Search Results (171)

Modern protection relays require accurate and fast phasor estimation under harsh transient conditions, including a decaying DC component, harmonics, interharmonics, noise, and frequency instability. The original CCHDF (Cleaned Characteristic Harmonic Digital Filter) produced a harmonic cleaned signal using the Biunivocal Frequency Relationship of Phasors (BFRP) technique, but relied on DFT, Hanning windowing, and peak detection to identify interharmonic components. This paper replaces that spectral estimation block with the Modified Covariance Method (MCM) estimator, a high resolution autoregressive (AR) spectral estimator capable of superior frequency, magnitude, and phase estimation of non-harmonic components even with a short data window. The result is an improved filter named MCCCHDF (Modified Covariance CCHDF), preserving the original algorithmic pipeline, but achieving higher accuracy and faster convergence in the presence of closely spaced harmonics/interharmonics and noisy decaying DC conditions. Full article

Background: Perceptual decision-making requires transforming sensory inputs into goal-directed actions under uncertainty. Neural oscillations in the theta band (3–7 Hz), particularly within frontal regions, have been implicated in cognitive control and decision confidence. However, whether changes in theta oscillations reflect greater effort during ambiguous decisions or more efficient control during clear conditions remains debated, and theta’s relationship to stimulus clarity is incompletely understood. Purpose: This study’s purpose was to examine how task difficulty modulates theta activity and how theta dynamics evolve across the decision-making process using two complementary analytical approaches. Methods: Electroencephalography (EEG) data were acquired from 26 healthy adults performing a face/house categorization task with images containing three levels of scrambled phase and Gaussian noise: clear (0%), moderate (40%), and high (55%). Theta dynamics were assessed from current source density (CSD) time courses of event-related potentials (ERPs) and single-trials. Statistical comparisons used Wilcoxon signed-rank tests with false discovery rate (FDR) correction for multiple comparisons. Results: Frontal theta power was greater for clear than noisy face stimuli (corrected p < 0.001), suggesting that theta activity reflects cognitive control effectiveness and decision confidence rather than processing difficulty. Connectivity decomposition revealed that frontoparietal theta coupling was modulated by stimulus clarity through both phase-locked (evoked: corrected p = 0.0085, dz = −0.61) and ongoing (induced: corrected p = 0.049, dz = −0.36) synchronization, with phase-locked coordination dominating the effect and showing opposite directionality to the induced components. Conclusions: Theta oscillations support perceptual decision-making through stimulus clarity modulation of both phase-locked and ongoing synchronization, with evoked component dominating. These findings underscore the importance of methodological choices in EEG-based connectivity research, as different analytical approaches capture different aspects of the same neural dynamics. The pattern of stronger theta activity for clear stimuli is consistent with neural processes related to decision confidence, though confidence was not measured behaviorally. Full article

Given the central importance of maritime logistics to global trade, accurate and efficient vessel motion forecasting is essential for strengthening supply chain resilience and improving operational efficiency. However, traditional physical and statistical models often fail to effectively capture the multivariate, noisy, and strongly coupled nature of maritime dynamics. In this manuscript, we adapt the DSformer architecture for ship motion forecasting, leveraging its dual sampling and dual-attention design to address the multi-scale and cross-variable dependencies inherent in maritime data. Across three real-world datasets, the adapted DSformer reduces prediction error by 23% and training time by 70% compared with 13 state-of-the-art (SOTA) baselines. Moreover, we identify a consistent relationship between sampling strategies and sea states, where dense sampling performs best under stable conditions, whereas moderately sparse sampling with multi-head attention improves robustness under turbulent environments. These results apply the algorithm’s new capabilities to the daily management of maritime logistics. By adapting the architecture to real-world operational settings and optimizing its key parameters, the approach enables efficient, real-time vessel forecasting and decision support across global supply chains. Full article

Hyperspectral image (HSI) classification is fundamental to a wide range of remote sensing applications, such as precision agriculture, environmental monitoring, and urban planning, because HSIs provide rich spectral signatures that enable the discrimination of subtle material differences. Deep learning approaches, including Convolutional Neural Networks (CNNs), Graph Convolutional Networks (GCNs), and Transformers, have achieved strong performance in learning spatial–spectral representations. However, these models often face difficulties in jointly modeling long-range dependencies, fine-grained local structures, and non-Euclidean spatial relationships, particularly when labeled training data are scarce. This paper proposes a Spectral–Spatial Graph Transformer Network (SSGTN), a dual-branch architecture that integrates superpixel-based graph modeling with Transformer-based global reasoning. SSGTN consists of four key components, namely (1) an LDA-SLIC superpixel graph construction module that preserves discriminative spectral–spatial structures while reducing computational complexity, (2) a lightweight spectral denoising module based on $1\times 1$ convolutions and batch normalization to suppress redundant and noisy bands, (3) a Spectral–Spatial Shift Module (SSSM) that enables efficient multi-scale feature fusion through channel-wise and spatial-wise shift operations, and (4) a dual-branch GCN-Transformer block that jointly models local graph topology and global spectral–spatial dependencies. Extensive experiments on three public HSI datasets (Indian Pines, WHU-Hi-LongKou, and Houston2018) under limited supervision (1% training samples) demonstrate that SSGTN consistently outperforms state-of-the-art CNN-, Transformer-, Mamba-, and GCN-based methods in overall accuracy, Average Accuracy, and the $\kappa$ coefficient. The proposed framework provides an effective baseline for HSI classification under limited supervision and highlights the benefits of integrating graph-based structural priors with global contextual modeling. Full article

Multiple-Instance Learning (MIL) is a standard paradigm for classifying gigapixel Whole-Slide Images (WSIs). However, prominent models such as Attention-Based MIL (ABMIL) treat image patches as independent instances, ignoring their inherent spatial context. More advanced frameworks like MuRCL employ reinforcement learning for instance selection but do not explicitly enforce spatial coherence, often resulting in noisy localizations. Although Graph Neural Networks (GNNs), attention smoothing, and reinforcement learning (RL) are each powerful, state-of-the-art strategies for addressing these issues individually, their integration remains a significant challenge. This paper introduces SG-MuRCL, a framework that enhances MuRCL by first employing a GNN to explicitly model spatial relationships, departing from ABMIL’s independence assumption and, second, incorporating an attention-smoothing operator to regularize the MIL aggregator, aiming to improve robustness by generating more coherent and clinically meaningful heatmaps. Empirical evaluation yielded an important finding: while the baseline MuRCL trained successfully, the integrated SG-MuRCL consistently collapsed into a trivial solution. This outcome shows that the theoretical synergy between GNNs, attention smoothing, and RL does not trivially translate into practice. The contribution of this work is therefore not a high-performing model, but a concrete demonstration of scalability and stability challenges that arise when unifying these advanced paradigms. Full article

Numerical modelling of airflow in underground mines is gaining importance in modern ventilation system design and safety assessment. Computational Fluid Dynamics (CFD) simulations enable detailed analyses of air movement, contaminant dispersion, and heat transfer, yet their reliability depends strongly on the accuracy of the geometric representation of excavations. Raw point cloud data obtained from laser scanning of underground workings are typically irregular, noisy, and contain discontinuities that must be processed before being used for CFD meshing. This study presents a methodology for automatic segmentation and regularization of large-scale point cloud data of underground excavation systems. The proposed approach is based on skeleton extraction and trajectory analysis, which enable the separation of excavation networks into individual tunnel segments and crossings. The workflow includes outlier removal, alpha-shape generation, voxelization, medial-axis skeletonization, and topology-based segmentation using neighbor relationships within the voxel grid. A proximity-based correction step is introduced to handle doubled crossings produced by the skeletonization process. The segmented sections are subsequently regularized through radial analysis and surface reconstruction to produce uniform and watertight models suitable for mesh generation in CFD software (Ansys 2024 R1). The methodology was tested on both synthetic datasets and real-world laser scans acquired in underground mine conditions. The results demonstrate that the proposed segmentation approach effectively isolates single-line drifts and crossings, ensuring continuous and smooth geometry while preserving the overall excavation topology. The developed method provides a robust preprocessing framework that bridges the gap between point cloud acquisition and numerical modelling, enabling automated transformation of raw data into CFD-ready geometric models for ventilation and safety analysis of complex underground excavation systems. Full article

Accurate state estimation is essential for the real-time operation and control of modern distribution systems characterized by high renewable energy penetration, bidirectional power flows, and volatile loads. Conventional model-driven approaches such as the Weighted Least Squares (WLS) exhibit limited robustness under noisy and sparse measurements, while existing data-driven methods often neglect critical physical constraints inherent to power systems. To address these limitations, this paper proposes a physics-constrained Graph Attention Network (GAT) framework for distribution system state estimation (DSSE) that synergistically integrates data-driven learning with physical domain knowledge. The proposed method comprises three key components: (1) a Gaussian Mixture Model (GMM)-based data augmentation strategy that captures the stochastic characteristics of loads and distributed generation to generate synthetic samples consistent with actual operating distributions; (2) a GAT-based feature extractor with topology-aware admittance matrix embedding that effectively learns spatial dependencies and structural relationships among network nodes; and (3) a physics-constrained loss function that incorporates nodal power and voltage limit penalties to enforce operational feasibility. Comprehensive evaluations on the real-world 141-bus test system demonstrate that the proposed method achieves mean absolute error (MAE) reductions of 52.4% and 45.5% for voltage magnitude and angle estimation, respectively, compared to conventional Graph Convolutional Network (GCN)-based approaches. These results validate the superior accuracy, robustness, and adaptability of the proposed framework under challenging measurement conditions. Full article

In various real-world scenarios, directed graphs can express the nature of relationships more clearly than undirected ones. Meanwhile, decentralized networks have attracted increasing attention in recent years. In decentralized directed networks (e.g., the Bitcoin Network), each user maintains only their own local view of the network. To provide better services, third-party providers often need to construct a global graph based on the local views uploaded by users for downstream graph-analysis tasks. However, directly collecting users’ local views poses significant privacy risks. For directed graphs, symmetry plays an important role in restoring data balance and preserving structural integrity. In this paper, we propose DGG-LDP, a directed graph generation algorithm based on local edge differential privacy, tailored for decentralized directed graphs. The core idea of the algorithm is to balance coarse-grained and fine-grained structural information so as to preserve geometric symmetry: we first synthesize an initial graph by collecting one round of community degree vectors, and then—guided by symmetry principles—we iteratively refine the graph using a second round of noisy community degree vectors, removing redundant asymmetric edges in the community vectors to better approximate the original graph. Additionally, the algorithm incorporates graph structure learning and graph embedding techniques to mitigate the impact of noise. Experiments on four real-world datasets demonstrate the effectiveness of the proposed method. Full article

Urban noise pollution poses a significant obstacle to sustainable development by compromising public health and well-being. Within this context, the soundscape emerges as a critical component in creating healthier and more livable cities. To further investigate the relationship between urban land-use planning characteristics and soundscape distribution, this study examines the spatial distribution of urban soundscapes and urban spatial functions. It explores the influence of urban land-use types on both the acoustic environment and soundscape perception and evaluation, aiming to better understand the influencing factors and dynamics of composite soundscapes in urban environments. The results show that (a) acoustic environment characteristics and soundscape perception evaluations are influenced by urban land-use function, exhibit a spatial aggregation effect, and are affected by the surrounding environment. (b) The key acoustic indices affecting the perception and evaluation of urban soundscapes are the equivalent continuous A-weighted sound pressure level (L_Aeq), the background sound level (L₉₀), the difference between C-weighted and A-weighted levels (L_C–L_A), and loudness. People perceive quiet environments more positively and report strong discomfort in noisy environments. (c) Urban land-use planning significantly impacts the urban soundscape, with significant differences observed in both the acoustic environment and soundscape perception evaluations across different land-use types. This study deepens the understanding of the acoustic environment and demonstrates that soundscape-oriented land-use planning can function as an effective tool for fostering inclusive, healthy, and socially sustainable communities. Full article

Quantum computers, due to their superposition and entanglement properties, provide significant advantages in solving certain problems compared with classical computers. Therefore, it is crucial to identify issues that can be efficiently solved by noisy intermediate-scale quantum (NISQ) systems. Xanadu has introduced the X8 quantum chip, based on integrated photonic technology, along with important photonic platforms such as Strawberry Fields and Gaussian Boson Sampling (GBS), to solve specific computational problems. In this review article, after reviewing Boson Sampling (BS) and Gaussian Boson Sampling (GBS), we discuss the relationship between GBS and graph theory, including how graphs can be encoded in GBS. Some applications of GBS, particularly molecular docking and molecular vibrations, are also considered. The future goal of this study is to identify problems that can be represented as small graphs and solved using GBS with a limited number of optical modes. Full article

Peer assessment has emerged as a crucial approach for scaling evaluation in educational scenarios, fostering learner engagement, critical thinking, and collaborative learning. Nevertheless, traditional aggregation-based and probabilistic methods often fail to capture the intricate relational dependencies among students and submissions, thereby limiting their capacity to ensure reliable and equitable outcomes. Recent advances in graph neural networks (GNNs) offer promising avenues for representing peer-assessment data as graphs. However, most existing approaches treat all relations uniformly, overlooking variations in the reliability of evaluative interactions. To bridge this gap, we accordingly propose ReSAN (Relation-Sensitive Assessment Network), a novel framework that integrates relation-sensitive attention into the message-passing process. ReSAN dynamically evaluates and weights relationships, enabling the model to distinguish informative signals from noisy or biased assessments. Comprehensive experiments on both synthetic and real-world datasets demonstrate that ReSAN consistently surpasses strong baselines in prediction accuracy and robustness. These findings underscore the importance of explicitly modeling evaluator reliability for effectively capturing the dynamics of peer-assessment networks. Overall, this work advances reliable graph-based evaluation methods and provides new insights into leveraging representation learning techniques for educational analytics. Full article

Accurate uncertainty estimation in unlabeled data represents a fundamental challenge in active learning. Traditional deep active learning approaches suffer from a critical limitation: uncertainty-based selection strategies tend to concentrate excessively around noisy decision boundaries, while diversity-based methods may miss samples that are crucial for decision-making. This over-reliance on confidence metrics when employing deep neural networks as backbone architectures often results in suboptimal data selection. We introduce Distance-Measured Data Mixing (DM2), a novel framework that estimates sample uncertainty through distance-weighted data mixing to capture inter-sample relationships and the underlying data manifold structure. This approach enables informative sample selection across the entire data distribution while maintaining focus on near-boundary regions without overfitting to the most ambiguous instances. To address noise and instability issues inherent in boundary regions, we propose a boundary-aware feature fusion mechanism integrated with fast gradient adversarial training. This technique generates adversarial counterparts of selected near-boundary samples and trains them jointly with the original instances, thereby enhancing model robustness and generalization capabilities under complex or imbalanced data conditions. Comprehensive experiments across diverse tasks, model architectures, and data modalities demonstrate that our approach consistently surpasses strong uncertainty-based and diversity-based baselines while significantly reducing the number of labeled samples required for effective learning. Full article

Noisy permutation channels are applied in modeling biological storage systems and communication networks. For noisy permutation channels with strictly positive and full-rank square matrices, new achievability bounds are given in this paper, which are tighter than existing bounds. To derive this bound, we use the $ϵ$-packing with Kullback–Leibler divergence as a distance and introduce a novel way to illustrate the overlapping relationship of error events. This new bound shows analytically that for such a matrix W, the logarithm of the achievable code size with a given block n and error probability $ϵ$ is closely approximated by $\ell log\left({\displaystyle \frac{\sqrt{n}}{-{\Phi }^{-1}(ϵ/G)}}\right)+logV\left(W\right)$, where $\ell =\mathsf{rank}\left(W\right)-1$, $G=2\left({\displaystyle \genfrac{}{}{0pt}{}{\ell +1}{2}}\right)$, and $V\left(W\right)$ is a characteristic of the channel referred to as channel volume ratio. Our numerical results show that the new achievability bound significantly improves the lower bound of channel coding. Additionally, the Gaussian approximation can replace the complex computations of the new achievability bound over a wide range of relevant parameters. Full article

Noisy data and outliers are among the main challenges in machine learning, as their presence in training data can significantly reduce model performance and generalization. Detecting and handling these anomalous samples is particularly difficult because it is hard to distinguish them from normal data. In this study, we propose a novel bias-based method (BT-SVR) to detect outliers and noisy inputs. The method uses a bias term derived from pairwise relationships among data points, which captures structural information about input distances. Outliers and noisy samples typically produce near-zero bias responses, allowing them to be identified effectively. A root-mean-square (RMS) scoring mechanism is then applied to quantify the anomaly strength of each sample, enabling the impact of outliers to be underweighted before training. Experiments demonstrate that BT-SVR improves the performance of Support Vector Regression (SVR) and enhances its robustness against noisy and anomalous data. Full article

Soil organic carbon (SOC) is a critical indicator of soil health, directly influencing crop productivity, soil structure, and environmental sustainability. Existing SOC estimation techniques using satellite reflectance data are effective for large-scale applications; however, their accuracy is reduced due to various types of noisy samples caused by vegetation interference, sensor-related anomalies, atmospheric effects, and other spectral distortions. This study proposes a robust data refinement framework capable of handling any soil sample, whether clean or noisy, by identifying and correcting noisy samples to enable more accurate SOC estimation outcomes. The approach first explores complex global relationships among spectral bands to understand and represent subtle patterns in soil reflectance using the Transformer network. To remove redundancy and retain only essential information of the transformed features, we apply a dimensional reduction technique for efficient analysis. Building upon this refined representation, noisy samples are detected without relying on strict data distribution assumptions, ensuring effective identification of noisy samples in diverse conditions. Finally, instead of excluding these noisy samples, the proposed framework corrects their reflectance through a conditional Generative Adversarial Network (cGAN) to align with expected soil spectral characteristics, thereby preserving valuable information for more accurate SOC estimation. The proposed approach was evaluated on benchmark satellite datasets, demonstrating superior performance over existing noise correction techniques. Experimental validation using the Landsat 8 dataset demonstrated that the proposed framework improved SOC estimation performance by increasing $R^2$ by 1.52%, reducing RMSE by 4.45%, and increasing RPD by 5.14% compared to the best baseline method (OC-SVM + Kriging). These results confirm the framework’s effectiveness in enhancing SOC estimation under noisy conditions. This scalable framework supports accurate SOC monitoring across diverse conditions, enabling informed soil management and advancing precision agriculture. Full article