Search Results (2,820)

There is diminished transparency, fragmented information exchange, and lack of trust among geographically dispersed stakeholders, which increasingly challenge global supply chains. The classic centralized systems of supply chain management are not always capable of being able to offer real-time traceability and data integrity which is dependable and effective in contract enforcement. The proposed study is a blockchain-based smart contract design that is focused on ensuring increased transparency, traceability and trust in global supply chain management. The suggested framework will combine automated smart contracts, cryptographic provenance tracking, permissioned blockchain consensus, and a decentralized trust score evaluation mechanism to overcome some of the major operation and governance challenges. A simulated assessment with a multi-tier global supply chain setting of 15 blockchain nodes and 12,000 transactions was performed through experimentation. The findings show that the proposed system attained an average transaction delay of 210 ms, which is very low compared to centralized systems (520 ms), with throughput being raised to 120 transactions per minute. End-to-end traceability performance also improved significantly, with a reduction in trace-back time to 8 s compared with 95s this represents a 100% tampering detection rate. The consensus mechanism ensured that the ledger integrity failed only at a rate of less than 1.1%, even when more than 30% of nodes were faulty. Risk-wise, the trust evaluation algorithm dynamically enhanced reliable supplier scores up to 12%, which facilitated the selection of reliable partners. On the whole, the results prove that smart contracts based on blockchains can drastically enhance the efficiency of operations, data integrity, and confidence in global supply chains, with the platform capable of providing a resilient and scalable backbone for the future supply chain management model. Full article

Chronic Kidney Disease (CKD) affects over 850 million people globally, with early detection critical for effective intervention. We present DeepCKD-Net, a hybrid deep learning framework that synergistically integrates transformer architectures with gradient-boosting ensembles for multi-stage CKD prediction. Using a clinical dataset of 400 patients with 26 biomarker features from the UCI repository, our framework introduces three key innovations: (1) a hierarchical attention mechanism capturing complex inter-dependencies among clinical parameters, (2) an adaptive feature fusion module combining transformer-learned patterns with gradient-boosting decision boundaries, and (3) a confidence-aware ensemble strategy providing uncertainty quantification for clinical decision support. DeepCKD-Net achieves 98.7% accuracy and 0.993 AUC, surpassing state-of-the-art methods by 4.2% while maintaining 16.8 ms inference time suitable for real-time clinical deployment. Integrated SHAP analysis provides interpretable predictions, with serum creatinine (SHAP value: 0.342) and blood urea (0.287) identified as top predictive biomarkers, aligning with established clinical knowledge. The framework demonstrates robust performance under realistic clinical conditions, maintaining >90% accuracy with 20% missing data. Our contributions advance AI-driven nephrology diagnostics by providing a deployable, interpretable, and clinically validated solution for early CKD detection. Full article

Web application firewalls (WAFs) are critical defenses against persistent threats to web applications, yet their security evaluation remains challenging. Traditional manual testing methods are often inefficient and resource-intensive, while existing reinforcement learning (RL)-based automated approaches face two key limitations: (1) attackers cannot perceive opaque WAF rule logic; (2) boolean feedback from WAFs results in sparse/delayed rewards—sparse rewards trap agents in blind exploration, and delayed rewards hinder the association between early actions and final outcomes, adversely affecting learning efficiency. To address those challenges, we propose Ouroboros—a framework integrating genetic algorithm-based symbolic rule reconstruction (translating WAF rules into interpretable RNNs for fine-grained confidence scoring), timing side-channel analysis (evaluating rule-matching depth), and a multi-tiered reward mechanism to enable self-evolving RL testing. Experiments show that the framework reaches 89.2% bypass success rate on signature-based WAFs. This paper presents an efficient solution for automated WAF testing and delivers insights for optimizing rule logic and anomaly detection mechanisms. Full article

Background: Leading sports medicine and nutrition organizations recommend replacing sodium losses during prolonged exercise; however, practical guidance for implementing sodium replacement strategies remains limited. Estimating sodium needs during exercise requires assessment of both whole-body sweat sodium concentration (WBSSC) and sweat rate. Objectives: This study focused on WBSSC by examining its temporal stability, reproducibility, and predictability during prolonged cycling exercise while drinking according to two hydration strategies. Methods: Using a randomized, crossover, counterbalanced design, eight highly trained men completed two 5 h cycling sessions (183 ± 14 W, 30 °C) while consuming fluids either in a programmed (P) or ad libitum (A_L) fashion. Sweat was collected with patches applied on the forearm for ~20 min before sampling, which occurred at ~40, 130, 220, and 290 min. Local sweat sodium concentration was converted to WBSSC using a validated equation. Results: A main effect of time was observed for WBSSC (p < 0.05), with only the 40 min time point differing from later measurements; no condition or interaction effects were detected. The within-trial typical variation in WBSSC was 7.2 mmol·L⁻¹ for P and 6.1 mmol·L⁻¹ for A_L, while the between-trial typical variation was 5.6 mmol·L⁻¹. The WBSSC measured at 40 min predicted mean exercise WBSSC with good precision and moderate stability (y = 0.2738 + 1.3397x, R² = 0.87, standard error of the estimate = 5.4 mmol·L⁻¹, 95% confidence interval slope = 0.82–1.86 mmol·L⁻¹). Conclusions: These findings indicate that during prolonged cycling exercise, WBSSC (1) varies trivially within and between trials; (2) can reasonably be predicted using a single sweat sample and; (3) is not influenced by P or A_L drinking. Full article

In recent years, deep learning has driven remarkable progress in remote sensing change detection (CD); however, practical deployment is still hindered by two limitations. First, CD results are easily degraded by imaging-induced uncertainties—mixed pixels and blurred boundaries, radiometric inconsistencies (e.g., shadows and seasonal illumination changes), and slight residual misregistration—leading to pseudo-changes and fragmented boundaries. Second, prevailing methods follow a static one-pass inference paradigm and lack an explicit feedback mechanism for adaptive error correction, which weakens generalization in complex or unseen scenes. To address these issues, we propose a feedback-driven CD framework that integrates a dual-branch U-Net with deep reinforcement learning (RL) for pixel-level probabilistic iterative refinement of an initial change probability map. The backbone produces a preliminary posterior estimate of change likelihood from multi-scale bi-temporal features, while a PPO-based RL agent formulates refinement as a Markov decision process. The agent leverages a state representation that fuses multi-scale features, prediction confidence/uncertainty, and spatial consistency cues (e.g., neighborhood coherence and edge responses) to apply multi-step corrective actions. From an imaging and interpretation perspective, the RL module can be viewed as a learnable, self-adaptive imaging optimization mechanism: for high-risk regions affected by blurred boundaries, radiometric inconsistencies, and local misalignment, the agent performs feedback-driven multi-step corrections to improve boundary fidelity and spatial coherence while suppressing pseudo-changes caused by shadows and illumination variations. Experiments on four datasets (CDD, SYSU-CD, PVCD, and BRIGHT) verify consistent improvements. Using SiamU-Net as an example, the proposed RL refinement increases mIoU by 3.07, 2.54, 6.13, and 3.1 points on CDD, SYSU-CD, PVCD, and BRIGHT, respectively, with similarly consistent gains observed when the same RL module is integrated into other representative CD backbones. Full article

Multi-Object Tracking (MOT) is a fundamental research topic in the field of computer vision, with broad application potential in unmanned aerial vehicle (UAV) videos. However, existing methods still face significant challenges in detection discriminability and identity association stability due to the small scale and weak appearance of objects under aerial viewpoints, as well as complex background interference. To address these issues, we propose an Edge-Graph Enhanced Network (EGEN) for UAV aerial MOT, aiming to improve the performance of small object detection (SOD) and tracking in complex scenes. The framework follows a one-step tracking paradigm and consists of three main components: object detection, embedding feature extraction, and data association. In the detection stage, we design an Edge-Guided Gaussian Enhancement Module (EGGEM), which models edge relationships between objects and backgrounds from a global perspective and selectively enhances Gaussian features guided by edge information, thereby strengthening key structural features of small objects while suppressing background interference. In the embedding feature extraction stage, we develop a Graph-Guided Embedding Enhancement Module (GGEEM), which explicitly represents re-identification (ReID) embeddings as a graph structure and jointly models nodes and their neighborhood relationships to fully capture inter-object associations and enhance embedding discriminability. In the data association stage, we introduce a hierarchical two-stage association strategy to match objects with different confidence levels separately, improving tracking stability and robustness. Extensive experiments on the VisDrone, UAVDT, and self-constructed WildDrone datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches in both SOD and MOT, demonstrating strong generalization and practical applicability. Full article

Background: Atrial fibrillation (AF) frequently develops in patients with atrial flutter (AFL), even after successful cavotricuspid isthmus (CTI) ablation. Identifying simple clinical markers for early detection is crucial. Diagonal earlobe crease (ELC), also known as Frank’s sign, has been proposed as a marker of aging and cardiovascular risk. This study investigates the association between ELC and the risk of new-onset AF following CTI ablation in patients with AFL. Methods: We conducted a retrospective cohort study of 292 patients without a prior history of AF who underwent CTI ablation for typical AFL between 2015 and 2024. The presence of ELC was assessed at baseline CTI ablation. The primary outcome was the occurrence of new-onset AF during follow-up, stratified according to the presence of ELC. The median follow-up duration was 49 months, with a minimum follow-up of 6 months. Results: Among the 292 patients, 72 (24.7%) exhibited ELC. Patients with ELC were older (59 ± 11 years vs. 55 ± 14 years, p = 0.05). During the follow-up period, new-onset AF occurred in 31 patients with ELC (43.1%) and 65 patients without ELC (29.5%) (p = 0.03). Kaplan–Meier analysis demonstrated that the occurrence of AF was significantly higher in the ELC group than in the non-ELC group (log-rank test, p = 0.013). Multivariate analysis revealed that ELC was independently associated with an increased risk of AF (hazard ratio 1.67, 95% confidence interval 1.03–2.72, p = 0.039). Conclusions: The presence of ELC is associated with a higher risk of new-onset AF following CTI ablation in patients with AFL. ELC may serve as a simple, non-invasive clinical marker to identify patients who may benefit from closer rhythm surveillance after AFL ablation. Full article

Bird’s-eye-view (BEV) perception has emerged as a key representation for unified scene understanding in autonomous driving. However, current BEV methods relying solely on monocular cameras suffer from severe degradation under adverse weather and dynamic scenes due to limited depth cues and illumination dependency. To address these challenges, we propose a robust multi-modal BEV perception framework that integrates dual-source 4D millimeter-wave radar and multi-view camera images. The proposed architecture systematically exploits Doppler velocity and temporal information from 4D radar to model dynamic object motion, while introducing a deformable fusion strategy in the BEV space for accurate semantic alignment across modalities. Our design includes four key modules: a Doppler-Aware Radar Encoder (DARE) that enhances motion-sensitive features via velocity-guided attention; a Fog-Aware Feature Denoising Module (FADM) that suppresses modality inconsistency in low-visibility conditions through cross-modal attention and residual enhancement; a Multi-Modal Temporal Fusion Module (TFM) that encodes radar temporal sequences using a Transformer encoder for motion continuity modeling; and a confidence-aware multi-task loss that jointly supervises semantic segmentation, motion estimation, and object detection. Extensive experiments on the DualRadar dataset and adverse-weather simulations demonstrate that our method achieves significant gains over state-of-the-art baselines in BEV segmentation accuracy, detection robustness, and motion stability. The proposed framework offers a scalable and resilient solution for real-world autonomous perception, especially under challenging environmental conditions. Full article

Multimodal fusion methods leveraging various sensors provide strong support for 3D object detection. However, under adverse weather conditions such as rain, fog, snow, and intense glare, complex environmental factors can degrade sensor data quality, leading to increased false positives and missed detections. In addition, sensor modalities (e.g., LiDAR and cameras) inherently vary in information density, and directly fusing them can cause critical details in high-density data to be diluted by low-density data, thereby increasing errors. To address these issues, we propose a Semantic-Enhanced Bidirectional Multimodal Fusion (SeBFusion) framework. By introducing a semantic enhancement mechanism and a bidirectional fusion strategy, SeBFusion mitigates the impact of noise under adverse weather and alleviates information dilution in multimodal fusion. Specifically, SeBFusion first employs a virtual point generation and camera semantic injection module to selectively map image semantic features into 3D space, producing semantically enhanced LiDAR features to compensate for the sparsity of the raw LiDAR point cloud. Then, during cross-modal interaction, we design a bidirectional cross-attention fusion module. This module estimates the confidence of each modality and adaptively reweights the bidirectional information flow, thereby reducing the risk of noise propagation across modalities and improving the robustness and accuracy of 3D object detection in complex environments. Experiments on adverse-weather versions of datasets such as KITTI-C and nuScenes-C validate the effectiveness and superiority of the proposed method. On the nuScenes-C dataset, it achieves 66.2% mAP and 66.6% mAP under fog and snow conditions, respectively. Full article

Background/Objectives: Mitochondrial DNA (mtDNA) is an important resource for understanding human ancestry, population diversity, and the molecular mechanisms of mitochondrial diseases. However, analyzing mtDNA thoroughly often requires advanced bioinformatics skills and command-line knowledge. To address this challenge, we created Mitochondrial Genome Explorer (MitoGEx), a user-friendly computational pipeline optimized for human mtDNA analysis that combines multiple mtDNA analysis modules within a single graphical user interface. Methods: The platform simplifies key analytical steps, such as quality control, sequence alignment, alignment quality assessment, variant detection, haplogroup classification, and phylogenetic reconstruction. Users can choose between Quick and Advanced modes, which offer default settings or customizable options based on their analysis needs. To demonstrate its effectiveness, we analyzed 15 whole-exome sequencing (WES) samples from Songklanagarind Hospital using MitoGEx. Results: The sequencing data were of high quality, with over 92 percent of bases scoring above a Phred score and consistent GC content across all samples. Variant detection using the GATK mitochondrial pipeline and annotation with ANNOVAR and the MitImpact database revealed multiple high-confidence variants. Haplogroup classification with Haplogrep 3 and phylogenetic analysis with IQ-TREE 2 confirmed diverse maternal lineages within the cohort. Conclusions: Taken together, MitoGEx facilitates mitochondrial genome analysis in a reproducible and accessible manner for both research and clinical bioinformatics applications. The analytical results produced by MitoGEx are concordant with those obtained using standalone bioinformatic tools, demonstrating analytical correctness. By integrating all analysis steps into a single automated workflow, MitoGEx reduces execution time and limits human error inherent to manual, multi-step pipelines. Full article

Reservoirs are critical infrastructure for water and energy security, and require accurate and timely monitoring of reservoir water extent to make informed decisions. Optical remote sensing provides frequent, large-area observations; however, automated water extraction is often complicated by dam operation and surface heterogeneity, which increase spectral variability. Supervised methods, though widely used, generally require manual labels and often perform poorly when transferred across sensors and regions, limiting operational deployment. In this paper, we develop a geo-spectral feature-guided Self-Supervised Water Detection (SWD) framework, an automated algorithm designed for multi-source optical imagery. SWD consists of two stages: pixel-level classification and object-level refinement. Initially, SWD integrates spatial priors with spectral features to automatically derive high-confidence samples, which are then utilized to parameterize Gaussian mixture model to represent multimodal spectral distribution throughout the image. Furthermore, superpixel-constrained region growing is applied to refine shoreline and ensure object-level consistency. We validated SWD across 36 test cases comprising three sensors, six reservoirs, and two hydrological conditions. Compared with Random Forest and U-Net, SWD achieved the best performance. Specifically, (1) in cross-scale tests, SWD achieved high consistency with IoU ≥ 0.774; (2) in cross-region transfers, SWD maintained stable generalization (SD: 0.010); and (3) in hydrological response assessments, SWD captured water-level fluctuations with minimal bias variation (ΔRE < 1%). In addition, SWD framework is computationally efficient, with processing times of 0.49–1.29 s/Mpx on a standard CPU. This study demonstrates that SWD effectively addresses spectral variability and surface complexity in reservoir water area detection across multi-source optical imagery. It operates without manual labels or model training, enabling automated, large-scale and multi-temporal reservoir water monitoring. Full article

Background: Spatial granularity plays a central role in the analysis of environmental hazards, yet its influence on health impact assessment remains overlooked. This study explicitly treats spatial aggregation level as a methodological variable and examines how different spatial aggregation strategies affect the association between high temperature, ozone, and out-of-hospital cardiovascular emergencies recorded by emergency medical services. Methods: A distribution thresholding approach is applied to both the environmental hazard and the health outcome. The analysis is conducted at three spatial levels: a fully aggregated region-wide level, population-based districts, and a combined strategy that cumulates district level results. The model estimates the Odds Ratio for each configuration. Results: The combined district-based strategy provides the most robust association, with an Odds Ratio of 1.13 (95% confidence interval 1.10 to 1.17). The region-wide and single district approaches show weaker or inconsistent significance. The findings indicate that the spatial level of analysis heavily impacts both the significance and the interpretability of the statistical results. Conclusions: The study demonstrates that the spatial structure of data strongly influences the detection of short-term health effects linked to environmental stressors. This contributes to the geomatics field by explicitly isolating spatial aggregation as an analytical dimension, demonstrating how spatial aggregation choices and explicit consideration of the Modifiable Areal Unit Problem can enhance methodological accuracy, support clearer spatial reasoning, and guide the development of more reliable territorial health indicators. Full article

Objective: To evaluate the performance of photon-counting detector CT (PCD-CT) angiography for the detection and quantification of vascular stenosis. Methods: Web of Science, PubMed, and Cochrane databases were searched from January 1980 to December 2025 to identify studies assessing PCD-CT angiography for the detection and quantification of vascular stenosis, using invasive angiography as the reference standard. The risk of bias of the included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Diagnostic performance metrics, including sensitivity and specificity and quantification values, were extracted from the included studies and a formal narrative synthesis was performed. The meta-analysis included studies reporting true-positive, false-positive, true-negative, and false-negative data. A meta-analysis was conducted only when a minimum of two eligible studies assessed diagnostic performance within the given vascular territory. Statistical analyses were performed using R software (v4.5.0), applying a random-effects model for the meta-analysis. Results: Of 415 identified studies, 20 were included in the systematic review, comprising a total of 9165 participants, with the majority (17/20, 85%) focusing on coronary artery stenosis. In the meta-analysis of three studies, ultra-high-resolution (UHR) PCD-CT demonstrated excellent diagnostic performance for detecting coronary stenosis for patients with ≥50%, having a pooled sensitivity of 96.1% (95% confidence level (CI): 89.3–99.6), specificity of 87.5% (95% CI: 78.2–93.3), positive predictive value (PPV) of 91.9% (95% CI: 70.3–98.2), and negative predictive value (NPV) of 94.8% (95% CI: 86.0–98.6). Compared with conventional energy-integrating detector CT (EID-CT), PCD-CT consistently showed superior diagnostic performance, particularly in the specificity and PPV. In terms of stenosis quantification, PCD-CT showed closer agreement with reference standards than EID-CT, leading to the reclassification of coronary stenosis severity in up to 49% of patients. Evidence for non-coronary vascular territories, including intracranial and peripheral arteries remains limited but suggests promising diagnostic performance. For lower-limb arterial stenosis, the reported sensitivity was 77.4–91%, and specificity was 72.1–91%. For intracranial in-stent stenosis, PCD-CT demonstrated a sensitivity of 100% and a specificity of 89%. Conclusions: PCD-CT angiography provides high diagnostic performance and improved stenosis quantification for coronary artery stenosis. UHR PCD-CT has excellent diagnostic performance for detecting coronary stenosis and consistently outperforms conventional EID-CT, especially in the specificity and positive predictive value. Full article

Background: Automated monitoring of crop health and the precise detection of abiotic stress, such as herbicide damage, are demanding challenges for modern agriculture. Abiotic stresses are a demanding challenge for modern agriculture, responsible for up to 82% of yield losses in major food crops. To address this, researchers are increasingly leveraging artificial intelligence (AI) to automate the detection and management of these stressors. Methods: In particular, this paper presents an instance segmentation framework to precisely detect interveinal chlorosis and leaf curling on potato leaves, two common symptoms of herbicide damage and soft wind. Within the context of precision agriculture and the need to address the inherent ambiguity in manual leaf assessment, this study employs a partial label learning approach to refine the dataset. This method utilizes an EfficientNet-b1 model to classify ambiguous samples, generating high-confidence pseudo-labels for instances that are difficult to categorize visually. The core of the proposed framework is a Mask2Former model, which is first fine-tuned on general potato leaf dataset to enhance its segmentation capabilities and then transferred on the refined, pseudo-labeled dataset. Results & Conclusions: This two-stage approach yields a highly accurate segmentation tool, achieving 89% mAP₅₀ and a pseudo-label classification accuracy of 95%, designed for integration into smart agriculture systems like ground level robotics or unmanned aerial vehicles for real-time, automated crop monitoring. Full article

Straw burning is a major source of regional air pollution. However, its reliable remote sensing detection faces problems in distinguishing agricultural fires from non-agricultural thermal anomalies, adequately leveraging burning seasonality, and overcoming the scarcity of pixel-level annotations. To comprehensively address these issues, this study proposes an end-to-end framework for straw burning identification that integrates spatio-temporal weighting and semi-supervised learning. The framework introduces a data-driven spatial weight optimization method to automatically learn discriminative weights for diverse land cover types (e.g., farmland, industry), replacing subjective empirical settings. Furthermore, a temporal weighting model, developed using Kernel Density Estimation, dynamically adjusts classification confidence according to historical burning seasonality, enhancing recall during peak seasons while suppressing off-season false positives. Finally, an adapted Dual-Backbone Dynamic Mutual Training (DB-DMT) strategy collaboratively leverages both limited labeled (24.5%) and abundant unlabeled (75.5%) high-resolution imagery, significantly improving model generalization in label-scarce scenarios. Validation across five representative regions of China demonstrated the framework’s superior performance, achieving a semantic segmentation mean Intersection over Union (mIoU) improvement of 3.33% (to 71.92%) and increasing precision in Henan from 95.21% to 97.71%. Crucially, the framework effectively reduced the off-season false positive rate (FPR) from 5.14% to a mere 0.23% in highly industrialized regions like Tianjin. By systematically mitigating both spatial geolocation bias and seasonal phenology confusion, our approach offers a robust and scalable solution for straw burning monitoring and a transferable paradigm for other environmental remote sensing applications. Full article