Search Results (35,255)

The leaf area index (LAI) is a key parameter reflecting vegetation canopy structure and growth status. This study systematically compares the performance of spectral and texture features derived from Sentinel-2A imagery for LAI retrieval in winter wheat and maize. Multiple vegetation indices and gray-level co-occurrence matrix (GLCM) texture features were extracted, and three types of texture indices—Normalized Difference Texture Index (NDTI), Ratio Texture Index (RTI), and Difference Texture Index (DTI)—were constructed. Modeling was performed using Partial Least Squares Regression (PLSR) and Gaussian Process Regression (GPR). Results show that red-edge vegetation indices and mean texture features (e.g., NDVI_M) are robust predictors for both crops, with correlation coefficients reaching 0.87 for winter wheat and 0.83 for maize. Texture indices further enhance the representation of canopy structural information; the optimal NDTI achieved |R| > 0.88 for both crops, though the specific feature pairs were crop-specific. Using the proposed two-stage feature optimization strategy combined with GPR, the LAI estimation accuracy for winter wheat reached R² = 0.87 with RMSE = 0.41 on an independent test set, while for maize the accuracy was R² = 0.75 with RMSE = 0.38. The strategy significantly improved accuracy for winter wheat (uniform canopy) but yielded limited gains for maize (heterogeneous canopy), largely due to differences in canopy architecture. This study demonstrates that integrating multi-dimensional features with nonlinear modeling enhances LAI estimation accuracy. By providing a side-by-side comparative evaluation across two contrasting crop canopies, this study underscores the necessity of crop-adaptive feature selection and modeling strategies. The findings offer practical guidance rather than a universal model for large-scale crop monitoring in agricultural remote sensing. Full article

This paper proposes an adaptive residual extended Kalman filter method optimized by a multi-strategy improved parrot optimization algorithm (MIPO-ARKEKF) to improve the kinematic parameter calibration accuracy and efficiency of robotic polishing systems. To address the limitations of the standard extended Kalman filter (EKF), such as truncation-error accumulation during repeated linearization and sensitivity to manually selected noise parameters, an integrated improvement framework is developed. Specifically, a gradient stabilizer based on state-estimation increments is introduced to alleviate estimation degradation caused by accumulated truncation errors, while the proposed MIPO algorithm is employed to adaptively optimize the process and measurement noise covariance matrices, thereby improving the robustness of parameter identification under practical measurement uncertainty. The calibration process is established on the basis of high-precision external measurement data obtained from the robotic polishing system. In benchmark-function tests, MIPO demonstrates superior convergence performance. In physical experiments based on a KUKA KR210 R2700 robot, the proposed MIPO-ARKEKF method reduces the root mean square positioning error from 0.8927 mm to 0.4858 mm, corresponding to a 45.58% improvement in accuracy. Compared with representative hybrid calibration methods, the proposed method achieves comparable compensation accuracy while reducing computation time by 34.88% to 65.08%. Practical polishing experiments on ultra-low-expansion glass lenses further verify that the proposed method effectively improves end-effector trajectory tracking accuracy and polishing quality, providing an efficient solution for high-precision robotic polishing. Full article

Wheeled inverted-pendulum robots with movable upper structures and variable payloads exhibit configuration-dependent equilibrium drift and payload-dependent dynamic variation, which complicate balancing control. This paper proposes a gain-scheduled controller–observer framework for payload-adaptive balancing of such a robot. First, the multi-body system is reduced to a control-oriented equivalent inverted-pendulum model through center-of-mass lumping, from which a parameter-varying linearized model is established. On this basis, an H∞ state-feedback controller with input constraints is synthesized in a linear matrix inequality (LMI) framework, and an augmented-state observer is designed to estimate the residual equilibrium offset induced by payload variation. To improve robustness over the operating range, the frozen-point design is extended to a sampled-model multi-model synthesis framework, and gain scheduling is implemented with respect to the measurable arm angle. Nonlinear Simscape simulations show that the proposed method can recover balance at representative fixed operating points, compensate effectively for load-induced equilibrium drifts, and preserve stable balancing performance under slow arm-angle variation. Quantitative comparisons with an LQR baseline further support the effectiveness of the proposed framework for payload-adaptive balancing control. Full article

In this paper we investigate the potential of Magnifying Networks, an architecture recently proposed in the domain of digital pathology, in the realm of satellite imagery analysis, an increasingly important remote sensing modality of practical significance in a wide range of domains. In particular, we address the challenges posed by the extreme size of satellite images and the inadequacy of the current state of the art in capturing salient information across scales while remaining computationally feasible. Specifically, we adapt the MagNet architecture by adjusting the number of magnifying layers and by employing the softmax function as a specific mechanistic means in the exploratory search within each magnifying layer. In addition, we conduct a series of comparative experiments to identify effective design choices and their effect on performance in the specific context of satellite remote sensing. Focusing on the most challenging classes in the Functional Map of the World with small object-to-image ratios, the adapted MagNet surpasses an Inception-v3 baseline (AUROC $0.89$ vs. $0.85$, Accuracy $0.83$ vs. $0.71$, F1-score $0.84$ vs. $0.76$), supporting adaptive magnification as an effective modelling approach to gigapixel satellite imagery. Full article

Against the backdrop of the digital economy, digital transformation has increasingly evolved from a firm-level upgrading process into a collaborative decision-making issue among supply chain members. From the perspective of intelligent supply chain management, this study develops a two-echelon game model of a vertical manufacturer–retailer supply chain to examine digital collaborative decision-making under heterogeneous power structures. By comparing a centralized cooperative benchmark with decentralized non-cooperative scenarios, the study investigates how power structures affect firms’ digital transformation efforts, pricing decisions, and system-level outcomes, while also considering the role of knowledge spillovers. The results show that, under the same power structure, cooperation leads to higher digital transformation effort levels and greater total supply chain profit than non-cooperation. Knowledge spillovers further strengthen firms’ incentives to invest in digital transformation and improve market demand, consumer surplus, and social welfare. Compared with asymmetric power structures, a balanced power structure generates lower retail prices, higher market demand, and better overall supply chain performance. Numerical simulations further show that higher digital transformation costs weaken collaborative gains, whereas greater market sensitivity to digitalization strengthens them. Overall, this study suggests that digital collaboration contributes to supply chain sustainability by improving coordination efficiency, enhancing adaptive operations, and promoting system-level value realization under heterogeneous governance structures. Full article

To address the difficulty of directly measuring the minimum burden in medium-length hole blasting and the low accuracy of single-algorithm extraction methods, this study proposes an automatic extraction method for the minimum burden based on combined region growing and DBSCAN. Using UAV-acquired three-dimensional point cloud data from open-pit mines, the elbow method is first applied to determine the clustering number of point cloud zenith distances, enabling initial extraction of the slope surface under roughness constraints. Subsequently, DBSCAN parameters are adaptively determined using the K-nearest neighbor average distance method, and density optimization is performed on the region-growing results to remove noise points such as rock protrusions and blasting residues, thereby refining the reconstruction of the free surface. Based on the reconstructed surface, the minimum burden is calculated using three-dimensional borehole modeling combined with the shortest Euclidean distance algorithm. Field experiments were conducted at the 5015 platform of the Huatailong open-pit mine in Tibet, with additional validation at the Qianshan limestone mine in Liaoyang and the Qidashan iron mine in Anshan. Results show that the proposed method effectively identifies slope free surfaces and accurately extracts the minimum burden. In the Huatailong case, the average absolute error was 0.077 m and the average relative error was 2.68%. The method provides a reliable basis for blasting fragmentation control and blast-hole pattern design in open-pit mines. Full article

Reliable monocular depth estimation (MDE) is essential for agricultural robots and unmanned platforms, where low-cost visual perception is required for safe navigation and scene understanding in complex field environments. However, general-purpose depth foundation models remain limited by substantial domain gaps in agriculture, while full fine-tuning of large backbones is computationally expensive and less suitable for deployment on resource-constrained platforms. In this paper, an efficient agricultural MDE framework, termed AgriLoRA-DA, is proposed based on Depth-Anything-V2. Specifically, the pretrained DINOv2 encoder is kept frozen and adapted using LoRA in selected attention projections, while the original Dense Prediction Transformer (DPT) decoder is replaced with a lightweight Lite-FPNHead to reduce decoding overhead and improve deployment efficiency. Experiments conducted on the WE3DS dataset indicate that, although Depth-Anything-V3 provides the strongest zero-shot generalization among the evaluated baselines, target-domain adaptation is still necessary for WE3DS agricultural scenes. After adaptation, AgriLoRA-DA achieves the best overall performance with AbsRel = 0.0133, SqRel = 3.518, RMSE = 132.264, log10 = 0.0057, and delta1 = 0.9990, while requiring only 0.19 M (0.87%) trainable parameters. These results suggest that parameter-efficient adaptation and lightweight decoding provide a practical direction for deployable depth estimation in crop-row scenes similar to WE3DS, while broader cross-dataset validation remains an important direction for future work. Full article

Accurate automatic sleep staging remains challenging due to complex temporal dynamics, inter-subject variability, and the difficulty of effectively integrating heterogeneous physiological signals. Electroencephalogram (EEG) and electrooculogram (EOG) recordings provide complementary information for sleep analysis; however, most existing multimodal approaches rely on simple feature concatenation, which limits their ability to capture structured inter-modality relationships. This paper proposes MFSleepNet, a multimodal sleep staging framework that explicitly models interactions between EEG and EOG signals. The proposed system incorporates a multimodal feature fusion module to enable bidirectional information exchange between modality-specific representations, followed by a gated temporal-channel attention mechanism to adaptively emphasize informative temporal segments and signal channels, facilitating joint representation learning while preserving modality-specific characteristics. Experiments on three public datasets (Sleep-EDF, SHHS, and HSP) under an epoch-level cross-validation protocol show that MFSleepNet consistently outperforms representative single-modality and multimodal baseline methods in terms of overall accuracy, Cohen’s κ, and Macro-F1. Ablation studies further demonstrate the contribution of each functional module. Correlation analysis indicates stage-dependent variations in EEG–EOG relationships, while interaction-based experiments show that explicit feature interaction improves both joint and modality-specific representations. Grad-CAM visualizations provide interpretability of model decisions. External validation on unseen subjects reveals a noticeable performance drop, highlighting the challenges of inter-subject variability and the limited baseline generalization capability of the model. To address this, a lightweight subject-specific adaptation strategy is introduced, which improves performance using a small amount of labeled subject-specific data. Overall, the proposed framework provides an effective and interpretable solution for multimodal sleep staging while emphasizing the importance of structured inter-modality interaction and subject-adaptive modeling in practical applications. Full article

Accurate price forecasting and portfolio optimization in emerging financial markets remain challenging due to the non-stationary dynamics, structural breaks, and heterogeneous behavior of traded instruments. This paper proposes the Time-series Adaptive Forecast Ensemble (TAFE), a method that combines single popular forecasting methods, such as ARIMA, by using an algorithm derived from both the simulated annealing (SA) and Threshold Accepting algorithms. The TAFE is applied to twenty-four weekly price series of Mexican exchange-traded funds (ETFs) and Real Estate Investment Trusts (FIBRAs) over the period 2020–2025. A top-K pre-selection strategy is used, mitigating the adverse cross-model interaction effect of some assets over others, in other words, reducing the propagation of errors from poorly performing base learners. In addition, the sample results show that the TAFE achieves the lowest mean SMAPE across the panel, with statistical superiority over the equal-weight benchmark and a Hybrid Model, confirmed by Diebold–Mariano and Harvey–Leybourne–Newbold tests. Out-of-sample evaluation over a 26-week horizon reveals a regime-shift-driven performance reversal consistent with the bias–variance tradeoff in adaptive combination schemes. Portfolio optimization using SA-generated forecasts yields with an expected return of 35.77%; thus, the model presents a slight overestimation of the return, with a variance of 2.4%. However, it has an acceptable level of risk. Full article

X-band marine radar offers unique advantages for monitoring nearshore oil spills. However, oil films and sea clutter exhibit high pixel intensity overlap in radar images. Traditional threshold segmentation and machine learning methods have certain limitations in terms of feature extraction, Region of Interest (ROI) guidance, threshold optimization adaptability, and unsupervised capabilities. To address these issues, a method of oil film detection for ship radar based on multi-dimensional feature-guided extraction and hybrid optimization search is proposed. By combining Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering with multidimensional features, this method automatically extracts ROIs under unlabeled conditions, effectively suppressing sea clutter interference. Subsequently, an improved Beaver Behavior Optimizer (BBO) and simulated annealing (SA) hybrid algorithm (BBO-SA) is introduced within the ROIs, along with a designed adaptive temperature update strategy, to achieve coordinated optimization of global and local searches. The experimental results demonstrate that the method described in this paper performs exceptionally well across all evaluation metrics, confirming its accuracy and robustness in oil film detection. It provides a viable technical approach for emergency monitoring of nearshore oil spills. Full article

Active Distribution Networks (ADNs) rely on the precise coordination of flexible resources to mitigate the stochasticity of high-penetration renewables. However, the hierarchical and partitioned nature of modern ADNs transforms the day-ahead scheduling problem into a high-dimensional many-objective optimization task, typically involving conflicting objectives across multiple regions. Standard evolutionary algorithms often struggle with the “curse of dimensionality” in such scenarios. To address this limitation, this study formulates a hierarchical partition-based scheduling model for many-objective optimization and introduces a novel adaptive MOEA/D algorithm. Specifically, a double-layer weight generation method and an adaptive neighborhood adjustment strategy are introduced to balance global search capability with local convergence speed. The methodology is validated using a practical 47-node ADN case study in Panzhihua, China. Comprehensive analysis of evaluation metrics (e.g., Hypervolume and IGD) indicates that the proposed algorithm achieves enhanced performance at the expense of a marginal increase in cost. Furthermore, it demonstrates strong competitiveness against advanced heuristic algorithms in solving high-dimensional scheduling problems, effectively balancing economic efficiency and voltage stability under renewable uncertainty. Full article

This narrative review summarizes evidence on the bovine β-casein (CSN2) A1/A2 polymorphism as a case study of how intensive dairy selection and global gene flow can reshape allele frequencies in ways that matter for consumers, processing and agroecological resilience. We draw together evidence from (i) population-genetic surveys of CSN2 in contrasting cattle populations, including a descriptive summary of published genotype-frequency studies; (ii) controlled human studies that separate A1-containing from A2-only dairy exposure; and (iii) dairy technology and the authenticity literature relevant to identity-preserved A2 value chains. Across intensively selected Holstein-Friesian populations, A1 was consistently present at substantial frequency (approximately one-third), whereas indigenous, beef and zebu-adjacent populations were typically A2-enriched, highlighting the role of historical breed formation and modern introgression in shaping apparent geographic and climatic patterns. Human intervention studies most consistently support improved short-term gastrointestinal tolerance with A2-only milk in susceptible individuals, while evidence for longer-horizon systemic outcomes remains mixed and insufficient for causal disease claims. Processing and analytical studies suggest that β-casein genotype can modestly affect coagulation and product behavior in a context-dependent manner and that validated proteoform quantification coupled with traceability is essential for credible A2 labeling at scale. We discuss implications for breeding programs, including staged A2 selection that avoids performance trade-offs, and emphasize governance of artificial insemination and supply-chain segregation as levers to limit inadvertent allele diffusion while supporting climate-relevant genetic resources in locally adapted breeds. Collectively, the reviewed evidence suggests that A1/A2 β-casein can be usefully interpreted within a One Health framework spanning animal genetics, dairy systems and human tolerance research. Full article

In this paper, an adaptive output feedback control scheme is proposed for a class of parametric strict feedback systems with asymmetric full-state constraints and unknown output gain. Firstly, an adaptive state observer is constructed to estimate the unmeasured system states. To compensate for the effect of the unknown output gain on the tracking performance, a new error signal incorporating an adaptive compensation coefficient is introduced into the backstepping design. Then, by combining the universal transformed function with a coordinate transformation, all system states are kept within time-varying asymmetric bounds, and the feasibility issues of conventional constrained control methods are avoided. Based on Lyapunov stability analysis, all signals in the closed-loop system are proven to be globally uniformly ultimately bounded. Finally, simulation results based on motor models demonstrate the effectiveness of the proposed scheme. Full article

In the cloud computing environment, various heterogeneous architectures have emerged, and the cloud-edge collaborative task scheduling architecture has come into being under this background. However, the complexity of cloud-edge heterogeneous architecture significantly restricts the improvement of scheduling performance. Therefore, researchers propose solving this problem by leveraging intelligent optimization algorithms. The Artificial Lemming Algorithm has received extensive attention due to its strong robustness. However, when dealing with the problem of cloud-edge collaborative task scheduling, there are still some drawbacks, such as long system response time and unstable scheduling performance. In response to the above problems, this paper proposes a multi-strategy artificial lemming algorithm. Specifically, by coordinating high-order Chebyshev polynomials with chaotic mapping to enhance the richness of the initial population, the scheduling response time is indirectly shortened. Secondly, the Adaptive Spatial Search Mechanism is introduced to make up for the deficiencies in the exploration stage, enhance the algorithm’s exploration ability, and thereby improve the optimization effect of scheduling satisfaction. Furthermore, the Bernstein-Guided Correction Strategy is introduced to enhance the exploitation capability of the algorithm to improve the stability of cloud-edge scheduling. The experimental results demonstrate that compared with the baseline algorithms, the proposed MALA reduces the total scheduling cost by at least 3% across cloud-edge collaborative resource scheduling problems of different scales. Full article

Astronomical positioning of space targets is an important task in space situational awareness. In both ground-based and space-based optical observation scenarios, accurate positioning relies on the reliable matching of numerous stars in observational images. However, dense star scenes increase the ambiguity of local patterns and the computational burden of candidate retrieval. Building on established geometric voting and catalog-indexing strategies, this paper develops a two-stage star map matching method that specifically combines adaptive magnitude stratification with seed-guided residual-star diffusion for large-field dense star scenes. In the first stage, an adaptive magnitude-stratified bright-star subset is selected according to field density, and angular-distance voting is used to obtain reliable seed correspondences. In the second stage, residual-star candidates are retrieved from seed-centered dual-feature sub-libraries indexed by angular distance and magnitude difference, and are then refined through single-seed local diffusion and multi-seed global fusion. Experimental results from both simulated and real observational data demonstrate that the proposed method achieves a high matching success rate with low computational cost and performs effectively in large-field, dense star scenes. The proposed method provides a practical matching solution for astronomical positioning in dense star scenes. Full article