to the zero-crossing. A convolutional neural network (CNN)-based classification model was developed to categorize signals into delamination, non-delamination, and insignificant classes. Through systematic parameter tuning, optimal values of 1 ms signal duration and 0.1 ms starting time were identified, resulting in a classification accuracy of 88.8%. Laboratory test results were used to validate the signal behavior trends observed during the parameter optimization process. Comparison of defect maps generated before and after applying the CNN-optimized signal parameters revealed significant enhancements in detection accuracy. The findings highlight the effectiveness of integrating advanced signal analysis and deep learning techniques with impact-echo testing, offering a robust non-destructive evaluation approach for large-scaled infrastructures such as bridge deck condition assessment. Full article

This study aimed to evaluate the effectiveness of a multimodal trust assessment approach that integrated electroencephalography (EEG) and self-report questionnaires compared with unimodal methods within the context of lower-limb rehabilitation training. Twenty-one mobility-impaired participants performed tasks using handrails, walkers, and stairs. Synchronized EEG, questionnaire, and behavioral data were collected. EEG trust scores were derived from the alpha-beta power ratio, while subjective trust was assessed via questionnaire. An adaptive neuro-fuzzy inference system was used to fuse these into a composite score. Analyses included variance, correlation, and classification consistency against behavioral ground. Results showed that EEG-based scores had higher dynamic sensitivity (Spearman’s ρ = 0.55) but greater dispersion (Kruskal–Wallis H-test: p = 0.001). Questionnaires were more stable but less temporally precise (ρ = 0.40). The fused method achieved stronger behavioral correlation (ρ = 0.59) and higher classification consistency (κ = 0.69). Cases with discordant unimodal results revealed complementary strengths: EEG captured real-time neural states despite motion artifacts, while questionnaires offered contextual insight prone to bias. Multimodal fusion through fuzzy logic mitigated the limitations of isolated assessment methods. These preliminary findings support integrated measures for adaptive rehabilitation monitoring, though further research with a larger cohort is needed due to the small sample size. Full article

Research on surfaces generated by curves plays a central role in linking differential geometry with physical applications, especially following Hasimoto’s transformation and the development of Hasimoto-inspired surface models. In this work, we introduce a new class of such surfaces, referred to as RM Hasimoto surfaces, constructed by employing the rotation-minimizing (RM) Darboux frame along both timelike and spacelike curves in Minkowski 3-space ${\mathbb{E}}_1^3$. In contrast to the classical Hasimoto surfaces defined via the Frenet or standard Darboux frames, the RM approach eliminates torsional difficulties and reduces redundant rotational effects. This leads to more straightforward expressions for the first and second fundamental forms, as well as for the Gaussian and mean curvatures, and facilitates a clear classification of key parameter curves. Furthermore, we establish the associated evolution equations, analyze the resulting geometric invariants, and present explicit examples based on timelike and spacelike generating curves. The findings show that adopting the RM Darboux frame provides greater transparency in Lorentzian surface geometry, yielding sharper characterizations and offering new perspectives on relativistic vortex filaments, magnetic field structures, and soliton behavior. Thus, the RM framework opens a promising direction for both theoretical studies and practical applications of surface geometry in Minkowski space. Full article

Digital Twin (DT) technology has emerged as a valuable tool for researchers and engineers, enabling them to optimize performance and enhance system efficiency. This paper presents a comprehensive Systematic Literature Review (SLR) following the PRISMA framework to explore current applications of DT technology in the power generation sector while highlighting key advancements. A new framework is developed to categorize DTs in terms of time-scale horizons and applications, focusing on power plant types (emissive vs. non-emissive), operational behaviors (including condition monitoring, predictive maintenance, fault detection, power generation prediction, and optimization), and specific components (e.g., power transformers). The time-scale is subdivided into a six-level structure to precisely indicate the speed and time range at which it is used. More importantly, each category in the application is further subcategorized into a three-level framework: component-level (i.e., fundamental physical properties and operational characteristics), system-level (i.e., interaction of subsystems and optimization), and service-level (i.e., value-adding service outputs). This classification can be utilized by various parties, such as stakeholders, engineers, scientists, and policymakers, to gain both a general and detailed understanding of potential research and operational gaps. Addressing these gaps could improve asset longevity and reduce energy consumption and emissions. Full article

Efficient public transportation systems are fundamental to achieving sustainable urban development. As the backbone of urban mobility, the coordinated development of rail transit and bus systems is crucial. The opening of a new rail transit line inevitably reshapes urban travel patterns, posing significant challenges to the existing bus network. Understanding passenger switch behavior is key to optimizing the competition and cooperation between these two modes. However, existing methods on the switch behavior of bus passengers along the newly opened rail transit line cannot balance the predictive accuracy and model interpretability. To bridge this gap, we propose a CART (classification and regression tree) decision tree-based switch behavior model that incorporates both predictive and interpretive abilities. This paper uses the massive passenger swiping-card data before and after the opening of the rail transit to construct the switch dataset of bus passengers. Subsequently, a data-driven predictive model of passenger switch behavior was established based on a CART decision tree. The experimental findings demonstrate the superiority of the proposed method, with the CART model achieving an overall prediction accuracy of 85%, outperforming traditional logit and other machine learning benchmarks. Moreover, the analysis of factor significance reveals that ‘Transfer times needed after switch’ is the dominant feature (importance: 0.52), and the extracted decision rules provide clear insights into the decision-making mechanisms of bus passengers. Full article

This study evaluates the feasibility of using a lightweight, off-the-shelf sensing system for short-term stress detection during exergaming. Most existing studies in stress detection compare rest and task conditions, providing limited insight into continuous stress dynamics, and there is no agreement on optimal sensor configurations. To address these limitations, we investigated dynamic stress responses induced by a cognitive–motor task designed to simulate rehabilitation-like scenarios. Twenty-three participants completed the experiment, providing electrodermal activity (EDA), blood volume pulse (BVP), self-report, and in-game data. Features extracted from physiological signals were analyzed statistically, and shallow machine learning classifiers were applied to discriminate among stress levels. EDA-based features reliably differentiated stress conditions, while BVP features showed less consistent behavior. The classification achieved an overall accuracy of 0.70 across four stress levels, with most errors between adjacent levels. Correlations between EDA dynamics and perceived stress scores suggested individual variability possibly linked to chronic stress. These results demonstrate the feasibility of low-cost, unobtrusive stress monitoring in interactive environments, supporting future applications of dynamic stress detection in rehabilitation and personalized health technologies. Full article

Markov chain Monte Carlo (MCMC) methods are fundamental to Bayesian inference but are often computationally prohibitive for large datasets, as the full likelihood must be evaluated at each iteration. Subsampling-based approximate Metropolis–Hastings (MH) algorithms offer a popular alternative, trading a manageable bias for a significant reduction in per-iteration cost. While this bias–variance trade-off is empirically understood, a formal theoretical framework for its optimization has been lacking. Our work establishes such a framework by bounding the mean squared error (MSE) as a function of the subsample size (m), the data size (n), and the number of epochs (E). This analysis reveals two optimal asymptotic scaling laws: the optimal subsample size is $m^{★}=O\left(E^{1/2}\right)$, leading to a minimal MSE that scales as ${\mathrm{MSE}}^{★}=O\left(E^{-1/2}\right)$. Furthermore, leveraging the large-sample asymptotic properties of the posterior, we show that when augmented with a control variate, the approximate MH algorithm can be asymptotically more efficient than the standard MH method under ideal conditions. Experimentally, we first validate the two optimal asymptotic scaling laws. We then use Bayesian logistic regression and Softmax classification models to highlight a key difference in convergence behavior: the exact algorithm starts with a high MSE that gradually decreases as the number of epochs increases. In contrast, the approximate algorithm with a practical control variate maintains a consistently low MSE that is largely insensitive to the number of epochs. Full article

This study introduces a theoretical and computational framework for modeling acoustic wave propagation in defective concrete, with applications to non-destructive testing and structural health monitoring. The formulation is based on a coupled system of evolutionary hyperbolic equations, where internal defects are explicitly represented as localized energetic sources or sinks. A key contribution is the definition of a coercivity coefficient, which quantifies the energetic effect of defects and enables their classification as stabilizing, neutral, or dissipative. The model establishes a rigorous relationship between defect morphology, spatial distribution, and the global energetic stability of the material. Numerical simulations performed with an explicit finite-difference time-domain scheme confirm the theoretical predictions: the normalized total energy remains above $95\%$ for stabilizing defects (${\mu }_i>0$), decreases by about $10\%$ for quasi-neutral cases (${\mu }_i\approx 0$), and drops below $50\%$ within $200\mathsf{\mu }\mathrm{s}$ for dissipative defects (${\mu }_i<0$). The proposed approach reproduces the attenuation and phase behavior of classical Biot-type and Kelvin–Voigt models with deviations below $5\%$ while providing a richer energetic interpretation of local defect dynamics. Although primarily theoretical, this study establishes a physically consistent and quantitatively validated framework that supports the development of predictive ultrasonic indicators for the energetic classification of defects in concrete structures. Full article