Search Results (191)

Forecasting pedestrian congestion in urban back streets is challenging due to “shadow areas” where CCTV coverage is absent and trajectory data cannot be directly collected. To address these gaps, we propose the Peak-aware Graph-attention Temporal Fusion Transformer (PGTFT), a lightweight hybrid model that extends the Temporal Fusion Transformer by integrating a non-parametric attention-based Graph Convolutional Network, a peak-aware Gated Residual Network, and a Peak-weighted Quantile Loss. The model leverages both physical connectivity and functional similarity between roads through a fused adjacency matrix, while enhancing sensitivity to high-congestion events. Using real-world trajectory data from 38 CCTVs in Anyang, South Korea, experiments show that PGTFT outperforms LSTM, TFT, and GCN-TFT across different sparsity settings. Under sparse 5 m neighbor conditions, the model achieved the lowest MAE (0.059) and RMSE (0.102), while under denser 30 m settings it maintained superior accuracy with standard quantile loss. Importantly, PGTFT requires only 1.54 million parameters—about half the size of conventional Transformer–GCN hybrids—while delivering equal or better predictive performance. These results demonstrate that PGTFT is both parameter-efficient and robust, offering strong potential for deployment in smart city monitoring, emergency response, and transportation planning, as well as a practical approach to addressing data sparsity in urban sensing systems. Full article

Nanoparticles have found widespread application across diverse fields, including agriculture and animal husbandry. However, a persistent challenge in laboratory-based studies involving nanoparticle exposure is the limited availability of experimental data, which constrains the robustness and generalizability of findings. This study presents a comprehensive analysis of the impact of zinc oxide nanoparticles (ZnO NPs) in feed on elemental homeostasis in male Wistar rats. Using correlation-based network analysis, a correlation graph weight value of 15.44 and a newly proposed weighted importance score of 1.319 were calculated, indicating that a dose of 3.1 mg/kg represents an optimal balance between efficacy and physiological stability. To address the issue of limited sample size, synthetic data generation was performed using generative adversarial networks, enabling data augmentation while preserving the statistical characteristics of the original dataset. Machine learning models based on fully connected neural networks and kernel ridge regression, enhanced with a custom loss function, were developed and evaluated. These models demonstrated strong predictive performance across a ZnO NP concentration range of 1–150 mg/kg, accurately capturing the dependencies of essential element, protein, and enzyme levels in blood on nanoparticle dosage. Notably, the presence of toxic elements and some other elements at ultra-low concentrations exhibited non-random patterns, suggesting potential systemic responses or early indicators of nanoparticle-induced perturbations and probable inability of synthetic data to capture the true dynamics. The integration of machine learning with synthetic data expansion provides a promising approach for analyzing complex biological responses in data-scarce experimental settings, contributing to the safer and more effective application of nanoparticles in animal nutrition. Full article

Understanding psychological change requires a quantitative framework capable of capturing the complex and dynamic relationships among personal constructs. Personal Construct Psychology emphasizes the hierarchical reorganization of bipolar constructs, yet existing qualitative methods inadequately model the reciprocal and graded influences involved in such change. This paper introduces the Presence–Balance (PB) space, a centrality measure for constructs represented within Fuzzy Cognitive Maps (FCMs). FCMs model cognitive systems as directed, weighted graphs, allowing for nuanced analysis of construct interactions. The PB space operationalizes two orthogonal dimensions: Presence, representing the overall connectivity and activation of a construct, and Implication Balance, quantifying the directional asymmetry between influences exerted and received. By formalizing Hinkle’s hierarchical theory within a rigorous mathematical framework, the PB space enables precise identification of constructs that drive or resist transformation. This dual-dimensional model provides a structured method for analyzing personal construct systems, supporting both theoretical exploration and clinically relevant interpretations in the study of psychological change. Full article

To tackle the limitations in simultaneously modeling long-term dependencies in the time dimension and nonlinear interactions in the feature dimension, as well as their inability to fully reflect the impact of real-time load changes on spatial dependencies, a short-term multi-energy load forecasting method based on Transformer Spatio-Temporal Graph neural network (TSTG) is proposed. This method employs a multi-head spatio-temporal attention module to model long-term dependencies in the time dimension and nonlinear interactions in the feature dimension in parallel across multiple subspaces. Additionally, a dynamic adaptive graph convolution module is designed to construct adaptive adjacency matrices by combining physical topology and feature similarity, dynamically adjusting node connection weights based on real-time load characteristics to more accurately characterize the spatial dynamics of multi-energy interactions. Furthermore, TSTG adopts an end-to-end spatio-temporal joint optimization framework, achieving synchronous extraction and fusion of spatio-temporal features through an encoder–decoder architecture. Experimental results show that TSTG significantly outperforms existing methods in short-term load forecasting tasks, providing an effective solution for refined forecasting in integrated energy systems. Full article

With the rapid development of intelligent transportation systems and online ride-hailing platforms, the demand for promptly responding to passenger requests while minimizing vehicle idling and travel costs has grown substantially. This paper addresses the challenges of suboptimal vehicle path planning and partially connected pickup stations by formulating the task as a Capacitated Vehicle Routing Problem (CVRP). We propose an Improved Genetic Algorithm (IGA)-based path planning model designed to minimize total travel distance while respecting vehicle capacity constraints. To handle scenarios where certain pickup points are not directly connected, we integrate graph-theoretic techniques to ensure route continuity. The proposed model incorporates a multi-objective fitness function, a rank-based selection strategy with adjusted weights, and Dijkstra-based path estimation to enhance convergence speed and global optimization performance. Experimental evaluations on four benchmark maps from the Carla simulation platform demonstrate that the proposed approach can rapidly generate optimized multi-vehicle path planning solutions and effectively coordinate pickup tasks, achieving significant improvements in both route quality and computational efficiency compared to traditional methods. Full article

The electroencephalogram (EEG), widely used for measuring the brain’s electrophysiological activity, has been extensively applied in the automatic detection of epileptic seizures. However, several challenges remain unaddressed in prior studies on automated seizure detection: (1) Methods based on CNN and LSTM assume that EEG signals follow a Euclidean structure; (2) Algorithms leveraging graph convolutional networks rely on adjacency matrices constructed with fixed edge weights or predefined connection rules. To address these limitations, we propose a novel algorithm: Dynamic Graph Convolutional Network with Dilated Convolution (DGDCN). By leveraging a spatiotemporal attention mechanism, the proposed model dynamically constructs a task-specific adjacency matrix, which guides the graph convolutional network (GCN) in capturing localized spatial and temporal dependencies among adjacent nodes. Furthermore, a dilated convolutional module is incorporated to expand the receptive field, thereby enabling the model to capture long-range temporal dependencies more effectively. The proposed seizure detection system is evaluated on the TUSZ dataset, achieving AUC values of 88.7% and 90.4% on 12-s and 60-s segments, respectively, demonstrating competitive performance compared to current state-of-the-art methods. Full article

The dynamic scheduling optimization of sports facilities faces challenges posed by real-time demand fluctuations and complex interdependencies between facilities. To address the adaptability limitations of traditional centralized approaches, this study proposes a decentralized multi-agent reinforcement learning framework based on graph neural networks (GNNs). Experimental results demonstrate that in a simulated environment comprising 12 heterogeneous sports facilities, the proposed method achieves an operational efficiency of 0.89 ± 0.02, representing a 13% improvement over Centralized PPO, while user satisfaction reaches 0.85 ± 0.03, a 9% enhancement. When confronted with a sudden 30% surge in demand, the system recovers in just 90 steps, 33% faster than centralized methods. The GNN attention mechanism successfully captures critical dependencies between facilities, such as the connection weight of 0.32 ± 0.04 between swimming pools and locker rooms. Computational efficiency tests show that the system maintains real-time decision-making capability within 800 ms even when scaled to 50 facilities. These results verify that the method effectively balances decentralized decision-making with global coordination while maintaining low communication overhead (0.09 ± 0.01), offering a scalable and practical solution for resource management in complex built environments. Full article

Situation awareness (SA) involves analyzing sensory data, such as audio signals, to identify anomalies. While acoustic features are widely used in audio analysis, existing methods face critical limitations; they often overlook the relevance of SA audio segments, failing to capture the complex relational patterns in audio data that are essential for SA. In this study, we first propose a graph neural network (GNN) with an attention mechanism that models SA audio features through graph structures, capturing both node attributes and their relationships for richer representations than traditional methods. Our analysis identifies suitable audio feature combinations and graph constructions for SA tasks. Building on this, we introduce a situation awareness gated-attention GNN (SAGA-GNN), which dynamically filters irrelevant nodes through max-relevance neighbor sampling to reduce redundant connections, and a learnable edge gated-attention mechanism that suppresses noise while amplifying critical events. The proposed method employs sigmoid-activated attention weights conditioned on both node features and temporal relationships, enabling adaptive node emphasizing for different acoustic environments. Experiments reveal that the proposed graph-based audio features demonstrate superior representation capacity compared to traditional methods. Additionally, both proposed graph-based methods outperform existing approaches. Specifically, owing to the combination of graph-based audio features and dynamic selection of audio nodes based on gated-attention, SAGA-GNN achieved superior results on two real datasets. This work underscores the importance and potential value of graph-based audio features and attention mechanism-based GNNs, particularly in situational awareness applications. Full article

This study examines the evolution of public debt among the 27 EU member states using Graph Theory tools; the Threshold Weighted–Minimum Dominating Set (TW–MDS) and the k-core decomposition method, alongside a standard network quantitative metric, the density. By separating the data into three distinct periods, pre-crisis (2000–2007), European sovereign debt crisis (2008–2015), and post-crisis (2016–2023), we examine the potential synchronization of the debt ratios among EU countries through cross-correlations of the public debts. The findings reveal that public debt correlation was at its highest level during the 2008–2015 period, reflecting the universal impact of the crisis and the subsequent synchronized fiscal and monetary policy measures taken within EU. A significantly lower network density is observed in both the pre- and post-crisis periods. These results contribute to the overall debate on fiscal stability and policy coordination by showing how EU countries tend to align their fiscal behaviors during periods of crisis while behaving more independently during stable times. In addition, we yield a deeper insight into how economic shocks reorganize public debt interconnections within the crisis period. Finally, this analysis highlights to what extent European economic integration strengthens connections between the fiscal positions (through public debt) of the European Union member countries. Full article

This paper addresses the central issue arising from the (SDAC) of facial expressions, namely, to balance the competing demands of good global features for detection, and fine features for good facial expression classifications by replacing the feature extraction part of the “neck” network in the feature pyramid network in the You Only Look Once X (YOLOX) framework with a novel architecture involving three attention mechanisms—batch, channel, and neighborhood—which respectively explores the three input dimensions—batch, channel, and spatial. Correlations across a batch of images in the individual path of the dual incoming paths are first extracted by a self attention mechanism in the batch dimension; these two paths are fused together to consolidate their information and then split again into two separate paths; the information along the channel dimension is extracted using a generalized form of channel attention, an adaptive graph channel attention, which provides each element of the incoming signal with a weight that is adapted to the incoming signal. The combination of these two paths, together with two skip connections from the input to the batch attention to the output of the adaptive channel attention, then passes into a residual network, with neighborhood attention to extract fine features in the spatial dimension. This novel dual path architecture has been shown experimentally to achieve a better balance between the competing demands in an SDAC problem than other competing approaches. Ablation studies enable the determination of the relative importance of these three attention mechanisms. Competitive results are obtained on two non-aligned face expression recognition datasets, RAF-DB and SFEW, when compared with other state-of-the-art methods. Full article

Accurate vehicle type recognition in low-light environments remains a critical challenge for intelligent transportation systems (ITSs). To address the performance degradation caused by insufficient lighting, complex backgrounds, and light interference, this paper proposes a Twin-Stream Feature Fusion Graph Neural Network (TFF-Net) model. The model employs multi-scale convolutional operations combined with an Efficient Channel Attention (ECA) module to extract discriminative local features, while independent convolutional layers capture hierarchical global representations. These features are mapped as nodes to construct fully connected graph structures. Hybrid graph neural networks (GNNs) process the graph structures and model spatial dependencies and semantic associations. TFF-Net enhances the representation of features by fusing local details and global context information from the output of GNNs. To further improve its robustness, we propose an Adaptive Weighted Fusion-Bagging (AWF-Bagging) algorithm, which dynamically assigns weights to base classifiers based on their F1 scores. TFF-Net also includes dynamic feature weighting and label smoothing techniques for solving the category imbalance problem. Finally, the proposed TFF-Net is integrated into YOLOv11n (a lightweight real-time object detector) with an improved adaptive loss function. For experimental validation in low-light scenarios, we constructed the low-light vehicle dataset VDD-Light based on the public dataset UA-DETRAC. Experimental results demonstrate that our model achieves 2.6% and 2.2% improvements in mAP50 and mAP50-95 metrics over the baseline model. Compared to mainstream models and methods, the proposed model shows excellent performance and practical deployment potential. Full article

This study focuses on the systematic conservation of historical architectural heritage in Heilongjiang Province, particularly addressing the challenges of point-based protection and spatial fragmentation. It explores the construction of a connected and conductive heritage corridor network, using historical building clusters across the province as empirical cases. A comprehensive analytical framework is established by integrating the nearest neighbor index, kernel density estimation, minimum cumulative resistance (MCR) model, entropy weighting, circuit theory, and network structure metrics. Kernel density analysis reveals a distinct spatial aggregation pattern, characterized by “one core, multiple zones.” Seven resistance factors—including elevation, slope, land use, road networks, and service accessibility—are constructed, with weights assigned through an entropy-based method to generate an integrated resistance surface and suitability map. Circuit theory is employed to simulate cultural “current” flows, identifying 401 potential corridors at the provincial, municipal, and district levels. A hierarchical station system is further developed based on current density, forming a coordinated structure of primary trunks, secondary branches, and complementary nodes. The corridor network’s connectivity is evaluated using graph-theoretic indices (α, β, and γ), which indicate high levels of closure, structural complexity, and accessibility. The results yield the following key findings: (1) Historical architectural resources in Heilongjiang demonstrate significant coupling with the Chinese Eastern Railway and multi-ethnic cultural corridors, forming a “one horizontal, three vertical” spatial configuration. The horizontal axis (Qiqihar–Harbin–Mudanjiang) aligns with the core cultural route of the railway, while the three vertical axes (Qiqihar–Heihe, Harbin–Heihe, and Mudanjiang–Luobei) correspond to ethnic cultural pathways. This forms a framework of “railway as backbone, ethnicity as wings.” (2) Comparative analysis of corridor paths, railways, and highways reveals structural mismatches in certain regions, including absent high-speed connections along northern trunk lines, insufficient feeder lines in secondary corridors, sparse terminal links, and missing ecological stations near regional boundaries. To address these gaps, a three-tier transportation coordination strategy is recommended: it comprises provincial corridors linked to high-speed rail, municipal corridors aligned with conventional rail, and district corridors connected via highway systems. Key enhancement zones include Yichun–Heihe, Youyi–Hulin, and Hegang–Wuying, where targeted infrastructure upgrades and integrated station hubs are proposed. Based on these findings, this study proposes a comprehensive governance paradigm for heritage corridors that balances multi-level coordination (provincial–municipal–district) with ecological planning. A closed-loop strategy of “identification–analysis–optimization” is developed, featuring tiered collaboration, cultural–ecological synergy, and multi-agent dynamic evaluation. The framework provides a replicable methodology for integrated protection and spatial sustainability of historical architecture in Heilongjiang and other cold-region contexts. Full article

A new multi-robot path planning (MRPP) algorithm for 2D static environments was developed and evaluated. It combines a roadmap method, utilising the visibility graph (VG), with the algebraic connectivity (second smallest eigenvalue (λ₂)) of the graph’s Laplacian and Dijkstra’s algorithm. The paths depend on the planning order, i.e., they are in sequence path-by-path, based on the measured values of algebraic connectivity of the graph’s Laplacian and the determined weight functions. Algebraic connectivity maintains robust communication between the robots during their navigation while avoiding collisions. The algorithm efficiently balances connectivity maintenance and path length minimisation, thus improving the performance of path finding. It produced solutions with optimal paths, i.e., the shortest and safest route. The devised MRPP algorithm significantly improved path length efficiency across different configurations. The results demonstrated highly efficient and robust solutions for multi-robot systems requiring both optimal path planning and reliable connectivity, making it well-suited in scenarios where communication between robots is necessary. Simulation results demonstrated the performance of the proposed algorithm in balancing the path optimality and network connectivity across multiple static environments with varying complexities. The algorithm is suitable for identifying optimal and complete collision-free paths. The results illustrate the algorithm’s effectiveness, computational efficiency, and adaptability. Full article

Background: Both aging and cognitive fatigue are significant factors influencing alpha activity in the brain. However, the interactive effects of age and mental fatigue on the alpha spectrum and functional connectivity have not been fully elucidated. Methods: Using resting-state EEG data from an open-access dataset (younger: N = 198; older: N = 227) collected before and after a 2 h cognitive task block, we systematically examined the effects of aging and mental fatigue on alpha (8–13 Hz) oscillations via an aperiodic-corrected power spectrum, the weighted phase lag index (wPLI), and graph theory analysis. Results: In both spectral power and network efficiency, mental fatigue primarily modulates low alpha in younger individuals, while high alpha reflects stable age-related changes. The aperiodic offset and exponent decrease with age, while mental fatigue leads to an increase in the exponent. Notable interactions between age and mental fatigue are observed in low-alpha power, the aperiodic exponent, and the network efficiency of both low- and high-alpha bands. Conclusions: This study provides valuable insights into the differential modulation patterns of alpha activity by age and mental fatigue, as well as their interactions. These findings advance our understanding of how aging and mental fatigue differentially and interactively shape neural dynamics. Full article

To enhance the adaptability of grid partitioning under transient scenarios, this paper proposes a two-stage dynamic partitioning strategy based on structure–function coupling. Electrical coupling strength is first characterized using short-circuit impedance and the sensitivity between reactive power and voltage, while transient voltage correlation is incorporated through cosine similarity as edge weights in a graph model. Grid partitioning is then conducted by maximizing modularity through a staged approach that ensures network connectivity and automatically determines partition numbers. Case studies on the modified IEEE 39-bus system demonstrate that compared with transient voltage-based partitioning and conventional complex network methods, the proposed approach improves modularity by 69%, reduces the maximum post-fault voltage deviation by 38.6%, and achieves the highest regional decoupling rate. The result shows strong intra-regional cohesion and weak inter-regional connectivity, verifying the strategy’s effectiveness in enhancing adaptability and decoupling under transient conditions. Full article