Search Results (6,541)

Introduction: Accurate nuclear segmentation is essential for the reliable diagnostic interpretation of fluorescence in situ hybridization (FISH) results. However, automated 2D digital algorithms often fail in samples with dense or overlapping nuclei, such as lymphomas, due to the loss of spatial depth information. Here, we tested if AI-based 3D nuclear segmentation can improve the accuracy, reproducibility, and diagnostic reliability of FISH reading in critical situations. Materials and Methods: Formalin-fixed follicular lymphoma sections were FISH-labeled for BCL2 gene rearrangements and digitally scanned in multilayer Z-stacks. The analytic performance in nuclear segmentation of the adaptive thresholding-based FISHQuant, and the freely accessible AI-based NucleAIzer, StarDist, and Cellpose algorithms, were compared to the eye control-based traditional FISH testing, primarily focusing on nuclear segmentation. Results: We revealed that the Cellpose algorithm showed limited sensitivity to low-intensity signals and the adaptive thresholding 2D segmentation, and FISHQuant struggled to resolve densely packed nuclei, occasionally underestimating their counts. In contrast, 3D segmentation across focal planes significantly improved the nuclear separation and signal localization. AI-driven 3D models, especially NucleAIzer and StarDist, showed improved precision, lower variance (VP/VS ≈ 0.96), and improved gene spot correlation (r > 0.82) across multiple focal planes. The similar average number of gene spots per cell nuclei in the AI-based analyses as the eye control counting, despite the elevated number of cell nuclei found with AI, validated the AI nuclear segmentation results. Conclusions: Inaccurate segmentation limits automated diagnostic FISH signal evaluation. Deep learning 3D approaches, particularly NucleAIzer and StarDist, may overcome thresholding and 2D constraints and improve the consistency of nuclear detection, resulting in better classification of pathogenetic gene aberrations with automated workflows in digital pathology. Full article

The mapping of vineyard cultivars presents a substantial challenge in digital agriculture due to the crop’s high intra-class heterogeneity and low inter-class variability. High-dimensional spectral datasets, such as hyperspectral or spectrometry data, can overcome these difficulties. However, research has yet to fully address the need for optimal spectral feature subsets tailored for grapevine cultivar discrimination, while few studies have systematically examined waveband subsets that transfer effectively across different learning algorithms. This study sets out to address these gaps by introducing a Partial Least Squares (PLS)-based ensemble feature selection framework with Weighted Borda Count aggregation for cultivar discrimination. Using in-field spectrometry data, collected for six cultivars, and 18 PLS-based feature selection methods spanning filter, wrapper, and hybrid approaches, the PLS–ensemble identified 100 wavebands most relevant for cultivar discrimination, reducing dimensionality by ~95%. The efficacy and transferability of this subset were evaluated using five classification algorithms: Oblique Random Forest (oRF), Multinomial Logistic Regression (Multinom), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and a 1D Convolutional Neural Network (CNN). For oRF, Multinom, SVM, and MLP, the PLS–ensemble subset improved accuracy by 0.3–12% compared with using all wavebands. The subset was not optimal for the 1D-CNN, where accuracy decreased by up to 5.7%. Additionally, this study investigated waveband binning to transform narrow hyperspectral bands into broadband spectral features. Using feature multicollinearity and wavelength position, the 100 selected wavebands were condensed into 10 broadband features, which improved accuracy over both the full dataset and the original subset, delivering gains of 4.5–19.1%. The SVM model with this 10-feature subset outperformed all other models (F1: 1.00; BACC: 0.98; MCC: 0.78; AUC: 0.95). Full article

This study introduces a predictive model based on artificial neural networks (ANNs) for estimating the dynamic performance of commercially available sensible thermal energy storage (STES) systems. The model was trained and validated using high-resolution experimental data measured from two vertical cylindrical tanks (0.3 m³ each) including internal heat exchangers and operating under both heating and cooling modes. A comprehensive sensitivity analysis was conducted on 28 ANN architectures by varying the number of hidden neurons and input delays. The optimal configuration, designated as ANN5 (12 neurons, delay = 1), demonstrated superior accuracy in predicting temperature profiles and energy exchange. Validation against an independent dataset confirmed the model’s robustness, achieving normalized root mean square errors (NRMSEs) between 0.0022 and 0.0061 for the hot tank and between 0.0057 and 0.0283 for the cold tank. Energy prediction errors were within −3.87% for charging and 0.09% for discharging in heating mode, and 7.08% for charging and 0.13% discharging in cooling mode, respectively. These results highlight the potential of ANN-based approaches for real-time control, forecasting, and digital twin applications in STES systems. Full article

Carbon capture and storage (CCS) is essential for achieving net-zero emissions, yet amine-based capture systems face significant challenges including high energy penalties (20–30% of power plant output) and operational costs ($50–120/tonne CO${}_2$). This study develops and validates a novel multi-scale Digital Twin (DT) framework integrating Physics-Informed Neural Networks (PINNs) to address these challenges through real-time optimization. The framework combines molecular dynamics, process simulation, computational fluid dynamics, and deep learning to enable real-time predictive control. A key innovation is the sequential training algorithm with domain decomposition, specifically designed to handle the nonlinear transport equations governing CO${}_2$ absorption with enhanced convergence properties.The algorithm achieves prediction errors below 1% for key process variables (R${}^2$> 0.98) when validated against CFD simulations across 500 test cases. Experimental validation against pilot-scale absorber data (12 m packing, 30 wt% MEA) confirms good agreement with measured profiles, including temperature (RMSE = 1.2 K), CO${}_2$ loading (RMSE = 0.015 mol/mol), and capture efficiency (RMSE = 0.6%). The trained surrogate enables computational speedups of up to four orders of magnitude, supporting real-time inference with response times below 100 ms suitable for closed-loop control. Under the conditions studied, the framework demonstrates reboiler duty reductions of 18.5% and operational cost reductions of approximately 31%. Sensitivity analysis identifies liquid-to-gas ratio and MEA concentration as the most influential parameters, with mechanistic explanations linking these to mass transfer enhancement and reaction kinetics. Techno-economic assessment indicates favorable investment metrics, though results depend on site-specific factors. The framework architecture is designed for extensibility to alternative solvent systems, with future work planned for industrial-scale validation and uncertainty quantification through Bayesian approaches. Full article

Background: Globally, an estimated 1.4 billion people had hypertension in 2014, yet only just over 20% had controlled blood pressure, and about 580 million remained undiagnosed. Evidence indicates that salt substitutes facilitate meaningful blood-pressure reductions, yet their implementation remains restricted by social and healthcare constraints. The comparative effectiveness of alternative sodium-reduction interventions for elevated blood pressure remains unclear, limiting their introduction across diverse clinical and public health contexts. This study is registered with PROSPERO (CRD420251130153). Methods: We systematically searched PubMed, MEDLINE, and supplementary sources for randomised controlled trials (RCTs) published between 2000 and 2025. All behavioural sodium-reduction interventions among populations with elevated blood pressure, including hypertension, were included. The mean difference in systolic blood pressure (SBP) was the primary outcome, as evidence indicates that intensive control of SBP to levels below 120–130 mmHg is significantly associated with a reduced risk of major cardiovascular disease (CVD) and all-cause mortality. Network and subgroup pairwise meta-analyses were performed, with sensitivity analyses conducted to assess robustness of the findings and subgroup analyses used to explore clinical and public health factors influencing intervention effectiveness (clinical factors: blood pressure stage, trial duration, and medication status; public health factors: setting, implementation period, and country income level). Results: Of 10,404 records identified, 42 studies (46 trials, n = 46,771) were included. While the use of salt substitutes was ranked the most effective intervention in the network meta-analysis, with reductions of −6.78 mmHg (95% CI, −8.42, −5.14) compared to no intervention and −5.35 mmHg (95% CI, −7.89, −2.81) compared to conventional health education, self-monitoring devices and low-sodium diets, when combined with health education, demonstrated similar magnitudes of SBP reductions. Digital health education showed a larger point estimate for SBP reduction by −3.59 mmHg (95% CI −7.40 to 0.22) than conventional education (−1.43 mmHg; 95% CI −3.49 to 0.63), but both confidence intervals crossed zero, indicating no statistically significant difference. Subgroup analyses indicated that, except for trial duration, intervention setting, and country income level in specific intervention comparisons, clinical and public health factors did not generally account for differences in SBP reduction. No evidence of publication bias was observed, except between salt substitutes and no intervention and low-sodium diets and no intervention. Conclusions: Network meta-analysis ranked the use of salt substitutes as the most effective intervention, yet self-regulated interventions, such as low-sodium diets and self-monitoring devices, when combined with education-based sodium-reduction approaches, showed comparable point estimates for SBP reductions. Digital health education showed promise as a supportive adjunct to self-regulated interventions, although its effects were variable and require further quantification. These findings underscore the need for alternative sodium-reduction interventions supported by digital or conventional health education to improve blood pressure control. Health education on sodium reduction, including clinical counselling, should be viewed primarily as a complementary component that enhances other interventions. Full article

This systematic review examines how emotional well-being in journalism has been de-fined, experienced, and supported between 2010 and 2025. It draws on 15 peer-reviewed empirical studies identified in Web of Science and Scopus and evaluated using PRISMA 2020 and the MMAT. The review addresses three main gaps in the field: unclear definitions, limited synthesis of risk and protective factors, and scarce assessment of support interventions. Across studies, emotional distress emerges from structural pressures, such as overwork, trauma exposure, online harassment, job precarity, and the erosion of collegial networks. These pressures, rather than inherent traits of journalistic work, shape vulnerability. Protective factors include social support, editorial autonomy, professional experience, purpose-driven motivation, and practices like mindfulness or digital disconnection. Yet their impact is often limited by weak organizational infrastructures. Vulnerability is higher among women, freelancers, and early career journalists, although intersectional analyses remain rare. Sectoral and organizational responses—peer networks, resilience programs, trauma-informed training, and emerging digital safety policies—show promise but remain fragmented. The review concludes that emotional well-being should be framed as an ethical and structural responsibility within journalism, and that sustainable progress requires systemic measures that foster psychological safety and professional dignity. Full article

Parkinson’s disease (PD) is characterized by alterations in movement dynamics that are difficult to quantify with conventional clinical assessment. This study proposes an integrated approach combining graph-based kinematic analysis with explainable machine learning to identify digital biomarkers of Parkinsonian motor impairment. Kinematic signals were acquired using Xsens inertial sensors from 51 patients with PD and 53 healthy controls. For each participant, subject-specific kinematic networks were constructed by modeling inter-segment similarities through Jensen–Shannon divergence, from which global and local graph-theoretical metrics were extracted. A machine learning pipeline incorporating voting feature selection, and XGBoost classification was evaluated using a nested cross-validation design. The model achieved robust performance (AUC = 0.87), and explainability analyses using SHAP identified a subset of 13 features capturing alterations in velocity, inter-segment connectivity, and network centrality. PD was characterized by increased positional variability, reduced distal limb velocity, and a redistribution of network centrality towards proximal body segments. These features were associated with clinical severity, confirming their physiological relevance. By integrating graph-theoretical modeling, explainable artificial intelligence, and machine learning methodology, this work provides a method of discovering quantitative biomarkers capturing alterations in motor coordination. These findings highlight the potential of ML and kinematic networks to support objective motor assessment in PD. Full article

Tunnel point cloud semantic segmentation is a critical step in achieving refined perception and intelligent management of tunnel structures. Addressing common challenges including indistinct boundaries and fine-grained category discrimination, this paper proposes MFPNet, a multi-scale feature perception network specifically designed for tunnel scenarios. This approach employs kernel convolution to effectively model local point cloud geometries within continuous spaces. Building upon this foundation, an error-feedback-based local-global feature fusion mechanism is designed. Through bidirectional information exchange, higher-level semantic information compensates for and constrains lower-level geometric features, thereby mitigating information fragmentation across semantic hierarchies. Furthermore, an adaptive feature re-calibration and cross-scale contextual correlation mechanism is introduced to dynamically modulate multi-scale feature responses. This explicitly models contextual dependencies across scales, enabling collaborative aggregation and discriminative enhancement of multi-scale semantic information. Experimental results on tunnel point cloud datasets demonstrate that the proposed MFPNet has achieved significant improvements in both overall segmentation accuracy and category balance, with mIoU reaching 87.5%, which is 5.1% to 33.0% higher than mainstream methods such as PointNet++ and RandLA-Net, and the overall classification accuracy reaching 96.3%. These results validate the method’s efficacy in achieving high-precision three-dimensional semantic understanding within complex tunnel environments, providing robust technical support for tunnel digital twin and intelligent detection applications. Full article

Background: The rapid advancement in artificial intelligence (AI) has fundamentally reshaped gut microbiome research by enabling high-resolution analysis of complex, high-dimensional microbial communities and their functional interactions with the human host. Objective: This narrative review aims to synthesize recent methodological advances in AI-driven gut microbiome research and to evaluate their translational relevance for therapeutic optimization, personalized nutrition, and precision medicine. Methods: A narrative literature review was conducted using PubMed, Google Scholar, Web of Science, and IEEE Xplore, focusing on peer-reviewed studies published between approximately 2015 and early 2025. Representative articles were selected based on relevance to AI methodologies applied to gut microbiome analysis, including machine learning, deep learning, transformer-based models, graph neural networks, generative AI, and multi-omics integration frameworks. Additional seminal studies were identified through manual screening of reference lists. Results: The reviewed literature demonstrates that AI enables robust identification of diagnostic microbial signatures, prediction of individual responses to microbiome-targeted therapies, and design of personalized nutritional and pharmacological interventions using in silico simulations and digital twin models. AI-driven multi-omics integration—encompassing metagenomics, metatranscriptomics, metabolomics, proteomics, and clinical data—has improved functional interpretation of host–microbiome interactions and enhanced predictive performance across diverse disease contexts. For example, AI-guided personalized nutrition models have achieved AUC exceeding 0.8 for predicting postprandial glycemic responses, while community-scale metabolic modeling frameworks have accurately forecast individualized short-chain fatty acid production. Conclusions: Despite substantial progress, key challenges remain, including data heterogeneity, limited model interpretability, population bias, and barriers to clinical deployment. Future research should prioritize standardized data pipelines, explainable and privacy-preserving AI frameworks, and broader population representation. Collectively, these advances position AI as a cornerstone technology for translating gut microbiome data into actionable insights for diagnostics, therapeutics, and precision nutrition. Full article

Extended reality (XR), encompassing virtual reality (VR), augmented reality (AR), and mixed reality (MR), is rapidly reshaping the landscape of digital interaction and immersive communication. As XR evolves toward ultra-realistic, real-time, and interactive experiences, it places unprecedented demands on wireless communication systems in terms of bandwidth, latency, and reliability. Conventional RF-based networks, constrained by limited spectrum and interference, struggle to meet these stringent requirements. In contrast, visible light communication (VLC) offers a compelling alternative by exploiting the vast unregulated visible spectrum to deliver high-speed, low-latency, and interference-free data transmission—making it particularly suitable for future XR environments. This paper presents a comprehensive survey on VLC-enabled XR communication systems. We first analyze XR technologies and their diverse quality-of-service (QoS) and quality-of-experience (QoE) requirements, identifying the unique challenges posed to existing wireless infrastructures. Building upon this, we explore the fundamentals, characteristics, and opportunities of VLC systems in supporting immersive XR applications. Furthermore, we elaborate on the key enabling techniques that empower VLC to fulfill XR’s stringent demands, including high-speed transmission technologies, hybrid VLC-RF architectures, dynamic beam control, and visible light sensing capabilities. Finally, we discuss future research directions, emphasizing AI-assisted network intelligence, cross-layer optimization, and collaborative multi-element transmission frameworks as vital enablers for the next-generation VLC–XR ecosystem. Full article

Accurate Digital Terrain Models (DTMs) are essential for managing forest drainage networks as a crucial element of water management, yet dense canopies and complex micro-topography challenge Airborne Laser Scanning (ALS) precision. This study evaluates the vertical accuracy of an ALS-derived DTM specifically within forest drainage ditches, utilizing 706 GNSS and total station measurements for validation. The results indicate a positive elevation bias, with a mean elevation error of 0.415 m and an RMSE of 0.464 m, 54.7% higher than the 0.3 m declared in the DTM technical report. Forest height, acting as a proxy for forest structural density and canopy closure, was significantly associated with a reduction in ground reflection density and an increase in the distance to the nearest ground reflection (p < 0.05). Mixed-effects ANOVA confirmed that there are significantly more ground reflections in low vegetation (0–1 m). Crucially, multiple regression analysis revealed that forest height was not the primary driver of elevation error; instead, ditch geometry was the most significant predictor. Narrower ditches exhibited substantially higher errors than wider ones, regardless of the canopy height. Furthermore, while ground reflection density decreased in mature stands, this reduction did not significantly diminish DTM vertical accuracy, suggesting that some of the LiDAR reflections of low vegetation could be misclassified as ground reflections, decreasing accuracy. These findings suggest that while ALS is effective for general forest topography and mapping drainage infrastructure, its application may require corrections for ditch dimensions rather than vegetation height alone to mitigate systematic overestimation of ditch bed elevations. Full article

This study aims to enhance the value of the Montepulciano d’Abruzzo PDO supply chain by integrating multi-elemental and isotopic profiling with chemometric analysis. The objective is to establish a pilot study for origin authentication, supporting strategic, managerial, and regulatory decision-making for stakeholders in the wine sector. Wine and soil samples from producers in the Abruzzo region were analyzed for 63 elements and selected isotopic ratios using HR-ICP-MS and MC-ICP-MS. Exploratory data analysis, including PCA and clustering, was employed to investigate intrinsic data structure. Variable selection techniques identified the most discriminant markers, and multiple classification models were tested to assess producer-level differentiation. The combined elemental and isotopic dataset showed strong intrinsic structure. Four variables—Mo, ²⁰⁸Pb/²⁰⁶Pb, P, and ⁸⁷Sr/⁸⁶Sr—emerged as key discriminants. Quadratic Discriminant Analysis and Artificial Neural Networks achieved 100% accuracy in classifying samples by producer. The results demonstrate that integrating multi-elemental and isotopic data with chemometric tools offers a pilot approach to authenticate wine origin and enhance transparency across the PDO supply chain. Beyond scientific innovation, this study provides a pilot decision support model that can strengthen competitive differentiation, regulatory compliance, and sustainable territorial development, highlighting opportunities for digital transformation in PDO management. Full article

Dual-target drug design addresses complex diseases and drug resistance, yet existing computational approaches struggle with simultaneous multi-protein optimization. This study presents SFG-Drug, a novel dual-target molecular generation model combining Monte Carlo tree search with gated recurrent unit neural networks for simultaneous MEK1 and mTOR targeting. The methodology employed DigFrag digital fragmentation on ZINC-250k dataset, integrated low-frequency masking techniques for enhanced diversity, and utilized molecular docking scores as reward functions. Comprehensive evaluation on MOSES benchmark demonstrated superior performance compared to state-of-the-art methods, achieving perfect validity (1.000), uniqueness (1.000), and novelty (1.000) scores with highest internal diversity indices (0.878 for IntDiv1, 0.860 for IntDiv2). Over 90% of generated molecules exhibited favorable binding affinity with both targets, showing optimal drug-like properties including QED values in [0.2, 0.7] range and high synthetic accessibility scores. Generated compounds demonstrated structural novelty with Tanimoto coefficients below 0.25 compared to known inhibitors while maintaining dual-target binding capability. The SFG-Drug model successfully bridges the gap between computational prediction and practical drug discovery, offering significant potential for developing new dual-target therapeutic agents and advancing AI-driven pharmaceutical research methodologies. Full article

The residential energy sector contributes substantially to global energy-related emissions. Effective energy management requires an understanding occupant behavior through activity detection and habit identification. Recent advances in artificial intelligence (AI) and machine learning (ML) enable the automatic detection of user activities and prediction of energy needs based on historical consumption data. Non-intrusive load monitoring (NILM) facilitates device-level disaggregation without additional sensors, supporting demand forecasting and behavior-aware control in Home Energy Management Systems (HEMSs). This review synthesizes various AI and ML approaches for detecting user activities and energy habits in HEMSs from 2020 to 2025. The analyses revealed that deep learning (DL) models, with their ability to capture complex temporal and nonlinear patterns in multisensor data, achieve superior accuracy in activity detection and load forecasting, with occupancy detection reaching 95–99% accuracy. Hybrid systems combining neural networks and optimization algorithms demonstrate enhanced robustness, but challenges remain in limited cross-building generalization, insufficient interpretability of deep models, and the absence of dataset standardized. Future work should prioritize lightweight, explainable edge-ready models, federated learning, and integration with digital twins and control systems. It should also extend energy optimization toward occupant wellbeing and grid flexibility, using standardized protocols and open datasets for ensuring trustworthy and sustainability. Full article

Research on road transport infrastructures is rapidly evolving as electrification, automation, and digital connectivity reshape how systems are designed, operated, and managed. This study presents a combined bibliometric, scientometric, and network analysis of 2755 publications published between 2021 and 2025 to map the intellectual structure, main contributors, and dominant technological themes shaping contemporary road transport research. Using data from the Web of Science Core Collection, co-occurrence mapping, thematic analysis, and collaboration networks were generated using Bibliometrix and VOSviewer. The results reveal strong growth in research output, with China, the United States, and Europe forming the core of high-impact publication and collaboration networks. Six bibliometric clusters were identified and consolidated into three overarching domains: road transport systems, emphasizing vehicle dynamics, control, and real-time computational frameworks; energy and efficiency-oriented mobility research, focusing on electrification, optimization, and infrastructure integration; and emerging digital technologies, including IoT, AI, and autonomous vehicles. The analysis highlights persistent research gaps related to interoperability, cybersecurity, large-scale deployment, and governance of intelligent transport infrastructures. Overall, the findings provide a data-driven overview of current research priorities and structural patterns shaping next-generation road transport systems. Full article