Search Results (585)

Organ-preserving strategies have gained increasing relevance in the management of rectal cancer, driven by the improved ability of neoadjuvant therapies to induce major and complete tumor regression. The introduction of Total Neoadjuvant Therapy (TNT), delivered through induction and/or consolidation chemotherapy combined with radiotherapy, has substantially increased both pathological and clinical complete response rates. This progress has renewed interest in non-operative management—namely Watch-and-Wait (W&W)—and in local excision (LE) as potential alternatives to total mesorectal excision (TME). However, the W&W strategy raises important oncologic concerns, including a non-negligible rate of local regrowth—consistently reported at approximately 20–30%—which is associated with inferior distant metastasis-free survival and overall survival. These limitations underscore the inherent uncertainty in reliably defining a true clinical complete response. Within this context, LE may serve as a valuable diagnostic and therapeutic modality by confirming the pathological response, improving local control through removal of residual resistant tumor clones, and enabling more accurate stratification of patients suitable for organ preservation versus those requiring completion TME. Overall, while TNT has expanded the therapeutic opportunities for rectal preservation, LE appears to play a critical role in reducing the discordance between clinical and pathological assessment, thereby offering a more oncologically secure pathway toward organ preservation. This narrative review discusses the current role, benefits, and limitations of organ-preserving approaches after TNT in both locally advanced and early rectal cancer. Full article

The evolution of electrical energy in all its aspects is one of the biggest challenges facing the operation of modern power systems. With the addition of numerous new, networked components to these systems, such as intelligent devices, electric vehicles, renewable energy sources, and battery storage, maintaining reliability and security is becoming increasingly difficult. To ensure that power transmission systems are secure and reliable, network security and reliability evaluations must be performed on a regular basis. The conventional approaches of using engineering tools for power flow analyses need to be enhanced in light of current grid challenges. More comprehensive analyses require the use of complex network concepts. This research proposes employing a combination of the Neplan engineering software and complex network concepts using Python NetworkX, both of which are recent advances, to address the challenges related to the modern grid by assessing the security and reliability of the power transmission system. The experimental results show enhanced reliability and security by employing complex network concepts to assess the grid’s topology and identify essential elements based on their centrality and betweenness and power flow analyses to comprehend how power flows and how various operating conditions impact the system. Full article

Debate persists over whether classical econometric or modern machine learning (ML) approaches provide superior forecasts for volatile monthly price series. Despite extensive research, no systematic cross-domain comparison exists to guide model selection across diverse asset types. In this study, we compare traditional econometric models with classical ML baselines and hybrid approaches across financial assets, futures, commodities, and market index domains. Universal Python-based forecasting tools include month-end preprocessing, automated ARIMA order selection, Fourier terms for seasonality, circular terms, and ML frameworks for forecasting and residual corrections. Performance is assessed via anchored rolling-origin backtests with expanding windows and a fixed 12-month horizon. MAPE comparisons show that ARIMA-based models provide stable, transparent benchmarks but often fail to capture the nonlinear structure of high-volatility series. ML tools can enhance accuracy in these cases, but they are susceptible to stability and overfitting on monthly histories. The most accurate and reliable forecasts come from models that combine ARIMA-based methods with Fourier transformation and a slight enhancement using machine learning residual correction. ARIMA-based approaches achieve about 30% lower forecast errors than pure ML (18.5% vs. 26.2% average MAPE and 11.6% vs. 16.8% median MAPE), with hybrid models offering only marginal gains (0.1 pp median improvement) at significantly higher computational cost. This work demonstrates the domain-specific nature of model performance, clarifying when hybridization is effective and providing reproducible Python pipelines suited for economic security applications. Full article

Precision agriculture increasingly recognizes the transformative potential of unmanned aerial systems (UASs) for crop monitoring and field assessment, yet research consistently highlights significant usability barriers as the main constraints to widespread adoption. Complex mission planning processes, including detailed flight plan creation and way point management, pose substantial technical challenges that mainly affect non-expert operators. Farmers and their teams generally prefer user-friendly, straightforward tools, as evidenced by the rapid adoption of GPS guidance systems, which underscores the need for simpler mission planning in UAS operations. To enhance accessibility and safety in UAS control, especially for non-expert operators in agriculture and related fields, we propose a Secure UAS Control Framework (SAUCF): a comprehensive system for natural-language-driven UAS mission management with integrated dual-factor biometric authentication. The framework converts spoken user instructions into executable flight plans by leveraging a language-model-powered mission planner that interprets transcribed voice commands and generates context-aware operational directives, including takeoff, location monitoring, return-to-home, and landing operations. Mission orchestration is performed through a large language model (LLM) agent, coupled with a human-in-the-loop supervision mechanism that enables operators to review, adjust, or confirm mission plans before deployment. Additionally, SAUCF offers a manual override feature, allowing users to assume direct control or interrupt missions at any stage, ensuring safety and adaptability in dynamic environments. Proof-of-concept demonstrations on a UAS plat-form with on-board computing validated reliable speech-to-text transcription, biometric verification via voice matching and face authentication, and effective Sim2Real transfer of natural-language-driven mission plans from simulation environments to physical UAS operations. Initial evaluations showed that SAUCF reduced mission planning time, minimized command errors, and simplified complex multi-objective workflows compared to traditional waypoint-based tools, though comprehensive field validation remains necessary to confirm these preliminary findings. The integration of natural-language-based interaction, real-time identity verification, human-in-the-loop LLM orchestration, and manual override capabilities allows SAUCF to significantly lower the technical barrier to UAS operation while ensuring mission security, operational reliability, and operator agency in real-world conditions. These findings lay the groundwork for systematic field trials and suggest that prioritizing ease of operation in mission planning can drive broader deployment of UAS technologies. Full article

The high energy consumption characteristics across all segments of the agricultural supply chain, coupled with rural areas’ excessive reliance on traditional power grids and fossil fuel-based energy supply models, not only result in persistently high energy utilization costs and low efficiency but also inflict ongoing negative environmental impacts. This undermines sustainable development and the achievement of energy security. In response, this paper proposes a multi-timescale robust operation scheme for the coordinated operation of rural integrated energy systems and agricultural supply chains. Its core components are as follows: (1) Establish a collaborative operation framework integrating renewable energy-based rural integrated energy systems with agricultural supply chains; (2) Holistically consider energy consumption characteristics across supply chain segments, leveraging sensor-based environmental parameters for crop yield forecasting and hourly energy consumption assessment. This effectively addresses misalignments between crop growth and energy optimization scheduling, as well as inconsistent energy measurement scales across supply chain segments, thereby advancing agricultural sustainability; (3) Introducing a two-stage robust optimization model to quantify the impact of environmental uncertainty on the collaborative framework and integrated energy system, ensuring optimal operation of supply chain equipment under worst-case conditions; (4) Identifying critical energy consumption nodes in the supply chain through system performance analysis and revealing optimization potential in the collaborative mechanism, enabling flexible load shifting and cross-temporal energy allocation. Simulation results demonstrate that this coordinated operation scheme enables dynamic estimation and optimization of crop growth and energy consumption, reducing system operating costs while enhancing supply chain reliability and renewable energy integration capacity. The two-stage robust optimization mechanism effectively strengthens system robustness and adaptability, mitigates the impact of renewable energy output fluctuations, and achieves spatiotemporal optimization of energy allocation. Full article

In the current digital landscape, where platforms process AI-generated content and intelligent network traffic on a large scale, it is the duty of such platforms to continuously measure the reliability, trustworthiness, and security of various data streams. Driven by this practical challenge, this research develops an effective decision-support mechanism in intelligent decision-making in big-data AI-generated content and network systems. The decision problem has considered several uncertainties, including content authenticity, processing efficiency, user trust, cybersecurity, system scalability, privacy protection, and cost of computing. The multidimensional uncertainty of AI-generated information and trends in network behavior are challenging to capture in traditional crisp and fuzzy decision-making models. To fill that gap, a new Picture Fuzzy Faire Un Choix Adequat (PF-FUCA) methodology is proposed, based on multi-perspective expert assessment and better computational aggregation to improve the accuracy of rankings, symmetry, and uncertainty treatment. A case scenario comprising fifteen different alternative intelligent decision strategies and seven evaluation criteria are examined under the evaluation of four decision-makers. The PF-FUCA model successfully prioritizes the best strategies to control AI-based content and network activities to generate a stable and realistic ranking. The comparative and sensitivity analysis show higher robustness, accuracy, and flexibility levels than the existing MCDM techniques. The results indicate that PF-FUCA is specifically beneficial in settings where a large amount of data has to flow, a high uncertainty rate exists, and the variables of decision are dynamic. The research introduces a scalable and credible methodological conception that can be used to facilitate high levels of intelligent computing applications to content governance and network optimization. Full article

Climate change and water scarcity are major threats to the sustainability of wheat production in Mediterranean regions. Thus, timely and reliable water demand assessments are crucial to drive decisions on crop management strategies that are useful for agricultural adaptation to climate change challenges. Although the AquaCrop model is widely used to infer crop yields, it requires continuous field-based observations (mainly soil water content and crop coverage). Often, these areas suffer from a scarcity of in situ data, suggesting the need for remote sensing and model-based decision support. In this framework, this research intends to compare the performance of the AquaCrop model using four different input combinations, with one employing ERA5-Land and crop cover retrieved by satellite images exclusively. A field experiment was conducted on durum wheat (highly sensitive to water stress and playing a strategic role in national food security) in northwest Tunisia during the growing season of 2024–2025, where meteorological variables, green Canopy Cover (gCC), Soil Water Content (SWC), and final yields (biological and grain) were monitored. The AquaCrop model was applied. Four model input combinations were evaluated. In situ meteorological data or ERA5-Land (E5L) reanalysis were combined with either measured-gCC (measured-gCC) or Sentinel-2 NDVI-derived gCC (NDVI-gCC). The results showed that E5L reproduced temperature with RMSE < 2.4 °C (NSE > 0.72) and ETo with RMSE equal to 0.57 mm d⁻¹ (NSE = 0.79), while precipitation presented larger discrepancies (RMSE = 4.14 mm d⁻¹, NSE = 0.58). Sentinel-2 effectively captured gCC dynamics (RMSE = 15.65%, NSE = 0.73) and improved AquaCrop perfomance (RMSE = 5.29%, NSE = 0.93). Across all combinations, AquaCrop reproduced yields within acceptable deviations. The simulated biological yield ranged from 9.7 to 11.0 t ha⁻¹ compared to the observed 10.3 t ha⁻¹, while grain yield ranged from 3.0 to 3.5 t ha⁻¹ against the observed 3.3 t ha⁻¹. As expected, the best agreement with measured yield data was obtained using in situ meteorological data and measured-gCC, even if the use of in situ meteorological data coupled with NDVI-gCC, or E5L-based meteorological data coupled with NDVI-gCC, produced realistic estimates. These results highlight that the application of AquaCrop employing E5L and Sentinel-2 inputs is a feasible alternative for crop monitoring in data-scarce environments. Full article

Groundwater depletion is among the most critical hydrological threats to sustainable agriculture and water security in semi-arid regions. This study presents a high-resolution, multi-sensor assessment of groundwater storage (GWS) dynamics across the Lower Chenab Canal (LCC) command area in Punjab, Pakistan—an intensively irrigated agro-hydrological system within the Indus Basin. We integrated downscaled GRACE/GRACE-FO-derived total water storage anomalies with CHIRPS precipitation, MODIS evapotranspiration (ET) and vegetation indices, TerraClimate soil moisture, land surface temperature (LST), land use/land cover (LULC), and population density using the Google Earth Engine (GEE) platform to reconstruct spatiotemporal GWS changes from 2002 to 2020. The results reveal a persistent and accelerating decline in groundwater levels, averaging 0.52 m yr⁻¹, which intensified to 0.73 m yr⁻¹ after 2014. Cumulative GWS losses exceeded 320 mm yr⁻¹, with severe depletion (up to −3800 mm) in northern districts such as Sheikhupura, Gujranwala, and Narowal. Validation with borewell data (R² = 0.87; NSE = 0.85) confirms the reliability of the remote sensing estimates. Statistical analysis indicates that anthropogenic drivers (population growth, urban expansion, and intensive irrigation) explain over two-thirds of the observed variability (R² = 0.67), whereas precipitation contributes only marginally (R² = 0.28), underscoring the dominance of human-induced stress over climatic variability. The synergistic rise in evapotranspiration, land surface temperature, and cultivation of high-water-demand crops such as rice and sugarcane has further amplified hydrological imbalance. This study establishes an operational framework for integrating satellite and ground-based observations to monitor aquifer stress at basin scale and highlights the urgent need for adaptive, data-driven groundwater governance in the Indus Basin. The approach is transferable to other data-scarce semi-arid regions facing rapid aquifer depletion, aligning with the global targets of Sustainable Development Goal 6 on water sustainability. Full article

This study presents SpineCheck, a fully integrated deep-learning-based clinical decision support platform for automatic vertebra segmentation and Cobb angle (CA) measurement from scoliosis X-ray images. The system unifies end-to-end preprocessing, U-Net-based segmentation, geometry-driven angle computation, and a web-based clinical interface within a single deployable architecture. For secure clinical use, SpineCheck adopts a stateless “process-and-delete” design, ensuring that no radiographic data or Protected Health Information (PHI) are permanently stored. Five U-Net family models (U-Net, optimized U-Net-2, Attention U-Net, nnU-Net, and UNet3++) are systematically evaluated under identical conditions using Dice similarity, inference speed, GPU memory usage, and deployment stability, enabling deployment-oriented model selection. A robust CA estimation pipeline is developed by combining minimum-area rectangle analysis with Theil–Sen regression and spline-based anatomical modeling to suppress outliers and improve numerical stability. The system is validated on a large-scale dataset of 20,000 scoliosis X-ray images, demonstrating strong agreement with expert measurements based on Mean Absolute Error, Pearson correlation, and Intraclass Correlation Coefficient metrics. These findings confirm the reliability and clinical robustness of SpineCheck. By integrating large-scale validation, robust geometric modeling, secure stateless processing, and real-time deployment capabilities, SpineCheck provides a scalable and clinically reliable framework for automated scoliosis assessment. Full article

Agricultural irrigation accounts for nearly 70% of global freshwater withdrawals, making sustainable water management crucial for food security and ecological stability—particularly in arid and semi-arid regions. However, dynamic water-saving thresholds at both inter-annual and intra-annual scales remain insufficiently quantified in current research. To address this gap, this study developed an integrated SWAT-MODFLOW model for the Hetao Irrigation District and quantified dynamic water-saving thresholds by simulating crop yield responses under a range of irrigation scenarios. The model was calibrated (2008–2014) and validated (2014–2016), demonstrating reliable performance (R² = 0.75, NSE = 0.74) in capturing local hydrological processes. Inter-annual scenarios assessed water-saving levels of 5%, 10%, 20%, and 30% under wet, normal, and dry years, while intra-annual scenarios adjusted seasonal irrigation volumes in spring, summer, and autumn with reduction gradients of 33%, 50%, and 100%. Results show that wet and normal years could achieve a water-saving threshold of up to 20%, whereas dry years were limited to 5%. Intra-annually, autumn irrigation offered the greatest saving potential (33–100%), followed by spring (33–50%). Spatially, crop responses varied substantially: the western part of the region proved particularly sensitive, with even the optimal district-wide strategy reducing local crop yields by 10–20%. This study quantifies dynamic water-saving thresholds and incorporates spatial heterogeneity into scenario assessment. The resulting framework is transferable and provides a basis for sustainable water management in water-limited agricultural regions. Full article

Internet of Things deployments face escalating security threats, yet systematic methods for auditing the defensive posture of IoT device networks remain underdeveloped. Current intrusion detection evaluations focus on algorithmic accuracy while neglecting operational requirements—computational efficiency, reproducibility, and interpretable risk assessment—that security audits demand. This paper introduces a reproducible security audit framework for IoT device networks, demonstrated through systematic evaluation of four machine learning models (Random Forest, LightGBM, XGBoost, Logistic Regression) on the TON_IoT dataset containing nine attack categories targeting smart environments. Our audit methodology enforces strict feature hygiene by excluding identity-revealing attributes, benchmarks both threat detection capability and computational cost, and provides complete reproducibility artifacts including preprocessing pipelines and trained models. The framework evaluates security posture through dual lenses: binary classification (distinguishing compromised from legitimate traffic) and multiclass classification (attributing threats to specific attack types). Binary audit results show ensemble models achieve 99.8–99.9% accuracy with perfect ROC-AUC (100%) and sub-15 ms inference latency per 1000 flows, confirming reliable attack detection. Multiclass auditing reveals more nuanced findings: while overall accuracy reaches 99.0% with macro-F1 near 97%, rare attack types expose critical blind spots—man-in-the-middle threats achieve only 78% F1 despite representing serious security risks. LightGBM provides optimal audit performance, balancing 99.93% detection accuracy with 2.76 MB deployment footprint. We translate audit findings into actionable security recommendations (network segmentation, rate-limiting, TLS metadata collection) and compare against twenty published studies, demonstrating that our framework achieves competitive detection rates while uniquely delivering the transparency, efficiency metrics, and reproducibility required for credible security assessment of production IoT networks. Full article

This paper presents a portable cluster architecture based on a lightweight Kubernetes distribution designed to provide enhanced computing capabilities in isolated environments. The architecture is validated in two operational scenarios: (1) machine learning operations (MLOps) for on-site learning, fine-tuning and retraining of models and (2) web hosting for isolated or resource-constrained networks, providing resilient service delivery through failover and load balancing. The cluster leverages low-cost Raspberry Pi 4B units and virtualized nodes, integrated with Docker containerization, Kubernetes orchestration, and Kubeflow-based workflow optimization. System monitoring with Prometheus and Grafana offers continuous visibility into node health, workload distribution, and resource usage, supporting early detection of operational issues within the cluster. The results show that the proposed dual-mode cluster can function as a compact, field-deployable micro-datacenter, enabling both real-time Artificial Intelligence (AI) operations and resilient web service delivery in field environments where autonomy and reliability are critical. In addition to performance and availability measurements, power consumption, scalability bottlenecks, and basic security aspects were analyzed to assess the feasibility of such a platform under constrained conditions. Limitations are discussed, and future work includes scaling the cluster, evaluating GPU/TPU-enabled nodes, and conducting field tests in realistic tactical environments. Full article

High-voltage (HV) bushings are critical hub components in power systems, whose operational reliability is paramount to the safety and stability of transmission and distribution infrastructure. Conventional management paradigms are hampered by challenges such as information silos, reactive maintenance, and imprecise condition assessment, rendering them in-adequate for the evolving demands of modern power systems. Digital twin technology, by creating a high-fidelity, re-al-time interplay between physical entities and their virtual counterparts, provides a revolutionary pathway toward the intelligent full-life-cycle management (FLCM) of HV bushings. This paper presents a review of the current state of research in this domain. It begins by reviewing research on the construction a five-dimensional digital twin framework that encompasses the entire lifecycle: design, manufacturing, operation and maintenance (O&M), and decommissioning. Subsequently, it delves into the application paradigms of digital twins across typical scenarios, including external insulation design, intelligent condition assessment, insulation defect identification, fault diagnosis, and predictive maintenance. The paper then examines the core technological underpinnings, such as multi-physics coupled modeling, multi-source heterogeneous data fusion, and data-driven model updating and condition assessment. Finally, it identifies current challenges related to data, models, standards, and costs, and offers a forward-looking perspective on future research directions, including group digital twins, deep integration with artificial intelligence, edge-side deployment, and standardization initiatives. This work aims to provide a theoretical reference and technical guidance for advancing the intelligent O&M of HV bushings and bolstering grid security. Full article

Background: Efficient and accurate clinical data management is crucial for stroke care and research; however, for complex stroke cohorts, manual data entry is often complicated by high human error rates and significant inefficiency. This study addressed this gap by developing and evaluating an automated system for constructing high-quality stroke cohorts from electronic health records (EHRs). Methods: This retrospective cohort study was conducted at a single specialty hospital, comparing manual data entry (January–June 2022) with an automated system (January–June 2024). The system uses C# and secure SQL protocols for direct EHR integration. We developed an automated system using the C# programming language to extract 133 items covering the full hospitalization period (from admission to discharge) from EHRs, aligning with the Korean Stroke Registry, the Registry of Stroke Care Quality, and national quality assessment programs. The system’s effectiveness was evaluated by assessing the data entry time, data error rate, and medical record completion rate and comparing the automated method’s performance against conventional data entry. Results: The automated system significantly reduced the data entry time from 35 min to 19 s per patient. Furthermore, the data error rate decreased from 2.32% to 0.15% (p < 0.001), and the rate of missing medical records decreased from 28.9% to 16.2% (p < 0.001). Conclusions: The proposed clinical data collection and cohort construction system effectively improved data quality and efficiency compared to the manual method. This system provides a reliable and scalable data infrastructure that could facilitate research on stroke and quality improvement initiatives. Full article

Federated Learning (FL) offers a promising way to train machine learning models collaboratively on decentralized edge devices, addressing key privacy, communication, and regulatory challenges in smart city environments. This survey adopts a narrative approach, guided by systematic review principles such as PRISMA and Kitchenham, to synthesize current FL research in urban contexts. Unlike prior domain-focused surveys, this work introduces a challenge-oriented taxonomy and integrates an explicit analysis of reproducibility, including datasets and deployment artifacts, to assess real-world readiness. The review begins by examining how FL supports the privacy-preserving analysis of environmental and mobility data. It then explores strategies for resource optimization, including load balancing, model compression, and hierarchical aggregation. Applications in anomaly and event detection across power grids, water infrastructure, and surveillance systems are also discussed. In the energy sector, the survey emphasizes the role of FL in demand forecasting, renewable integration, and sustainable logistics. Particular attention is given to security issues, including defenses against poisoning attacks, Byzantine faults, and inference threats. The study identifies ongoing challenges such as data heterogeneity, scalability, resource limitations at the edge, privacy–utility trade-offs, and lack of standardization. Finally, it outlines a structured roadmap to guide the development of reliable, scalable, and sustainable FL solutions for smart cities. Full article