Search Results (35,919)

The Centralized Teacher with Decentralized Student (CTDS) framework is a multi-agent reinforcement learning (MARL) approach that utilizes knowledge distillation within the Centralized Training with Decentralized Execution (CTDE) paradigm. In this framework, a teacher module learns optimal Q-values using global observations and distills this knowledge to a student module that operates with only local information. However, CTDS has limitations including inefficient knowledge distillation processes and performance gaps between teacher and student modules. This paper proposes the evolutionary sampling method that employs genetic algorithms to optimize selective knowledge distillation in CTDS frameworks. Our approach utilizes a selective sampling strategy that focuses on samples with large Q-value differences between teacher and student models. The genetic algorithm optimizes adaptive sampling ratios through evolutionary processes, where the chromosome represent sampling ratio sequences. This evolutionary optimization discovers optimal adaptive sampling sequences that minimize teacher–student performance gaps. Experimental validation in the $StarCraft$ Multi-Agent Challenge (SMAC) environment confirms that our method achieved superior performance compared to the existing CTDS methods. This approach addresses the inefficiency in knowledge distillation and performance gap issues while improving overall performance through the genetic algorithm. Full article

Cotton is a globally strategic crop that plays a crucial role in sustaining national economies and livelihoods. To address the challenges of accurate cotton field extraction in the complex planting environments of Xinjiang’s Alaer reclamation area, a cotton field identification model was developed that integrates multi-source satellite remote sensing data with machine learning methods. Using imagery from Sentinel-2, GF-1, and Landsat 8, we performed feature fusion using principal component, Gram–Schmidt (GS), and neural network techniques. Analyses of spectral, vegetation, and texture features revealed that the GS-fused blue bands of Sentinel-2 and Landsat 8 exhibited optimal performance, with a mean value of 16,725, a standard deviation of 2290, and an information entropy of 8.55. These metrics improved by 10,529, 168, and 0.28, respectively, compared with the original Landsat 8 data. In comparative classification experiments, the endmember-based random forest classifier (RFC) achieved the best traditional classification performance, with a kappa value of 0.963 and an overall accuracy (OA) of 97.22% based on 250 samples, resulting in a cotton-field extraction error of 38.58 km². By enhancing the deep learning model, we proposed a U-Net architecture that incorporated a Convolutional Block Attention Module and Atrous Spatial Pyramid Pooling. Using the GS-fused blue band data, the model achieved significantly improved accuracy, with a kappa coefficient of 0.988 and an OA of 98.56%. This advancement reduced the area estimation error to 25.42 km², representing a 34.1% decrease compared with that of the RFC. Based on the optimal model, we constructed a digital map of continuous cotton cropping from 2021 to 2023, which revealed a consistent decline in cotton acreage within the reclaimed areas. This finding underscores the effectiveness of crop rotation policies in mitigating the adverse effects of large-scale monoculture practices. This study confirms that the synergistic integration of multi-source satellite feature fusion and deep learning significantly improves crop identification accuracy, providing reliable technical support for agricultural policy formulation and sustainable farmland management. Full article

Predictive maintenance (PdM) is a cornerstone of smart manufacturing, enabling the early detection of equipment degradation and reducing unplanned downtimes. This study proposes an advanced machine learning framework that integrates the Extreme Learning Machine (ELM) with a novel hybrid metaheuristic optimization algorithm, the Polar Lights Salp Cooperative Optimizer (PLSCO), to enhance predictive modeling in manufacturing processes. PLSCO combines the strengths of the Polar Light Optimizer (PLO), Competitive Swarm Optimization (CSO), and Salp Swarm Algorithm (SSA), utilizing a cooperative strategy that adaptively balances exploration and exploitation. In this mechanism, particles engage in a competitive division process, where winners intensify search via PLO and losers diversify using SSA, effectively avoiding local optima and premature convergence. The performance of PLSCO was validated on CEC2015 and CEC2020 benchmark functions, demonstrating superior convergence behavior and global search capabilities. When applied to a real-world predictive maintenance dataset, the ELM-PLSCO model achieved a high prediction accuracy of 95.4%, outperforming baseline and other optimization-assisted models. Feature importance analysis revealed that torque and tool wear are dominant indicators of machine failure, offering interpretable insights for condition monitoring. The proposed approach presents a robust, interpretable, and computationally efficient solution for predictive maintenance in intelligent manufacturing environments. Full article

Driven by the urgent need to decarbonize the logistics sector—where conventional vehicles exhibit high energy consumption and emissions, posing significant environmental sustainability challenges—electrification represents a pivotal strategy for reducing emissions and achieving sustainable urban freight transport. Despite rising global electric vehicle sales, the penetration rate of electric logistics vehicles (ELVs) remains comparatively low, impeding progress toward sustainable logistics objectives. Battery-swapping mode (BSM) has emerged as a potential solution to enhance operational efficiency and economic viability, thereby accelerating sustainable adoption. This model improves ELV operational efficiency through rapid battery swaps at centralized stations. This study constructs a tripartite evolutionary game model involving government, consumers, and BSM-ELV manufacturers to analyze market dynamics under diverse strategies. Key considerations include market scale, government environmental benefits, battery leasing/purchasing costs, lifecycle cost analysis (via discount rates), and resource efficiency (reserve battery ratio $\lambda$). MATLAB-2021b-based simulations predict participant strategy evolution paths. Findings reveal that market size and manufacturer expectations significantly influence governmental and manufacturing strategies. Crucially, incorporating discount rates demonstrates that battery leasing reduces consumer enterprises’ initial investment, enhancing economic sustainability and cash flow while offering superior total cost of ownership. Furthermore, gradual reduction of government subsidies effectively stimulates market self-regulation, incentivizes leasing adoption, and bolsters long-term economic/operational sustainability. Market feedback can guide policy adjustments toward fiscally sustainable support mechanisms. This study proposes the following management implications for advancing sustainable logistics: 1. Governments should phase out subsidies systematically to foster market resilience; 2. Manufacturers must invest in BSM R&D to improve efficiency and resource circularity; 3. Consumer enterprises can achieve economic benefits and emission reductions by adopting BSM-ELVs. Full article

The environmental challenges posed by global warming have significantly increased the global pursuit of renewable and clean energy sources. Among these, solar energy stands out due to its abundance, renewability, low environmental impact, and favorable long-term economic viability. However, its intermittent nature and dependence on weather conditions hinder consistent and efficient utilization. To address these limitations, nanoparticle-enhanced phase change materials (NPCMs) have emerged as a promising solution for enhancing thermal energy storage in solar thermal systems. NPCMs incorporate superior-performance nanoparticles within traditional phase change material matrices, resulting in improved thermal conductivity, energy storage density, and phase change efficiency. This review systematically examines the recent advances in NPCMs for solar energy applications, covering their classification, structural characteristics, advantages, and limitations. It also explores in-depth analytical approaches, including mechanism-oriented analysis, simulation-based modelling, and algorithm-driven optimization, that explain the behavior of NPCMs at micro and macro scales. Furthermore, the techno-economic implications of NPCM integration are evaluated, with particular attention to cost-benefit analysis, policy incentives, and market growth potential, which collectively support broader adoption. Overall, the findings highlight NPCMs as a frontier in materials innovation and enabling technology for achieving low-carbon, environmentally responsible energy solutions, contributing significantly to global sustainable development goals. Full article

Stroke is a major global cause of death and disability and necessitates both quick diagnosis and treatment within narrow windows of opportunity. CT scanning is still the first-line imaging in the acute phase, but correct interpretation may not always be readily available and may not be resource-available in poor and rural health systems. Automated stroke classification systems can offer useful diagnostic assistance, but clinical application demands high accuracy and explainable decision-making to maintain physician trust and patient safety. In this paper, a ResNet-18 model was trained on 6653 CT brain scans (hemorrhagic stroke, ischemia, normal) with two-phase fine-tuning and transfer learning, XRAI explainability analysis, and web-based clinical decision support system integration. The model performed with 95% test accuracy with good performance across all classes. This system has great potential for emergency rooms and resource-poor environments, offering quick stroke evaluation when specialists are not available, particularly by rapidly excluding hemorrhagic stroke and assisting in the identification of ischemic stroke, which are critical steps in considering tissue plasminogen activator (tPA) administration within therapeutic windows in eligible patients. The combination of classification, explainability, and clinical interface offers a complete framework for medical AI implementation. Full article

Background/Objectives: Hepatocellular carcinoma (HCC) remains a leading cause of global cancer mortality, with increasing incidence and persistently poor survival. Hepatitis C virus (HCV) is a major risk factor for HCC, and while the advent of direct-acting antivirals (DAAs) has significantly altered HCV-related hepatocellular cancer (HCC-HCV) risk, the global burden remains substantial. With the World Health Organization (WHO) aiming to reduce hepatitis-related deaths by 2030, we set out to evaluate global HCC-HCV trends from 1990 to 2021, stratified by sex, WHO region, and sociodemographic index (SDI), using data from the Global Burden of Disease (GBD) 2021 study. Methods: We analyzed age-standardized incidence (ASI), deaths, and disability-adjusted life years (DALYs) due to HCV-HCC from 1990 to 2021 using GBD 2021 data. Trends were stratified by WHO region, sociodemographic index (SDI), and sex. Joinpoint regression modeling was used to identify statistically significant temporal inflection points and calculate the annual percent change (APC) in unique time segments and average annual percent change (AAPC) over the entire study period (1990 to 2021). Results: Globally, deaths and DALYs attributable to HCV-HCC increased over the study period while ASI declined modestly. The region of the Americas exhibited the highest AAPC in all three metrics, potentially driven by an aging HCV-infected population, rising comorbidities (e.g., obesity, diabetes), and improved case detection. Nevertheless, on a global level, high-SDI regions showed the most favorable trends, particularly after 2016, likely reflecting the earlier adoption of DAAs and a differential success of WHO goals. Lower-SDI regions continued to exhibit increasing burden. Notably, ASI began to rise again between 2019 and 2021, suggesting an ongoing need to critically evaluate and restructure our approach to reducing HCV and HCV-HCC. Conclusions: Our findings underscore the urgent need for equity-driven, region-specific strategies to achieve better control of this highly morbid disease. Full article

The impact of invasive alien species (IAS) is one of the direct factors causing global biodiversity decline and economic losses, and predicting the potential invasion risks of invasive species is crucial for developing prevention and control strategies. In recent years, an increasing number of studies have shown that invasive species undergo rapid shifts in climate niche in invaded areas. Accurately quantifying the dynamic shifts in the climate niche of invasive species in invaded areas is crucial for developing a more accurate framework for early warning of invasive species risks. Pomacea canaliculata is a freshwater snail found in South America and has become one of the most aggressive aquatic species in the world. Since its introduction to China in 1981, it has rapidly spread and caused multiple serious damages to agriculture, ecology, and public health. Therefore, based on multi-source distribution data of P. canaliculata, this study calculated the climate niche overlap by Schoener’ s D, quantified the niche shifts between the P. canaliculata in native and invaded areas (China) via the COUE scheme (a unified terminology representing niche centroid shift, overlap, unfilling, and expansion), and analyzed their changes on a time scale. The results revealed that there have been significant climate niche shifts (Schoener’s D < 0.2, niche similarity tests p > 0.01, niche equivalence tests p < 0.01) between the native and invaded areas (China) of P. canaliculata, which does not support the climate niche conservation hypothesis. The minimum temperature of the coldest month (Bio 6) and precipitation seasonality (Bio 15) were the key climate variables driving the climatic niche shift, and P. canaliculata can survive in colder and more arid regions than their native counterparts. The changes in the niche shifts in P. canaliculata on a time scale show significant temporal heterogeneity, and its invasion behavior in China presents a discontinuous and phased expansion pattern, with strong adaptability to new environments. The results are of great significance for the future development of more accurate ecological niche model (ENM), the formulation of more targeted prevention and control strategies, and the study of adaptive evolution mechanisms of invasive species. Full article

The refined aerodynamic design optimization of multistage compressors is a typical high-dimensional and expensive optimization problem. This study proposes an integrated surrogate model-assisted evolutionary algorithm combined with a Directly Manipulated Free-Form Deformation (DFFD)-based parametric dimensionality reduction method, establishing a high-precision and efficient global parallel aerodynamic optimization platform for multistage axial compressors. The DFFD method achieves a balance between flexibility and low-dimensional characteristics by directly controlling the surface points of blades, which demonstrates a particular suitability for the aerodynamic design optimization of multistage axial compressors. The integrated surrogate model enhances prediction accuracy by simultaneously identifying optimal solutions and the most uncertain solutions, effectively addressing highly nonlinear design space challenges. A three-stage axial compressor in a heavy-duty gas turbine is selected as the optimization object. The results demonstrate that the optimization task takes less than 48 h and achieves an improvement of 0.6% and 4% in the adiabatic efficiency and surge margin, respectively, while maintaining a nearly unchanged flow rate and pressure ratio at the design point. The proposed approach provides an efficient and reliable solution for complex aerodynamic optimization problems. Full article

This study pioneers an investigation into how artificial intelligence (AI)—shaped by financial development and knowledge production—is transforming the energy transition across BRICS economies and paving the way for a digitally enabled, sustainable future. Using panel data for 2005–2020, the findings confirm that AI is the primary driver of both explicit (EET) and implicit (IET) energy transitions in the BRICS nations, while economic growth, human capital, and financial globalization play comparatively smaller roles. We further find that AI’s effect on the explicit transition is fully mediated by efficiency gains. Financial development weakens—whereas knowledge production strengthens—AI’s green impact. Robustness checks across alternative models support these results, and spillover analyses indicate that cross-border AI advances, economic growth, human capital, and innovation flows shape each BRICS country’s energy-transition path. Based on these findings, the study proposes coordinated policy packages to harness AI for the energy transition while managing distributional and cross-border effects. Full article

Urban greenspace exposure associates with improved health outcomes, particularly chronic disease mitigation. Based on the need to characterize spatial heterogeneity in the health benefits of urban greenspaces, this study quantified the association between greenspace accessibility and chronic disease mortality in London, while examining the modulating effects of urbanization and age. Utilizing nighttime light (NTL) data to define urbanization gradients and road-network analysis to measure greenspace accessibility, we applied geographically weighted regression (GWR) across 983 neighborhoods. Key findings reveal that over 60% of central London residents live within 300 m of greenspace, yet 20% fall short of WHO standards. Greenspace accessibility showed significant negative associations with standardized mortality ratios for both cancer (β = −0.0759) and respiratory diseases (β = −0.0358), and this relationship was more pronounced in highly urbanized areas and neighborhoods with higher working-age populations. Crucially, central urban zones show amplified effects: a 100 m accessibility improvement was associated with a potential reduction in cancer deaths of 1.9% and in respiratory disease deaths of 2.4% in high-sensitivity areas. Urbanization levels and working-age population proportions exert significantly stronger moderating effects on greenspace–respiratory disease relationships than on cancer outcomes. While observational, our findings provide spatially explicit evidence that the greenspace–mortality relationship is context-dependent. This underscores the need for precision in urban health planning, suggesting interventions should prioritize equitable greenspace coverage in highly urbanized cores and tailor functions to local demographics to optimize potential co-benefits. This study reframes understanding of greenspace health benefits, enhances spatial management precision, and offers models for healthy planning in global high-density cities. Full article

Digital ink Chinese characters (DICCs) written by international students often contain various errors and irregularities, making the recognition of these characters a highly challenging pattern recognition problem. This paper designs a graph convolutional network with agent attention (GCNAA) for recognizing DICCs written by international students. Each sampling point is treated as a vertex in a graph, with connections between adjacent sampling points within the same stroke serving as edges to create a Chinese character graph structure. The GCNAA is used to process the data of the Chinese character graph structure, implemented by stacking Block modules. In each Block module, the graph agent attention module not only models the global context between graph nodes but also reduces computational complexity, shortens training time, and accelerates inference speed. The graph convolution block module models the local adjacency structure of the graph by aggregating local geometric information from neighboring nodes, while graph pooling is employed to learn multi-resolution features. Finally, the Softmax function is used to generate prediction results. Experiments conducted on public datasets such as CASIA-OLWHDB1.0-1.2, SCUT-COUCH2009 GB1&GB2, and HIT-OR3C-ONLINE demonstrate that the GCNAA performs well even on large-category datasets, showing strong generalization ability and robustness. The recognition accuracy for DICCs written by international students reaches 98.7%. Accurate and efficient handwritten Chinese character recognition technology can provide a solid technical foundation for computer-assisted Chinese character writing for international students, thereby promoting the development of international Chinese character education. Full article

This study examines the evolution of agricultural raw material exports in seven emerging economies of Central and Eastern Europe (Romania, Poland, Slovakia, Croatia, Bulgaria, the Czech Republic, and Hungary) from 1995 to 2023 and provides forecasts for 2024–2026 using ARIMA models. The results indicate a general downward trend in the share of agricultural raw material exports within total exports, reflecting ongoing economic modernization and a structural shift toward higher value-added products and industrial sectors. Romania, Poland, and Hungary remain as significant players in the cereals market, while Slovakia and the Czech Republic show the most pronounced transitions toward non-agricultural industries. Croatia, however, follows an atypical trajectory, maintaining a relatively high share of agricultural exports. Statistical tests (Dickey–Fuller) confirm the non-stationarity of the initial series, necessitating differencing for ARIMA modeling. Correlation analyses reveal a synchronized regional dynamic, with strong links among Poland, Slovakia, the Czech Republic, and Bulgaria. Forecasts suggest continued decline or stabilization at low levels for most countries: Romania (0.45% in 2026), Poland (0.93%), Slovakia (0.62%), Bulgaria (0.51%), the Czech Republic (0.95%), and Hungary (0.53%), while Croatia is an exception, with a projected moderate increase to 4.19% in 2026. Although the share of raw agricultural exports is decreasing, the findings confirm that agriculture remains a strategic sector for food security and regional trade. The study recommends investments in processing, technological modernization, and export market diversification to strengthen the competitiveness and resilience of the agricultural sector in the context of global economic transformations. Full article

Global ambitions for net-zero emissions and resource circularity are propelling industry from linear “make-use-dispose”models toward closed-loop value creation. Remanufacturing, which aims to restore end-of-life products to a “like-new” condition, plays a central role in this transition. However, its stochastic inputs and complex, multi-stage processes pose significant challenges to traditional production planning methods. This study delivers an integrated overview of remanufacturing scheduling by combining a systematic bibliometric review of 190 publications (2005–2025) with a critical synthesis of modelling approaches and enabling technologies. The bibliometric results reveal five thematic clusters and a 14% annual growth rate, highlighting a shift from deterministic, shop-floor-focused models to uncertainty-aware, sustainability-oriented frameworks. The scheduling problems are formalised to capture features arising from variable core quality, multi-phase precedence, and carbon reduction goals, in both centralised and cloud-based systems. Advances in human–robot disassembly, vision-based inspection, hybrid repair, and digital testing demonstrate feedback-rich environments that increasingly integrate planning and execution. A comparative analysis shows that, while mixed-integer programming and metaheuristics perform well in small static settings, dynamic and large-scale contexts benefit from reinforcement learning and hybrid decomposition models. Finally, future directions for dynamic, collaborative, carbon-conscious, and digital-twin-driven scheduling are outlined and investigated. Full article

Heritage landscapes endure not through the preservation of fixed forms but through the capacity to adapt to changing social, political, economic, and environmental conditions. Conservation policies that privilege static ideals of authenticity risk undermining the very systems they aim to protect. This paper advances a model of shared stewardship that links conservation of heritage to support for livelihoods, functional flexibility, and community authority in decision-making. Using the Ifugao Rice Terraces of the Philippine Cordillera as a case study, we integrate archaeological, ethnographic, spatial, and agricultural economic evidence to examine the terraces as a dynamic socio-ecological system. Archaeological findings and oral histories show that wet-rice agriculture expanded in the 17th century, replacing earlier taro-based systems and incorporating swidden fields, managed forests, and ritual obligations. Contemporary changes such as the shift from heirloom tinawon rice to commercial crops, the impacts of labor migration, and climate variability reflect long-standing adaptive strategies rather than cultural decline. Comparative cases from other UNESCO and heritage sites demonstrate that economic viability, adaptability, and local governance are essential to sustaining long-inhabited agricultural landscapes. We thus argue that the Ifugao terraces, like their global counterparts, should be conserved as living systems whose cultural continuity depends on their ability to respond to present and future challenges. Full article