Search Results (227)

This paper addresses the problem of decision-making support for the modernization of distributed automated control systems (ACS) in power engineering by proposing an integral quality criterion that combines similarity-driven Markov process modeling with geometric programming. The methodology transforms the transition rate matrix of a continuous-time Markov chain (CTMC) into a matrix polynomial, enabling the derivation of normalized similarity indices and the development of a criterion-based model to quantify relative variations in system quality without requiring global optimization. The proposed approach yields a generalized criterion model that facilitates the ranking of modernization alternatives and the evaluation of the sensitivity of optimal decisions to parameter variations. The practical implementation is demonstrated through updated state transition graphs, quality functions, and UML-based architectures of diagnostic-ready evaluation modules. The scientific contribution of this work lies in the integration of similarity-based Markov modeling with the mathematical framework of geometric programming into a unified criterion model for the quantitative assessment of functional readiness under multistate conditions and probabilistic failures. The methodology enables the comparison of modernization scenarios using a unified integral indicator, assessment of sensitivity to structural and parametric changes, and seamless integration of quality evaluation into SCADA/Smart Grid environments as part of real-time diagnostics. The accuracy of the assessment depends on the adequacy of transition rate identification and the validity of the Markovian assumption. Future extensions include the real-time estimation of transition rates from event streams, generalization to semi-Markov processes, and multicriteria optimization considering cost, risk, and readiness. Full article

In this paper, we propose a novel speech emotion recognition model, named MAGTF-Net (Multi-scale Attention Graph Transformer Fusion Network), which addresses the challenges faced by traditional hand-crafted feature-based approaches in modeling complex emotional nuances and dynamic contextual dependencies. Although existing state-of-the-art methods have achieved improvements in recognition performance, they often fail to simultaneously capture both local acoustic features and global temporal structures, and they lack adaptability to variable-length speech utterances, thereby limiting their accuracy and robustness in recognizing complex emotional expressions. To tackle these challenges, we design a log-Mel spectrogram feature extraction branch that combines a Multi-scale Attention Graph (MAG) structure with a Transformer encoder, where the Transformer module adaptively performs dynamic modeling of speech sequences with varying lengths. In addition, a low-level descriptor (LLD) feature branch is introduced, where a multilayer perceptron (MLP) is employed for complementary feature modeling. The two feature branches are fused and subsequently classified through a fully connected layer, further enhancing the expressive capability of emotional representations. Moreover, a label-smoothing-enhanced cross-entropy loss function is adopted to improve the model’s recognition performance on difficult-to-classify emotional categories. Experiments conducted on the IEMOCAP dataset demonstrate that MAGTF-Net achieves weighted accuracy (WA) and unweighted accuracy (UA) scores of 69.15% and 70.86%, respectively, outperforming several baseline models. Further ablation studies validate the significant contributions of each module in the Mel-spectrogram branch and the LLD feature branch to the overall performance improvement. The proposed method effectively integrates local, global, and multi-source feature information, significantly enhancing the recognition of complex emotional expressions and providing new theoretical and practical insights for the field of speech emotion recognition. Full article

The increasing scale and operational complexity of cyberattacks have exposed the limitations of static taxonomies for representing multistage threat scenarios. This study addresses the need for more flexible classification models by proposing a relational taxonomy of cyberattacks grounded in documented incidents. Therefore, the main objective is to propose a relational taxonomy that encodes direct transitions across eight groups in a dependency matrix and a directed graph while preserving traceability to MITRE ATT&CK. The taxonomy was validated by an independent panel of experts who assessed methodological clarity and operational utility. The results reveal consistent transition patterns across groups, delineate reproducible escalation routes, and pinpoint cut-off points linked to specific detection and control activities, providing an operational map of progression and intervention. The conclusions show that the taxonomy clarifies escalation paths, strengthens alignment across security monitoring and incident response functions, threat intelligence workflows and training, and provides an operational structure to manage interdependencies, anticipate escalation and focus monitoring on critical points. Full article

Background/Objectives: Major depressive disorder (MDD) and metabolic syndrome (MetS) are highly prevalent, bidirectionally linked conditions. Individuals with MetS are at increased risk of developing depression, while depression predisposes to metabolic dysfunction. Evidence suggests that comorbid MDD and MetS present a distinct psychopathological profile, with neurovegetative symptoms such as fatigue, sleep disturbances, and appetite dysregulation being more prominent. This study aimed to determine whether depressive symptom structures differ between MDD patients with and without MetS, applying Bayesian network methods to uncover probabilistic dependencies that may inform precision psychiatry. Methods: Data were drawn from 1779 adults with ICD-10-diagnosed MDD in the 2013–2020 National Health and Nutrition Examination Survey (NHANES). Using standard metabolic criteria, participants were categorized as MetS (n = 315) or non-MetS (n = 1464). Depressive symptoms were assessed with the Patient Health Questionnaire (PHQ-9). Directed Acyclic Graphs (DAGs) were estimated via a hill-climbing algorithm with 5000 bootstrap replications to ensure network stability. Results: MetS patients displayed a denser and more interconnected symptom network. Fatigue (PHQ4) emerged as a central hub linking sleep, appetite, cognition, and functional impairment. In contrast, non-MetS patients showed a more fragmented network dominated by affective symptoms (low mood, anhedonia) and negative self-cognitions. Conclusions: Depressive symptoms propagate differently depending on metabolic status. These results highlight the value of personalized medicine approaches, advocating for treatment strategies that address neurovegetative dysfunctions in MDD with MetS and affective-cognitive symptoms in non-MetS. Aligning interventions with individual symptom architectures and metabolic profiles may enhance therapeutic precision and improve clinical outcomes. Full article

Accurate water-level prediction is a critical component for ensuring safe maritime navigation, optimizing port operations, and mitigating coastal flooding risks. However, the complex, non-linear spatiotemporal dynamics of water systems pose significant challenges for current forecasting models. The proposed framework introduces three key innovations. First, a dual-weight graph construction mechanism integrates geographical proximity with Dynamic Time Warping (DTW)-derived temporal similarity to better represent hydrodynamic connectivity in coastal and estuarine environments. Second, a state-aware weighted loss function is designed to enhance predictive accuracy during critical hydrological events, such as storm surges and extreme tides, by prioritizing the reduction in errors in these high-risk periods. Third, the WS-STGTN architecture combines graph attention with temporal self-attention to capture long-range dependencies in both space and time. Extensive experiments are conducted using water-level data from five stations in the tidal-influenced lower Yangtze River, a vital artery for shipping and a region susceptible to coastal hydrological extremes. The results demonstrate that the model consistently surpasses a range of baseline methods. Notably, the WS-STGTN achieves an average reduction in Mean Squared Error (MSE) of 27.6% compared to the standard Transformer model, along with the highest coefficient of determination ($R^2\approx 0.96$) across all datasets, indicating its stronger explanatory power for observed water-level variability. This work provides a powerful tool that can be directly applied to improve coastal risk management, marine navigation safety, and the operational planning of port and coastal engineering projects. Full article

Multi-agent inverse reinforcement learning (MA-IRL) infers the underlying reward functions or objectives of multiple agents by observing their behavioral data, thereby providing insights into collaboration, competition, or mixed interaction strategies among agents, and addressing the symmetrical ambiguity problem where multiple rewards may correspond to the same strategy. However, most existing algorithms mainly focus on solving cooperative and non-cooperative tasks among homogeneous multi-agent systems, making it difficult to adapt to the dynamic topologies and heterogeneous behavioral strategies of multi-agent systems in real-world applications. This makes it difficult for the algorithm to adapt to scenarios with locally sparse interactions and dynamic heterogeneity, such as autonomous driving, drone swarms, and robot clusters. To address this problem, this study proposes a dynamic heterogeneous multi-agent inverse reinforcement learning framework (GAMF-DHIRL) based on a graph attention mean field (GAMF) to infer the potential reward functions of agents. In GAMF-DHIRL, we introduce a graph attention mean field theory based on adversarial maximum entropy inverse reinforcement learning to dynamically model dependencies between agents and adaptively adjust the influence weights of neighboring nodes through attention mechanisms. Specifically, the GAMF module uses a dynamic adjacency matrix to capture the time-varying characteristics of the interactions among agents. Meanwhile, the typed mean-field approximation reduces computational complexity. Experiments demonstrate that the proposed method can efficiently recover reward functions of heterogeneous agents in collaborative tasks and adversarial environments, and it outperforms traditional MA-IRL methods. Full article

On GPU-based clusters, the training workloads of machine learning (ML) models, particularly neural networks (NNs), are often structured as Directed Acyclic Graphs (DAGs) and typically deployed for parallel execution across heterogeneous GPU resources. Efficient scheduling of these workloads is crucial for optimizing performance metrics such as execution time, under various constraints including GPU heterogeneity, network capacity, and data dependencies. DAG-structured ML workload scheduling could be modeled as a Nonlinear Integer Program (NIP) problem, and is shown to be NP-complete. By leveraging a positive correlation between Scheduling Plan Distance (SPD) and Finish Time Gap (FTG) identified through an empirical study, we propose to develop a Running Time Gap Strategy for scheduling based on Whale Optimization Algorithm (WOA) and Reinforcement Learning, referred to as WORL-RTGS. The proposed method integrates the global search capabilities of WOA with the adaptive decision-making of Double Deep Q-Networks (DDQN). Particularly, we derive a novel function to generate effective scheduling plans using DDQN, enhancing adaptability to complex DAG structures. Comprehensive evaluations on practical ML workload traces collected from Alibaba on simulated GPU-enabled platforms demonstrate that WORL-RTGS significantly improves WOA’s stability for DAG-structured ML workload scheduling and reduces completion time by up to 66.56% compared with five state-of-the-art scheduling algorithms. Full article

A clustering ensemble, which leverages multiple base clusterings to obtain a reliable consensus result, is a critical challenging task for Earth observation in remote sensing applications. With the development of multi-source remote sensing data, exploring the underlying graph-structured patterns has become increasingly important. However, existing clustering ensemble methods mostly employ shallow clustering in the base clustering generation stage, which fails to utilize the structural information. Moreover, the high dimensionality inherent in data further increases the difficulty of clustering. To address these problems, we propose a novel method termed Global Self-Attention-driven Graph Clustering Ensemble (GSAGCE). Specifically, GSAGCE firstly adopts basic autoencoders and global self-attention graph autoencoders (GSAGAEs) to extract node attribute information and structural information, respectively. GSAGAEs not only enhance structural information in the embedding but also have the capability to capture long-range vertex dependencies. Next, we employ a fusion strategy to adaptively fuse this dual information by considering the importance of nodes through an attention mechanism. Furthermore, we design a self-supervised strategy to adjust the clustering distribution, which integrates the attribute and structural embeddings as more reliable guidance to produce base clusterings. In the ensemble strategy, we devise a double-weighted graph partitioning consensus function that simultaneously considers both global and local diversity within the base clusterings to enhance the consensus performance. Extensive experiments on benchmark datasets demonstrate the superiority of GSAGCE compared to other state-of-the-art methods. Full article

Based on the analysis of grooves of regular and partially regular microreliefs formed on flat surfaces, the relationship between the geometric parameters of the grooves of their microreliefs, which ensures their regularity, was revealed. The functionality of the existing parameter for assessing the oil capacity of the surface of the relative area of the grooves of the microrelief was analyzed. It was proved that the parameter—the relative area of the grooves of the microrelief—is insensitive to their distribution on the plane. A new graph-analytical method for determining the planar heterogeneity of the distribution of the area of the grooves of the microreliefs was developed. A numerical parameter—the coefficient of planar heterogeneity, which determines the uniformity of the distribution of the area of the grooves on the plane, was also substantiated. The effectiveness of the new approach was demonstrated and proven. Graphs of longitudinal and transverse planar heterogeneity of the main forms of the grooves of the microreliefs were constructed, which will eliminate the need to obtain complex analytical dependencies to determine the area of these grooves. By analyzing the graphs of planar heterogeneity, numerical values of the heterogeneity coefficient were determined—a parameter that characterizes the homogeneity of microrelief grooves in the axial and interaxial directions. It is proposed to search for optimal placement schemes of adjacent microrelief grooves on the plane based on the analysis of their planar heterogeneity coefficients. This will ensure an increase in the plane heterogeneity coefficient from 0.69 to 0.97 for the triangular shape of the grooves, from 0.87 to 0.83 for the sinusoidal and from 0.46 to 0.69 for the groove shape in the form of a truncated cycloid, with the same relative areas of the microrelief. Full article

Current federated identity management systems lack contextual awareness of workflows across independent systems, creating security gaps and workflow integrity challenges. This article details the design and implementation of Alohomora, a distributed workflow-aware authentication system that maintains cross-system workflow context through path-bound tokens. Alohomora complements existing identity providers such as OAuth and SAML by adding workflow orchestration capabilities while leveraging standard authentication protocols for initial user verification. The system introduces workflow graphs as a formal model for representing dependencies between functions across heterogeneous systems and employs a distributed caching architecture with collaboration groups for scalable session management. In a typical deployment scenario, an employee onboarding workflow across human resources services, account provisioning, and benefits systems forms a trust group where Alohomora enforces ordered step execution, validates prerequisite completion at each transition, and generates cryptographic completion assertions upon workflow finalization. Extensive performance evaluation under concurrent user requests demonstrates polynomial performance characteristics with superior scalability compared to centralized OAuth introspection. The results show that Alohomora maintains high throughput under heavy load while providing strong, secure access control through workflow path binding and distributed trust orchestration. The prototype implementation is available as open source. Full article

The scalability of coordination policies is a critical challenge in swarm robotics, where agent numbers may vary substantially between deployment scenarios. Reinforcement learning (RL) offers a promising avenue for learning decentralized policies from local interactions, yet a fundamental question remains: can policies trained on one swarm size transfer to different population scales without retraining? This zero-shot transfer problem is particularly challenging because the traditional RL approaches learn fixed-dimensional representations tied to specific agent counts, making them brittle to population changes at deployment time. While existing work addresses scalability through population-aware training (e.g., mean-field methods) or multi-size curricula (e.g., population transfer learning), these approaches either impose restrictive assumptions or require explicit exposure to varied team sizes during training. Graph Neural Networks (GNNs) offer a fundamentally different path. Their permutation invariance and ability to process variable-sized graphs suggest potential for zero-shot generalization across swarm sizes, where policies trained on a single population scale could deploy directly to larger or smaller teams. However, this capability remains largely unexplored in the context of swarm coordination. For this reason, we empirically investigate this question by combining GNNs with deep Q-learning in cooperative swarms. We focused on well-established 2D navigation tasks that are commonly used in the swarm robotics literature to study coordination and scalability, providing a controlled yet meaningful setting for our analysis. To address this, we introduce Deep Graph Q-Learning (DGQL), which embeds agent-neighbor graphs into Q-learning and trains on fixed-size swarms. Across two benchmarks (goal reaching and obstacle avoidance), we deploy up to three times larger teams. The DGQL preserves a functional coordination without retraining, but efficiency degrades with size. The ultimate goal distance grows monotonically (15–29 agents) and worsens beyond roughly twice the training size ($\approx 20$ agents), with task-dependent trade-offs. Our results quantify scalability limits of GNN-enhanced DQL and suggest architectural and training strategies to better sustain performance across scales. Full article

The power system, as a critical national infrastructure, faces stealthy and persistent intrusions from Advanced Persistent Threat (APT) attacks. These attack chains span multiple stages and components, while heterogeneous data sources lack unified semantics, limiting the interpretability of current detection methods. To address this, we combine the W3C PROV-DM standard with power-specific semantics to map generic provenance data into standardized provenance graphs. On this basis, we propose a graph neural network framework that jointly models temporal dependencies and structural features. The framework constructs unified provenance graphs with snapshot partitioning, applies Functional Time Encoding (FTE) for temporal modeling, and employs a graph attention autoencoder with node masking and edge reconstruction to enhance feature representations. Through pooling, graph-level embeddings are obtained for downstream detection. Experiments on two public datasets show that our method outperforms baselines across multiple metrics and exhibits clear inter-class separability. In the context of scarce power-domain APT data, this study improves model applicability and interpretability, and it provides a practical path for provenance graph-based intelligent detection in critical infrastructure protection. Full article

Building clustering is a key challenge in cartographic generalization, where the goal is to group spatially related buildings into semantically coherent clusters while preserving the true distribution patterns of urban structures. Existing methods often rely on either spatial distance or building feature similarity alone, leading to clusters that sacrifice either accuracy or spatial continuity. Moreover, most deep learning-based approaches, including graph attention networks (GATs), fail to explicitly incorporate spatial distance constraints and typically restrict message passing to first-order neighborhoods, limiting their ability to capture long-range structural dependencies. To address these issues, this paper proposes LA-GATs, a multi-feature constrained and spatially adaptive building clustering network. First, a Delaunay triangulation is constructed based on nearest-neighbor distances to represent spatial topology, and a heterogeneous feature matrix is built by integrating architectural spatial features, including compactness, orientation, color, and height. Then, a spatial distance-constrained attention mechanism is designed, where attention weights are adjusted using a distance decay function to enhance local spatial correlation. A second-order neighborhood aggregation strategy is further introduced to extend message propagation and mitigate the impact of triangulation errors. Finally, spectral clustering is performed on the learned similarity matrix. Comprehensive experimental validation on real-world datasets from Xi’an and Beijing, showing that LA-GATs outperforms existing clustering methods in both compactness, silhouette coefficient and adjusted rand index, with up to about 21% improvement in residential clustering accuracy. Full article

Reservoir computing is an approach to machine learning that leverages the dynamics of a complex system alongside a simple, often linear, machine learning model for a designated task. While many efforts have previously focused their attention on integrating neurons, which produce an output in response to large, sustained inputs, we focus on using differentiating neurons, which produce an output in response to large changes in input. Here, we introduce a small-world graph built from rings of differentiating neurons as a Reservoir Computing substrate. We find the coupling strength and network topology that enable these small-world networks to function as an effective reservoir. The dynamics of differentiating neurons naturally give rise to oscillatory dynamics when arranged in rings, where we study their computational use in the Reservoir Computing setting. We demonstrate the efficacy of these networks in the MNIST digit recognition task, achieving comparable performance of 90.65% to existing Reservoir Computing approaches. Beyond accuracy, we conduct systematic analysis of our reservoir’s internal dynamics using three complementary complexity measures that quantify neuronal activity balance, input dependence, and effective dimensionality. Our analysis reveals that optimal performance emerges when the reservoir operates with intermediate levels of neural entropy and input sensitivity, consistent with the edge-of-chaos hypothesis, where the system balances stability and responsiveness. The findings suggest that differentiating neurons can be a potential alternative to integrating neurons and can provide a sustainable future alternative for power-hungry AI applications. Full article

Cell–cell interactions play a pivotal role in maintaining tissue homeostasis and driving disease progression. Conventional Cell–cell interactions modeling approaches depend on ligand–receptor databases, which often fail to capture context-specific or newly emerging signaling mechanisms. To address this limitation, we propose a data-driven computational framework, data-driven cell–cell interaction inference (DD-CC-II), which employs a graph-based model using eigen-cells to represent cell groups. DD-CC-II uses eigen-cells (i.e., functional module within the cell population) to characterize cell groups and construct correlation coefficient networks to model between-group associations. Correlation coefficient networks between eigen-cells are constructed, and their statistical significance is evaluated via over-representation analysis and hypergeometric testing. Monte Carlo simulations demonstrate that DD-CC-II achieves superior performance in inferring CCIs compared with ligand–receptor-based methods. The application to whole-blood RNA-seq data from the Japan COVID-19 Task Force revealed severity stage-specific interaction patterns. Markers such as FOS, CXCL8, and HLA-A were associated with high severity, whereas IL1B, CD3D, and CCL5 were related to low severity. The systemic lupus erythematosus pathway emerged as a potential immune mechanism underlying disease severity. Overall, DD-CC-II provides a data-centric approach for mapping the cellular communication landscape, facilitating a better understanding of disease progression at the intercellular level. Full article