Search Results (1,081)

The black-winged kite algorithm (BKA) integrates the Cauchy mutation strategy and the leader selection strategy to simulate high-altitude circling exploration, fixed-point diving attack, and group cooperative migration of the black-winged kites to approximate the global optimal solution. The BKA exhibits deficiencies in ponderous convergence efficacy, inefficient calculation precision, and insufficient population diversity. To strengthen the convergence property and computational practicability, an enhanced BKA with multiple strategies (MSBKA) is advocated to accommodate global optimization and constrained engineering applications. The objective is to systematically verify its advancement and competitiveness and accurately actualize the global optimal solution. The ranking-based differential mutation can strengthen population information interaction, accelerate convergence efficiency, restrain premature convergence, diminish homogenization competition, promote exploration and exploitation, intensify elite individual guidance, downscale ineffective iterations, and materialize orderly population renewal. The simplex method can execute the local refinement operations of reflection, expansion, compression and contraction, strengthen local mining efficiency, ameliorate solution accuracy, abate parameter sensitivity, eschew local optimal traps, accelerate accurate convergence, and preserve the optimal individual potential. The elite opposition-based learning strategy can fabricate reverse solutions, expand the monolithic detection space, shorten the convergence process, elevate the quality of initial and iterative solutions, boost population diversity, guide intelligent search direction, and relieve premature convergence. The MSBKA utilizes deficiency orientation, strategy adaptation, and collaborative search to accomplish the realistic demands of high-precision, high-efficiency and strong constraint adaptation, surmount the static trade-off dilemma, endow a strong directional abscond mechanism to replace random perturbation, and actualize the inertia of directional exploration and the blind spots of solution exploitation. Twenty-three benchmark functions and six real-world engineering designs are employed to authenticate theoretical superiority and engineering practicability. The experimental results demonstrate that the MSBKA incorporates strong practicability and reliability to strengthen information interaction, restrain search stagnation, diminish convergence oscillation and fluctuation, facilitate globalized discovery and localized extraction, expedite convergence efficacy, ameliorate solution precision, and consolidate stability and robustness. Full article

Recent discussions on the future of European Union governance highlight a growing emphasis on integrated policy frameworks that align agricultural, territorial, and socio-economic development objectives within unified strategic planning systems. One of the proposed innovations for the next EU programming period is the introduction of National and Regional Partnership Plans (NRPPs), which aim to coordinate several EU funding instruments within a single national planning framework. This article explores stakeholder perspectives on the development of integrated policy planning in this context. The analysis is guided by analytical propositions derived from the literature on policy integration and multi-level governance, focusing on how stakeholder interpretations influence strategic priority alignment, perceived policy trade-offs, and governance coordination capacity. The study is based on a qualitative focus group discussion involving policy stakeholders, researchers, and institutional representatives in Lithuania. Using thematic analysis, the study examines how stakeholders interpret integrated planning concepts, identify strategic priorities, and assess governance challenges associated with policy integration. The findings reveal three key issues shaping stakeholder perspectives. First, conceptual ambiguity surrounding strategic priorities such as competitiveness, regional vitality, and sustainability may complicate policy coordination. Second, perceived conflicts between economic competitiveness and environmental sustainability may be less pronounced than often assumed. Third, the implementation of integrated policy frameworks requires stronger governance capacity, including improved cross-ministerial coordination and shared monitoring systems. The article contributes to research on policy integration and multi-level governance by providing empirical evidence on how policy actors interpret integrated strategic planning frameworks and how these interpretations shape perceptions of governance capacity, policy trade-offs, and stakeholder participation in EU funding reforms. Full article

The increasing competition for land between agriculture and electricity generation has driven the implementation agrivoltaic systems (AVSs) as a strategy aligned with Sustainable Development Goals 7 and 13. This study systematically analyzes how AVS design influences agricultural yield (AY), energy yield (EY), and overall sustainability. A systematic review was conducted following the PRISMA protocol, complemented by bibliometric analysis and an exploratory correlation analysis of design variables, productivity indicators, and environmental and economic metrics. From an initial set of 243 records, 79 studies published between 2018 and 2025 were included. The results identify general trends across heterogeneous studies, although these patterns should not be interpreted as universally applicable. Intermediate ground cover ratios (GCRs) (≈30–40%) are commonly associated with favorable trade-offs between AY and EY, often resulting in land equivalent ratios above 1.5 under specific conditions. Reported outcomes indicate that AVS can achieve increases in EY, improvements in water-use efficiency, reductions in CO₂ emissions, and competitive economic performance, although these results vary depending on crop type, climate, system configuration, and PV technology. Overall, the analysis highlights GCR as a key design parameter and underscores that AVS performance depends on multivariable and context-specific design rather than universally applicable thresholds, reinforcing its potential as a sustainable agri-energy solution. Full article

In top-N recommendation, incorporating item-side information can improve ranking quality under sparse user–item interactions; however, common flat concatenation strategies may weaken the structural correspondence between user ratings and item attributes while simultaneously increasing model size. To address this issue, this study proposes DAERec-GCA, a deep autoencoder-based collaborative filtering framework that organizes rating signals and genre information in a genre-channel-aligned two-dimensional representation. The model applies shared weights across genre channels and aggregates channel outputs to generate item scores, enabling side-information integration without the parameter growth associated with flattened genre-aware formulations. The framework was evaluated on MovieLens-100K, 1M, and 10M under a warm-start five-fold cross-validation protocol using ranking-based metrics. In addition, a structured ablation study was conducted against ROnly, Flat1D, GenreProfile, GenreEmbed, and GenreGated, together with a controlled train-side sparsity analysis and a computational profiling analysis covering trainable parameters, epoch time, inference latency, and peak GPU memory. The results show that DAERec-GCA remains competitive across all three datasets and exhibits its clearest advantage under sparse and moderately sparse training conditions. The findings suggest that genre-channel alignment provides a practical trade-off between structural expressiveness, parameter efficiency, and recommendation quality in sparse recommendation settings. Full article

Event cameras are bio-inspired vision sensors offering low latency, low power consumption, and high dynamic range, capturing motion with microsecond-level precision via a per-event triggering mechanism. Despite these advantages, the inherent sparsity and lack of color in event data hinder direct analysis, necessitating advanced deep learning approaches. To achieve low-latency and high-precision motion segmentation for indoor robotic applications, this paper introduces a dual-branch decoupled CNN framework. Specifically, Principal Component Analysis (PCA) is utilized to project 3D event point clouds into 2D motion trend maps, capturing local motion priors while suppressing ambiguity in structured environments. Concurrently, an Event Leaky Integration (ELI) model, inspired by biological membrane potentials, is designed to enhance the structural representation of sparse events. Within this framework, separate branches respectively perform motion validation and shape extraction and are fused via a Spatial Gated Fusion (SGF) module to suppress static background interference. It is demonstrated experimentally that with an input window of only 10 ms, the proposed method achieves a 77% average mIoU across five indoor test scenarios from the EV-IMO dataset with an inference latency of 10 ms per frame. Compared to state-of-the-art methods like MSRNN and GCN, which required 30–300 ms event slices, our framework achieves a favorable trade-off between computational efficiency and segmentation accuracy, maintaining competitive performance under ultra-short time windows for indoor event-based motion processing. Full article

Cattle behavior constitutes important phenotypic information reflecting animals’ health status, activity level, and welfare condition, and is therefore of considerable significance for automated monitoring and precision management in smart livestock farming. However, under complex barn conditions, cattle behavior recognition is easily affected by factors such as illumination variation, partial occlusion, background interference, and individual differences, thereby reducing recognition stability and generalization capability. To address these challenges, this study proposes a pose-driven method for cattle behavior recognition in complex barn environments. First, a 16-keypoint annotation scheme suitable for describing bovine posture, termed cow16, was constructed. Based on this scheme, OpenPose was employed to extract heatmaps (HMs) and part affinity fields (PAFs), which were then used to build an intermediate HM/PAF posture representation. Subsequently, this representation was taken as the input to a lightweight convolutional neural network for classifying three behavioral categories: stand, walk, and lying. On this basis, class-imbalance correction during training and a multi-random-seed logits ensemble strategy during inference were further introduced. In addition, knowledge distillation was adopted to transfer knowledge from a high-performance teacher model to a lightweight student model. Experimental results demonstrate that training-stage class-imbalance correction and inference-stage multi-random-seed logits ensembling exhibit strong complementarity; when combined, the AB configuration improves the test-set Macro-F1 by 3.83 percentage points. Moreover, the distilled student model still achieves competitive recognition performance while maintaining 1× inference cost, indicating a favorable trade-off between accuracy and efficiency. This study provides a useful reference for deployment-oriented cattle behavior recognition in smart farming scenarios and offers a lightweight technical basis for subsequent practical applications. Full article

Metallurgical-grade silicon (MG-Si) is an important source material for many industrial applications, including the manufacture of alloys, solar photovoltaics, and electronics. The process to refine raw materials into MG-Si is energy-intensive, with the predominant method of submerged-arc furnaces requiring energy consumption of approximately 11–13 kWh/kg Si. Recent research has discussed promising methods for reducing the energy required for the silicon production process, including the use of molten-salt electrolysis (MSE), a technique that offers potential savings in energy consumption without requiring carbon inputs for the process. This paper presents a techno-economic study of a potential industrial-scale MSE plant for MG-Si production to evaluate the trade-offs between capital and operating costs of the system. Capital costs are sourced from recent MG-Si plants and an existing cost model developed for MSE processes that includes the size of the plant and the operating temperature among its inputs. The results show that MSE technology has the potential to be an economically cost-competitive option for MG-Si production if the technology successfully scales to industrial production and matures enough to allow for financing costs similar to that of a comparably sized submerged-arc furnace plant. Full article

Using daily data from Investing.com South Africa, this study investigates the forecasting performance of four Rand currency rate markets (EUR/ZAR, CHF/ZAR, BRL/ZAR, and CNY/ZAR) from 13 February 2018 until 24 February 2025. The predictive fitness of three competing models, Support Vector Regression (SVR), Principal Component Regression (PCR), and eXtreme Gradient Boosting (XGBoost), is explored between 80%/20% and 95%/5% training-testing splits. Forecasting accuracy is evaluated based on evaluation errors, i.e., Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The Diebold–Mariano test is employed to check for statistical significance. Empirical results show that the linear SVR model outperforms PCR across all markets, while XGBoost achieves competitive predictive accuracy on average; the trade-offs between SVR and XGBoost are often very small. The data indicate that linear kernel methods provide a robust prediction pipeline, especially when macroeconomic factors (gold, oil, platinum prices, and the USD/ZAR exchange rate) and calendar-based factors are taken into account, and offer a strong framework for predicting daily exchange rate fluctuations. The results of this research provide practitioners (traders, risk managers, and policymakers) with insights into the relative efficiency of the kernel vs. ensemble learning approaches for forecasting the value of emerging-market currencies in the presence of structural volatility. Full article

Task scheduling in cloud computing environments is a complex NP-hard problem that requires maximizing resource utilization while satisfying quality-of-service (QoS) constraints. Traditional meta-heuristic algorithms often become stuck in local optima, while single deep reinforcement learning (DRL) models exhibit instability when exploring large-scale solution spaces. To address this, this paper proposes a hybrid scheduling algorithm based on multi-objective sand cat colony optimization (MoSCO). This algorithm utilizes a D3QN network to extract task features and guide population initialization, followed by a multi-objective Sand Cat Swarm Optimization (SCSO) algorithm for refined local search. Results from 50 independent replicate experiments conducted in a simulated cloud environment, coupled with an analysis of the dynamic convergence process, demonstrate that MoSCO exhibits significant superiority and robustness. Scatter plot convergence analysis further confirms that MoSCO’s knowledge injection mechanism effectively overcomes the blind exploration phase of traditional algorithms and successfully breaks through the local optimum bottleneck in the late iteration stages of single reinforcement learning, achieving higher-quality, denser, and more stable convergence. Furthermore, 3D and 2D Pareto front analyses show that MoSCO generates highly competitive, well-distributed non-dominated solutions, offering flexible trade-off options for conflicting objectives. Compared to PureD3QN, H-SCSO, and NSGA-II, MoSCO exhibits the smallest performance fluctuations in box plots. Specifically, MoSCO elevates the average resource utilization of clusters to 92.20%, while reducing the average maximum Makespan and Tardiness to 528 and 4187, respectively. Experimental data confirm that MoSCO effectively balances global exploration with local exploitation, delivering stable, high-quality solutions for dynamic cloud task scheduling. Full article

Hybrid renewable energy systems, which combine photovoltaic panels, wind turbines, batteries, generators, and grid connections, require careful sizing to balance economic performance, renewable integration, and supply reliability. In this context, this study proposes a deep reinforcement learning (DRL)-based sensitivity analysis framework in which the admissible energy contributions from the diesel generator and the grid are treated as explicit design-control parameters. The objective is to simultaneously minimize the levelized cost of energy, minimize the loss of power supply probability, and maximize the renewable energy fraction. A sensitivity analysis was conducted across different HRES configurations, load profiles, and tau/gamma values. The performance of the DRL approach was compared with that of multi-objective particle swarm optimization and the non-dominated sorting genetic algorithm II under the same study setting. The results indicate that DRL can identify competitive trade-offs, especially under standard load conditions, while also providing insight into how admissible backup-energy constraints reshape techno-economic and reliability compromises. The best trade-offs were observed around intermediate tau and gamma values, suggesting that moderate backup-energy margins are more favorable than extreme values. These findings should be interpreted within the scope of a simulation-based study and provide comparative design-oriented evidence rather than universally transferable design rules. Full article

Ports play a pivotal role in global trade but are also associated with significant environmental and social challenges. Despite growing research on green ports, existing studies remain fragmented, with limited integration between technological, environmental, and governance perspectives within the blue economy framework. This review examines the transition from green port initiatives toward integrated blue-economy-oriented port systems by synthesizing recent advances in sustainable maritime infrastructure, smart port technologies, renewable energy integration, and policy frameworks. The analysis reveals three major findings. First, ports are increasingly evolving into energy-integrated hubs, with leading examples adopting shore power systems, renewable energy microgrids, and hydrogen-based infrastructure, thereby contributing to emissions reductions. Second, digitalization through artificial intelligence, IoT, and data-driven logistics significantly enhances operational efficiency, reduces energy consumption, and improves real-time decision-making. Third, effective governance frameworks that combine regulatory measures and incentive-based instruments are critical to accelerating sustainability transitions while ensuring economic competitiveness. In addition, the review highlights the growing integration of biodiversity conservation, marine pollution mitigation, and community engagement into port management strategies, reflecting a shift toward ecosystem-based approaches. Overall, the findings demonstrate that ports are transitioning from conventional logistics hubs into integrated socio-technical systems that enable low-carbon maritime transport while supporting inclusive and resilient coastal development. Full article

Background/Objectives: Steady-State Visual Evoked Potential-based Brain–Computer Interfaces face a critical trade-off between system accuracy and user visual fatigue. To address this challenge, the objective of this study was to determine how the spatial manipulation of stimulus size modulates the full spectral dynamics of the Electroencephalogram, encompassing both the periodic oscillatory response and the aperiodic (1/f) background noise. Methods: Twenty-two healthy subjects completed a sustained visual attention task using a competitive stimulus paradigm (20 Hz and 30 Hz) presented in three spatial dimensions (Small, Medium, and Big). Parieto-occipital brain signals were decomposed using the spectral parameterization algorithm (SpecParam) to extract frequency-specific visually evoked response power and the aperiodic slope, while visual fixation was continuously monitored via eyetracking. Results: Increasing stimulus size induced a statistically significant gain in the power of the attended signal (Target) without increasing the response of the peripheral distractor. Simultaneously, larger stimuli produced a significant increase in the aperiodic slope during 20 Hz attention and visual rest, suggesting increased cortical inhibition and a reduction in broadband neural activity. This aperiodic modulation was not observed at 30 Hz. Conclusions: The improvement in Signal-to-Noise Ratio with increasing stimulus size arises from a dual neurophysiological mechanism: enhancement of the periodic evoked response together with a reduction in background neural noise. Full article

In insurance portfolios, classifying customers without a prior history at a given company is particularly challenging due to the absence of historical behavior, extreme class imbalance, heavy-tailed loss distributions, and strict operational constraints. Traditional machine learning approaches, including the baseline methodology proposed in previous studies, typically optimize global predictive accuracy and therefore fail to capture business-critical outcomes, especially the identification of high-risk clients. This study extends the existing approach by evaluating two complementary business-aware classification strategies: (i) a balanced bagging ensemble specifically designed to handle class imbalance and maximize expected profit under explicit customer-omission constraints, and (ii) a lightweight Transformer-based architecture capable of learning richer feature representations. Both approaches incorporate the asymmetric financial cost structure of insurance and operate under operational selection limits. The empirical analysis is conducted on a proprietary large-scale auto insurance dataset comprising 51,618 customers and is complemented by validation on nine synthetic datasets to assess robustness. Model performance is evaluated using statistical tests (ANOVA, Friedman, and pair-wise comparisons) together with business-oriented metrics. The results show that both proposed approaches consistently outperform the baseline methodology (p < 0.001) in terms of profit, with the ensemble offering a better balance of performance and efficiency, while the Transformer shows stronger robustness and generalization under data perturbations. The balanced ensemble provides the most favourable trade-off between predictive performance, robustness, interpretability, and computational efficiency, making it suitable for deployment in regulated insurance environments, while the Transformer achieves competitive results and exhibits stronger generalization under data perturbations. The proposed approach aligns machine learning with actuarial portfolio optimization by explicitly integrating profit-driven objectives and operational constraints, offering two practical and scalable solutions for risk-based decision-making in real-world insurance settings. Full article

The Brazilian craft beer market has experienced continuous growth, increasing operational challenges for small- and medium-sized breweries that frequently rely on empirical and spreadsheet-based production routines. These practices often lead to inefficient resource allocation, production instability, and sustainability concerns. This study proposes an integrated analytical framework combining Machine Learning (ML) and Operations Research (OR) to improve demand forecasting and production planning. The methodology is based on a synthetic dataset calibrated to the operational conditions of a Brasília-based craft brewery, incorporating realistic demand patterns such as seasonality, trend, and intermittency across multiple SKUs over an 18-month horizon. Forecasting models—including Moving Average, Single Exponential Smoothing, and a global ML-based proxy—were evaluated using rolling-origin validation. The resulting probabilistic forecasts were integrated into a capacity-constrained optimization model based on linear programming, extended with risk-aware decision-making using Conditional Value-at-Risk (CVaR). The results indicate that the ML-based approach achieved competitive forecasting performance (sMAPE = 5.83% and MAE = 11.76) while enabling the generation of capacity-feasible and risk-aware production plans aligned with service-level targets. The integration of probabilistic forecasts into the optimization model allowed explicit trade-offs between cost, service level, and resource utilization. The main contribution of this study lies in demonstrating how the integration of predictive and prescriptive analytics can support more sustainable production planning in resource-constrained manufacturing environments. By replacing ad hoc spreadsheet routines with a closed-loop decision-support system, the proposed framework advances the literature on data-driven PPC and provides practical guidance for SMEs operating under uncertainty. Full article

The electric vehicle (EV) battery industry has become a strategic pillar of the low-carbon transition, with far-reaching implications for industrial competitiveness and sustainability. This paper compares the policy mixes governing EV batteries in the EU and China and examines how different approaches shape technological innovation, industrial development, and export performance. A qualitative comparative case study is conducted, combining content analysis of core policy and regulatory documents with descriptive indicators on EV deployment, patenting activity, manufacturing capacity, and international trade. The analysis identifies two distinct but partly complementary policy models. The EU relies on innovation-driven and regulation-based instruments, coupling large research and development programs with stringent sustainability and circular-economy requirements; this model is associated with stronger performance in regulatory upgrading, collaborative innovation, and sustainability-oriented governance. China emphasizes demand expansion, large-scale fiscal support, and long-term industrial planning, which has accelerated capacity build-up, cost reductions, supply-chain integration, and manufacturing-based export competitiveness. The findings show that these contrasting policy mixes generate different technological trajectories and value-chain configurations, while both contribute to strengthening strategic competitiveness in the EV battery sector. More broadly, the study demonstrates that policy effectiveness depends less on any single instrument than on the coherence of the overall policy mix. It concludes that effective EV battery strategies should combine strong innovation incentives with mechanisms that support industrial scaling, supply-chain resilience, and high environmental standards. Full article