Search Results (4,387)

Earthquake-induced landslide reactivation poses a sustained hazard for years following major seismic events, yet operational prediction remains constrained by heterogeneous multi-modal data, sparse supervision, and the absence of uncertainty-aware frameworks. This paper presents PIMSEL, a physically guided multi-modal semi-supervised framework for post-seismic landslide reactivation risk assessment. PIMSEL integrates satellite-derived morphological features, precipitation time series, and seismic hazard attributes through four components: entropy-regularized optimal transport for cross-modal semantic alignment without paired supervision; causally constrained hierarchical fusion enforcing domain-consistent modal weighting; scenario-based prototype mutation for semi-supervised learning from sparse expert annotations; and prototype-anchored variational graph clustering that simultaneously stratifies landslides into HIGH, MEDIUM, and LOW risk tiers and produces decomposed aleatoric and epistemic uncertainty estimates for operational triage. The HIGH risk tier operationally corresponds to predicted reactivation, validated against 598 documented reactivation events across 7482 co-seismic landslides from three Sichuan Province earthquake sequences: the 2013 Lushan (Mw 7.0), 2017 Jiuzhaigou (Mw 7.0), and 2022 Luding (Mw 6.8) events. PIMSEL achieves 82.5% reactivation recall and 66.4% precision, outperforming twelve baselines across clustering quality, classification, and uncertainty calibration metrics. Ablation studies confirm that optimal transport alignment contributes the largest individual performance gain. Current limitations include quarterly assessment frequency and dependence on optical imagery under cloud cover, which future integration of real-time meteorological triggers and SAR data should address. Full article

Accurate and interpretable assessment of cognitive workload from EEG remains a central challenge in neuroergonomics and real-time human–machine interaction. To address the limitations of existing Empirical Mode Decomposition (EMD) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) approaches, particularly their instability, limited neuroscientific grounding, and sensitivity to amplitude fluctuations, this paper introduces Scale-Stabilized Relative Intrinsic Mode Energy (SS-RIME), a theoretically motivated and physiologically informed feature extraction framework. SS-RIME integrates instantaneous frequency stabilization to enforce a consistent oscillatory hierarchy across subjects, delta (1–4 Hz) and theta (4–7.5 Hz) spectral weighting based on established frontal-midline activity, and cross-IMF energy normalization to reduce amplitude-driven variability. Applied to 64-channel EEG recorded during N-back tasks, the proposed framework achieved high performance, outperforming both classical machine-learning baselines and deep learning models such as EEGNet, DeepConvNet, and ShallowConvNet. SS-RIME yielded accuracies of $99.12\pm 0.41\%$ (0 vs. 2-back), $97.84\pm 0.63\%$ (0 vs. 3-back), and $92.31\pm 1.12\%$ (2 vs. 3-back), demonstrating strong cross-subject generalization. Theta-dominant IMFs over frontal midline regions emerged as the most discriminative components, supporting the neuroscientific validity of the stabilized and spectrally weighted Hilbert–Huang representation. With an inference time below 20 ms per epoch, SS-RIME is computationally efficient and suitable for real-time neuroergonomics applications, providing a robust, explainable, and physiologically grounded solution for EEG-based cognitive workload decoding while addressing key methodological gaps in prior EMD/CEEMDAN and deep learning approaches. Full article

Aero-engine defects often exhibit micro-scale and high-frequency characteristics under complex metallic textures, which makes precise segmentation difficult. Most existing pixel-level methods rely on spatial-domain modeling and lack frequency-domain decoupling. As a result, high-frequency details are easily hidden by low-frequency background information. In addition, repeated downsampling weakens the representation of fine-grained structures, leading to inaccurate boundary localization and limited robustness. To address these issues, a spectrum-driven hierarchical learning network is proposed for aero-engine defect segmentation. First, a dual-band spectral module is constructed using the discrete cosine transform to separate high-frequency and low-frequency components, providing stable and physically meaningful frequency-domain priors for the network. Second, a detail-guided module is designed where high-frequency features adaptively guide skip connections, compensating information loss during encoding and improving boundary recovery. Furthermore, a low-frequency-driven region-aware modeling module is developed. The internal defect regions, boundary areas, and background regions are modeled hierarchically. A dynamic hyper-kernel generation mechanism performs region-sensitive convolutional modeling, improving adaptation to complex structural variations. Extensive experiments on the Turbo19 and NEU-Seg datasets demonstrate that the proposed method produces accurate defect boundaries and achieves mIoU scores of 89.82% and 91.44%, improving over the second-best method by 5.22% and 4.42%, respectively. Full article

The inherent non-uniformity of Infrared Focal Plane Arrays (IRFPA) inevitably results in stripe noise, which severely degrades image quality and hinders downstream applications. Existing deep learning methods often struggle to strike a balance between effective denoising and the preservation of fine thermal textures. To address this issue, we propose a Bottleneck-free Channel Dual-path Aggregation Network (BCDA-Net) based on a “Perception-Reconstruction” design principle. In the perception stage, the network jointly employs the Dual-Path Channel Down-sampling (DCD) module and the Context-Guided Stripe Attention Block (CGSAB). The DCD module utilizes a channel split strategy to simultaneously extract semantic features and preserve high-frequency textures, while the CGSAB performs global context modeling on these features to precisely perceive and locate global stripe noise patterns. In the reconstruction stage, we integrate the Cascaded Dense Feature Aggregation (CDFA) module with a Bottleneck-Free Aggregation Strategy (BFAS). The CDFA utilizes the perceived information to densely aggregate features and progressively reconstruct clean image details, whereas the BFAS structurally blocks the propagation of low-resolution noise during decoding, effectively mitigating aliasing artifacts induced by deep feature upsampling. Together, these components form a complete closed loop from accurate noise perception to high-fidelity reconstruction. Extensive experiments on public and real-world datasets demonstrate that BCDA-Net maximally preserves image details while removing non-uniform stripe noise. Both objective metrics and subjective visual quality outperform existing state-of-the-art methods. Full article

Chronic kidney disease (CKD) is a prevalent condition in cats and recognized as a leading cause of mortality among cats generally, yet it is difficult to detect by cat caregivers, especially in its early stages. This retrospective study aimed to enhance detection of CKD by cat caregivers through a smart litter box monitor technology that tracks feline elimination behaviors. We established cohorts of cats with CKD and cats with no known conditions and analyzed behavioral features captured by the monitor. A mixed-effects model identified significant differences, which were then integrated into a machine learning framework for predictive modeling. The model achieved a weighted F1-score of 92.7% in training using cross-validation and 89.9% in validation, demonstrating high precision for CKD predictions. Key findings included a behavioral profile unique to cats with CKD characterized by increased urination frequency, longer elimination durations, and reduced post-elimination covering behavior. These results suggest that the smart litter box monitor can provide valuable, continuous, and non-invasive data for CKD detection and management. Full article

Improving the prediction accuracy of renewable energy power generation units is an important goal of the “source-storage integration” approach. However, the abundance of anomalous data and indistinct features in renewable energy station data seriously affects the health status prediction of these generator sets. To effectively enhance the performance of renewable energy generation prediction, this paper proposes an efficient data cleaning method for renewable energy stations based on anomaly detection and feature enhancement. First, anomaly detection is achieved by calculating a baseline power curve and partitioning data, utilizing the Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Subsequently, considering that current models often learn low-frequency features while ignoring high-frequency features when processing time-series data, a data feature enhancement method is proposed. The proposed method integrates high-/low-frequency data decomposition, time–frequency domain conversion, and an improved attention mechanism to effectively enhance the high-frequency features of renewable energy station data, and reduces the RMSE of mainstream forecasting models significantly. Finally, using data from a renewable energy station in a region of China, the effectiveness and superiority of the anomaly detection and feature enhancement methods are analyzed. The results show that for renewable energy generation data, the proposed method reduces the RMSE of LSTM and Transformer models by 15.12%, 16.67% and 16.24%, 18.32% respectively, significantly improving prediction accuracy. Full article

Power systems with high renewable penetration impose multi-dimensional demands on energy storage (ES) regulation. Short-duration ES is required for power balance and frequency support, while medium- and long-duration ES is essential for daily, weekly, and seasonal peak shaving and energy time-shifting. Aiming at the challenge of multi-timescale configuration of hybrid energy storage (HES) in the initial planning stage of carbon-neutral transition, this paper proposes an optimal configuration strategy combining STL-PDM-VMD. First, the seasonal and trend decomposition using Loess (STL) is used to extract quarterly trends of annual net power for seasonal ES configuration. Then, the Past Decomposable Mixing (PDM) module in the time-mixer model is applied to decouple and mix multi-scale features of the detrended power curve for monthly and weekly configurations. Finally, an improved Variational Mode Decomposition (VMD) is adopted to decompose daily net power fluctuations and optimize intra-day energy storage schemes. Based on actual data from a carbon-neutral transition region, simulations are carried out and compared with the VMD method with decomposition layers optimized by Gurobi. The results show that the proposed STL-PDM-VMD multi-timescale hybrid energy storage configuration strategy can effectively capture the multi-timescale fluctuation characteristics of net load, significantly improve the Renewable Energy (RE) penetration rate, and ensure the power and energy balance of the new power system at multiple timescales. penetration, and maintain power and energy balance in the new-type power system. Full article

High-resolution remote-sensing semantic segmentation requires models to simultaneously capture global scene semantics and preserve fine-grained local structures. Although satellite-pretrained vision foundation models provide strong transferable representations, the features extracted by a frozen backbone remain insufficiently adapted to dense prediction, particularly for representing high-frequency details and multiscale local patterns. In addition, correcting residual prediction errors with dense full-map refinement introduces substantial computational redundancy, since hard errors are typically concentrated in only a small subset of locations. To address these challenges, we propose ADVMSeg, an efficient remote-sensing semantic segmentation framework built upon a frozen satellite-pretrained DINOv3 backbone. Specifically, we introduce a Spatial-Frequency Adapter (SF-Adapter) to improve backbone-level dense feature adaptation by jointly modeling global frequency responses and multiscale local spatial details in a lightweight bottleneck space. We further design an Adaptive Sparse Refinement (ASR) module after the pixel decoder, which identifies hard regions from coarse predictions via uncertainty and boundary cues, and performs targeted local cross-attention refinement only on selected critical locations. Extensive experiments on GID-15, LoveDA, and ISPRS Potsdam validate the effectiveness of the proposed framework. Under the unified setting, ADVMSeg achieves 63.1% mIoU on GID-15, 63.5% mIoU on LoveDA, and 81.4% mIoU on ISPRS Potsdam. These results validate the effectiveness of jointly improving backbone-level feature adaptation and prediction-stage computation allocation under the evaluated setting of frozen DINOv3, and three representative remote-sensing semantic-segmentation datasets. Full article

The Upper Zarafshon River Basin (UZRB) in Tajikistan hosts numerous glaciers, of which the Zarafshon glacier is the largest and most important source of meltwater for both Tajikistan and Uzbekistan. In this study, we analyzed glacier retreat, surface displacement, and the evolution of supraglacial features from 2016 to 2024 using multi-temporal, high-resolution satellite imagery from Gaofen-2 and PlanetScope (80 cm and 3 m spatial resolution). We selected five representative glaciers-№ 168, 178, 185, 202, and 203 based on their size (greater than 1 km²) and hydrological significance. Our comprehensive investigation of the glaciers in 2024 includes data on glacier area, length, supraglacial lakes, and morphological classification. The results show a decrease in total glacier area from 254.1 km² in 2016 to 252.8 km² in 2024. Surface movement patterns, derived from visual and geomorphological assessments, reveal spatially heterogeneous displacement, especially in debris-covered areas. Supraglacial lakes and ponds showed dynamic changes, with the most significant expansion in 2022, driven by increased surface melt and subglacial hydrological reorganization. These findings highlight the need for ongoing glacier monitoring in the Zarafshon River Basin (ZRB) due to the significant implications that cryospheric changes hold for regional hydrology, water security, and the frequency of climate-induced natural hazards. Full article

Point cloud semantic segmentation is a pivotal technology for realizing non-contact body measurement and refined management of livestock. However, processing sheep point clouds in smart livestock scenarios presents specific challenges, primarily due to non-rigid posture deformations and severe background interference. To address these issues, this paper proposes a novel symmetric encoder–decoder architecture named Local–Global Aggregation Network (LGA-Net), which achieves high-precision parsing of sheep point clouds by constructing a dual-scale feature aggregation mechanism. First, a Dual Attention Aggregation (DAA) module is designed to jointly encode geometric and color features, significantly enhancing the network’s ability to capture fine-grained local boundaries, such as sheep ears and hooves. Second, a Global Semantic Relation (GSR) module is introduced, utilizing spatial occupancy ratios to establish long-range dependencies, thereby effectively resolving semantic ambiguity caused by posture variations. Furthermore, a plug-and-play Dual-domain Feature Enhancement (DFE) module is proposed. By fusing bilinear interactions between explicit 3D space and implicit feature space, the DFE module constructs a high-pass filtering mechanism to suppress low-frequency background noise. Extensive experiments on a self-constructed point cloud dataset involving two semantic classes (Sheep and Fence) demonstrate that LGA-Net achieves a mIoU of 97.3%, an OA of 99.0%, and a mAcc of 97.8%. These results indicate that the proposed method outperforms existing mainstream algorithms in both segmentation accuracy and robustness. This study not only proposes a feasible solution for precise sheep extraction under the tested experimental conditions, but also provides solid technical support for subsequent automated body measurement and behavior analysis. Full article

Electroluminescence (EL) imaging is widely used for photovoltaic (PV) module inspection, yet EL defect detection remains challenging due to the need for high-resolution inputs, low-contrast defects, and strong structured background patterns. To address these issues, we propose MSW-Mamba-Det, an end-to-end defect detection framework built on RT-DETR, comprising three components. (1) MSW-Mamba, a multi-scale windowed state-space module, adopts a Local/Stripe/Grid architecture to jointly model fine details and long-range dependencies; the Stripe branch strengthens directional continuity for elongated defects, while the Grid branch introduces coarse global context to improve cross-region consistency. Saliency- and gradient-guided gating is further used to suppress background-induced false responses. (2) DetailAware compensates for detail attenuation by restoring high-frequency textures and edges through multi-scale local enhancement, and applies pixel-wise adaptive gating to integrate global semantics and mitigate smoothing effects in deep representations. (3) PAFB (Pyramid Attention Fusion Block) aligns adjacent-scale features and improves multi-scale fusion, enhancing localization stability across defect sizes. Experiments on two public EL datasets show that MSW-Mamba-Det achieves $A{P}_{50:95}$ of 60.4% on PV-Multi-Defect-main and 68.0% on PVEL-AD, improving over RT-DETR by 2.5 points (from 57.9% to 60.4%) and 2.2 points (from 65.8% to 68.0%), respectively. MSW-Mamba-Det also outperforms 12 representative baselines, including CNN-, Transformer-, and recent YOLO-based models, in $A{P}_{50:95}$ on both datasets, with particularly strong performance on medium and large defects. These results demonstrate the effectiveness of the proposed modules for robust PV EL defect inspection under low-contrast and structured-background conditions. Full article

To address the issues of difficult heterogeneous image registration and low segmentation accuracy caused by the severe lack of illumination and significant modal differences in concrete cracks in extremely dark environments, this paper proposes a two-stage processing framework of registration–fusion first, and decoupling–segmentation later. In the registration and fusion stage, a registration algorithm based on morphological priors and multi-level quadtree spatial constraints is designed. This approach transforms the problem from pixel grayscale matching to spatial topological matching, achieving a feature fusion of high infrared saliency and high visible light sharpness. In the segmentation stage, a Latent Frequency-Decoupled Topological Network (LFDT-Net) is proposed. It utilizes Discrete Wavelet Transform (DWT) to achieve high-fidelity frequency decoupling of the low-frequency infrared backbone and the high-frequency visible light edges. Furthermore, a Cross-Frequency Guidance Module is utilized to eliminate double-edged artifacts, and a skeleton-aware topological loss function is introduced to constrain the topological integrity of the cracks. Experimental results on a self-built heterogeneous multi-modal crack dataset demonstrate that the proposed method significantly outperforms existing mainstream methods in registration accuracy, fusion quality, and segmentation accuracy. Achieving a mean Intersection over Union (mIoU) of 81.7%, the method effectively suppresses background noise in dark environments and precisely restores the microscopic edges and continuous topological structures of faint cracks. Full article

We propose a monolithically integrated optical frequency comb (OFC) generation platform on thin-film lithium niobate (TFLN), featuring cascaded dual-drive Mach–Zehnder modulators (DDMZM) and a ${\mathrm{S}\mathrm{i}}_3{\mathrm{N}}_4$-assisted spot size converter (SSC). To capture microscopic mode mismatches and spatial phase accumulation often overlooked in idealized scalar simulations, we establish a multi-physics co-simulation framework integrating finite-difference time-domain (FDTD) analysis with macroscopic transmission modeling. Based on this framework, the cascaded modulator architecture generates 25 highly stable comb lines with a dense 2 GHz spacing and an envelope flatness within 2 dB. Tolerance analysis indicates that the comb generation is highly resilient to typical manufacturing and environmental variations, including thermal bias drift, RF phase mismatch, and half-wave voltage ($V_{\pi }$) dispersion. Furthermore, physical-layer modeling shows that the integrated SSC reduces fiber-to-chip coupling loss to 0.55 dB per facet, preserving the necessary optical power budget. To validate the platform’s viability as a multi-wavelength continuous-wave source for spatial-division multiplexed (SDM) interconnects, a parallel transmission over a 20 km standard single-mode fiber is modeled. Using a digital signal processing (DSP)-free 10 Gb/s non-return-to-zero (NRZ) scheme, the 25-channel system maintains a worst-case bit error rate strictly below the forward error correction (FEC) threshold. This work offers a practical, physics-based evaluation framework for high-density co-packaged optics (CPO). Full article

To address the limited accuracy of power demand prediction for hybrid electric vehicles under complex and dynamic driving conditions, this paper proposes a hybrid prediction approach based on the cascade correction of Long Short-Term Memory networks and Least Squares Support Vector Machines (LSTM-LSSVM-CC). The proposed method adopts a stage-wise modeling framework that exploits the least-squares optimality of LSSVM for low-frequency steady-state signals and the dynamic compensation capability of LSTM for high-frequency non-stationary residuals, thereby achieving complementary feature representation in the frequency domain. Specifically, an LSSVM is first used to construct a baseline regression model that captures stationary components, followed by an LSTM network that performs deep temporal modeling of the residual sequence to correct nonlinear prediction errors. Extensive experiments conducted on three standard driving cycles—CLTC-P, WLTP, and UDDS—demonstrate that the proposed model consistently outperforms conventional methods including LSSVM, RNN, ELMAN, and Random Forest in multi-step predictions, achieving an average RMSE reduction of 28–52% and maintaining correlation coefficients (R²) between 0.87 and 0.99. Particularly under highly dynamic and abrupt load conditions, the model exhibits superior real-time performance and stability while significantly mitigating cumulative prediction errors. These results demonstrate that the proposed LSTM-LSSVM-CC model achieves robust modeling performance of non-stationary time series while balancing prediction accuracy and computational efficiency, providing an effective technical foundation for hybrid vehicle energy management optimization and offering a transferable theoretical framework for time-series prediction in complex systems. Full article

Aiming to address the problems of low accuracy in coal–rock identification during coal mining, which lead to energy waste and safety hazards, a high-precision coal–rock medium identification method combining terahertz time-domain spectroscopy technology and multiple machine learning algorithms is proposed. By preparing coal–rock samples with a gradient change in coal content, terahertz time-domain spectroscopy data of coal–rock mixed media are collected, and optical parameters such as the refractive index and absorption coefficient are extracted. Principal component analysis is used to reduce the dimensionality of the terahertz data, and machine learning algorithms such as support vector machine, least squares support vector machine, artificial neural networks, and random forests are adopted for classification and identification. The study found that terahertz waves are more sensitive to coal–rock media in the 0.7–1.3 THz frequency band, and that the refractive index and absorption coefficient of coal–rock mixed media are significantly positively correlated with coal content within the range of 0–30%. After feature extraction and K-fold cross-validation, the random forest model achieved a coal–rock classification accuracy of over 96% on the test set, significantly outperforming other comparison algorithms. The research verifies the efficiency and practicality of terahertz technology combined with multiple machine learning algorithms in coal–rock identification, providing a new method for fields such as mineral separation. This method has, to a certain extent, broken through the accuracy bottleneck of traditional coal–rock identification technologies within its applicable range, providing a new solution for real-time detection of coal–rock interfaces and is expected to further reduce the risks of ineffective mining and roof accidents in the future. Full article