Search Results (14,501)

Rotated object detection is widely adopted in remote sensing to handle arbitrary object orientations and improve localization accuracy. However, existing methods still suffer from limited global context modeling, degraded feature representation under complex backgrounds, and suboptimal optimization caused by task coupling, which jointly restrict detection performance in challenging scenarios. To address these issues, this paper proposes a novel rotated object detection framework, termed LDA-YOLO, which systematically enhances feature modeling and prediction quality. Specifically, a Large Separable Kernel Attention (LSKA) module is introduced to approximate global spatial interactions through a low-rank separable formulation, enabling effective long-range dependency modeling with linear computational complexity. A Dual-Path Feature Refinement (DPFR) module is designed to improve feature representation by decomposing features into complementary subspaces and performing adaptive fusion to suppress redundancy and noise. In addition, an Angle-Aware Decoupled Head (AADH) is developed to explicitly separate classification, localization, and orientation estimation, thereby reducing inter-task interference and improving optimization stability. The proposed method achieves superior performance compared to existing approaches. Specifically, it improves mAP50 by 1.6% over the baseline YOLOv8n-OBB, while maintaining a lightweight design with significantly reduced computational cost. These results indicate that the proposed framework provides an effective solution for rotated object detection in complex remote sensing scenarios. Full article

Most existing DNN-based image watermarking methods adopt an “encoder–noise–decoder” paradigm, where the watermark is typically replicated and expanded in a straightforward manner and then directly fused with image features, which limits robustness under complex distortions. Although Transformers improve fusion via attention mechanisms, their quadratic computational complexity makes high-resolution processing prohibitively expensive. To address these issues, we propose CCViM, a robust watermarking framework built on Vision Mamba, which leverages the linear-complexity property of state-space models (SSMs) to enable efficient global interactions. We design a Watermark Representation Learning Module (WRLM) that performs hierarchical feature extraction and structured expansion of the watermark through cascaded VSS blocks, yielding semantically rich and perturbation-resistant watermark representations. In addition, we introduce an Interwoven Fusion Enhancement Module (IFEM), which employs a CCS6 structure to treat the watermark as a dynamic guidance signal. By combining contextual clustering with the Mamba mechanism, IFEM deeply interweaves the watermark into host features at both local and global levels. Experiments on COCO, DIV2K, and ImageNet demonstrate that CCViM consistently improves imperceptibility, robustness, and efficiency to varying degrees, and remains stable and high quality under attacks such as JPEG compression, cropping, and Gaussian blur. Full article

Bird strike events on rotating jet engine fan blades pose significant risks to aviation safety, yet high-fidelity numerical simulations remain computationally expensive, limiting their use in parametric design studies. This study develops a physics-guided machine learning surrogate framework for predicting bird strike response on rotating Ti-6Al-4V fan blades, systematically comparing Lagrangian (gelatin-based, Mooney–Rivlin) and Smoothed Particle Hydrodynamics (SPH, water-like) formulations. A total of 100 explicit dynamic simulations were conducted in ANSYS LS-DYNA (R2) (50 per formulation), varying bird impact velocity and blade angular speed. Random Forest, Support Vector Regression, Polynomial Regression, and XGBoost regression models were trained and evaluated using five-fold cross-validation. Results demonstrate that SPH-based surrogates achieve superior predictive accuracy, with Random Forest yielding R² = 0.9938 for maximum deformation and R² = 0.9962 for total energy dissipation. In contrast, Lagrangian-based stress surrogates exhibited severe performance degradation (R² = 0.24) due to mesh-dependent numerical noise. The trained surrogates achieved computational speed-up factors of 10⁴–10⁵ relative to direct simulation. These findings establish that surrogate model reliability is fundamentally governed by the numerical quality of the training data, providing guidance for integrating machine learning with impact simulation workflows in aero-engine blade design. Full article

Environmental chemicals are rarely considered stressors in the way that psychological or physical stressors are. Yet many endocrine-disrupting chemicals (EDCs) interact with the body’s core stress response system. This review examines how EDCs alter hypothalamic–pituitary–adrenal (HPA) regulation and how biological sex influences those responses. Drawing on human epidemiological data and experimental models, we describe how EDC exposure affects cortisol dynamics, feedback sensitivity, and adrenal signaling, with a particular focus on sex-dependent outcomes. We propose the concept of endocrine noise to describe how low-dose, often mixed EDC exposures introduce persistent interference into hormone signaling without necessarily causing overt endocrine deficiency or excess. In this framework, EDCs act as chronic, low-grade stressors that reset the timing, feedback precision, and rhythmic organization of the HPA axis rather than as isolated reproductive toxicants. We argue that EDCs should be understood as chronic, context-dependent stress modifiers that reshape sex-specific “risk architectures” for affective, metabolic, and immune disorders. Recognizing sex-specific HPA architecture and endocrine noise has immediate implications for study design and regulation, including the need for sex-stratified analyses, circadian-sensitive sampling of cortisol, and risk assessments that consider how the same exposure can push female and male stress systems in divergent directions. Full article

Impulsive alpha (α)-stable noise, characterized by heavy tails and intense outliers, is a key ingredient in simulating financial, medical, seismic, and digital communication technologies. It poses versatile challenges to conventional machine learning (ML) algorithms in predicting noise parameters for multidisciplinary artificial intelligence (AI)-embedded devices. In this study, we adopted a two-phase methodology to investigate the complexity and performance of supervised ML algorithms while classifying impulsive noise parameters. We generated synthetic datasets of α-stable noise distributions for experimentation in a controlled environment. It was followed by experimental evaluation to derive the complexity and performance of ML classifiers—k-nearest neighbors (KNN), Support Vector Machine (SVM), Naïve Bayes (NB), Decision Tree (DT), and Random Forest (RF). Moreover, we employed a very high channel noise level of −15 dB in the test datasets to ensure that the derived analysis applies to real-world devices. The results demonstrate the high performance of DT and RF in structured binary classification of the α regime and the sign of skewness, while incurring satisfactory computational costs. However, SVM and kNN are comparatively more robust for multi-class classification, albeit with higher memory and training costs. On the contrary, NB fails to address the skewed and impulsive behavior of α-stable noise. We observed that even the most effective classifiers struggle to achieve perfect accuracy in multi-class classification. Overall, the experimental results reveal significant trade-off relationships between the complexity and performance of ML classifiers. Conclusively, simple models are well-suited for coarse-grained tasks, such as α-approximation and sign-of-skewness classification. In contrast, sophisticated models can be deployed to predict noise parameters to some extent. Our study provides a clear set of trade-offs for future applied AI devices that address adversarial and impulsive noise. Full article

Frequency diverse array multiple-input multiple-output (FDA-MIMO) radar offers significant advantages in mainlobe deceptive interference suppression, as its transmit steering vector contains both angle and range information, providing additional degrees of freedom beyond the angular dimension. However, conventional FDA-MIMO radar suffers from insufficient angle-range resolution, which limits its ability to suppress interferences located close to the target. Moreover, it lacks robustness under limited snapshots and parameter mismatch conditions. To address these issues, this paper proposes a robust beamforming method based on the FDA-MIMO radar model. A collocated sparse array with a sinusoidal element spacing offset and a logarithmic frequency offset is adopted to enhance beam resolution and resolve the periodic angle-range ambiguity problem. Based on this model, the interference-plus-noise covariance matrix is reconstructed using two-dimensional Capon spatial spectrum, and the steering vector is corrected via a joint objective function that combines MUSIC orthogonality and the flatness of the covariance residual spectrum. Simulation results demonstrate that, under conditions of near-target interferences, random range-angle errors, and frequency offset errors, the proposed method achieves a signal-to-interference-plus-noise ratio (SINR) close to the ideal value, exhibiting excellent mainlobe interference suppression performance and robustness. Full article

Multivariate time series forecasting presents a challenging problem in stochastic modeling, particularly under non-stationary conditions with low signal-to-noise ratios. While recent inverted architectures enhance cross-variable dependency modeling, the conventional point-wise inversion strategy often compromises local temporal patterns. To address this limitation, we propose PiTransformer, a gated patch-wise inverted framework for multivariate time series modeling. Specifically, a Patch-wise Inverted Embedding (PIE) mechanism is introduced to segment temporal sequences into regional patches prior to inversion, enabling the preservation of localized temporal structures. In addition, a Variable–Temporal Gating (VTG) module is incorporated to regulate feature interactions based on the information bottleneck principle, thereby suppressing spurious correlations in noisy environments. Empirical evaluations on diverse benchmarks—including financial and energy datasets—demonstrate that PiTransformer achieves consistent improvements in predictive accuracy and stability over competitive baselines. These results suggest that the proposed framework provides a robust and interpretable approach for modeling high-dimensional stochastic time series under non-stationary conditions. Full article

Accurately and promptly acquiring the load history characteristics of impact events on composite aircraft structures is crucial for identifying impact-induced damage and developing high-fidelity digital twin models. To address this need, we propose a method for reconstructing the impact load history on composite structures, leveraging Generalized Cross-Validation (GCV) and a Fiber Bragg Grating (FBG) pattern. An equivalent expansion technique based on discretized time-domain sparse strain sampling is developed to mitigate the local distortion of impact response signals, a common issue arising from the low sampling rates of quasi-distributed FBG. By incorporating Tikhonov regularization, the ill-posed nature of the impact frequency response matrix is effectively managed. Furthermore, an adaptive optimization method based on the GCV criterion is introduced to overcome the limitations of manually selecting regularization parameters and the associated constraints on noise suppression. The results show that the proposed GCV-based reconstruction method achieves an average peak relative error of 11.4% and an average root mean square error of 0.36 N for the reconstructed impact load, demonstrating that the proposed method synergistically enhances both the reconstruction of the overall impact load waveform profile and the precise characterization of transient details, even with low-rate sampling. This provides robust technical support for health monitoring and condition-based maintenance of composite structures. Full article

The output power of photovoltaic (PV) systems is influenced by various environmental factors, exhibiting strong nonlinearity and non-stationarity, which poses significant challenges for accurate forecasting. To address these issues, this paper proposes a short-term PV power forecasting method based on wavelet convolutional neural networks and an improved Transformer. First, the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is employed to decompose the original PV power sequence into several intrinsic mode functions (IMFs). Fuzzy entropy is then utilized to evaluate the complexity of each component, and subsequences with similar entropy values are reconstructed to reduce the non-stationarity of the original series. Subsequently, Pearson correlation coefficients and the maximal information coefficient (MIC) are applied to capture both linear and nonlinear relationships between each reconstructed component and meteorological features, enabling the selection of strongly correlated variables. On this basis, a wavelet convolutional network (WTConv) is introduced to perform multi-scale decomposition and frequency-band feature extraction on the reconstructed components by integrating wavelet transform with convolution operations, effectively expanding the receptive field and extracting deep-seated features of the sequences. Finally, an improved iTransformer model is adopted for time-series modeling, leveraging its inverted encoding structure and self-attention mechanism to fully capture long-term dependencies among multivariate variables. The proposed model is validated using actual power data from a PV plant in Ningxia, China, across four seasons. Comprehensive experiments, including ablation studies, comparative analyses, loss function convergence evaluation, and Diebold–Mariano significance tests, are conducted to thoroughly assess the model’s effectiveness and superiority. Experimental results demonstrate that the proposed model achieves excellent prediction accuracy and stability in spring, summer, autumn, and winter, showing strong potential for engineering applications. Full article

Graphene possesses exceptional mechanical strength, high electrical conductivity, and a stable lattice structure, making it an ideal material for sensors in advanced manufacturing. However, these sensors face stability challenges due to complex electromagnetic interference (EMI) environments generated by electrical equipment. Therefore, investigating the influence of EMI on sensor performance is of significant importance. In this study, simulations were performed to analyze electrical parameter perturbations of intrinsic graphene films under EMI conditions. The Magnetic Fields, Solid Mechanics, and Electrostatics modules in COMSOL Multiphysics were employed to construct a coupled model of a three-phase power transformer and a graphene-based pressure sensor. The results indicate that EMI can induce baseline drift on the order of ~5% full scale (FS) in the graphene current density, accompanied by degradation in signal-to-noise ratio (SNR) exceeding ~15 dB under typical simulation conditions. Graphene in direct contact with metal electrodes shows enhanced sensitivity to EMI, with more pronounced noise amplification due to interfacial coupling effects. In contrast, cavity-suspended graphene configurations exhibit relatively improved robustness, suggesting that suspended membrane architectures can mitigate EMI by reducing parasitic coupling and enhancing mechanical isolation. Compared with previous studies, this work highlights the role of multiphysics coupling and membrane suspension in influencing EMI-induced perturbations, providing theoretical guidance for the design of graphene-based sensors in power system and industrial Internet of Things (IoT) applications. Full article

Physics-guided computational imaging typically aggregates data fidelity, geometric reconstruction, and sensor consistency into a single scalar loss. In low signal-to-noise ratio (low-SNR) non-line-of-sight imaging, this centralized approach creates asymmetric gradient conflicts where the dominant constraints suppress physically meaningful updates. We propose treating multi-constraint training as a gradient coordination problem rather than scalar balancing. Our framework coordinates heterogeneous objectives through branch-wise gradient routing: soft conflict projection (PCGrad), hard physical constraint enforcement (PhysGuard), learnable sensor calibration, and a staged training protocol that decouples representation learning from nuisance parameter estimation. On held-out test scenes, the fully staged model improved the peak signal-to-noise ratio (PSNR) from 19.09 dB to 20.49 dB and the structural similarity index (SSIM) from 0.67 to 0.71 over the baseline, with consistent gains across the 48, 28, and 25 dB SNR levels. Qualitative evaluation on seven real-world scenes indicates sharper structure recovery and fewer artifacts. In this NLOS setting, gradient-level coordination is more reliable than scalar aggregation under heterogeneous constraints. Full article

As food security gains increasing attention, automated pest monitoring is crucial for agricultural early warning systems. However, in practical light-trap capturing sensors, the extremely small scale of pests and complex background interference, such as unexpected reflection and occlusions, severely undermine the performance of existing models, resulting in frequent missed and false detections. To deal with these challenges, this study proposes EP-YOLO, an enhanced lightweight detection architecture based on YOLOv8n. Specifically, to retain the spatial pixels of micro-targets during downsampling and isolate pest features while eliminating background noise without compromising channel information, the Spatial-to-Depth Convolution (SPD) module and the Efficient Multi-Scale Attention (EMA) module are introduced. We evaluate our model through experiments on Pest24, a dataset consisting of 24 tiny pest categories. The results demonstrate that EP-YOLO achieves a mAP@50 and mAP@50:95 of 70.5% and 47.3%, respectively, improving upon the baseline by 1.1% and 1.9%. Furthermore, EP-YOLO achieves a significant improvement in detecting certain extremely small pests. For example, Rice planthopper and Plutella xylostella show improvements of 8.4% and 3.1%, respectively, compared to the baseline. In conclusion, the physical limitations of detecting tiny pests are successfully overcome by EP-YOLO, providing a robust and deployable design for real-time agricultural monitoring systems. Full article

Leaks in pipe systems result in significant economic losses, environmental hazards, and public health risks. Transient-based leak detection methods, which exploit the dynamics of pressure waves in response to system anomalies, have emerged as efficient techniques for identifying and characterizing leaks in pressurized pipelines. These methods offer distinct advantages, including minimal data requirements, high sensitivity to low-pressure anomalies, and resilience to the ill-posed conditions often affecting steady-state models. This paper reviews transient-based leak detection, synthesizing findings from over 139 peer-reviewed publications spanning the past three decades. The review categorizes transient-based methods into transient damping, transient reflection, system response, and inverse transient methods, analyzing the prevalence, evolution, and research rate of each category over time. By structuring the review around key aspects such as simulation domain type, analysis approach, system response, solver strategies, adaptability to noise, viscoelasticity, and network complexity, this paper identifies significant trends and shifts in research focus. A comprehensive tabular dataset of 139 studies captures how research activity in various areas has accelerated, slowed, or reached stability, offering insights into the evolving priorities within the field. This review highlights areas for further development, particularly in addressing AI-enhanced applications, transient excitation and measurement sites design, noise resilience, comprehensive leak characterization, validation approaches, and scalability for complex network applications, providing a resource to guide future research in transient-based leak detection. Full article

This study examines the relationship between major government support programs and farm-level technical efficiency in Thailand’s sticky rice sector. While existing studies have extensively analyzed rice efficiency, limited attention has been given to distinguishing the efficiency implications of different policy instruments or to modeling dependence between stochastic shocks and inefficiency. Methodologically, we employ a copula-based stochastic frontier efficiency effects model that jointly estimates production and inefficiency determinants while allowing for flexible dependence between noise and inefficiency components. Empirically, we use primary survey data from 429 farmers in Northern Thailand. The results indicate that participation in the debt moratorium program is positively associated with technical efficiency, whereas the widely implemented 1000-baht-per-rai subsidy is negatively associated with efficiency. The cost-reduction program exhibits no statistically significant association. The mean technical efficiency is 0.458, with a distribution concentrated at both low and high efficiency levels, indicating substantial heterogeneity across farmers. Full article

Satellite clock bias (SCB) is a critical error source affecting the positioning and timing accuracy of Global Navigation Satellite Systems (GNSSs). The conventional back propagation neural network (BP) model, when applied to SCB prediction, is prone to local optima and exhibits rapid error divergence. To address these limitations, this study proposes and investigates two enhanced BP models: one optimized by the genetic algorithm (GA) and another by the mind evolutionary algorithm (MEA). A comprehensive comparative analysis is conducted against the standard BP model. Experiments utilize precise clock products from the International GNSS Service (IGS), with data from six representative satellites featuring different atomic clock types (IIR, IIR-M, IIF rubidium, and cesium clocks). The models are trained on 24 h of historical data and evaluated by forecasting clock biases for 2, 6, 12, and 24 h ahead. Prediction accuracy is assessed using root mean square error (RMS), range, and mean error. The results demonstrate that optimization algorithms significantly improve the BP neural network’s performance. The genetic algorithm optimized back propagation neural network (GABP) model demonstrates comprehensive superiority, achieving the highest accuracy across all forecast horizons and satellite types. For instance, in 24 h predictions, the average RMS error of the GABP model (6.516 ns) is merely 10.9% of the standard BP model’s error. Notably, for the cesium clock on satellite G24, the GABP model’s 24 h RMS (1.600 ns) is approximately 23 times lower than that of the mind evolutionary algorithm optimized back propagation neural network (MEABP) model. The GABP model also shows strong adaptability, maintaining high precision for both rubidium and cesium clocks and exhibiting gradual error growth with extended forecast duration, indicating excellent generalization and resistance to overfitting. To further evaluate generalization across different seasons and time periods, additional experiments were conducted using data from February–March, June, and October 2021 on six different satellites. The results consistently show that GABP outperforms MEABP and BP across all tested conditions. While the MEABP model outperforms the standard BP, it shows limitations in long-term forecasts, particularly for cesium clocks, due to tendencies for premature convergence and sensitivity to data noise. In conclusion, the GABP model, leveraging the robust global optimization capability of the genetic algorithm is validated as a highly effective and reliable solution for high-accuracy short- and long-term satellite clock bias prediction. Full article