Search Results (9,694)

Ecosystem service value (ESV) is a critical indicator of regional ecological well-being. Assessing and forecasting ESV are essential for achieving the coordinated development of environmental and economic systems. This study employs the SD-PLUS model, integrating Shared Socioeconomic Pathways (SSPs) and Representative Concentration Pathways (RCPs) to assess the spatiotemporal dynamics of land use and land cover change (LUCC), as well as ESV in Zhengzhou from 2030 to 2040. It analyses the impact of various driving factors on ESV and examines the spatial correlations among ecosystem services across different regions. The results indicate that the total ESV is expected to decrease by 73.53 × 10⁷ yuan, primarily due to significant reductions in cropland and water areas. By 2040, ESV is projected to increase by 14.51 × 10⁷ yuan under the SSP126 scenario, decrease by 73.18 × 10⁷ yuan under the SSP585 scenario, and show a moderate decline under the SSP245 scenario. Climate factors, transportation location, and topographical features have a significantly positive impact on ESV, while environmental and socioeconomic factors exert a negative influence. The analysis of interrelationships among ecosystem services shows that synergies dominate, especially between supporting and cultural services, with only localised trade-offs observed. These findings contribute valuable insights for the development of scientifically sound, well-reasoned, and efficient strategies for ecological conservation and sustainable development. Full article

Structural Health Monitoring (SHM) of steel bridges is vital for ensuring the longevity, safety, and reliability of critical transportation infrastructure. This review synthesizes recent advancements in SHM technologies and methodologies for steel bridges, highlighting the shift from traditional vibration-based monitoring to data-driven, intelligent systems. It covers core technological themes, including various sensing systems such as wireless sensor networks, fiber optics, and piezoelectric transducers, along with the impact of machine learning, artificial intelligence, and statistical pattern recognition. The paper explores applications for damage detection, such as fatigue life assessment and monitoring of components like expansion joints. Persistent challenges, including deployment costs, data management complexities, and the need for real-world validation, are addressed. The future of SHM lies in integrating diverse sensing technologies with computational analytics, advancing from periodic inspections to continuous, predictive infrastructure management, which enhances bridge safety, resilience, and economic sustainability. Full article

Loeselia mexicana (Polemoniaceae) is a Mexican shrub with significant medicinal value since pre-Hispanic times. Despite its ethnobotanical importance and apparent role in supporting pollinator communities, detailed information about its reproductive biology remains limited, hindering conservation efforts for this increasingly harvested species. We investigated the reproductive ecology of L. mexicana across two flowering seasons (2023–2024 and 2024–2025) in central Mexico through an integrated approach examining flowering phenology, floral morphology, sexual maturation sequence, nectar characteristics, floral visitors, and breeding system experiments. Flowering occurs from September to March, peaking in October. Flowers exhibit protandry, with anther dehiscence on days 1–2 and stigma receptivity from day 2 onward (flower lifespan: 2.85 ± 0.11 days). Maximum nectar production (1.46 ± 0.05 µL per flower; 193.13 ± 8.8 mg/mL) coincided with peak visitor activity. Despite possessing classic ornithophilous traits, we recorded 21 floral visitor species (5 hummingbirds, 3 hymenopterans, 13 butterflies) with similar visitation patterns, challenging previous assumptions about pollination specialization. Controlled pollination experiments confirmed self-incompatibility, with cross-pollination producing significantly more seeds than autonomous selfing. Our findings reveal that L. mexicana maintains a generalized pollination system, while protandry and self-incompatibility enforce outcrossing, providing critical baseline information for conservation strategies. Full article

This study explores the role of sustainability-oriented education in supporting post-disaster recovery and resilience in Derna, Libya, following the catastrophic floods of September 2023. Using a qualitative descriptive design, twenty semi-structured interviews were conducted with academic experts, public health professionals, policymakers, and community leaders. The findings reveal that Education for Sustainable Development (ESD) is perceived as both a critical resilience tool and a moral imperative in fragile, disaster-affected contexts. However, institutional fragility, limited resources, and weak policy integration hinder its implementation. The study highlights the need to embed ESD within both formal education systems and informal community networks, aligning recovery strategies with local environmental realities. It offers practical recommendations for leveraging schools, faith-based institutions, and grassroots initiatives to foster adaptive capacity. These insights contribute to global debates on localising sustainable development in post-conflict settings and underscore the potential of ESD to bridge immediate recovery and long-term sustainability. The study explicitly aligns with the objectives of Sustainable Development Goal 4 (Quality Education) and Sustainable Development Goal 11 (Sustainable Cities and Communities). It demonstrates how sustainability-oriented learning can strengthen community resilience by connecting education with local recovery systems, environmental adaptation, and social rebuilding. Through this alignment, the research underscores the role of education as a mechanism for both immediate recovery and long-term sustainability within fragile and disaster-affected societies. Full article

In this research, an innovative, integrative method is applied, which not only links media discourse and statutory planning documents but also involves both quantitative and qualitative analysis. By going beyond the traditional extreme of either policy review or text-based SETS frameworks, this study becomes the pioneer of a dual-coded, matrix-driven approach, which is capable of measuring policy–implementation gaps and empirically revealing the impact of media framing on disaster management outcomes. The 29 October 2024 Valencia flood, which claimed over 229 lives, highlights critical shortcomings in the region’s flood management policies. This study evaluates media and institutional sources to examine how public discourse aligns with post-flood management strategies. It focuses on Valencia’s statutory flood management plan, the “Pla d’acció territorial de caràcter sectorial sobre prevenció del risc d’inundació a la Comunitat Valenciana” (“Regional Action Plan for Flood Risk Prevention,” PATRICOVA) and its limited integration with the Socio–Ecological–Technological Systems (SETS) framework, which we identify as a central weakness. By analyzing Spanish media coverage, particularly from sources such as El País, ABC, and La Vanguardia, alongside government policy documents, the study reveals a gap between theoretical flood risk planning and practical disaster response. Our keyword-based text mining of leading newspapers highlights the neglect of social, ecological, and technological interactions. While PATRICOVA emphasizes nature protection and technological infrastructure, it overlooks critical societal dimensions and climate adaptation scenarios. Media analysis reveals significant failures at the SETS interfaces, especially in early warning systems, intergovernmental coordination, and community preparedness. Full article

Medicine and vaccine supply chains in Nigeria are socio-technical systems exposed to persistent uncertainty and disruption. Existing studies rarely integrate systems thinking with uncertainty-aware decision tools to jointly prioritize challenges and policy responses. This study asks which policy mix most effectively strengthens these supply chains while balancing multiple, conflicting criteria and stakeholder judgments. We develop a two-stage Fermatean fuzzy framework that first weights 35 challenges using Fermatean Fuzzy Stepwise Weight Assessment Ratio Analysis (FF-SWARA) and then ranks four policy alternatives via Fermatean Fuzzy VIšeKriterijumska Optimizacija I Kompromisno Resenje (FF-VIKOR), based on expert elicitation and linguistic assessments. Results identify interruption of drug supplies, limited vaccine funding, cold-chain potency loss, human resource shortages, and product damage as the most critical challenges. FF-VIKOR prioritizes Effective Implementation of Existing Policies as the best alternative, followed by Improving Access to Medicines and Vaccines, indicating that governance quality and access-enabling infrastructure are complementary levers for resilience. To further enhance robustness, we embed the VIKOR outcomes into a policy-oriented game-theoretic analysis, where strategic weighting scenarios (e.g., cost-focused, infrastructure-driven, human-capital focused) interact with policy choices. The equilibrium results reveal that a mixed strategy combining Effective Implementation of Existing Policies and Strengthening Distribution and Storage Systems guarantees the best compromise performance across adversarial scenarios. The proposed framework operationalizes systems thinking for uncertainty-aware and strategically robust policy design and can be extended with real-time data integration, scenario planning, and regional replication to guide adaptive supply chain governance. Full article

A scientifically systematic credit evaluation system serves as a crucial safeguard mechanism for maintaining a healthy business environment in the construction market, effectively regulating industry entities’ behaviors and promoting ecosystem optimization. Current credit risk assessment relies excessively on financial data, neglecting the importance of corporate operational conditions. This study focuses on constructing a credit risk assessment model for construction general contractors. Innovatively incorporating both short-term financial status and long-term operational development factors, the research integrates grey relational analysis with a two-dimensional cloud model to establish a comprehensive credit risk assessment system featuring visualization of evaluation results. The methodology involves three key steps: (1) establishing a dual-dimensional credit risk indicator system covering financial and operational aspects; (2) determining risk factor weights through grey relational analysis and generating three-dimensional cloud diagrams using reverse cloud generators; (3) visualizing corporate credit risk levels through cloud mapping. Empirical analysis of representative Contractor A, utilizing Wind Financial Database data and field research, demonstrates the model’s significant advantages in critical risk factor identification and comprehensive credit risk assessment. Full article

Amidrapid advances in intelligent medicine, decoding brain activity from electroencephalogram (EEG) signals has emerged as a critical technical frontier for brain–computer interfaces and medical AI systems. Given the inherent spatial resolution limitations of an EEG, researchers frequently integrate functional magnetic resonance imaging (fMRI) to enhance neural activity representation. However, fMRI acquisition is inherently complex. Consequently, efforts increasingly focus on cross-modal transformation methods that map EEG signals to fMRI data, thereby extending EEG applications in neural mechanism studies. The central challenge remains generating high-fidelity fMRI images from EEG signals. To address this, we propose a diffusion model-based framework for cross-modal EEG-to-fMRI generation. To address pronounced noise contamination in electroencephalographic (EEG) signals acquired via simultaneous recording systems and temporal misalignments between EEGs and functional magnetic resonance imaging (fMRI), we first apply Fourier transforms to EEG signals and perform dimensionality expansion. This constructs a spatiotemporally aligned EEG–fMRI paired dataset. Building on this foundation, we design an EEG encoder integrating a multi-layer recursive spectral attention mechanism with a residual architecture.In response to the limited dynamic mapping capabilities and suboptimal image quality prevalent in existing cross-modal generation research, we propose a diffusion-model-driven EEG-to-fMRI generation algorithm. This framework unifies the EEG feature encoder and a cross-modal interaction module within an end-to-end denoising U-Net architecture. By leveraging the diffusion process, EEG-derived features serve as conditional priors to guide fMRI reconstruction, enabling high-fidelity cross-modal image generation. Empirical evaluations on the resting-state NODDI dataset and the task-based XP-2 dataset demonstrate that our EEG encoder significantly enhances cross-modal representational congruence, providing robust semantic features for fMRI synthesis. Furthermore, the proposed cross-modal generative model achieves marked improvements in structural similarity, the root mean square error, and the peak signal-to-noise ratio in generated fMRI images, effectively resolving the nonlinear mapping challenge inherent in EEG–fMRI data. Full article

Soybeans (Glycine max (L.) Merr.) are a vital global crop; however, Thailand currently imports 99% of its domestic requirement, highlighting the critical need for enhanced domestic production. Morkhor 60, a new high-yielding variety, lacks optimized agronomic management for cultivation in the challenging sandy soils of Northeast Thailand. This study evaluated the effects of NPK fertilizer rates and plant spacing on Morkhor 60 growth and yield through two independent experiments conducted in sandy soils over a four-season period (2022–2023). Results demonstrated that 23.44 kg ha⁻¹ NPK provided optimal cost-effectiveness for Morkhor 60, achieving yields of 1238 kg ha⁻¹ statistically comparable to higher rates (1286 kg ha⁻¹) while reducing input costs by 50%. Plant spacing significantly affected productivity, with 30 × 20 cm spacing producing the highest yield (1775 kg ha⁻¹), representing 41% improvement over the narrow spacing (20 × 20 cm: 1257 kg ha⁻¹). The integrated management system (23.44 kg ha⁻¹ NPK with 30 × 20 cm spacing) achieved 87.6% ground cover for moisture conservation and delivered net profits of 29,850 THB ha⁻¹, with a benefit–cost ratio of 3.1. This research provides evidence-based agronomic recommendations for Morkhor 60 cultivation in sandy soil environments, contributing to Thailand’s soybean self-sufficiency through sustainable and economically viable production practices. Full article

Multivariate time series anomaly detection is a critical task in modern engineering, with applications spanning environmental monitoring, network security, and industrial systems. While reconstruction-based methods have shown promise, they often suffer from overfitting and fail to adequately distinguish between normal and anomalous data, limiting their generalization capabilities. To address these challenges, we propose the AOST model, which integrates adversarial learning with an outlier suppression mechanism within a Transformer framework. The model introduces an outlier suppression attention mechanism to enhance the distinction between normal and anomalous data points, thereby improving sensitivity to deviations. Additionally, a dual-decoder generative adversarial architecture is employed to enforce consistent data distribution learning, enhancing robustness and generalization. A novel anomaly scoring strategy based on longitudinal differences further refines detection accuracy. Extensive experiments on three public datasets—SWaT, WADI, SMAP, and PSM—demonstrate the model’s superior performance, achieving an average F1 score of 88.74%, which surpasses existing state-of-the-art methods. These results underscore the effectiveness of AOST in advancing multivariate time series anomaly detection. Full article

The proliferation of drones across precision agriculture, disaster response operations, and delivery services has accentuated the critical need for secure communication frameworks. Due to the limited computational capabilities of drones and the fragility of real-time wireless communication networks, the cellular connected drones confront mounting cybersecurity threats. Traditional authentication mechanisms, such as public-key infrastructure-based authentication, and identity-based authentication, are centralized and have high computational costs, which may result in single point of failure. To address these issues, this paper proposes a blockchain-enabled authentication and key agreement scheme for cellular-connected drones. Leveraging identity-based cryptography (IBC) and the Message Queuing Telemetry Transport (MQTT), the scheme flow is optimized to reduce the communication rounds in the authentication. By integrating MQTT brokers with the blockchain, it enables drones to authenticate through any network node, thereby enhancing system scalability and availability. Additionally, cryptographic performance is optimized via precompiled smart contracts, enabling efficient execution of complex operations. Comprehensive experimental evaluations validate the performance, scalability, robustness, and resource efficiency of the proposed scheme, and show that the system delivers near-linear scalability and accelerated on-chain verification. Full article

With the growing advantages and conveniences provided by digital transactions, the financial sectors also face a loss of billions of dollars each year. While the use of credit cards has made life easier and convenient, it has also become a significant threat. Detecting fraudulent transactions in financial sectors, such as banking, is a major issue because existing fraud detection methods are rule-based and unable to detect unknown patterns. The tactics and techniques used by fraudsters are far more advanced than they are, making machine learning (ML) a valuable approach to improve detection efficiency. While numerous studies have explored machine learning models for credit card fraud detection, most have prioritized accuracy metrics alone, offering little attention to how or why models make decisions. This lack of interpretability creates barriers for financial institutions, where regulatory compliance and user trust are critical. In particular, the systematic application of explainable AI (XAI) techniques such as SHAP and LIME to fraud detection remains scarce. This study addresses this gap by combining high-performing ensemble models (Random Forest and XGBoost) with advanced interpretability methods (SHAP and LIME), providing both strong predictive performance and transparent feature-level explanations. Such integration not only improves fraud detection but also strengthens the trustworthiness and deployability of AI systems in real-world financial contexts. A real-world credit card dataset is used to evaluate both models, and experimental results show that Random Forest achieved higher precision (89.09%) and F1 score (0.9159), while XGBoost yielded better recall (95.56%) and ROC AUC (0.9997). To address the crucial need for interpretability, SHAP and LIME analyses were applied, revealing the most influential features behind model predictions and enhancing transparency in decision-making. Overall, this study demonstrates the potential of integrating explainable artificial intelligence (XAI) into fraud detection systems, thereby enhancing trust and reliability in financial institutions. Full article

The use of digital photogrammetry and laser data acquisition systems, along with the ability to mount these sensors on unmanned aerial vehicles (UAVs), has revolutionized rockfall assessment. While these techniques have facilitated numerous studies across diverse scenarios, complex environments like narrow gorges necessitate the integration of various geomatic techniques to achieve complete and accurate spatial products. To address the critical gap in the literature regarding standardized multi-sensor integration in narrow gorges, this study presents a novel methodology for the cohesive integration of data from these techniques, leveraging their respective strengths to generate reliable products for rockfalls risk assessment. To validate the methodology, we applied this approach to a challenging rockfall susceptibility study at the Caminito del Rey in Málaga, Spain. The site presented significant complexities, including vertical walls hundreds of meters high with abundant overhangs, and canyons as narrow as 10 m, severely limiting single-technique approaches. The successful integration of these diverse datasets yielded a comprehensive, very high-resolution point cloud (1–10 cm density), among other products, covering the entire study area, making it ideal for detailed rockfall assessment and simulation. The approach has demonstrated that data fusion from multiple techniques supposes an advantage because one supports the other both in data coverage and in processing. Although processing the extensive acquired information presented a significant challenge, a successful balance between data volume and processing capacity was achieved, ensuring the outputs met the specific requirements for these studies. Full article

Background and Objective: Accurate classification of standard fetal ultrasound planes is a critical step in prenatal diagnostics, enabling reliable biometric measurements and anomaly detection. Conventional deep learning approaches, particularly convolutional neural networks (CNNs) and transformers, often face challenges such as domain variability, noise artifacts, class imbalance, and poor calibration, which limit their clinical utility. This study proposes a hybrid state–space and vision transformer framework designed to address these limitations by integrating sequential dynamics and global contextual reasoning. Methods: The proposed framework comprises five stages: (i) preprocessing for ultrasound harmonization using intensity normalization, anisotropic diffusion filtering, and affine alignment; (ii) hybrid feature encoding with a state–space model (SSM) for sequential dependency modeling and a vision transformer (ViT) for global self-attention; (iii) multi-task learning (MTL) with anatomical regularization leveraging classification, segmentation, and biometric regression objectives; (iv) gated decision fusion for balancing local sequential and global contextual features; and (v) calibration strategies using temperature scaling and entropy regularization to ensure reliable confidence estimation. The framework was comprehensively evaluated on three publicly available datasets: FETAL_PLANES_DB, HC18, and a large-scale fetal head dataset. Results: The hybrid framework consistently outperformed baseline CNN, SSM-only, and ViT-only models across all tasks. On FETAL_PLANES_DB, it achieved an accuracy of 95.8%, a macro-F1 of 94.9%, and an ECE of 1.5%. On the Fetal Head dataset, the model achieved 94.1% accuracy and a macro-F1 score of 92.8%, along with superior calibration metrics. For HC18, it achieved a Dice score of 95.7%, an IoU of 91.7%, and a mean absolute error of 2.30 mm for head circumference estimation. Cross-dataset evaluations confirmed the model’s robustness and generalization capability. Ablation studies further demonstrated the critical role of SSM, ViT, fusion gating, and anatomical regularization in achieving optimal performance. Conclusions: By combining state–space dynamics and transformer-based global reasoning, the proposed framework delivers accurate, calibrated, and clinically meaningful predictions for fetal ultrasound plane classification and biometric estimation. The results highlight its potential for deployment in real-time prenatal screening and diagnostic systems. Full article

Integrating artificial intelligence (AI) with wearable sensor technologies can revolutionize the monitoring and management of various chronic diseases and acute conditions. AI-integrated wearables are categorized by their underlying sensing techniques, such as electrochemical, colorimetric, chemical, optical, and pressure/stain. AI algorithms enhance the efficacy of wearable sensors by offering personalized, continuous supervision and predictive analysis, assisting in time recognition, and optimizing therapeutic modalities. This manuscript explores the recent advances and developments in AI-powered wearable sensing technologies and their use in the management of chronic diseases, including COVID-19, Diabetes, and Cancer. AI-based wearables for heart rate and heart rate variability, oxygen saturation, respiratory rate, and temperature sensors are reviewed for their potential in managing COVID-19. For Diabetes management, AI-based wearables, including continuous glucose monitoring sensors, AI-driven insulin pumps, and closed-loop systems, are reviewed. The role of AI-based wearables in biomarker tracking and analysis, thermal imaging, and ultrasound device-based sensing for cancer management is reviewed. Ultimately, this report also highlights the current challenges and future directions for developing and deploying AI-integrated wearable sensors with accuracy, scalability, and integration into clinical practice for these critical health conditions. Full article