Search Results (192,606)

Aphids are significant pests of winter wheat, causing damage by feeding on plant sap and reducing crop yield and quality. This study evaluates the potential of hyperspectral remote sensing (350–2500 nm) and machine learning (ML) models for classifying healthy and aphid-infested wheat canopies. Field-based hyperspectral measurements were conducted at three growth stages—T1 (stem elongation–heading), T2 (flowering), and T3 (milky grain development)—with infestation levels categorized according to established economic thresholds (ET) for each growth stage. Spectral data were analyzed using Uniform Manifold Approximation and Projection (UMAP); vegetation indices; and ML classification models, including Logistic Regression (LR), k-Nearest Neighbors (KNNs), Support vector machines (SVMs), Random Forest (RF), and Light Gradient Boosting Machine (LGBM). The classification models achieved high performance, with F1-scores ranging from 0.88 to 0.99, and SVM and RF consistently outperforming other models across all input datasets. The best classification results were obtained at T2 with an F1-score of 0.98, while models trained on the full spectrum dataset showed the highest overall accuracy. Among vegetation indices, the Modified Triangular Vegetation Index, MTVI (r_pb = −0.77 to −0.82), and Triangular Vegetation Index, TVI (r_pb = −0.66 to −0.75), demonstrated the strongest correlations with canopy condition. These findings underscore the utility of canopy spectra and vegetation indices for detecting aphid infestations above ET levels, allowing for a clear classification of wheat fields into “treatment required” and “no treatment required” categories. This approach provides a precise and timely decision making tool for insecticide application, contributing to sustainable pest management by enabling targeted interventions, reducing unnecessary pesticide use, and supporting effective crop protection practices. Full article

Recent advancements in image processing technology have positively impacted some fields, such as image, document, and video production. However, the negative implications of these advancements have also increased, with document image manipulation being a prominent issue. Document image manipulation involves the forgery or alteration of documents like receipts, invoices, various certificates, and confirmations. The use of such manipulated documents can cause significant economic and social disruption. To prevent these issues, various methods for the detection of forged document images are being researched, with recent proposals focused on deep learning techniques. An essential aspect of using deep learning to detect manipulated documents is to enhance or augment the characteristics of document images before inputting them into a model. Enhancing the distinctive features of manipulated documents before inputting them into a deep learning model is crucial to achieve high accuracy. One crucial characteristic of document images is their inherent symmetrical patterns, such as consistent text alignment, structural balance, and uniform pixel distribution. This study investigates document forgery detection through a symmetry-aware approach. By focusing on the symmetric structures found in document layouts and pixel distribution, the proposed LTHE technique enhances feature extraction in deep learning-based models. Therefore, this study proposes a new image enhancement technique based on the results of three general-purpose CNN models to enhance the characteristics of document images and achieve high accuracy in deep learning-based forgery detection. The proposed LTHE (Log-Transform Histogram Equalization) technique increases low pixel values through log transformation and increases image contrast by performing histogram equalization to make the features of the image more prominent. Experimental results show that the proposed LTHE technique achieves higher accuracy when compared to other enhancement methods, indicating its potential to aid the development of deep learning-based forgery detection algorithms in the future. Full article

This paper investigates the dynamics of Hurricane-Induced Failure (HIF) by developing a probabilistic framework using a Dynamic Bayesian Network (DBN) model. The model captures the complex interplay of factors influencing Hurricane Wind Speed Intensity (HWSI) and its impact on asset failures. In the proposed DBN model, the pole failure mechanism is represented using Bayesian probabilistic principles, encompassing bending elasticity endurance and the foundational strength of the system poles. To characterize the stochastic properties of HIF, Monte Carlo simulation (MCS) is employed in conjunction with fragility curves (FC) and the scenario reduction (SCENRED) algorithm. The proposed DBN model evaluates the probability of asset failure and compares the results using stochastic Monte Carlo simulation based on the fragility curve scenario reduction algorithm (FC-MCS-SCENRED) model. The results are validated on a standard IEEE 15 bus and IEEE 33 bus radial distribution system as a case study. The DBN results show that they are consistent with the data obtained using the FC-MCS-SCENRED model. The results also reveal that the HWSI plays a critical role in determining HIF rates and the likelihood of asset failures. These findings hold significant implications for the inspection and maintenance scheduling of distribution overhead power lines susceptible to hurricane-induced impacts. Full article

The integration of edge-to-cloud infrastructures in smart grid (SG) data center networks requires scalable, efficient, and secure architecture. Traditional server-based SG data center architectures face high computational loads and delays. To address this problem, a lightweight data center network (DCN) with low-cost, and fast-converging optimization is required. This paper introduces a container-based time synchronization model (CTSM) within a spine–leaf virtual private cloud (SL-VPC), deployed via AWS CloudFormation stack as a practical use case. The CTSM optimizes resource utilization, security, and traffic management while reducing computational overhead. The model was benchmarked against five DCN topologies—DCell, Mesh, Skywalk, Dahu, and Ficonn—using Mininet simulations and a software-defined CloudFormation stack on an Amazon EC2 HPC testbed under realistic SG traffic patterns. The results show that CTSM achieved near-100% reliability, with the highest received energy data (29.87%), lowest packetization delay (13.11%), and highest traffic availability (70.85%). Stateless container engines improved resource allocation, reducing administrative overhead and enhancing grid stability. Software-defined Network (SDN)-driven adaptive routing and load balancing further optimized performance under dynamic demand conditions. These findings position CTSM-SL-VPC as a secure, scalable, and efficient solution for next-generation smart grid automation. Full article

The adoption of land cover standards is essential for resolving inconsistencies in global, regional, and national land cover datasets. This study examines the challenges associated with integrating existing datasets, including variations in land cover class definitions, classification methodologies, limited interoperability, and reduced comparability across scales. Focusing on Ghana as a case study, this research aims to develop a land cover legend and land cover map aligned with International Organization for Standardization (ISO) 19144-2 standards, evaluate the effectiveness of improving land cover classification and accuracy of data, and finally, assess the challenges and opportunities for the adoption of land cover standards. This study uses a multi-sensor remote sensing approach, integrating Sentinel-1 and Sentinel-2 optical imagery with ancillary data (elevation, slope, and aspect), to produce a national land cover dataset for 2023. Using the random forest (RF) algorithm, the land cover map was developed based on a land cover legend derived from the West African land cover reference system (WALCRS). The study also collaborates with national and international organizations to ensure the dataset meets global reporting standards for Sustainable Development Goals (SDGs), including those for land degradation neutrality. Using a survey form, stakeholders in the land cover domain were engaged globally (world), regionally (Africa), and nationally (Ghana), to assess the challenges to and opportunities for the adoption of land cover standards. The key findings reveal a diverse range of land cover types across Ghana, with cultivated rainfed areas (28.3%), closed/open forest areas (19.6%), and savanna areas (15.9%) being the most dominant classes. The classification achieved an overall accuracy of 90%, showing the robustness of the RF model for land cover mapping in a heterogeneous landscape such as Ghana. This study identified a limited familiarity with land cover standards, lack of documentation, cost implication, and complexity of standards as challenges to the adoption of land cover standards. Despite the challenges, this study highlights opportunities for adopting land cover standards, including improved data accuracy, support for decision-making, and enhanced capacity for monitoring sustainable land cover changes. The findings highlight the importance of integrating land cover standards to meet international reporting requirements and contribute to effective environmental monitoring and sustainable development initiatives. Full article

This work explores the effectiveness of explainable artificial intelligence in mapping solar photovoltaic power outputs based on weather data, focusing on short-term mappings. We analyzed the impact values provided by the Shapley additive explanation method when applied to two algorithms designed for tabular data—XGBoost and TabNet—and conducted a comprehensive evaluation of the overall model and across seasons. Our findings revealed that the impact of selected features remained relatively consistent throughout the year, underscoring their uniformity across seasons. Additionally, we propose a feature selection methodology utilizing the explanation values to produce more efficient models, by reducing data requirements while maintaining performance within a threshold of the original model. The effectiveness of the proposed methodology was demonstrated through its application to a residential dataset in Madeira, Portugal, augmented with weather data sourced from SolCast. Full article

This study examines the energy savings in a ship’s central cooling system using feedforward control with IMC (Internal Model Control)-based PID tuning. A central cooling system is essential for maintaining the temperature of the engine and other major machinery, thereby improving the overall energy efficiency. The seawater pump in the central cooling system consumes a relatively large amount of power, which makes efficient operation essential. This study compared the power consumption of variable-speed seawater pumps based on actual operational data from a ship. By incorporating a feedforward PI controller into the IMC-based PI-PID controller combinations, this study simulated energy savings. The results indicate that the proposed controller combined with the feedforward PI controller reduces the power consumption of seawater pumps compared with conventional methods. Simulation tests were conducted using approximately 11 days of operational data to verify the effectiveness of the proposed control strategy in achieving energy savings. The proposed controller combination saves approximately 277.4 kWh of power over 11 days compared to conventional control methods. Full article

Ecological carrying capacity (ECC) is a crucial indicator for assessing sustainable development capabilities. However, mountain ecosystems possess unique complexities due to their diverse topography, high biodiversity, and fragile ecological environments. Addressing the current shortcomings in mountain ECC assessments, this paper proposes a novel hybrid evaluation framework that integrates improved ecological footprint (EF) and ecosystem service value (ESV) approaches with spatial econometric models. This framework allows for a more comprehensive understanding of the dynamic changes and driving factors of the mountain ecological carrying capacity index (ECCI), using Pingbian County as a case study. The results indicate the following: (1) Land use changes and biodiversity exert varying impacts on the ECCI across different regions. The ECCI decreased by 42% from 2003 to 2021 (from 4.41 to 2.54), exhibiting significant spatial autocorrelation and heterogeneity. (2) The ecological service value coefficient is the main factor increasing the ECCI, while the energy consumption value and per capita consumption value inhibited the increase in the ECCI. For every 1% increase in the ecosystem service value coefficient, the ECCI increased by 0.66%, whereas every 1% increase in energy consumption value and per capita consumption value reduced the ECCI by 0.18% and 0.28%, respectively. (3) The overall spatial distribution pattern of the ECCI is primarily “southwest to northeast”, with the distance of centroid migration expanding over time. Based on these key findings, implementing differentiated land use practices and ecological restoration measures can effectively enhance the mountain ECCI, providing scientific support for the sustainable management of mountain areas. Full article

The problem of increasing the tool durability (service life) when machining hard-to-machine materials is one of the major practical problems of modern mechanical engineering. This paper aims to improve the wear resistance of modular disk mills using the pre-processing method. Second-order rotatable planning was applied for the experimental study of the pre-processing of modular disk mills. Experimental research on the pre-processing of modular disk mills was carried out on a vertical milling machine XH950A when milling a workpiece made of steel 45. It was revealed that the increase in pre-processing modes up to specific values (f = 60 mm/min; 𝑣𝑐 = 17 m/min; t = 6 min) on the tool durability period has a positive effect. At the same time, the tool durability period was increased up to T = 155 min. Tests of the machined modular disk mills were carried out in the conditions of the laboratory base to determine the durability period. After pre-processing at different modes, each modular disk mill was used to machine the workpiece until wear signs appeared on the cutting edge. At the same time, the time was recorded to determine the durability period. It was found that the optimum mode of tool preliminary pre-processing provides the best deformation and thermal conditions for hardening the tool cutting part. As a result of modeling with the ANSYS 2024 R1 program, it was found that a hardened layer is indeed formed on the cutting part of the modular disk mill after pre-processing. The results obtained show the possibility of using the preliminary pre-processing method to improve the wear resistance of other metal-cutting tools. Full article

Natural gas hydrate (NGH) is a clean resource characterized by abundant potential reserves, clean combustion, and high energy density. Although significant progress has been made in the development of NGH resources all around the world, challenges still exist that hinder commercial exploitation, such as a low daily gas production rate and short steady production periods. One significant reason lies in the complex gas–liquid–solid phase transitions occurring within the formation during production, which lead to changes in flow capacity. Understanding the phase change mechanism of NGH reservoirs will help to further reveal the production increase mechanism. To address the phase transitions’ effect on production, this paper establishes a numerical simulation model for the depressurization exploitation of natural gas hydrates in order to investigate phase transition characteristics at the field scale. First, the phase equilibrium calculation method is presented and the phase equilibrium curve is modified by considering the capillary effect, soluble salt, and surface adsorption. Then, the phase transition model is successfully characterized in a simulation and the numerical simulation model is established based on the first test project parameters in the Shenhu area. The production characteristics of different sediment types (montmorillonite, South China Sea sediments, kaolin, and silt) are analyzed under the effects of water content and salinity. It is shown that lower initial water content and higher salinity result in higher gas production. The results provide a better understanding of the effects of phase transition parameters on NGH production at the field scale. Full article

Due to the complex operating environment of valves, when a fault occurs inside a valve, the vibration signal generated by the fault is easily affected by the environmental noise, making the extraction of fault features difficult. To address this problem, this paper proposes a feature extraction method based on the combination of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Fuzzy Entropy (FN). Due to the slow convergence speed and the tendency to fall into local optimal solutions of the Hippopotamus Optimization Algorithm (HO), an improved Hippopotamus Optimization (IHO) algorithm-optimized Support Vector Machine (SVM) model for valve leakage diagnosis is introduced to further enhance the accuracy of valve leakage diagnosis. The improved Hippopotamus Optimization algorithm initializes the hippopotamus population with Tent chaotic mapping, designs an adaptive weight factor, and incorporates adaptive variation perturbation. Moreover, the performance of IHO was proven to be optimal compared to HO, Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), Whale Optimization Algorithm (WOA), and Sparrow Search Algorithm (SSA) by calculating twelve test functions. Subsequently, the IHO-SVM classification model was established and applied to valve leakage diagnosis. The prediction effects of the seven models, IHO-SVM. HO-SVM, PSO-SVM, GWO-SVM, WOA-SVM, SSA-SVM, and SVM were compared and analyzed with actual data. As a result, the comparison indicated that IHO-SVM has desirable robustness and generalization, which successfully improves the classification efficiency and the recognition rate in fault diagnosis. Full article

The aim of this study is to examine the impact of key competitiveness factors on sustainable business performance in the hospitality sector through the application of an integrated approach, from the perspective of hotel service users. The research was conducted on a sample of 1640 hotel guests who stayed in hotels operating in the Republic of Serbia, Croatia, and Slovenia. Utilizing a structural equation modeling (SEM) framework, the study meticulously analyzed various competitiveness factors: service quality, service, service recovery, hotel user satisfaction, loyalty and discretionary behavior and dysfunctional consumer behavior. The results of the research reveal that all identified key factors significantly impact the sustainable performance of hotel operations. The findings suggest that hotels must prioritize these elements to enhance their competitiveness and ensure ongoing success in a challenging market environment. Notably, one intriguing finding is that loyalty does not serve as a buffer in the relationship between customer dissatisfaction and dysfunctional behavior, indicating that even loyal customers can exhibit negative behaviors when their expectations are not met. This underscores the importance of addressing guest satisfaction proactively to mitigate potential adverse outcomes and retain a loyal customer base. Moreover, this study provides valuable insights for hotel management, highlighting the necessity for holistic strategies that not only aim to improve guest experiences but also consider the intricate dynamics between various competitiveness factors that ultimately contribute to the sustainability and profitability of the hospitality industry. Rejecting the sub-hypothesis that loyalty among hotel service users moderates the impact of dissatisfaction on the expression of dysfunctional consumer behavior indicates the need to review certain theories that comprise the dominant theoretical framework in the field of hospitality. This implies the need for further analysis of the validity of the dominant theories in the hospitality industry, especially in defining the conditions under which their postulates hold indisputably. Second, further examination of the role of loyalty is needed, since there are different types of loyalty. Full article

To address the challenges of carbon emission reduction in the global shipping industry and the requirements of the International Maritime Organization (IMO)’s Carbon Intensity Indicator (CII) rating, this paper takes China’s commuter ships as an example to study the dynamic optimization of ship routes based on CII implementation requirements. In response to the existing research gap in the collaborative optimization of routes and carbon emissions under CII constraints, this paper constructs a mixed-integer programming model that comprehensively considers CII limits, port throughput capacity, channel capacity, and the stochastic demand for spot cargo. The objective is to minimize the operating costs of shipping companies, and an adaptive genetic algorithm is designed to solve the dynamic route scheduling problem. Numerical experiments demonstrate that the model can reasonably plan routes under different sequences of spot cargo arrivals, ensuring compliance with CII ratings while reducing total costs and carbon emissions. The results indicate that the proposed method provides efficient decision-making support for dynamic ship scheduling under CII constraints, contributing to the green transformation of the shipping industry. Future work will extend the model to scenarios involving multiple ship types and complex maritime conditions, further enhancing its applicability. Full article

With the rapid development of UAV technology, UAV delivery has gained attention for its potential to reduce labor costs. However, limitations in load capacity and energy restrict UAVs’ distribution capabilities. This paper proposes a cooperative delivery scheme combining traditional trucks and UAVs to extend UAV coverage and improve delivery completion rates. For densely distributed depots in wide-area regions, we develop algorithms for task allocation and path planning in a truck-independent UAV system. Specifically, a minimum-cost, maximum-flow model is constructed to obtain sub-paths covering all delivery tasks, and resource tree-based algorithms are used to construct global paths for UAVs and trucks. Simulation results show that our algorithms reduce total energy consumption by 11.53% and 9.15% under different task points, which suggests that our proposed method can significantly enhance delivery efficiency, offering a promising solution for future logistics operations. Full article

Weeds are a significant adverse factor affecting rice growth, and their efficient removal necessitates an accurate, efficient, and well-generalizing weed detection method. However, weed detection faces challenges such as a complex vegetation environment, the similar morphology and color of weeds, and crops and varying lighting conditions. The current research has yet to address these issues adequately. Therefore, we propose GE-YOLO to identify three common types of weeds in rice fields in the Hunan province of China and to validate its generalization performance. GE-YOLO is an improvement based on the YOLOv8 baseline model. It introduces the Neck network with the Gold-YOLO feature aggregation and distribution network to enhance the network’s ability to fuse multi-scale features and detect weeds of different sizes. Additionally, an EMA attention mechanism is used to better learn weed feature representations, while a GIOU loss function provides smoother gradients and reduces computational complexity. Multiple experiments demonstrate that GE-YOLO achieves 93.1% mAP, 90.3% F1 Score, and 85.9 FPS, surpassing almost all mainstream object detection algorithms such as YOLOv8, YOLOv10, and YOLOv11 in terms of detection accuracy and overall performance. Furthermore, the detection results under different lighting conditions consistently maintained a high level above 90% mAP, and under conditions of heavy occlusion, the average mAP for all weed types reached 88.7%. These results indicate that GE-YOLO has excellent detection accuracy and generalization performance, highlighting the potential of GE-YOLO as a valuable tool for enhancing weed management practices in rice cultivation. Full article