Search Results (2,156)

With the rapid evolution of artificial intelligence technologies in power systems, data-driven time-series forecasting has become instrumental in enhancing the stability and reliability of power systems, allowing operators to anticipate demand fluctuations and optimize energy distribution. Despite the notable progress made by current methods, they are still hindered by two major limitations: most existing models are relatively small in architecture, failing to fully leverage the potential of large-scale models, and they are based on fixed nonlinear mapping functions that cannot adequately capture complex patterns, leading to information loss. To this end, an LLM-Empowered Kolmogorov–Arnold frequency learning (LKFL) is proposed for time series forecasting in power systems, which consists of LLM-based prompt representation learning, KAN-based frequency representation learning, and entropy-oriented cross-modal fusion. Specifically, LKFL first transforms multivariable time-series data into text prompts and leverages a pre-trained LLM to extract semantic-rich prompt representations. It then applies Fast Fourier Transform to convert the time-series data into the frequency domain and employs Kolmogorov–Arnold networks (KAN) to capture multi-scale periodic structures and complex frequency characteristics. Finally, LKFL integrates the prompt and frequency representations through an entropy-oriented cross-modal fusion strategy, which minimizes the semantic gap between different modalities and ensures full integration of complementary information. This comprehensive approach enables LKFL to achieve superior forecasting performance in power systems. Extensive evaluations on five benchmarks verify that LKFL sets a new standard for time-series forecasting in power systems compared with baseline methods. Full article

The accelerated global urbanization process has positioned land use/land cover change modeling as a critical component of contemporary geographic science and urban planning research. Traditional approaches face substantial challenges when addressing urban system complexity, multiscale spatial interactions, and high-dimensional data associations, creating urgent demand for sophisticated analytical frameworks. This review comprehensively evaluates machine learning applications in land use prediction through systematic analysis of 74 publications spanning 2020–2024, establishing a taxonomic framework distinguishing traditional machine learning, deep learning, and hybrid methodologies. The review contributes a comprehensive methodological assessment identifying algorithmic evolution patterns and performance benchmarks across diverse geographic contexts. Traditional methods demonstrate sustained reliability, while deep learning architectures excel in complex pattern recognition. Most significantly, hybrid methodologies have emerged as the dominant paradigm through algorithmic complementarity, consistently outperforming single-algorithm implementations. However, contemporary applications face critical constraints including computational complexity, scalability limitations, and interpretability issues impeding practical adoption. This review advances the field by synthesizing fragmented knowledge into a coherent framework and identifying research trajectories toward integrated intelligent systems with explainable artificial intelligence. Full article

Spiking neural networks (SNNs) have emerged as a promising model for energy-efficient, event-driven processing of asynchronous event streams from Dynamic Vision Sensors (DVSs), a class of neuromorphic image sensors with microsecond-level latency and high dynamic range. Nevertheless, challenges persist in optimising training and effectively handling spatio-temporal complexity, which limits their potential for real-time applications on embedded sensing systems such as object tracking and recognition. Targeting this neuromorphic sensing pipeline, this paper proposes the Dynamic Tracking with Event Attention Spiking Network (DTEASN), a novel framework designed to address these challenges by employing a pure SNN architecture, bypassing conventional convolutional neural network (CNN) operations, and reducing GPU resource dependency, while tailoring the processing to DVS signal characteristics (asynchrony, sparsity, and polarity). The model incorporates two innovative, self-developed components: an event-driven multi-scale attention mechanism and a spatio-temporal event convolver, both of which significantly enhance spatio-temporal feature extraction from raw DVS events. An Event-Weighted Spiking Loss (EW-SLoss) is introduced to optimise the learning process by prioritising informative events and improving robustness to sensor noise. Additionally, a lightweight event tracking mechanism and a custom synaptic connection rule are proposed to further improve model efficiency for low-power, edge deployment. The efficacy of DTEASN is demonstrated through empirical results on event-based (DVS) object recognition and tracking benchmarks, where it outperforms conventional methods in accuracy, latency, event throughput (events/s) and spike rate (spikes/s), memory footprint, spike-efficiency (energy proxy), and overall computational efficiency under typical DVS settings. By virtue of its event-aligned, sparse computation, the framework is amenable to highly parallel neuromorphic hardware, supporting on- or near-sensor inference for embedded applications. Full article

In the ecologically fragile western Shanxi Loess region, stand density regulation of artificial Robinia pseudoacacia L. forests plays a crucial role in sustaining the water regulation functions of the litter-soil system, yet multi-scale mechanistic analyses remain scarce. To address this gap, we established six stand density classes (ranging from 1200 to 3200 stems/ha) and quantified litter water-holding traits and soil physicochemical properties. We then applied principal component analysis (PCA) and structural equation modeling (SEM) to examine density-litter-soil relationships. Low-density stands (≤2000 stems/ha) exhibited significantly higher litter accumulation (6.08–6.37 t/ha) and greater litter water-holding capacity (maximum 20.58 t/ha) than the high-density stands (p < 0.05). Soil capillary water-holding capacity decreased with increasing density (4702.63–4863.28 t/ha overall), while non-capillary porosity (5.26–6.21%) and soil organic carbon (~12.5 g/kg) were higher in high-density stands (≥2800 stems/ha), reflecting a structural-carbon optimization trade-off. PCA revealed a primary hydrological function axis with low-density stands clustering in the positive quadrant, while high-density stands shifted toward nutrient-conservation traits. SEM confirmed that stand density affected soil capillary water-holding capacity indirectly through litter accumulation (significant indirect path; non-significant direct path), highlighting the central role of litter quantity. When density exceeded ~2400 stems/ha, litter decomposition rate decreased by ~56%, coinciding with capillary porosity falling below ~47%, a threshold linked to impaired balance between water storage and infiltration. These findings identify 1200–1600 stems/ha as the optimal density range; in this range, soil capillary water-holding capacity reached 4788–4863 t/ha, and available phosphorus remained ≥2.1 mg/kg, providing a density-centered, near-natural management paradigm for constructing “water-conservation vegetation” on the Loess Plateau. Full article

The accurate assessment of Chinese bayberry (Myrica rubra) maturity is critical for intelligent harvesting. This study proposes a novel cascaded framework combining instance segmentation and multi-feature regression for accurate maturity detection. First, a lightweight SOLOv2-Light network is employed to segment each fruit individually, which significantly reduces computational costs with only a marginal drop in accuracy. Then, a multi-feature extraction network is developed to fuse deep semantic, color (LAB space), and multi-scale texture features, enhanced by a channel attention mechanism for adaptive weighting. The maturity ground truth is defined using the a*/b* ratio measured by a colorimeter, which correlates strongly with anthocyanin accumulation and visual ripeness. Experimental results demonstrated that the proposed method achieves a mask mAP of 0.788 on the instance segmentation task, outperforming Mask R-CNN and YOLACT. For maturity prediction, a mean absolute error of 3.946% is attained, which is a significant improvement over the baseline. When the data are discretized into three maturity categories, the overall accuracy reaches 95.51%, surpassing YOLOX-s and Faster R-CNN by a considerable margin while reducing processing time by approximately 46%. The modular design facilitates easy adaptation to new varieties. This research provides a robust and efficient solution for in-field bayberry maturity detection, offering substantial value for the development of automated harvesting systems. Full article

The accuracy of numerical model outputs strongly depends on the quality of the initial wind field, yet ground observation data are typically sparse and provide incomplete spatial coverage. More importantly, many current mainstream correction models rely on reanalysis grid datasets like ERA5 as the true value, which relies on interpolation calculation, which directly affects the accuracy of the correction results. To address these issues, we propose a new deep learning model, PPWNet. The model directly uses sparse and discretely distributed observation data as the true value, which integrates observation point positions and a physical consistency term to achieve a high-precision corrected wind field. The model design is inspired by biological intelligence. First, observation point positions are encoded as input and observation values are included in the loss function. Second, a parallel dual-branch DenseInception network is employed to extract multi-scale grid features, simulating the hierarchical processing of the biological visual system. Meanwhile, PPWNet references the PointNet architecture and introduces an attention mechanism to efficiently extract features from sparse and irregular observation positions. This mechanism reflects the selective focus of cognitive functions. Furthermore, this paper incorporates physical knowledge into the model optimization process by adding a learned physical consistency term to the loss function, ensuring that the corrected results not only approximate the observations but also adhere to physical laws. Finally, hyperparameters are automatically tuned using the Bayesian TPE algorithm. Experiments demonstrate that PPWNet outperforms both traditional and existing deep learning methods. It reduces the MAE by 38.65% and the RMSE by 28.93%. The corrected wind field shows better agreement with observations in both wind speed and direction, confirming the effectiveness of incorporating position information and a physics-informed approach into deep learning-based wind field correction. Full article

Polycrystalline copper optics are widely utilized in infrared systems due to their exceptional electrical and thermal conductivity combined with favorable machining characteristics. The grain size profoundly influences both surface quality consistency and fundamental material removal behavior during processing. This investigation employs multiscale numerical modeling to simulate nanoscale cutting processes in polycrystalline copper with controlled grain structures, coupled with experimental ultra-precision machining validation. Comprehensive analysis of stress distribution, subsurface damage formation, and cutting force evolution reveals that refined grain structures promote more homogeneous plastic deformation, resulting in superior surface finish with reduced roughness and diminished grain boundary step formation. However, the enhanced grain boundary density in fine-grained specimens necessitates increased cutting energy input. These findings establish critical process–structure–property relationships essential for advancing precision manufacturing of copper-based optical systems. Full article

This study presents the development and deployment of a modular digital twin system designed to enhance sustainable facility management within a smart campus context. The system was implemented at the Faculty of Engineering, Chiang Mai University, and integrates 3D spatial modeling, real-time environmental and energy sensor data, and multiscale dashboard visualization. Grounded in stakeholder-driven requirements, the platform emphasizes energy management, which is the top priority among campus administrators and technicians. The development process followed a four-phase methodology: (1) stakeholder consultation and requirement analysis; (2) physical data acquisition and 3D model generation; (3) sensor deployment using IoT technologies with NB-IoT and LoRaWAN protocols; and (4) real-time data integration via Firebase and standardized APIs. A suite of dashboards was developed to support interactive monitoring across faculty, building, floor, and room levels. System testing with campus users demonstrated high usability, intuitive spatial navigation, and actionable insights for energy consumption analysis. Feedback indicated strong interest in features supporting data export and predictive analytics. The platform’s modular and hardware-agnostic architecture enables future extensions, including occupancy tracking, water monitoring, and automated control systems. Overall, the digital twin system offers a replicable and scalable model for data-driven facility management aligned with sustainability goals. Its real-time, multiscale capabilities contribute to operational transparency, resource optimization, and climate-responsive campus governance, setting the foundation for broader applications in smart cities and built environment innovation. Full article

The enhancement effect and mechanism of porous frameworks on hydrogel thermal control performance are key factors in evaluating their engineering applications and performance improvements. This study investigates the enhancement mechanism of porous framework composite phase-change materials (CPCM) on hydrogel thermal control performance through multi-scale visualization comparison experiments. Results indicate that pure hydrogels, due to their dense internal structure, hinder water vapor escape, thereby impeding overall fluidity and mass transfer rates. The introduction of a porous framework significantly improves internal heat transfer and moisture transport pathways within the hydrogel, enabling smooth water vapor release during heating and preventing localized heat accumulation. Under 100 °C heating conditions, CPCM exhibited a 65% reduction in mass-specific dehydration rate compared to pure hydrogel, with a 25% lower temperature drop. Energy efficiency increased by 13.5% over hydrogel, while the coefficient of variation decreased by 34.1%, demonstrating superior thermal stability and temperature control capabilities. This study elucidates from a mechanistic perspective how porous frameworks regulate the thermal and mass transfer behaviors of hydrogels, providing a theoretical basis and experimental support for their advanced application and optimization in the thermal control systems of electronic devices. Full article

This study elucidated the evolution and catastrophic failure mechanisms of concrete’s mechanical properties under high-temperature and moisture-coupled environments. Specimens underwent hygrothermal shock simulation via constant-temperature drying (100 °C/200 °C, 4 h) followed by water quenching (20 °C, 30 min). Uniaxial compression tests were performed using a uniaxial compression test machine with synchronized multi-scale damage monitoring that integrated digital image correlation (DIC), acoustic emission (AE), and infrared thermography. The results demonstrated that hygrothermal coupling reduced concrete ductility significantly, in which the peak strain decreased from 0.36% (ambient) to 0.25% for both the 100 °C and 200 °C groups, while compressive strength declined to 42.8 MPa (−2.9%) and 40.3 MPa (−8.6%), respectively, with elevated elastic modulus. DIC analysis revealed the temperature-dependent failure mode reconstruction: progressive end cracking (max strain 0.48%) at ambient temperature transitioned to coordinated dual-end cracking with jump-type damage (abrupt principal strain to 0.1%) at 100 °C and degenerated to brittle fracture oriented along a singular path (principal strain band 0.015%) at 200 °C. AE monitoring indicated drastically reduced micro-damage energy barriers at 200 °C, where cumulative energy (4000 mV·ms) plummeted to merely 2% of the ambient group (200,000 mV·ms). Infrared thermography showed that energy aggregation shifted from “centralized” (ambient) to “edge-to-center migration” (200 °C), with intensified thermal shock effects in fracture zones (ΔT ≈ −7.2 °C). The study established that hygrothermal coupling weakens the aggregate-paste interfacial transition zone (ITZ) by concentrating the strain energy along singular weak paths and inducing brittle failure mode degeneration, which thereby provides theoretical foundations for fire-resistant design and catastrophic failure warning systems in concrete structures exposed to coupled environmental stressors. Full article

Precise oriented object detection of corn provides critical support for automated agricultural tasks such as harvesting, spraying, and precision management. In this work, we address this challenge by leveraging oriented object detection in combination with depth information to estimate corn poses. To enhance detection accuracy while maintaining computational efficiency, we construct a precise annotated oriented corn detection dataset and propose YOLOv11OC, an improved detector. YOLOv11OC integrates three key components: Angle-aware Attention Module for angle encoding and orientation perception, Cross-Layer Fusion Network for multi-scale feature fusion, and GSConv Inception Network for efficient multi-scale representation. Together, these modules enable accurate oriented detection while reducing model complexity. Experimental results show that YOLOv11OC achieves 97.6% mAP@0.75, exceeding YOLOv11 by 3.2%, and improves mAP_50:95 by 5.0%. Furthermore, when combined with depth maps, the system achieves 92.5% pose estimation accuracy, demonstrating its potential to advance intelligent and automated cultivation and spraying. Full article

Brain tumors are highly malignant diseases that severely threaten the nervous system and patients’ lives. MRI is a core technology for brain tumor diagnosis and treatment due to its high resolution and non-invasiveness. However, existing YOLO-based models face challenges in brain tumor MRI image detection and segmentation, such as insufficient multi-scale feature extraction and high computational resource consumption. This paper proposes an improved lightweight brain tumor detection and instance segmentation model named FALS-YOLO, based on YOLOv8n-Seg and integrating three key modules: FLRDown, AdaSimAM, and LSCSHN. FLRDown enhances multi-scale tumor perception, AdaSimAM suppresses noise and improves feature fusion, and LSCSHN achieves high-precision segmentation with reduced parameters and computational burden. Experiments on the tumor-otak dataset show that FALS-YOLO achieves Precision (B) of 0.892, Recall (B) of 0.858, mAP@0.5 (B) of 0.912 in detection, and Precision (M) of 0.899, Recall (M) of 0.863, mAP@0.5 (M) of 0.917 in segmentation, outperforming YOLOv5n-Seg, YOLOv8n-Seg, YOLOv9s-Seg, YOLOv10n-Seg and YOLOv11n-Seg. Compared with YOLOv8n-Seg, FALS-YOLO reduces parameters by 31.95%, computational amount by 20.00%, and model size by 32.31%. It provides an efficient, accurate and practical solution for the automatic detection and instance segmentation of brain tumors in resource-limited environments. Full article

The intelligent development of unmanned aerial vehicles (UAVs) will make power inspection work more convenient. However, challenges such as reliance on precise tower coordinates and the low accuracy in recognizing small targets limit its further development. In this regard, this study proposes an autonomous inspection method based on target detection, encompassing both flight route planning and defect detection. For route planning, the YOLOv8 model is lightly modified by incorporating the VanillaBlock module, the GSConv module, and structured pruning techniques to enable real-time tower detection. Based on the detection results and UAV states, an adaptive route planning strategy is then developed, effectively mitigating the dependence on predefined tower coordinates. For defect detection, the YOLOv8 model is further enhanced by introducing the SPD-Conv module, the CBAM, and the BiFPN multi-scale feature fusion network to improve detection performance for small targets. Compared with multiple baseline models, the computational cost of the improved lightweight model is reduced by 23.5%, while the detection accuracy is increased by 4.5%. Flight experiments further validate the effectiveness of the proposed route planning approach. The proposed fully autonomous inspection method provides valuable insights into enhancing the autonomy and intelligence of UAV-based power inspection systems. Full article

This study introduces a non-destructive computer vision method for estimating postharvest quality parameters of oranges, including maturity index, soluble solid content (expressed in degrees Brix), and firmness. A novel image-based descriptor, termed Citrus Color Index—Gray Level Co-occurrence Matrix Texture Features (CCI–GLCM-TF), was developed by integrating the Citrus Color Index (CCI) with texture features derived from the Gray Level Co-occurrence Matrix (GLCM). By combining contrast, correlation, energy, and homogeneity across multiscale regions of interest and applying geometric calibration to correct image acquisition distortions, the descriptor effectively captures both chromatic and structural information from RGB images. These features served as input to an Adaptive Neuro-Fuzzy Inference System (ANFIS), selected for its ability to model nonlinear relationships and gradual transitions in citrus ripening. The proposed ANFIS models achieved R-squared values greater than or equal to 0.81 and root mean square error values less than or equal to 1.1 across all quality parameters, confirming their predictive robustness. Notably, representative models (ANFIS 2, 4, 6, and 8) demonstrated superior performance, supporting the extension of this approach to full-surface exploration of citrus fruits. The results outperform methods relying solely on color features, underscoring the importance of combining spectral and textural descriptors. This work highlights the potential of the CCI–GLCM-TF descriptor, in conjunction with ANFIS, for accurate, real-time, and non-invasive assessment of citrus quality, with practical implications for automated classification, postharvest process optimization, and cost reduction in the citrus industry. Full article

This study proposes an image-enhancement method to address the challenges of low visibility and color distortion in images captured during yellow sandstorms for an image sensor based outdoor surveillance system. The technique combines traditional image processing with deep learning to improve image quality while preserving color consistency during transformation. Conventional methods can partially improve color representation and reduce blurriness in sand–dust environments. However, they are limited in their ability to restore fine details and sharp object boundaries effectively. In contrast, the proposed method incorporates Retinex-based processing into the training phase, enabling enhanced clarity and sharpness in the restored images. The proposed framework comprises three main steps. First, a cycle-consistent generative adversarial network (CycleGAN) is trained with unpaired images to generate synthetically paired data. Second, CycleGAN is retrained using these generated images along with clear images obtained through multiscale image decomposition, allowing the model to transform dust-interfered images into clear ones. Finally, color preservation is achieved by selecting the A and B chrominance channels from the small-scale model to maintain the original color characteristics. The experimental results confirmed that the proposed method effectively restores image color and removes sand–dust-related interference, thereby providing enhanced visual quality under sandstorm conditions. Specifically, it outperformed algorithm-based dust removal methods such as Sand-Dust Image Enhancement (SDIE), Chromatic Variance Consistency Gamma and Correction-Based Dehazing (CVCGCBD), and Rank-One Prior (ROP+), as well as machine learning-based methods including Fusion strategy and Two-in-One Low-Visibility Enhancement Network (TOENet), achieving a Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score of 17.238, which demonstrates improved perceptual quality, and an Local Phase Coherence-Sharpness Index (LPC-SI) value of 0.973, indicating enhanced sharpness. Both metrics showed superior performance compared to conventional methods. When applied to Closed-Circuit Television (CCTV) systems, the proposed method is expected to mitigate the adverse effects of color distortion and image blurring caused by sand–dust, thereby effectively improving visual clarity in practical surveillance applications. Full article