Search Results (4,282)

Existing research has made significant strides in UAV formation control, particularly in active localization and certain passive methods. However, these approaches face substantial limitations in electromagnetically silent environments, often relying on strong assumptions such as fully known and stationary emitter positions. To overcome these challenges, this paper proposes a comprehensive framework for bearing-only passive localization and adjustment of UAV formations under strict electromagnetic silence constraints. We systematically develop three core models: (1) a geometric triangulation model for scenarios with three known emitters, enabling unique target positioning; (2) a hierarchical identification mechanism leveraging an angle database to resolve label ambiguity when some emitters are unknown; and (3) a cyclic cooperative strategy, Perceive-Explore-Judge-Execute (PEJE), optimized via an improved genetic algorithm with adaptive discrete neighborhood search (GA-IADNS), for dynamic formation adjustment. Extensive simulations demonstrate that our proposed methods exhibit strong robustness, rapid convergence, and high adjustment accuracy across varying initial deviations. Specifically, after adjustment, the maximum radial deviation of all UAVs from the desired position is less than 0.0001 m, and the maximum angular deviation is within $0.{00013}^{\circ }$; even for the $30\%R$ initial deviation scenario, the final positional error remains negligible. Furthermore, comparative experiments with a standard Genetic Algorithm (GA) confirm that GA-IADNS achieves superior performance: it reaches stable peak average fitness at the 6th generation (vs. no obvious convergence of GA even after 20 generations), reduces the convergence time by over $70\%$, and improves the final adjustment accuracy by more than $95\%$ relative to GA. These results significantly enhance the autonomous collaborative control capability of UAV formations in challenging electromagnetic conditions. Full article

With the increasing use of horizontal wells in oil and gas development, measurement-while-drilling (MWD) systems require higher magnetic azimuth accuracy to ensure precise trajectory control. This study proposes a three-stage magnetic azimuth error compensation method based on multi-station analysis (MSA). First, the OPTICS clustering algorithm is utilized to identify and remove noise points, and ellipse fitting is applied to suppress radial magnetic interference. Second, an improved MSA model incorporating wellbore trajectory constraints is developed to minimize axial interference and enhance correction stability. Finally, a Gaussian Process Regression (GPR) model, using accelerometer and magnetometer data as features, is introduced to model and compensate for residual nonlinear errors. Experimental validation under simulated complex magnetic conditions shows that OPTICS-based preprocessing significantly improves ellipse fitting and reduces hard magnetic interference. The improved MSA lowers the mean azimuth error to approximately 2.5°, while integrating GPR further decreases it to below 0.04°. The proposed GPR model achieves an R² of 0.99972 and an RMSE of 0.02928° on the test set, confirming its strong nonlinear compensation capability. Overall, the proposed framework effectively suppresses magnetic interference and enhances azimuth accuracy, providing a robust solution for high-precision MWD applications in horizontal wells. Full article

This paper develops a Sustainable Artificial Intelligence-Driven Wind Power Forecasting System (SAI-WPFS) to enhance the integration of renewable energy while minimizing the environmental footprint of deep learning computations. Although deep learning models such as CNN, LSTM, and GRU have achieved high accuracy in wind power forecasting, existing research rarely considers the computational energy cost and associated carbon emissions, creating a gap between predictive performance and sustainability objectives. Moreover, limited studies have addressed the need for a balanced framework that jointly evaluates forecast precision and eco-efficiency in the context of large-scale renewable deployment. Using real-time data from the Dumat Al-Jandal Wind Farm, Saudi Arabia’s first utility-scale wind project, this study evaluates multiple deep learning architectures, including CNN-LSTM-AM and GRU, under a dual assessment framework combining accuracy metrics (MAE, RMSE, R²) and carbon efficiency indicators (CO₂ emissions per computational hour). Results show that the CNN-LSTM-AM model achieves the highest forecasting accuracy (MAE = 29.37, RMSE = 144.99, R² = 0.74), while the GRU model offers the best trade-off between performance and emissions (320 g CO₂/h). These findings demonstrate the feasibility of integrating sustainable AI into wind energy forecasting, aligning technical innovation with Saudi Vision 2030 goals for zero-carbon cities and carbon-efficient energy systems. Full article

Against the backdrop of global economic digital transformation and the rapid flow of creative factors, innovation spaces, as the key carriers of inventive activities, drive high-quality development in urban agglomerations. This study develops a three-dimensional framework of “Spatial Structure–Factor Synergy–Institutional Drivers” to uncover the evolution of innovation spaces and industrial shifts in the Beijing–Tianjin–Hebei urban agglomeration, China. Methodologically, spatial econometric techniques were applied to capture both the overall concentration and spatial disparities of innovation. Spatial Gini and variation coefficients measured innovation clustering, while standard deviation ellipses and location entropy identified spatial linkages among high-tech innovation clusters. Geographically weighted regression models explored spatial heterogeneity in influencing factors, and a policy intensity index was constructed to assess the effectiveness of differentiated policy interventions in optimizing innovation resources. Key findings include the following: (1) Innovation spaces are spatially polarized in a “core–periphery” pattern, yet require cross-regional collaboration. Concurrently, high-tech industries demonstrate a gradient structure: central cities leading in R&D, sub-central cities driving industrial applications, and node cities achieving specialized development through industrial transfer. (2) The driving mechanisms exhibit significant spatial heterogeneity: economic density shows diminishing returns in core areas, whereas R&D investment and ecological quality demonstrate increasingly positive effects, with foreign investment’s role evolving positively post-institutional reforms. (3) Regional innovation synergy has formed a preliminary framework, but strengthening sustainable policy mechanisms remains pivotal to advancing market-driven coordination and dismantling administrative barriers. These findings underscore the importance of integrated policy reforms for achieving balanced and high-quality innovation development in administratively coordinated urban agglomerations like BTH. Full article

This paper analyzes a finite-capacity $GI/M/2/N$ queue with two heterogeneous servers operating under a multiple working-vacation policy, Bernoulli feedback, and customer impatience. Using the supplementary-variable technique in tandem with a tailored recursive scheme, we derive the stationary distributions of the system size as observed at pre-arrival instants and at arbitrary epochs. From these, we obtain explicit expressions for key performance metrics, including blocking probability, average reneging rate, mean queue length, mean sojourn time, throughput, and server utilizations. We then embed these metrics in an economic cost function and determine service-rate settings that minimize the total expected cost via the Bat Algorithm. Numerical experiments implemented in R validate the analysis and quantify the managerial impact of the vacation, feedback, and impatience parameters through sensitivity studies. The framework accommodates general renewal arrivals ($GI$), thereby extending classical ($M/M/2/N$) results to more realistic input processes while preserving computational tractability. Beyond methodological interest, the results yield actionable design guidance: (i) they separate Palm and time-stationary viewpoints cleanly under non-Poisson input, (ii) they retain heterogeneity throughout all formulas, and (iii) they provide a cost–optimization pipeline that can be deployed with routine numerical effort. Methodologically, we (i) characterize the generator of the augmented piecewise–deterministic Markov process and prove the existence/uniqueness of the stationary law on the finite state space, (ii) derive an explicit Palm–time conversion formula valid for non-Poisson input, (iii) show that the boundary-value recursion for the Laplace–Stieltjes transforms runs in linear time $\mathcal{O}\left(N\right)$ and is numerically stable, and (iv) provide influence-function (IPA) sensitivities of performance metrics with respect to $({\mu }_1,{\mu }_2,\nu ,\alpha ,\varphi ,\beta )$. Full article

In the context of Industry 4.0 and smart manufacturing, predicting cutting tool remaining useful life (RUL) is crucial for enabling and enhancing the reliability and efficiency of CNC machining. This paper presents an innovative predictive model based on the data fusion architecture of Graph Neural Networks (GNNs) and Transformers to address the complexity of shallow multimodal data fusion, insufficient relational modeling, and single-task limitations simultaneously. The model harnesses time-series data, geometric information, operational parameters, and phase contexts through dedicated encoders, employs graph attention networks (GATs) to infer complex structural dependencies, and utilizes a cross-modal Transformer decoder to generate fused features. A dual-head output enables collaborative RUL regression and health state classification of cutting tools. Experiments are conducted on a multimodal dataset of 824 entries derived from multi-sensor data, constructing a systematic framework centered on tool flank wear width (VB), which includes correlation analysis, trend modeling, and risk assessment. Results demonstrate that the proposed model outperforms baseline models, with MSE reduced by 26–41%, MAE by 33–43%, R² improved by 6–12%, accuracy by 6–12%, and F1-Score by 7–14%. Full article

This study investigates how increasing prompt complexity affects the performance of Large Language Models (LLMs) across multiple Natural Language Processing (NLP) tasks. We introduce an incremental evaluation framework where six tasks—JSON formatting, English-Italian translation, sentiment analysis, emotion classification, topic extraction, and named entity recognition—are progressively combined within a single prompt. Six representative open-source LLMs from different families (Llama 3.1 8B, Gemma 3 4B, Mistral 7B, Qwen3 4B, Granite 3.1 3B, and DeepSeek R1 7B) were systematically evaluated using local inference environments to ensure reproducibility. Results show that performance degradation is highly architecture-dependent: while Qwen3 4B maintained stable performance across all tasks, Gemma 3 4B and Granite 3.1 3B exhibited severe collapses in fine-grained semantic tasks. Interestingly, some models (e.g., Llama 3.1 8B and DeepSeek R1 7B) demonstrated positive transfer effects, improving in certain tasks under multitask conditions. Statistical analyses confirmed significant differences across models for structured and semantic tasks, highlighting the absence of a universal degradation rule. These findings suggest that multitask prompting resilience is shaped more by architectural design than by model size alone, and they motivate adaptive, model-specific strategies for prompt composition in complex NLP applications. Full article

This paper proposes a fuzzy copula-based optimization framework for modeling dependence structures and financial risk under parameter uncertainty. The parameters of selected copula families are represented as trapezoidal fuzzy numbers, and their α-cut intervals capture both the support and core ranges of plausible dependence values. This fuzzification transforms the estimation of copula parameters into a fuzzy optimization problem, enhancing robustness against sampling variability. The methodology is empirically applied to gold and oil futures (1 January 2015–1 January 2025), comparing symmetric copulas, i.e., Gaussian and Frank and asymmetric copulas, i.e., Clayton, Gumbel and Student-t. The results prove that the fuzzy copula framework provides richer insights than classical point estimation by explicitly expressing uncertainty in dependence measures (Kendall’s τ, Spearman’s ρ) and risk indicators (Value-at-Risk, Conditional Value-at-Risk). Rolling-window analyses reveal that fuzzy VaR and fuzzy CVaR effectively capture temporal dependence shifts and tail severity, with fuzzy CVaR consistently producing more conservative risk estimates. This study highlights the potential of fuzzy optimization and fuzzy dependence modeling as powerful tools for quantifying uncertainty and managing extreme co-movements in financial markets. Full article

The implementation of Euro 7 emission standards demands advanced real-time NO_x monitoring systems for diesel vehicles. Existing unified models inadequately capture phase-dependent emission mechanisms during cold-start, urban, and highway operation. This study develops a novel Mixture of Experts (MoE) architecture with data-driven phase classification based on aftertreatment thermal dynamics. Real-world data from a Euro 6d commercial vehicle (3247 PEMS samples) were classified into three phases, cold (<70 °C coolant temperature), hot low-speed (<90 km/h), and hot high-speed (≥90 km/h), validated through t-SNE analysis (silhouette coefficient = 0.73). The key innovation integrates thermal–kinematic domain knowledge with specialized XGBoost regressors, achieving R² = 0.918 and a 58% RMSE reduction versus unified models (RMSE = 1.825 mg/s). The framework operates within real-time constraints (1.5 ms inference latency), integrating autoencoder-based anomaly detection (95.2% sensitivity) and Model Predictive Control (11–13% NO_x reduction). This represents the first systematic phase-specific NO_x modeling framework with validated Euro 7 OBM compliance capability, providing both methodological advances in expert allocation strategies and practical solutions for next-generation emission control systems. Full article

Soil nutrient detection in wetlands is critical for rapidly and effectively managing these ecosystems. Our objective was to provide a methodological framework for identifying optimal data processing methods and machine learning model for predicting soil organic carbon (SOC) and total nitrogen (TN) content using Vis–NIR spectroscopy, under the confounding influence of varying soil moisture. Soil samples (474) were collected from the Shaanxi Yellow River Wetland Provincial Nature Reserve with five moisture levels (0, 5, 10, 20, and 30%). Using a Vis–NIR spectroscopy system (ASD FS4 spectrometer), soil organic carbon (SOC) and total nitrogen (TN) were detected within the 350–2500 nm spectral range. Machine learning models were established using the Random Forest model (RF), eXtreme Gradient Boosting (XGBoost), and Partial Least Squares Regression (PLSR). The results indicated: (1) spectral reflectance values increased as soil moisture content decreased, with the 0% moisture model being consistently more accurate; (2) models for SOC and TN on first-derivative spectra had higher accuracy; and (3) the RF exhibited higher inversion accuracy and stability (R² = 0.30–0.69). (4) The SHAP analysis confirmed 1865 nm and 1419 nm as the most contributory bands for SOC and TN prediction respectively, validating the RF model’s spectral interpretation capability. Full article

The systematic failure of standard Value-at-Risk (VaR) models for the Tokyo Commodity Exchange (TOCOM) rubber futures contract poses significant challenges for risk management. This study addresses the issue by examining the market’s split trading sessions, which induce distinct overnight and intraday volatility regimes. We decompose daily returns into these two components and apply tailored Generalized Autoregressive Conditional Heteroskedasticity (GARCH) family models. Our empirical results, strengthened by extensive robustness checks using EGARCH, IGARCH, and GJR-GARCH specifications, reveal that intraday volatility is persistent and influenced by leverage effects, whereas overnight volatility behaves as a jump-driven process unaccounted for by conventional models. Comprehensive VaR backtesting confirms that while traditional models accurately capture intraday risk, all standard daily models—including asymmetric variants—systematically and severely underestimate overnight risk. These findings demonstrate that aggregating returns into a single daily series conflates different volatility dynamics, leading to model failures. We propose a two-tiered risk management framework that separately applies conventional models to intraday risk and jump-aware measures for overnight risk. This approach aligns risk assessment with underlying market microstructure, improving model validity and capital adequacy for TOCOM rubber futures. Full article

Peat mosses of the genus Sphagnum are keystone species in peatland ecosystems and play critical roles in carbon sequestration, nitrogen fixation, and hydrological regulation. Indeed, these ecological functions are largely mediated by endophytic bacteria associated with Sphagnum. Here, five populations of the endemic Chinese moss species, S. multifibrosum, were sampled across southern China in peatland (PH) and rock habitats (RH). High-throughput sequencing of 16S rRNA and nitrogenase (nifH) genes was applied to characterize overall endophytic bacterial diversity and diazotroph diversity associated with S. multifibrosum, respectively, alongside host microsatellite genotyping. Proteobacteria was the dominant endophytic bacterial phylum. The bacterial communities exhibited significant spatial separation between eastern and western communities and community dissimilarities significantly increased with increasing geographic distances. Environmental heterogeneity and host genetics jointly shaped endophytic bacterial community assemblage. Climate was the most important determinant influencing bacterial composition, followed by host genotype and habitat type. Temperature, precipitation, and nitrogen deposition were the primary environmental factors that influenced composition. Bacterial diversity and composition exhibited no statistically significant differences between the two habitats. Further, the richness and abundances of diazotrophs and methanotrophs from PH communities were higher than in RH communities. Co-occurrence network analysis suggested that RH bacterial networks had lower connectance but were more modularized and exhibited higher complexity than PH networks. These results highlight the ecological functions of peat mosses in carbon and nitrogen cycling and suggest a need to prioritize the conservation of S. multifibrosum in peatland environments under global climate change. The results also provide a framework to help future wetland management and biodiversity conservation efforts in China. Full article

Flight delays during extreme weather events exhibit spatio-temporal propagation and cascading effects, posing serious challenges to the resilience of aviation systems. Existing prediction approaches often neglect dynamic dependencies across flight chains and struggle to model sparse extreme events. This study develops a data-driven framework that explicitly models delay propagation paths, incorporates historical scenario retrieval to capture rare disruption patterns, and integrates meteorological, airport operational, and flight-specific information through multi-source fusion. Using U.S. flight operations and weather records, the framework demonstrates clear advantages over established baselines in extreme-delay scenarios, achieving a MAE of 3.23 min, an RMSE of 6.25 min, and an R² of 0.92—improving by 8.8%, 26.0%, and 5.75% compared to the best benchmark. Ablation studies confirm the contribution of the propagation modeling, historical retrieval, and multi-source integration modules, while cross-airport evaluations reveal consistent accuracy at both major hubs (e.g., Atlanta, Chicago O’Hare) and regional airports (e.g., Kona, Anchorage). These findings demonstrate that the proposed framework enables reliable forecasting of delay propagation under complex weather conditions, providing valuable support for proactive departure management and enhancing the resilience of aviation operations. Full article

Most reinforcement learning (RL) methods for portfolio optimization remain limited to single markets and a single algorithmic paradigm, which restricts their adaptability to regime shifts and heterogeneous conditions. This paper introduces a generalized version of the Modular Portfolio Learning System (MPLS), extending beyond its initial PPO backbone to integrate four RL algorithms: Proximal Policy Optimization (PPO), Deep Q-Network (DQN), Deep Deterministic Policy Gradient (DDPG), and Soft Actor-Critic (SAC). Building on its modular design, MPLS leverages specialized components for sentiment analysis, volatility forecasting, and structural dependency modeling, whose signals are fused within an attention-based decision framework. Unlike prior approaches, MPLS is evaluated independently on three major equity indices (S&P 500, DAX 30, and FTSE 100) across diverse regimes including stable, crisis, recovery, and sideways phases. Experimental results show that MPLS consistently achieved higher Sharpe ratios—typically +40–70% over Minimum Variance Portfolio (MVP) and Risk Parity (RP)—while limiting drawdowns and Conditional Value-at-Risk (CVaR) during stress periods such as the COVID-19 crash. Turnover levels remained moderate, confirming cost-awareness. Ablation and variance analyses highlight the distinct contribution of each module and the robustness of the framework. Overall, MPLS represents a modular, resilient, and practically relevant framework for risk-aware portfolio optimization. Full article

Traditional power system planning methods are often based on deterministic assumptions, which cannot effectively address the uncertainties brought by high proportions of renewable energy sources. This may result in insufficient power supply or wasted resources. This paper proposes a novel optimization planning method for power systems, combining a hierarchical Copula model with a comprehensive risk assessment approach. The aim is to optimize the balance between investment costs and operational risks in large-scale power systems. The hierarchical Copula model is employed to handle the spatial correlation and temporal dependence between wind power, photovoltaic power, and load. Multiple joint scenarios are generated using the Monte Carlo method to reflect the complex interactions between different geographic locations, providing more comprehensive data support for risk assessment. Additionally, a CVaR-based comprehensive risk assessment method is used to quantify the risks of power loss and resource wastage, which are then integrated into a comprehensive risk indicator through weighted aggregation. An optimization framework considering supply–demand probability balance constraints is proposed, allowing for supply–demand balance at a certain probability level. Benders decomposition is used to improve computational efficiency. Simulation results show that, compared to traditional methods, the proposed model significantly reduces the curtailment rate and supply–demand imbalance frequency, improving the system’s adaptability to uncertainties and extreme scenarios. Full article