Search Results (1,622)

Seismic attribute selection remains a critical yet often heuristic component in deep learning-based segmentation workflows. In this work, we propose a redundancy-aware framework to systematically analyse the contribution of seismic attributes by combining input-space statistics, representational similarity (CKA), and error-based evaluation. Our results suggest that statistical redundancy in the input space does not directly translate to functional redundancy within the network. In particular, attributes such as amplitude and instantaneous phase may exhibit high similarity in the input space while producing distinct error patterns and meaningful performance gains. We further observe that complementary attributes do not necessarily yield additive improvements. While some combinations introduce conflicting interactions that limit global performance, others provide stable and consistent improvements across classes. Notably, the combination of amplitude, phase, and local variance forms a minimal informative subset that improves segmentation performance in a balanced manner, particularly in challenging facies. These findings suggest that attribute selection should be guided by functional complementarity and interaction stability rather than by input diversity alone. The proposed framework provides a principled approach for identifying effective attribute subsets, contributing to more efficient and interpretable seismic segmentation workflows. Full article

Recent advances in generative Artificial Intelligence (AI) have rapidly transformed research and practice across the Cultural Heritage domain. While several studies have investigated AI applications in documentation, analysis and dissemination, a focused and critical assessment of generative AI within 3D virtual reconstruction workflows is still lacking. This paper presents a systematic review of the literature addressing the use of generative AI in 3D heritage virtual reconstructions, with particular attention to methodological implications, scientific reliability and ethical challenges. A large-scale bibliographic analysis covering publications from 2015 to 2024 was conducted using OpenAlex, complemented by targeted manual searches. From an initial corpus of over 8700 papers on 3D heritage reconstruction, only 13 directly addressed generative AI-driven reconstruction processes. The analysis highlights a significant gap between the rapid technological development of AI-based tools and their cautious, often problematic, adoption in virtual reconstruction practices. Results reveal recurring issues related to terminological ambiguity, opacity of reconstruction processes, evaluation metrics focused on visual plausibility rather than scientific transparency and the risk of interpretative bias. The paper argues that current AI-driven approaches tend to privilege speed and aesthetic outcomes over heuristic, source-based reconstruction workflows. Finally, future research directions are discussed, emphasizing the potential role of AI as an evaluative and analytical support tool rather than a fully autonomous reconstruction agent, in alignment with established charters and principles of virtual archaeology. Full article

Precision psychiatry promises a more objective and effective approach to psychiatric care, yet its implementation raises growing ethical challenges as technology advances. This narrative review offers a qualitative synthesis of the ethical issues reported in 62 studies, with emphasis on the practical tensions that arise when core principles conflict. Rather than organising concerns around traditional ethical principles, the review maps them across the main modalities of precision psychiatry, namely genomics, neuroimaging, digital phenotyping, and AI-driven interventions. Four explicit positions are advanced. First, equity must be engineered from the outset rather than assumed. Second, interpretability should outweigh marginal gains in accuracy in a field built on subjective report. Third, stigma is bidirectional and contingent on framing and the availability of meaningful intervention. Fourth, individualised care must demonstrate clinical and economic superiority over standardised approaches. Precision psychiatry is likely to reshape psychiatric practice and the therapeutic relationship itself. Interdisciplinary collaboration, clear guidelines, and continuous ethical vigilance will be essential for responsible adoption and sustained public trust. Full article

Shear wave elastography (SWE) is an increasingly investigated ultrasound-based technique in musculoskeletal imaging that provides quantitative information on tissue stiffness and biomechanical properties. This narrative review aims to summarize the basic principles, technical considerations, current clinical applications, limitations, and future perspectives of SWE in musculoskeletal imaging. Unlike conventional grayscale and Doppler ultrasonography, which mainly assess morphology and vascularity, SWE may provide additional functional information in major musculoskeletal tissues, including tendons and ligaments, skeletal muscles, peripheral nerves, fibrocartilaginous structures, plantar fascia, and selected soft tissue lesions. Current evidence suggests potential roles for SWE in detecting early biomechanical alterations, assessing disease severity, differentiating symptomatic from asymptomatic tissues, and monitoring response to treatment or rehabilitation. However, musculoskeletal tissues are anisotropic, viscoelastic, and position-dependent; as a result, SWE measurements are influenced by acquisition-related factors, tissue biomechanics, positioning and loading conditions, region of interest (ROI) placement, tissue depth, and device-related variability. For this reason, SWE findings should not be interpreted as standalone diagnostic criteria but should be considered together with clinical findings, conventional ultrasonography, MRI, electrophysiology, histopathology, and patient-centered outcomes when appropriate. This review highlights the need for tissue-specific measurement protocols, standardized reporting, normative reference data, inter-vendor harmonization, and longitudinal validation against clinically meaningful outcomes before SWE can be more reliably integrated into routine musculoskeletal imaging and rehabilitation practice. Full article

Strict minimum message length (SMML) is an information-theoretic coding principle that represents a continuous statistical model by a finite set of assertions and a partition of the sample space. We show that the SMML objective decomposes into assertion entropy and conditional cross-entropy, balancing the cost of identifying an assertion against the cost of encoding data under the assigned model. For any fixed partition, the optimal codepoint for each cell is the model distribution that minimises Kullback–Leibler (KL) divergence from the data distribution restricted to that cell. Using the local Fisher–Rao geometry of regular parametric models, we show that, under a high-resolution LAN-scale regime, SMML partitions are asymptotically the pullback, through the maximum-likelihood estimator, of weighted Fisher–Rao Voronoi tessellations in parameter space, with assertion probabilities appearing as additive weights. For regular canonical exponential families, SMML codepoints satisfy a moment-matching condition and admit an interpretation as KL/Bregman centroids, while exact SMML cells are pullbacks of convex polyhedra in sufficient-statistic space. Together, these results show that SMML induces a natural information-geometric quantisation linking entropy-based coding, KL projection, and divergence-based Voronoi geometry. Full article

Wikidata provides extensive coverage of tourism-related Points of Interest (POIs), yet its heterogeneous type system and uneven metadata limit its direct use in smart tourism applications. This paper presents an end-to-end pipeline that transforms Wikidata POIs into a compact and interpretable tourism-oriented representation supporting multi-category assignments. We collect POIs from six countries—Greece, Italy, Spain, Norway, Sweden, and Denmark—and construct a dataset that integrates core identifiers with textual descriptions, type information, heritage indicators, geographic coordinates, and Wikipedia sitelinks. We introduce an eight-category tourism taxonomy capturing key themes, including cultural venues, archaeological and historic sites, monuments, fortifications, religious sites, protected areas, natural features, and coastal or water locations. As a reproducible baseline, category likelihoods are estimated using sentence embeddings and similarity to category anchor descriptions, producing a probability vector for each POI. Building on this baseline, we propose a fuzzy inference layer that integrates embedding-based probabilities with structured Wikidata signals to generate interpretable membership degrees across categories and enable principled multi-category classification. This fusion is particularly valuable for smart tourism applications, as it supports robust faceted exploration and personalized recommendations (e.g., “historic + coastal”), while providing evidence-based explanations that enhance user trust and facilitate curator oversight when POI metadata is sparse or ambiguous. The resulting pipeline produces ranked POI catalogs by country and category, country-level tourism profiles, and diagnostic views for examining uncertain cases. The approach is fully reproducible and readily adaptable to other geographic regions or domain taxonomies. Full article

The rapid expansion of molecular point-of-care (POC) diagnostics into decentralized settings, including emergency departments, retail pharmacies, and home environments, has shifted the burden of diagnostic performance from laboratory professionals to heterogeneous, often non-expert users. While traditional evaluation frameworks focus on analytical and clinical validity, they often overlook the impact of human-system interactions on real-world reliability. This review introduces the concept of Operational Validity: the ability of a diagnostic system to preserve its intended performance when operated by intended users within the constraints of real-world workflows and environments. To establish a rigorous foundation for this concept, this study provides a critical comparative analysis contrasting Operational Validity against traditional clinical evaluation dimensions (analytical validity, clinical validity, and clinical utility) and post-market metrics. While existing literature outlines isolated usability principles, the significance of this study lies in its synthesis of these fragmented concepts into a formalized, lifecycle-based “Operational Validity” framework that explicitly maps the causal mechanisms connecting initial user interaction directly to downstream clinical outcomes. By synthesizing international standards (IEC 62366-1) alongside the newly finalized May 2026 U.S. Food and Drug Administration (FDA) guidance on the Content of Human Factors Information in Medical Device Marketing Submissions, we examine how human factors engineering (HFE) and usability engineering serve as the methodological foundation for operational validity. We analyze the specific complexities of molecular workflows, identify key parameters of use-related failure modes in pre-analytical and interpretation stages, and detail the mandatory role of iterative formative and final summative usability testing in mitigating these risks. Finally, we propose a lifecycle-based approach to HFE that integrates design, simulated-use validation, and post-market surveillance. Establishing operational validity is essential to ensure that the high analytical sensitivity of molecular POC platforms translates into consistent clinical utility across the full spectrum of decentralized care. Full article

João António de Aguiar was one of the most prolific Portuguese architect-planners of the twentieth century, producing an extensive body of work within the framework of the 1934 legislative reform. He employed Urban Development Plans as a key scientific and technical instrument for territorial intervention, both in mainland Portugal and in the overseas territories. Despite his significance, Aguiar’s contribution remains relatively understudied, frequently overshadowed by the reformist ministry of Duarte Pacheco and by the dominant ideological narratives of the period. This article advances a critical analysis centred on urban composition and city design, with particular emphasis on the transformation of coastal urban structures and on Aguiar’s interventions in the Portuguese colonial context. Through a comparative and interpretative methodology, the study examines the formal and spatial principles underpinning his plans, while addressing the cultural challenges involved in adapting European urban models to non-European contexts. By shifting the focus from a merely descriptive inventory of planning instruments to a deeper investigation of urban form, this research offers a more nuanced reading of urban transformation processes in overseas coastal settlements. It contributes to a clearer and more structured understanding of Aguiar’s influence on African and Asian urbanism and on colonial planning practices more broadly. Full article

Artificial intelligence (AI) is reshaping the field of diagnostic radiology; however, its applications in interventional radiology and pediatric interventional radiology (PIR) remain limited despite clear clinical needs and the rich multimodal data environment characteristic of pediatric procedural care. In this narrative review, I summarize the current state of AI technologies relevant to PIR and outline future perspectives for their clinical integration. Peer-reviewed literature and position statements identified through MEDLINE/PubMed, Embase, Scopus, and major society publications up to the first quarter of 2026 are synthesized, focusing on AI applications across the PIR care pathway, including dose-sparing image acquisition and reconstruction, automated image interpretation and computer-aided diagnosis, data-driven procedural planning and navigation, and post-procedural risk prediction and monitoring. After briefly introducing core machine learning and deep learning concepts, pediatric-specific challenges are discussed, including radiation sensitivity, growth-related anatomical variability, regulatory constraints, and the scarcity of large, annotated datasets, as well as existing and emerging applications along the PIR care pathway: AI-assisted dose reduction and image reconstruction, automated image interpretation, segmentation, and computer-aided diagnosis; data-driven procedural planning, including three-dimensional modelling, augmented reality, AI-enabled/AI-adjacent robotics, and AI-directed procedural navigation; and post-procedural risk prediction and outcome monitoring. Finally, emerging paradigms, including explainable AI, federated learning, and multimodal integration, are highlighted, and research priorities, collaborative frameworks, and governance principles required to ensure safe, equitable, and effective AI deployment in PIR are outlined. In doing so, this review delineates the current evidence gaps and priority directions for clinically meaningful AI adoption in PIR. Although AI has the potential to improve patient care, it has not yet been specifically designed, validated, or deployed in children. Existing work demonstrates feasibility across the PIR workflow, but most tools remain weakly linked to pediatric clinical endpoints. Full article

Background/Objectives: The stability of complete dentures is strongly influenced by the biomechanical properties of the oral mucosa, whose heterogeneity results in non-uniform load distribution, while its clinical evaluation remains predominantly qualitative. This article proposes a theoretical differential hypothesis aimed at providing a conceptual mathematical framework for interpreting the relationship between mucosal resilience and load distribution in complete dentures. Methods: The denture-mucosa system was represented along a one-dimensional coordinate, defining resilience R(x) and pressure P(x) as continuous functions related by a first-order differential equation, interpreted through elementary principles of differential calculus. Results: A theoretical simulation based on physiological parameters (F = 50 N, Young’s modulus 19.75 MPa, R = 2 mm) highlights that areas of thinner mucosa tend to behave as stress concentration points, while spatial variability of resilience generates deformation gradients potentially associated with prosthetic instability. Conclusions: The model, although simplified and non-predictive, provides a coherent interpretative framework and can support the integration of biomechanical parameters into clinical reasoning and prosthetic planning. No clinical recommendations should be derived from this model until experimental validation has been performed. Full article

Introduction: Pedestrians lying on the road—collapsed through medical emergency, intoxication, or displacement following a prior collision—represent a disproportionately lethal and underaddressed category in road traffic safety. Forensic database analyses derived from Japan’s national police records document a fatality rate of 33.0% for collisions involving pedestrians lying on the road, more than double the rate for upright pedestrian collisions. Standard Advanced Driver-Assistance Systems (ADAS) yield a True Positive Rate (TPR) of only 21.4% for detecting pedestrians lying on the road under night conditions—a classification gap of 73.3 percentage points. Methods: In simulation trials, we evaluated the Advanced Falling Object Detection System (AFODS—where “falling object” denotes the low-profile human form at road level, distinguishing the prone pedestrian from the upright postures addressed by conventional ADAS) on a composite dataset of 3200 annotated fall events and 12,000 negative samples (training/validation), with 320 independent controlled simulation trials used for performance evaluation, spanning real-world, forensic-reconstruction, and Total Human Body Model for Safety (THUMS)-validated synthetic scenarios. No physical prototype has been evaluated; all performance data are derived from simulation, and 37.5% of positive samples are synthetically generated. These simulation conditions represent a first feasibility demonstration pending real-world hardware validation. This paper introduces three original contributions absent from prior work: a three-stage quantitative injury-risk model, a formal ISO 26262 Hazard Analysis and Risk Assessment (HARA), and a medicolegal SHAP interpretability framework. The injury-risk model translated detection latency via impact velocity to Head Injury Criterion (HIC) and estimated fatal injury probability (AIS ≥ 5); these model outputs should be interpreted as exploratory estimates pending ATD validation. Reporting follows principles consistent with the TRIPOD statement. Results: Under clear daytime conditions, AFODS demonstrated a TPR of 98.2% (95% CI: 97.4–98.8%) in simulation, decreasing to 95.6% under night dry-road conditions and 89.4% under night rain. The system achieved an AUC of 0.981 and a mean end-to-end latency of 46.5 ms, representing a 76.8 percentage-point improvement in simulation over the monocular RGB baseline (p < 0.001). The injury-risk model projects a reduction in estimated fatal head injury probability from 66.2% (Monte Carlo mean) (no detection, 50 km/h full-speed impact) to 0.7% under AFODS worst-case night/rain conditions, and to ≈0% under clear daytime simulation conditions. Conclusions: A 73.3 percentage-point classification gap places pedestrians lying on the road outside the effective detection envelope of current ADAS, compounded by the systematic exclusion of non-upright postures from regulatory test protocols and benchmark datasets. AFODS supports proof-of-concept feasibility under simulation conditions. Three translational steps are required: prototype validation on real-world hardware using instrumented Anthropomorphic Test Devices (ATDs); prone-posture biomechanical injury modelling using HIC and BrIC criteria; and regulatory extension of pedestrian AEB test standards to non-upright scenarios. Full article

Industrial control systems (ICS), which manage critical infrastructure such as power grids and water treatment, are increasingly exposed to cyber threats and operational faults as their connectivity to external networks grows. AI-based anomaly detection has emerged as a key defense, yet three limitations restrict its practical deployment: (i) detected anomalies are treated uniformly without distinguishing between transient faults and intentional attacks, hindering tailored incident response; (ii) the trade-off between detection accuracy and the false-positive rate burdens experts with extensive manual triage and delays prompt action; and (iii) prevailing feature-attribution Explainable AI (XAI) techniques such as SHAP and LIME produce fragmented sensor-level explanations and fail to capture correlations among sensors in time-series data, undermining trust in model decisions. To address these gaps, this paper proposes a graph-based deep learning framework that (a) defines anomaly types in terms of the anomalous-sensor ratio measured before and after smoothing—which operationalizes the correlation-maintenance principle that faults keep coupled sensors jointly anomalous while attacks isolate them—enabling explicit separation of faults, attacks, false positives, and false negatives; (b) identifies ambiguous decisions near the detection threshold as candidate false alarms via dynamic threshold smoothing; and (c) provides correlation-aware graph visualizations for intuitive interpretation. Experiments on the Secure Water Treatment (SWaT) dataset center on this post-detection layer: built on a standard graph-based detector (F1-score 0.787 at Top-K = 10) that serves only as the substrate, the categorization separates faults from attacks, and the subsequent ambiguity analysis identifies false negatives with 83% precision and false positives with 73% precision. By separating attacks from faults and surfacing high-likelihood false alarms together with intuitive sensor-correlation explanations, the proposed approach reduces analyst workload and supports more reliable, prioritized incident response in ICS environments. Full article

Ensemble learning has been widely adopted in fraud detection; however, conventional ensemble strategies rely on uniform or performance-based weighting schemes that treat explainability as a post hoc annotation rather than an architectural component. This study addresses the research goal of whether SHAP attribution values can serve as a principled, instance-specific weighting mechanism within an ensemble, thereby embedding interpretability directly into the aggregation process. A SHAP-Weighted Ensemble (SWE) framework is proposed in which the L2 norm of each base model’s SHAP attribution vector, computed at prediction time, is used to derive instance-specific voting weights via Softmax normalization. Three linear base learners (logistic regression, robust LR, calibrated linear SVM) are combined, with LinearSHAP providing exact attribution values. A comprehensive evaluation protocol was applied on a real-world vehicle insurance claims dataset, including bootstrap 95% confidence intervals, McNemar’s test, a three-way ablation study comparing equal weighting, SWE, and validation-AUC weighting, F1-optimal threshold selection, expected calibration error, and cost-sensitive evaluation under asymmetric misclassification costs. The central finding is that SWE achieves performance statistically comparable to both simpler baselines across all evaluated metrics (ROC-AUC = 0.774, 95% CI [0.681, 0.862]; F1 = 0.679, 95% CI [0.569, 0.774]; McNemar p = 1.000), while producing a transparent, per-claim weighting trace that equal-weight voting cannot provide. A KernelSHAP influence analysis conducted directly on the SWE confirms that SHAP-derived weights are substantially aligned with actual model influence ratios (LR: 1.05×, LR_R: 1.05×, SVM: 0.81×), validating the weighting mechanism empirically. An exploratory analysis of a seven-model equal-weight diagnostic ensemble reveals a negative correlation (r = −0.721, p = 0.067) between individual model performance and ensemble influence; a theoretically coherent finding that does not reach statistical significance at conventional thresholds. The primary contribution of SWE is architectural and interpretability-driven: it produces an auditable, instance-level model-weighting mechanism grounded in SHAP attribution theory, supporting regulatory accountability under GDPR Article 22 and the EU AI Act. Full article

In this paper, the Tricomi problem for a second-kind mixed-type equation with a lower-order term is studied in an unbounded domain. The elliptic part of the domain is a vertical half-strip, while the hyperbolic part is bounded by characteristics. Homogeneous Dirichlet conditions are imposed on the walls of the half-strip, gluing conditions are given on the parabolic degeneracy line, and the trace of the desired solution is prescribed on one of the characteristics. The uniqueness of the solution is proved using the extremum principle and the Zaremba–Giraud principle. The existence of the solution is established by Green’s function method: in the elliptic part, Green’s function of the mixed problem is constructed in the form of a rapidly convergent series; in the hyperbolic part, a generalized solution of the Cauchy problem of a special class is used. The functional relations on the degeneracy line lead to a singular integral equation, which is regularized by the Carleman–Vekua method into a Fredholm integral equation of the second kind with a weak singularity. Explicit formulas for the trace of the solution and its normal derivative are obtained. For a specific set of parameters, a numerical visualization of the solution is performed, the gluing conditions are verified, and a physical interpretation of the obtained graphs is given in the context of transonic gas dynamics. The results can be useful for mathematical modeling of flows in Laval nozzles and other problems of mechanics. Full article

Voltage-gated sodium channels are central to electrical excitability, and Nav1.7 is a major therapeutic target implicated in pain disorders and sensory signaling. Within the channel pore, permeating Na⁺ ions experience dynamically fluctuating hydration and coordination environments that may influence local ion–protein interactions. Identifying chemically distinct coordination states from molecular dynamics (MD) simulations is an important prerequisite for future higher-level electronic structure investigations. In this study, we present a reproducible workflow for identifying and classifying Na⁺ hydration–coordination microstates in the Nav1.7 pore using explicit-solvent molecular dynamics simulations. A geometrically defined pore region was used to quantify pore hydration and Na⁺ inner-shell coordination based on a 3.2 Å Na–O distance criterion. Na⁺ configurations were classified according to ligand identity into water-only (W), mixed protein–water (PW), and protein-only (P) microstates. Analysis of a 2 ns proof-of-principle simulation revealed a persistently hydrated pore environment, with Na⁺ coordination dominated by water-rich states and a smaller but distinct population of protein-contact configurations. These observations demonstrate that local coordination environments are chemically heterogeneous and cannot be fully described by hydration number alone. Representative structures from each microstate class were extracted to provide candidate configurations for future quantum mechanical, Quantum Mechanics/Molecular Mechanics (QM/MM), or density functional theory investigations of ion–ligand interactions in confined pore environments. The present work establishes a transparent and reproducible microstate-selection framework and does not report quantum mechanical energies, free-energy landscapes, or converged microstate populations. More broadly, the workflow provides a practical strategy for reducing complex MD ensembles into chemically interpretable coordination states suitable for subsequent higher-level analysis. Full article