Search Results (8,185)

The Middle Route of the South-to-North Water Diversion Project (SNWD-MR) serves as a strategic infrastructure critical to safeguarding water security in Northern China. Traversing complex geographical units, the project is perpetually exposed to long-term risks of land subsidence. Conventional Interferometric Synthetic Aperture Radar (InSAR) monitoring is hampered by waterbody isolation, causing spatial discontinuities in the retrieved deformation fields; furthermore, relying solely on deformation metrics fails to comprehensively quantify multidimensional risks. To address these issues, this study proposes an integrated assessment framework that couples time-series InSAR observations with the Analytic Hierarchy Process-Fuzzy Comprehensive Evaluation (AHP-FCE) model. To specifically mitigate the challenge of waterbody isolation, we developed a connectivity-aware multiscale down-sampling phase unwrapping strategy. By exploiting cross-canal bridges to construct a spatial connection network, a highly accurate, spatiotemporally continuous deformation field across the entire alignment was successfully reconstructed. Using the derived deformation field as the core dynamic indicator, an AHP-FCE model integrating hydrogeological features and human perturbations was constructed. A complementary evaluation process comprising sensitivity analysis and an internal physical consistency assessment was subsequently implemented. The results demonstrate that (1) the proposed algorithm effectively resolves the spatial discontinuity issue of the cross-canal deformation fields, reducing the deformation-velocity RMSE from 7.9 to 5.7 mm/y, corresponding to an approximately 27.8% reduction in RMSE relative to the traditional Minimum Cost Flow (MCF) method; (2) land subsidence along the alignment exhibits prominent spatial heterogeneity, with the northern Henan and southern Hebei sections identified as very-high-risk zones; and (3) InSAR deformation magnitude and the groundwater elevation indicator emerge as the most influential factors in the modeled risk distribution. Overall, this study expands conventional deformation monitoring into a systematic, quantitative risk assessment framework, thereby providing scientific insights and theoretical support for the early warning of geo-hazards and the smart operation and maintenance of large-scale water diversion projects. Full article

Industry–University–Research (IUR) networks are vital for knowledge sharing and collaborative innovation, yet existing network research largely ignores the maintenance cost of inter-organizational ties, which creates persistent theoretical tension between social capital theory (advocating dense connections) and structural hole theory (advocating sparse non-redundant ties). This study constructs a simulation model integrating barter knowledge exchange and multi-dimensional relational maintenance cost loss and systematically simulates the evolution of average knowledge stock (AKS) under regular, small-world and random network structure. The simulation results show that there exists a stable optimal node degree range of 20–40 for IUR actors, which is robust against changes in network scale, initial knowledge endowment and relational cost coefficients. Under moderate technological complexity, small-world networks realize the highest efficiency of knowledge accumulation; when technological complexity rises to a high level, regular networks with local agglomeration advantages become more efficient. This study supplements a cost-based analytical perspective to reconcile the contradiction between two core network theories and provides preliminary simulation evidence for the contingent design of IUR collaborative networks. From a practical perspective, the findings offer reference for adaptive governance of IUR alliances to balance relational costs and knowledge gains and further respond to the United Nations Sustainable Development Goal 9 (Industry, Innovation, and Infrastructure). Limitations of this simulation-based analysis are clearly acknowledged in the discussion section. Full article

Aircraft often manifest as highly aspect/pose-sensitive, disjointed blobs made of pixels with fluctuating levels of brightness in classic grayscale SAR images, which makes the aircraft annotation task challenging even for human experts. As more and more high-resolution colorized SAR images acquired by the latest commercial imaging modes are released for open access, both the academia and the industry started to notice the benefits of color-coded SAR images. However, since the large-scale datasets in the area of SAR aircraft detection feature grayscale SAR images, research on discrimination feature learning in color space for SAR aircraft detection is very limited. To embrace the opportunity brought by the new generation of highly informative colored SAR images, we propose the Phase-Aware Clustering Enhanced Detector (PACE-Det), which consists of three main components: the Phase-Orientation Color Encoder (POCE) module, the core detection network, and the Multi-Space Clustering Constraint (MSCC) module. The front-end POCE module generates pseudo-color SAR images based on Phase Congruency (PC). The color representations are fed into the core detection network for feature extraction, where the phase-aware alignment loss is introduced in addition to the classification and regression losses in the standard object detection task. The initial predictions generated by the core detection network are further refined by the contextual information extracted by the post-processing MSCC module based on the image segmentation result in $L^{\ast }{a}^{\ast }{b}^{\ast }$ color space, where anisotropic objects like aircraft and isotropic scatterers like impervious surfaces exhibit distinct spatial distributions and color features. Experiments based on the Composite SAR Aircraft Dataset (CSAD), which is constructed by fusing airport scenes with SAR aircraft target patches, show that the proposed PACE-Det achieves a ${\mathrm{mAP}}_{75}$ of 0.948 and ${\mathrm{mAP}}_{90}$ of 0.561, which are higher than many state-of-the-art networks. Full article

The accurate estimation of forest aboveground biomass (AGB) typically relies on extensive field surveys, which are highly time-consuming and cost-prohibitive. While unmanned aerial vehicle (UAV) Light Detection and Ranging (LiDAR) provides ultra-high point densities capable of reliable individual-tree analysis, its limited flight coverage restricts large-scale applications. Conversely, regional airborne laser scanning (ALS) offers broad spatial coverage, but its relatively low point cloud density makes individual-tree level analysis unreliable. To bridge this scale and data gap, this study develops a scale-consistent framework that integrates UAV-LiDAR, three-dimensional simulation, multisource remote sensing, and machine learning for Chinese fir (Cunninghamia lanceolata) plantation AGB estimation. High-density UAV-LiDAR data were first used to construct individual-tree AGB models, and the predicted tree-level biomass was aggregated to generate spatially representative “agent plots” for stand-scale modeling. A three-dimensional (3D) radiative transfer simulation framework was further employed to reproduce airborne LiDAR observations under different point densities, enabling the evaluation of structural information loss caused by LiDAR sparsity. Structural features derived from simulated LiDAR and spectral information from Sentinel-2 imagery were integrated using the Tabular Prior-data Fitted Network (TabPFN). Model reliability was assessed through 10-fold spatial block cross-validation and Monte Carlo simulations, which quantified spatial generalization and uncertainty propagation from individual-tree estimation to stand-level prediction. Feature interpretation using SHapley Additive exPlanations (SHAP) revealed that the LiDAR-derived vertical canopy structure provided the primary constraints for biomass estimation, whereas Sentinel-2 shortwave infrared features supplied complementary information related to canopy conditions. The optimal TabPFN model achieved a stand-level accuracy of R² = 0.88 and RMSE = 9.23 Mg·ha⁻¹ using LiDAR combined with Sentinel-2 data. Uncertainty analysis further demonstrated the robustness of the proposed framework under propagated errors, highlighting its potential for scalable and reliable forest biomass estimation in data-limited subtropical ecosystems. Full article

Software-defined satellite networks (SDSNs) enhance resource utilization and flexibility in space-based networks by leveraging a global view and programmability. A highly reliable control plane is essential to sustain network operations. However, the highly dynamic topology and physical failures in Low Earth Orbit (LEO) environments can cause satellite node outages or inter-satellite link disruptions, leading to control plane interruptions and local load imbalances. To address this, we propose a switch migration mechanism for failure recovery and establish a multi-objective migration model that jointly optimizes control link delay, controller load variance, and normalized migration ratio. To accommodate distinct dynamic characteristics such as frequent topology changes, failure-intensive periods, and stable periods, we design two algorithms: a robust migration algorithm, DNSGA-II, which features population diversity maintenance and environmental awareness, and an efficient migration algorithm, IHAOAVOA, which integrates strong global exploration with powerful local exploitation. Simulation results show that IHAOAVOA rapidly converges under large-scale failures, achieving millisecond-level delay recovery and low normalized migration ratio overhead during failure-intensive periods, while DNSGA-II focuses on long-term load balancing and system stability during stable periods, effectively suppressing localized controller overload. By adopting IHAOAVOA during topology fluctuations or high-failure phases to reduce delay, and switching to DNSGA-II during stable phases to optimize load distribution, the overall network robustness can be improved under the evaluated failure scenarios. This work provides effective support for achieving highly reliable control in SDSNs under failure scenarios. Full article

The uniformity of maize plant spacing serves as a critical indicator for assessing sowing quality, seed vigor, and field seedling emergence stability. However, manual measurement is inefficient, and complex field conditions make automatic seedling detection and plant spacing measurement challenging. Aiming at the challenges of missed detection, insufficient accuracy for small targets, and large errors in plant spacing calculation under complex field conditions, this study constructs a high-quality dataset containing 693 maize seedling images and implements preprocessing enhancement for images degraded by haze or dust. An intelligent maize seedling detection and plant spacing measurement method based on improved YOLOv8 is proposed. The Global Attention Mechanism (GAM) is embedded into the backbone network to strengthen cross-dimension information interaction between channels and spaces, suppress background interference, and reduce the missed detection rate. The Bi-directional Feature Pyramid Network (BiFPN) is adopted to replace the original PAFPN for enhanced multi-scale feature fusion and deep semantic representation. A new 160 × 160 high-resolution small-object detection layer is added to significantly improve the detection performance of weak and small seedlings. Experimental results demonstrate that the improved model achieves a precision, recall, mAP50, and mAP50-95 of 89.4%, 90.3%, 94.4%, and 49.4%, respectively, which are 2.6, 0.5, 1.5, and 2.7 percentage points higher than those of the original YOLOv8 model. These results indicate that the proposed model improved maize seedling detection performance under complex field conditions. Automatic plant spacing calculation is realized based on detection outputs; the average plant spacing of the dataset is 30.42 cm, with a relative error of only 4.93% compared with the preset sowing spacing of 32 cm. The proposed method can efficiently accomplish field seedling identification, plant spacing quantification, and sowing quality evaluation, providing reliable technical support for precision maize sowing, seeder parameter optimization, and intelligent field management, which is of great significance for promoting the intelligent upgrading of grain crop production. Full article

Mobile LiDAR systems (MLS) enable rapid acquisition of large-scale 3D point cloud data. Semantic segmentation of the acquired point clouds is an important task in outdoor scene understanding and environmental perception for autonomous driving. However, existing methods tend to suffer from boundary confusion when segmenting MLS point clouds with long-tail categories. To address this problem, we propose the Dilated Context Attention Network (DCA-Net), which consists of a dilated local geometric encoding module, a channel attention pooling module, and a category-boundary sampling strategy. The dilated local geometric encoding module expands point-to-point connections within a fixed neighborhood to strengthen contextual modeling among neighboring points. The channel attention pooling module uses a channel attention mechanism to enhance informative channel responses in neighborhood features, thereby improving local feature representation. The category-boundary sampling strategy increases the sampling probabilities of minority-category points and boundary points, reducing feature information loss during down-sampling. Experimental results on the S3DIS, Toronto3D, and MLS road scene datasets show that DCA-Net achieves mIoU scores of 69.4%, 84.1%, and 96.6%, respectively. These results demonstrate that the proposed method alleviates boundary confusion in point cloud segmentation with long-tail categories, without causing a noticeable degradation in the segmentation performance of majority categories. Full article

The primary aim of this study is to identify how residents on the Hungarian and Slovak sides of the Lower Ipoly Valley perceive the most considerable material and immaterial local values and unique resources of their settlements. The research was designed to explore and compare the territorial capital of the two sides of the study area based on three major capital types: natural, social, and economic capitals. Data collection included 254 semi-structured interviews, conducted with 136 residents on the Slovak side (14 settlements) and 118 residents on the Hungarian side (12 settlements). Detailed interview summaries were analysed with qualitative content analysis using emergent coding. This resulted in an analytical framework comprising nine value dimensions. Across both sides of the border, we examined the same nine value dimensions: local workforce, local enterprises, civil organisations and cultural groups, local and community events, local gastronomy, natural values, built heritage, holders of local knowledge, and local products. Items mentioned that related to each value dimension were counted for each dimension and normalised to a 0–10 scale. The quantified values were aggregated at the settlement level (90 points being the maximum score). The average score of each dimension was also calculated for both sides of the study area. Our findings show that the Hungarian side achieved a total score of 40.4, while the Slovak side reached 36.6, both reflecting a similarly weak–moderate state of the local capitals with minimal differences. This indicates that the two sides of the study area share comparable developmental challenges but also considerable potential for improvement. The Hungarian side performed slightly better in nearly all dimensions except local gastronomy, where the Slovak side proved stronger. The Hungarian side’s relative advantages include a higher presence of local enterprises, a richer network of civil and cultural groups, and more diverse built heritage; in other dimensions, differences are marginal. One of the most pressing regional challenges is improving employment opportunities and stimulating entrepreneurial activity, which are essential for enhancing population retention. Overall, the results indicate that the settlements possess substantial—yet largely underutilised—value assets, whose conscious and consensus-based development could form a strong foundation for creative and innovative local development. Each settlement’s value matrix includes elements that define its uniqueness, enabling the identification of numerous potential development pathways, whether through nature-based educational and recreational programmes, the utilisation of culturally considerable built heritage, the revitalisation of living traditions, or the promotion of local traditional gastronomy on both sides of the study area. Full article

Proteomics has emerged as a powerful tool for advancing our understanding of brain disorders by enabling large-scale characterization of protein expression, post-translational modifications, and interaction networks. Neurological conditions are often characterized by complex and dynamic molecular changes that are not fully captured by traditional diagnostic approaches. Proteomic technologies, particularly mass spectrometry-based and affinity-based methods, offer the ability to identify disease-specific protein signatures and elucidate underlying pathophysiological mechanisms, including neurodegeneration, neurodevelopment and neuroinflammation and alterations happening to the extracellular matrix and body fluid homeostasis. In recent years, artificial intelligence has emerged as a powerful tool to proteomics, enabling improved analysis of complex biological datasets. This integration has significantly enhanced the discovery of biomarkers for early diagnosis, disease stratification, and monitoring of therapeutic responses. Thus, cerebrospinal fluid and blood-based proteomic analyses have revealed promising candidates for neurological diseases. This review summarizes current advances in proteomics across a range of brain disorders, highlighting key molecular pathways, biomarker discovery efforts, and evolving clinical applications. Furthermore, it outlines future directions, including the application of machine learning for improved biomarker identification and precision medicine. Full article

In flexibly interconnected regional power systems with high penetration of renewable energy, chronological production simulation encounters combinatorial explosion and computational inefficiency, especially over medium- and long-term horizons with large-scale network constraints. Centralized approaches become intractable due to problem scale and memory limitations, while existing alternating direction method of multipliers (ADMM) variants suffer from convergence instability and high computational cost when regional subproblems involve discrete unit commitment decisions. To address these issues, this paper establishes a network-constrained chronological production simulation model incorporating the operational characteristics of voltage-source-converter-based high-voltage direct-current (VSC-HVDC) transmission and inter-regional flexibility reserve sharing, and proposes a tailored consensus ADMM with network-constrained clustering linearization (ADMM-NCL) for an efficient parallel solution. The ADMM-NCL combines same-type unit clustering, which convexifies the unit commitment formulation for parallel solvability, with redundant network constraint screening thus retaining only the critical constraints. In representative spring and summer periods, ADMM-NCL achieves 12×~18× speedups over the centralized benchmark and 2×~10× over the tested ADMM variants; across four seasonal scenarios (spring, summer, autumn, and winter), it bounds the objective cost deviation within 0.41% while maintaining close agreement in key operational indicators. For the 8760 h case, where the centralized benchmark and several ADMM variants fail due to memory or time limits, ADMM-NCL completes the simulation within an available computational budget, thus demonstrating its scalability with respect to the full-year chronological horizon. Full article

Surface vegetation dynamics in mining areas are characterized by complex non-linear processes associated with anthropogenic disturbance and ecological restoration. Existing remote sensing approaches often face limitations in balancing temporal interpretability and the characterization of long-term vegetation trajectories at regional scales. To address this issue, this study proposes a trajectory-guided weakly supervised framework that integrates parameterized curve fitting with deep temporal learning for mining vegetation monitoring. Based on the characteristic “extraction–reclamation” cycle, six representative vegetation trajectory patterns were pre-defined to describe different stages of degradation and restoration. Long-term NDVI trajectories (1990–2023) derived from Landsat time-series data were modeled using linear and parameterized Sigmoid functions to automatically generate high-quality supervision samples and temporal transition labels. These trajectory-constrained samples were subsequently incorporated into a multi-task BiLSTM-Attention network to simultaneously perform pixel-level change classification and turning-point regression. Applied to the mining clusters of the Dongting Lake Basin, China, the proposed framework achieved an overall classification accuracy of 86.64% (Kappa = 0.83), while the temporal prediction error remained within two years. Results revealed that 28.66% of the 61.20 km² of significantly degraded mining land has undergone effective ecological restoration, with restoration activities increasing sharply between 2012 and 2014 in response to regional environmental policies. By coupling ecological trajectory modeling with weakly supervised temporal learning, this study offers a promising approach for large-scale mining restoration monitoring and ecological assessment. Full article

Reliable fruit quality assessment is crucial for ensuring food safety and value in modern agriculture. However, many current approaches still rely heavily on visual cues, making it difficult to assess internal quality indicators such as sweetness or internal decay. To address this limitation, we propose HSAF-Net, a heterogeneous multimodal fusion framework integrating spiking neural networks (SNNs) and artificial neural networks (ANNs) for comprehensive, non-destructive fruit quality assessment. Specifically, the SNN encodes near-infrared (NIR) spectral signals to extract internal sugar-related features, whereas the ANN-based TH-YOLOv8 model detects external surface defects from high-resolution RGB images. A microsecond-level synchronous acquisition scheme is implemented to ensure precise alignment between the NIR and RGB modalities. To effectively combine heterogeneous features, we design a Heterogeneous Modality Attention (HMA) mechanism that dynamically fuses multi-source information based on task-specific relevance. Compared with image-only detection, the proposed framework explicitly separates internal biochemical sensing from external defect localization and then integrates their complementary decisions in a unified grading pipeline. Experimental results on 616 pear samples demonstrate that the HSAF-Net achieves 95.2% classification accuracy, 95.1% mAP95, and an internal defect miss rate as low as 7.5%, outperforming conventional single-modality and early-fusion baselines by a notable margin. The system maintains a real-time inference speed of 55 ms per sample on the Ascend Atlas 200DK A2 edge platform, validating its deployment potential. The current evaluation is based on crisp pear samples collected under controlled acquisition conditions; therefore, broader cross-variety and cross-season validation remains necessary before large-scale commercial deployment. This study presents an end-to-end multimodal SNN-ANN fusion architecture tailored for fruit grading and provides a scalable, high-precision solution for post-harvest quality assessment with broad applicability to other agricultural products. Full article

Aiming at the challenges of potato storage scenarios, severe target stacking and occlusion, and large variations in defect characteristics in potato storage environments, a potato defect detection method named MDS-DETR was proposed, and its deployment on a robotic sorting platform was validated. First, potato images under different illumination conditions and stacking states were collected in potato storage warehouses to construct a potato defect dataset containing defects such as black spot, sprouting, dry rot, decay, green skin, and cracking. Subsequently, according to the characteristics of object detection tasks in storage scenarios, an MCF module was designed to strengthen the extraction and integration of contextual features across different spatial scales. An AIFI-DyMona structure, namely Anchor-free Instance Feature Interaction with Dynamic Mona, was constructed to improve the stability of feature representation under different illumination conditions. In addition, the Shape-IoU regression strategy was incorporated to improve the network sensitivity to irregular defect contours and geometric characteristics. Validation experiments demonstrated that the proposed MDS-DETR framework achieved 96.3% mAP@0.5, with only 14.2 M parameters and 42.9 G FLOPs. Compared with several representative object detection algorithms, the proposed method exhibited superior recognition capability and stronger robustness under complicated storage conditions, while also showing better suppression of missed and incorrect detections. To further evaluate its practical applicability, the trained network was integrated into an intelligent potato sorting robot and tested in real warehouse scenarios. Experimental observations indicated that the robotic system consistently maintained a sorting accuracy exceeding 95%, demonstrating the effectiveness and practical deployment potential of the proposed approach for potato storage applications. This study can provide a reference for intelligent detection and automated sorting in potato storage processes. Full article

Industrial control networks based on Supervisory Control and Data Acquisition (SCADA) systems used in critical infrastructure systems require reliable, scalable, and generalizable attack detection mechanisms in the face of increasing cyber-threats. However, a large portion of the datasets commonly used in the literature are based on general-purpose network traffic and do not adequately reflect the cyclical, deterministic, and process-oriented communication structure of industrial protocols such as Modbus/TCP. In this study, a completely isolated virtual SCADA environment was designed to address this limitation. A SCADA-specific multi-class attack dataset called SCADANet was developed, containing 13 different attack scenarios generated concurrently with legitimate network traffic. In this context, a hybrid deep learning architecture consisting of parallel dilated Convolutional Neural Network (CNN) structures, Residual-SE blocks, and Long Short-Term Memory (LSTM) layers, capable of modeling multi-scale spatial patterns and feature-level sequential and contextual relationships within transformed traffic representations, was proposed. To examine the generalizability of the proposed approach, the developed model was tested on both the SCADANet dataset and the WUSTL-IIoT-2021 dataset, which is widely used in the literature. Experimental results show that the proposed architecture achieves high accuracy and macro-F1-score on both datasets, particularly demonstrating a significant increase in sensitivity in minority attack classes. Furthermore, the ablation study conducted reveals that each component in the architecture contributes meaningfully and complementarily to the overall performance. The findings demonstrate that the proposed deep learning-based approach can effectively model traffic characteristics specific to SCADA systems and exhibits stable attack detection performance across different data sources. In this respect, the study makes important methodological and experimental contributions to the literature on cyber-attack detection in SCADA-based critical infrastructure systems. Full article

Automatic semantic parsing of architectural floor plans provides a two-dimensional semantic layer for building information modeling (BIM)-related workflows, intelligent plan checking, renovation, and large-scale drawing management. Unlike natural images, floor plans contain sparse textures, dense linework, small architectural symbols, and strong axis-aligned geometric regularities. These properties make conventional segmentation networks vulnerable to small-symbol dilution during downsampling, noisy skip-feature fusion, and fragmented predictions along long wall boundaries. Inspired by principles of hierarchical visual processing, selective attention, and spatial encoding, this study presents PCP-Net, an end-to-end Planar Component Parsing Network for room, icon, and boundary-aware floor plan parsing. PCP-Net uses a Grouped Residual Encoder to extract multi-scale local patterns, a Cross-Scale Feature Recalibration (CSFR) pipeline to recalibrate skip features through Adaptive Channel Gating, Spatial Response Amplification, and Axis-Decompositional Positional Embedding, and a Structural Gradient Propagation branch to provide training-time boundary regularization. Experiments on CubiCasa5K and three external datasets (R3D, CVC-FP, and ROBIN) evaluate PCP-Net under in-domain and zero-shot cross-domain protocols. On CubiCasa5K, PCP-Net attains 71.3% mIoU, 90.1% overall accuracy, and 78.9% mean accuracy; in the current ablation setting, ADPE improves mIoU by 0.8 percentage points over the ADPE-ablated configuration. These results indicate that cross-scale feature recalibration with axis-aware positional cues can improve floor plan semantic parsing within the evaluated datasets and pixel-level metrics, while downstream BIM generation still requires additional vectorization, topology graph construction, and attribute extraction. Full article