Search Results (4,555)

Background: Eating-rate regulation is a multidimensional behavioral process shaped by oral-processing dynamics, interoceptive cues, sensory engagement, and contextual influences. Despite its relevance, no validated self-report instrument currently assesses these mechanisms. Methods: The Food Consumption Rate Questionnaire (FCRQ) was developed as a behaviorally informed tool for measuring eating-rate regulation. Item generation followed a theory-driven process supported by expert review, forward–backward translation, and pilot testing. Structural validity was examined through Exploratory Factor Analysis (Principal Axis Factoring, Promax rotation) and a theory-driven Confirmatory Factor Analysis evaluating the proposed four-domain model. Reliability was assessed using Cronbach’s α and corrected item–total correlations. Behavioral heterogeneity was explored using hierarchical and k-means cluster analysis. Results: A clear four-factor structure emerged—Slowness, Awareness of Eating Rate, External Factors, and Awareness & Enjoyment—explaining 42.77% of the variance. CFA indicated acceptable model fit (CFI = 0.93, TLI = 0.91, RMSEA = 0.052), supporting the adequacy of the theoretical structure. Reliability indices were consistent with the multidimensional nature of the construct. All four domains were positively correlated. Cluster analysis identified distinct behavioral profiles, illustrating the instrument’s discriminative capacity. Conclusions: The FCRQ provides the first behaviorally informed, psychometrically evaluated framework for assessing eating-rate regulation. The instrument demonstrates a coherent theoretical structure, satisfactory early-stage validity, and the ability to differentiate meaningful behavioral patterns. Continued refinement and validation across diverse populations will further establish the FCRQ as a robust measure for behavioral-nutrition research and practice. Full article

Early childhood dental caries (ECC) remains one of the most prevalent and preventable chronic diseases affecting young children globally, yet behavioral and contextual determinants of its onset during the first 1000 days of life remain poorly understood and infrequently modeled in Latin American populations. This study presents a novel application of the PRECEDE diagnostic framework to conceptualize Early Childhood Dental Caries during the first 1000 days (1000ECDC) as a behaviorally rooted, socio-ecologically conditioned health problem. Drawing on a formative longitudinal pilot study (n = 10 mother–infant dyads, Caracas, Venezuela) and a complementary narrative literature review, we develop the first PRECEDE-based conceptual model linking maternal prenatal and postnatal behaviors to dental caries risk in a Latin American context. The model identifies dietary and feeding behaviors, oral health care practices, and healthcare service utilization as primary behavioral risk factors, modulated by predisposing factors (low oral health knowledge, limited self-efficacy, cultural norms), enabling factors (socioeconomic constraints, fragmented health systems), and reinforcing factors (social norms, family influence). Exploratory pilot findings indicated that more than 60% of children had advanced dental caries lesions at 24-month follow-up, consistent with regional estimates and underscoring the urgency of early intervention. This model provides practitioners and policymakers with a structured, evidence-informed diagnostic tool to guide the design of early-life oral health promotion programs, with particular relevance for low-resource Latin American settings. Future validation through expert consensus and prospective studies is warranted. Full article

This paper proposes METMAP, a comprehensive 6D evaluation framework designed to assess large language models in meteorological applications. The framework encompasses six critical capabilities including meteorological knowledge comprehension, expert-level meteorological content summarization, multilingual translation of meteorological information, geospatial mapping context understanding, alignment with authoritative meteorological standards, and professional meteorological service communication. To operationalize this framework, the paper further introduces MetSEval-1k, a high-quality benchmark comprising 1083 expert-curated questions spanning operational and public-facing meteorological services. The benchmark integrates both objective multiple-choice items and subjective open-ended tasks to enable holistic model assessment. This paper conducts systematic evaluations of multiple state-of-the-art large language models using MetSEval-1k, revealing substantial performance disparities across the six dimensions. The results highlight the critical necessity for domain-specific adaptation and rigorous validation before deploying large language models in operational meteorological contexts. MetSEval-1k is released as a foundational benchmark to advance research and development of trustworthy, service-oriented artificial intelligence application in meteorology. Full article

Background/Objectives: Skin lesion classification remains challenging in real clinical settings because diagnostically relevant information is distributed across different imaging modalities, class imbalance is often severe, and overall performance alone may conceal important weaknesses in model behavior. In this study, a dual-view meta-aware model, termed DVM-SLC was developed for multi-class skin lesion classification on the MILK10k dataset. Methods: The model jointly processes paired clinical and dermoscopic images and incorporates patient-level contextual information through a dedicated metadata branch. Cross-view information is integrated by a gated fusion mechanism to preserve modality-specific representations while allowing adaptive interaction between the two views. The model was evaluated not only in terms of comparative classification performance, but also with respect to calibration, robustness under common image corruptions, and expert-supported explainability. Results: Among the configurations evaluated using pooled out-of-fold predictions, the gated DVM-SLC achieved the highest Accuracy (0.7002) and the highest observed Macro-AUC (0.8774), whereas the gate-free dual-view model with metadata achieved the highest Macro F1-score (0.4174). The accuracy difference between the gated model and the dermoscopic-only baseline, which provided the highest non-proposed Accuracy, was statistically significant, whereas the observed Macro-AUC difference was not statistically significant. These findings indicated a metric-dependent trade-off rather than uniform superiority of a single fusion strategy. The raw confidence estimates were already reasonably aligned with empirical correctness, and temperature scaling provided only a modest, fold-dependent improvement in aggregate calibration. In robustness analysis, the strongest degradation was observed under Gaussian noise, while the model remained comparatively stable under blur, JPEG compression, brightness variation, contrast variation, and color shift. The explainability analysis was complemented by a structured dermatologist review. Gradient-weighted Class Activation Mapping (Grad-CAM) outputs from the clinical and dermoscopic branches were examined to determine whether the highlighted regions localized the lesion and corresponded to clinically meaningful morphological or dermoscopic features. This assessment was qualitative and was not intended as quantitative localization validation. Conclusions: Overall, the findings present DVM-SLC as a broadly evaluated approach with metric-dependent strengths and clear limitations, particularly in minority-class recognition. Its contribution lies in combining comparative performance analysis with calibration, robustness, and structured qualitative explainability assessment. Full article

China’s pork sector is a major component of the national food system. Establishing plant-based pork supply chains requires coordination across production, quality control, infrastructure, logistics, information exchange, and market formation. However, previous studies generally examine these barriers separately, limiting understanding of how they interact within the wider food-supply system. This study identifies and analyzes the systemic barriers to establishing plant-based pork supply chains in China. An integrated Fuzzy Delphi Method (FDM) and Decision-Making Trial and Evaluation Laboratory (DEMATEL) approach is applied. FDM is used to refine and validate 14 contextually relevant barriers based on expert consensus, while DEMATEL examines their direct and indirect relationships, systemic prominence, and net causal influence. Insufficient research and development funding and deficiencies in quality control emerge as the strongest net causal barriers. High infrastructure investment also belongs to the cause group, while technological, operational, and market-related barriers occupy different causal and dependent positions within the wider system. The results support a sequenced intervention strategy that begins with innovation capacity, quality assurance, and infrastructure, followed by operational coordination and market formation. This study contributes by moving beyond barrier identification and ranking to explain how multiple barrier domains interact and how interventions can be prioritized. The analysis concerns supply chain establishment and does not directly assess the environmental, economic, or social sustainability performance of plant-based pork. Full article

As population aging accelerates, providing psychosocial support for adults in the retirement transition has become increasingly important. For this population, a central challenge is adapting to changes in social roles, daily routines, and social relationships, yet existing social robot research has paid insufficient attention to these companionship-related needs. From an embodied cognition perspective, this study developed a needs-driven design pathway for a social companion robot for this population in urban China. Sixteen key needs were identified through user interviews and prioritized through a Kano survey with 184 valid responses from urban community-dwelling adults in the retirement transition. Based on the classification and prioritization results, these needs were synthesized into four design strategies: emotional responsiveness and trust building, social connectedness and sustained engagement, low-burden interaction and daily life support, and safety, health, and privacy protection. Privacy and safety were treated as foundational conditions for product design and practical deployment. The strategies were subsequently mapped to technical features and hardware elements through quality function deployment (QFD), using an expert-panel evaluation procedure and sensitivity analysis to determine module-level configuration priorities. A single-session, laboratory-based concept evaluation was conducted with 50 participants using concept renderings and interaction-flow videos. Concept 3, whose overall configuration emphasized coordinated voice, screen-based visual, and expression/action feedback, received a significantly higher mean participant-level Behavioral Intention (BI) score than Concept 2, which placed greater emphasis on spatial mobility assistance through a mobile wheel module (8.94 ± 0.97 vs. 8.51 ± 1.21; adjusted p = 0.003). These evaluation findings informed the final concept configuration and provided preliminary support for its companionship-oriented multimodal interaction approach. Full article

Background: This study evaluates transdermal delivery of tamoxifen (TXN) as an alternative to the oral route of administration in treating breast cancer, which is the leading cause of cancer-related death in women globally. Oral TXN, a Class II drug, is associated with first-pass metabolism and serious side effects, including secondary cancers. Objectives: To enhance transdermal delivery, lipid-based transethosomes (TRS) were formulated using three different 2⁴ factorial designs with various non-ionic surfactants, including Tween 20^®, Span 20^®, and Span 80^®. Methods: Optimized TRS formulations were incorporated into HPMC-based gels and characterized for morphology, drug content, pH, viscosity, spreadability, ex vivo skin penetration, and deposition. Additionally, cytotoxicity and stability were assessed. Results: All TXN-TRS gels were suitable for transdermal use; however, Span 20^®-based TRS gel demonstrated the highest skin penetration (40.3 ± 1.5 µg/cm²), representing a 127-fold enhancement rate compared with the non-ethosomal TXN gel. In line with the enhanced penetration profile, cellular studies on MCF-7 cells showed concentration-dependent cytotoxicity, reaching 91.24 ± 1.01% inhibition at 2% w/w after 72 h, with an IC₅₀ value of 0.85 ± 0.02% w/w. Stability testing showed all formulations were more stable under refrigeration than at dry room temperature storage, supporting their potential as preclinical transdermal tamoxifen delivery platforms. Conclusions: Span 20^®-based TXN transethosomal gel markedly enhanced skin penetration while maintaining potent cytotoxic activity, supporting its further preclinical evaluation as a promising transdermal alternative to oral tamoxifen. Full article

Digital platforms for cultural heritage are increasingly expected to document the geometric and material properties of sites. Furthermore, such platforms are increasingly expected to preserve and communicate the intangible practices and community knowledge that give these places cultural significance. In this context, this paper presents a hybrid virtual reality platform for the documentation, communication, and dissemination of both tangible and intangible heritage in underground wine landscapes. The framework integrates 360° panoramic imagery, 360° videos, lightweight object visualisations, and georeferenced 3D point clouds within a unified interface adapted to different device capabilities. The system’s key contributions include seasonal navigation, participatory recording of community practices, multiscale representation of artefacts and architecture, and a guided narrative system that improves orientation for non-expert users. The platform has been validated through the underground wineries of Baltanás (Spain), thereby demonstrating a novel approach that brings together metric documentation and immersive storytelling. This enhances accessibility, facilitates heritage interpretation, and ensures the digital preservation of living cultural practices in complex heritage settings with broad public dissemination potential. Full article

Detection of brain tumors through MRI scans is a difficult and crucial process since medical imaging is complex and there are not enough experts to analyze these images in many countries. The timely detection of diseases such as gliomas, meningiomas, and pituitary tumors is critical because delayed detection may have adverse impacts on the patient’s condition and result in incorrect treatment. These difficulties are why automated deep learning models were introduced to help diagnose brain tumors. In this research, we introduce a multi-stage sequential pipeline for brain tumor classification, localization, explainability, and report generation in a radiologist-style structured format based on MRI imaging data, with each stage trained and evaluated independently on its respective dataset. Specifically, an Xception-based classifier was used to classify MRI images into one of four classes, achieving 98.96% accuracy and an F1-score of 0.9876. To enhance interpretability, the Grad-CAM technique was used to visualize image patches the model used during prediction. If the tumor was present, U-Net was used to perform localization, giving a Dice score of 0.7835 and an IoU of 0.6919 with the use of T1-weighted MRI images. Finally, the obtained features were passed as input to a QLoRA fine-tuned language model that generates structured radiology reports, including such components as Technique, Findings, and Impression.The proposed framework was evaluated on a hold-out subset of publicly available T1-weighted MRI data, achieving LLM-as-a-Judge scores of 4.92/5 for accuracy and 4.95/5 for fluency. These results suggest that the proposed approach is promising and provide an initial proof of concept. However, additional validation on independent multi-center datasets and multimodal MRI data is still needed before considering its use in clinical practice. Full article

Objectives: The purpose of this study was to evaluate the ability of computer vision models to detect myopia from standard colour fundus photographs and to compare their diagnostic performance with that of experienced ophthalmologists. Methods: A previously published dataset of 324 retinal fundus images labelled as myopic or non-myopic based on cycloplegic refraction as used for model training and internal validation. Images were acquired using a non-mydriatic 45° fundus camera. Final model evaluation was performed on an independent test set of 50 images from different patients who were not included in the original dataset. YOLOv8 and YOLOv11 variants were trained for binary classification. Internal validation used patient-level cluster bootstrap confidence intervals, whereas image-level bootstrap confidence intervals were estimated for the independent test set. Pairwise model comparisons were adjusted using the Holm–Bonferroni correction. Five experienced ophthalmologists independently classified the test set, and their consensus was compared with the selected YOLO models using DeLong’s and exact McNemar tests. Results: Internal validation identified YOLOv8-m and YOLOv11-n as the best-performing models according to a predefined composite score used exclusively for model selection. On the independent test set, YOLOv11-n achieved the highest area under the curve (AUC = 0.889), followed by YOLOv8-m (0.806), although the difference was not statistically significant (DeLong test, p > 0.05). The clinical consensus achieved an AUC of 0.832, with no significant difference compared with either model. Exact McNemar testing likewise revealed no statistically significant differences in paired classification outcomes between either AI model and the clinical consensus. Limitations include the small, single-centre, class- and age-imbalanced dataset and the limited number of expert observers. Conclusions: Although neither YOLOv8-m nor YOLOv11-n showed statistically significant differences from the clinical consensus on this independent test set, these findings should be interpreted cautiously given the relatively small, single-centre study population. Larger multicentre studies with independent external validation are warranted to confirm the generalisability, robustness, and potential role of clinician-driven computer vision models as decision support tools for myopia screening. Full article

Background: Skew deviation, a vertical ocular misalignment caused by brainstem or cerebellar dysfunction, is strongly associated with central lesions in acute vestibular syndrome but has not been systematically studied in outpatient settings. This clinic-based study evaluated the prevalence of video-oculography (VOG)-guided skew deviation, its diagnostic value for posterior fossa lesions, and the accuracy of an automated VOG algorithm for skew detection. Methods: Consecutive dizzy patients attending a neurology clinic over 18 months underwent a VOG-guided alternate cover test. Vertical eye deviation was automatically quantified by the VOG software and validated by expert review of VOG traces and/or videos (expert review constituted the gold standard in this study). We analyzed the prevalence and diagnostic performance of skew deviation for posterior fossa lesions. Receiver operating characteristic analysis and area under the curve (AUC) were used to evaluate the automated algorithm. Results: Among 226 dizzy patients, skew deviation was identified in 5.3% (95% CI 3.1–9.1%). For predicting posterior fossa lesions, skew deviation showed a sensitivity of 23.7% (95% CI 13.0–39.2%), specificity of 98.4% (95% CI 95.4–99.5%), positive predictive value of 75.0% (95% CI 46.8–91.1%), and negative predictive value of 86.4% (95% CI 81.2–90.4%). The automated VOG algorithm demonstrated promising performance for detecting skew deviation, with AUCs of 0.88 for the right eye (95% CI 0.77–0.99) and 0.94 for the left eye (95% CI 0.91–0.97). Conclusions: Skew deviation is uncommon in outpatient dizzy patients, but its high positive predictive value supports its utility as an adjunctive predictor of posterior fossa lesions. Although the automated VOG algorithm showed promising performance, expert review of traces and/or video remains necessary because false-positive results may occur. Full article

This study addresses the need to establish precise variables to assess subjective urban vulnerability, moving beyond the strictly one-dimensional or perceptual–environmental measurements regularly applied in the study of this territorial reality. Following an initial theoretical proposal, a thematic content analysis of semi-structured interviews was conducted with stakeholders who carry out their professional activity in vulnerable neighborhoods. The diagnostic questionnaire was evaluated through a three-round Delphi process by a multidisciplinary panel of experts from the Spanish university system. The results definitively validated 32 indicators, distributed across three dimensions of subjective urban vulnerability: physical space of the neighborhood (16), social identity (8), and social cohesion (8). In conclusion, this framework provides researchers in the field of territorial science and public managers with a validated, precise instrument for designing interventions tailored to the psychosocial complexity of vulnerable neighborhoods, in the Spanish and European context, improving the understanding and management of these spaces. Full article

Background/Objectives: This paper focusses on the use of artificial intelligence (AI) in automated firearm and ammunition identification. It concentrates on firing pin impressions on fired cartridge cases and secondary rifling land impressions on fired bullets, since these traces represent two different problems in forensic ballistic comparison. The main question was whether machine learning and deep learning methods can support the comparison process while the final assessment remains in the hands of the firearms examiner. Methods: This study combines a critical methodological analysis of AI-based firearm identification with applied experimental results. A convolutional neural network (CNN) was used for firing pin mark classification, the reliability of which was assessed using output neuron parameters A1, A1/A2, and A1−A2. For bullet marks, CNN-based semantic binarization was applied to secondary rifling land impressions, followed by random forest classification of the binarized image pairs. Data augmentation was used to address the limited number of original training objects in this study. Results: Considering the three highest CNN output signals increased the overall firing pin classification accuracy from 82.6% to 92.8%, while the accuracy for unknown-class marks increased from 60.8% to 79.1%. CNN-based binarization of bullet marks achieved accuracy = 0.88 ± 0.05, recall = 0.76 ± 0.06, precision = 0.83 ± 0.06, F1 = 0.79 ± 0.05, and MCC = 0.71 ± 0.06. The random forest classification of binarized bullet mark pairs achieved an accuracy of approximately 84–86%. Conclusions: The findings indicate that AI can improve speed, consistency, candidate selection, image preprocessing, and reliability assessment in forensic ballistics. However, AI outputs remain dependent on dataset quality, firearm and ammunition variability, unknown class recognition, and external validation. The most reliable model is a hybrid human–AI workflow in which the algorithm supports the firearms examiner but does not replace expert judgement. Full article

The increasing demand for scalable digital learning environments has created a need for cloud-based educational content delivery systems that support efficient resource management, platform accessibility, and quality-assured learning experiences. While low-code web development platforms have enabled rapid deployment of educational websites, many implementations remain content-centric and lack systematic architectural design, deployment frameworks, and software quality evaluation mechanisms. This study proposes a modular architecture for cloud-based educational content delivery systems that integrates content management, user access, resource delivery, platform administration, and quality monitoring components within a unified web-based environment. The proposed architecture adopts a structured development framework consisting of requirements analysis, system architecture design, prototype development, deployment configuration, performance testing, and quality evaluation. The framework is designed to support the rapid development of lightweight educational platforms using low-code technologies while maintaining software engineering principles related to reliability, usability, accessibility, compatibility, and performance efficiency. The architecture further incorporates cloud-hosted deployment strategies that facilitate scalable content distribution and cross-platform accessibility for technology-enhanced learning environments. To demonstrate the feasibility of the proposed architecture, a prototype implementation was developed using a low-code web platform and deployed as a cloud-based educational content delivery system. The prototype was evaluated by expert validators using selected software product quality characteristics derived from the ISO/IEC 25010 standard. The evaluation results indicated a high level of technical acceptability across multiple quality dimensions, including performance efficiency, reliability, usability, compatibility, accessibility, and capacity. The findings support the effectiveness of the proposed architecture as a practical framework for developing quality-assured educational delivery platforms. The study contributes a replicable systems architecture and implementation framework for educational content delivery applications. The proposed model provides guidance for the design, deployment, and evaluation of cloud-based learning platforms and offers a foundation for future integration with learning analytics, adaptive content delivery mechanisms, and intelligent educational support systems. Full article

This study investigates the visual complexity of two opposing historic street façades on Sadrettin Konevi Street in Erzurum using an integrated framework that combines fractal analysis, user perception, expert evaluation, and TOPSIS-based decision-making. Fractal analysis was first performed using the box-counting method to calculate the façade fractal dimension (FD) values. In the second stage, perceived visual complexity was evaluated through a survey involving 100 architects and architecture-related professionals. In the third stage, visual complexity criteria identified from the literature were refined using the Delphi technique, reducing them to six key street-scale criteria. These criteria were then weighted using the Analytic Hierarchy Process (AHP) based on expert pairwise comparisons, and expert-based evaluation scores of the street façades were calculated accordingly. Finally, TOPSIS was used to integrate findings from fractal analysis, user perception, and expert evaluation into a unified comparative framework. The results demonstrated strong agreement among the three assessment approaches. The façade with the higher fractal dimension (FD) value (1.7574) was also perceived as more visually complex by most participants (67%) and achieved the highest expert-based weighted score. Rather than providing a universally validated model, the proposed framework is intended as a proof-of-concept that illustrates how computational, perceptual, and expert-based approaches can be integrated to assess visual complexity. Because the framework was demonstrated using only two opposing historic street façades, the findings should be interpreted as preliminary and case-specific rather than universally generalizable. Full article