Search Results (15)

Background/Objectives: This study introduces a reproducible and interpretable graph-based framework for resting-state functional near-infrared spectroscopy (fNIRS) that enables network-level biomarker discovery for Alzheimer’s disease (AD). Although resting-state fNIRS is well suited for task-free assessment, most existing approaches rely on static channel-wise features or conventional functional connectivity, limiting insight into coordinated network dynamics and reproducibility. Methods: Resting-state prefrontal fNIRS signals were represented as subject-level graphs in which edges captured coordinated fluctuations of nonlinear signal complexity across channels, computed using sliding-window analysis. Graph neural networks (GNNs) were employed as analytical tools to identify disease-stage-related network patterns. Interpretability was assessed using edge-level importance measures, and reproducibility was evaluated through fold-wise stability analysis and consensus network construction. Results: The proposed complexity–fluctuation-based graph representation consistently outperformed conventional amplitude-based functional connectivity. Statistically supported prefrontal network biomarkers distinguishing mild cognitive impairment (MCI) from healthy aging were identified, with statistically significant group differences (p = 0.001). In contrast, network patterns associated with Alzheimer’s disease were more heterogeneous and less consistently expressed. Consensus analysis revealed a subset of prefrontal connections repeatedly selected across cross-validation folds, and attention-based network patterns showed strong spatial correspondence with statistically derived biomarkers. Conclusions: This study establishes a reproducible and interpretable framework for resting-state fNIRS analysis that emphasizes coordinated complexity dynamics rather than classification accuracy. The results indicate that network-level alterations are most consistently expressed at the MCI stage, highlighting its role as a critical transitional state and supporting the potential of the proposed approach for longitudinal monitoring and clinically applicable fNIRS-based assessment of neurodegenerative disease. Full article

This paper tackles the growing uncertainty in distribution networks caused by distributed generation, load fluctuations, and frequent topological changes. It proposes a multi-source data fusion framework using enhanced selective convolution (SKNet) and graph attention networks (GAT). First, heterogeneous measurement data, including Phasor Measurement Unit (PMU) and Supervisory Control and Data Acquisition (SCADA) data, are processed through a unified normalization and outlier elimination technique to ensure data quality. Second, SKNet is utilized to extract spatiotemporal multi-scale features, improving the detection of both rapid disturbances and long-term trends. Third, the extracted features are fed into GAT to model node electrical couplings, while power flow residual constraints are embedded in the loss function to enforce the physical validity of the estimated states. This physics-informed design overcomes a key limitation of pure data-driven models and enables an end-to-end framework that integrates data-driven learning with physical mechanism constraints. Finally, comprehensive validation is performed on the improved IEEE 33-node and IEEE 123-node test systems. The test scenarios include Gaussian measurement noise, data outliers, missing measurements, and topological changes. The results show that the proposed method outperforms baseline models such as Multi-Scale Graph Attention Network (MS-GAT), Bidirectional Long Short-Term Memory (BiLSTM), and traditional weighted least squares (WLS). It achieves Root Mean Square Error (RMSE) reductions of up to 18% and Mean Absolute Error (MAE) reductions of up to 15%. The average inference latency is only 10–18 ms. Even under unknown topological changes, the estimation error increases by only 15–25%. These results demonstrate the superior accuracy, robustness, and real-time performance of the proposed method for intelligent distribution network state estimation. Full article

Automatic sleep staging technology based on wearable photoplethysmography can provide a non-invasive and continuous solution for large-scale sleep health monitoring. This study accordingly developed a novel cross-scale dynamically coupled extended long short-term memory network (SleepXLSTM) to realize automatic sleep staging based on heart rate signals collected by wearable devices. SleepXLSTM models the relationship between heart rate fluctuations and sleep stage labels by correlating physiological features with clinical semantics using a knowledge graph neural network. Furthermore, an excitation–inhibition dual-effect regulator is applied in an improved multiplicative long short-term memory network along with memory mixing in a scalar long short-term memory network to extract and strengthen the key heart rate timing features while filtering out noise produced by motion artifacts, thereby facilitating subsequent high-precision sleep staging. The benefits and functions of this comprehensive heart rate feature extraction were demonstrated using sleep staging prediction and ablation experiments. The proposed model exhibited a superior accuracy of 91.25% and Cohen’s kappa coefficient of 0.876 compared to an extant state-of-the-art neural network sleep staging model with an accuracy of 69.80% and kappa coefficient of 0.040. On the ISRUC-Sleep dataset, the model achieved an accuracy of 87.51% and F1 score of 0.8760. The dynamic coupling strategy employed by SleepXLSTM for automatic sleep staging using the heterogeneous temporal representation of heart rate data can promote the development of smart wearable devices to provide early warning of sleep disorders and realize cost-effective technical support for sleep health management. Full article

Sequence prediction is widely applied and has significant theoretical and practical application value in fields such as meteorology and medicine. Traditional models, such as LSTM(Long Short-Term Memory) and GRU(Gated Recurrent Unit), may perform better than this model when dealing with short-term dependencies, but their performance may decline on long sequences and complex data, especially in cases where sequence fluctuations are significant. However, the Transformer requires a large amount of computing resources (parallel computing) when dealing with long sequences. Aiming to solve the problems existing in sequence prediction models, such as insufficient modeling ability of long sequence dependencies, insufficient interpretability, and low efficiency of multi-element heterogeneous information fusion, this study embeds sequential data into the knowledge graph, enabling the model to associate context information when processing complex data and providing more reasonable decision support for the prediction results. Given the historical sequence and the predicted future sequence, three groups of sequence lengths were set in the experiment. And MAE (Mean Absolute Error)and MSE (Mean Square Error) are used as indicators for sequence prediction. In sequence prediction, dynamic evolution is conducive to enhancing the ability of the prediction model to capture the changing patterns of the current time series data and significantly improving the reliability of the prediction results. Experiments were conducted using five datasets from different application fields to verify the effectiveness of the prediction model. The experimental results show that based on the randomization of the prediction time step, the prediction model proposed in this study significantly improves the expression performance of stationary sequences. It has addressed the shortcomings of these traditional methods, such as maintaining good performance in the case of short sequences with large fluctuations. Full article

Accurate indoor floor classification is essential for wireless positioning systems. However, the performance of conventional received signal strength indictor (RSSI)-based fingerprinting approaches is often limited by signal fluctuations and insufficient feature representation. To address these challenges, this paper introduces a heterogeneous graph neural network (GNN) framework that models WiFi signals using two types of nodes: reference points and Media Access Control (MAC) address. The edges between reference points and MAC addresses are weighted by normalized RSSI values, allowing the model to capture signal strength interactions and perform relation-aware message passing. Through this graph-based representation, the model can learn spatial and signal dependencies more effectively than conventional vector-based approaches. The proposed model was extensively evaluated under both benchmark and practical settings. On small-scale datasets, it achieved performance comparable to that of a conventional convolutional neural network trained on large-scale datasets, confirming its effectiveness with limited samples. In addition, the proposed model consistently outperformed other models under noisy conditions, achieving 93.88% accuracy on the widely used UJIIndoorLoc dataset and 97.3% accuracy in real-time experiments conducted at a test site. These values are significantly higher than those achieved using conventional machine learning (ML) baselines, highlighting the ability of the proposed model to handle real-world signal variations. These findings highlight that the heterogeneous GNN effectively captures spatial and signal-level dependencies, offering a robust and scalable solution for accurate indoor floor classification. Overall, this work presents a promising pathway for improving the performance and reliability of future wireless positioning systems. Full article

Background: This study introduces the Adaptive Graph Fusion Network, an interpretable graph-based learning framework developed for large-scale prediction of intensive care outcomes. The proposed model dynamically constructs patient similarity networks through a density-aware kernel that adjusts neighborhood size based on local data distribution, thereby representing both frequent and rare clinical patterns. Methods: To characterize physiological evolution over time, the framework integrates a short-horizon convolutional encoder that captures acute variations in vital signs and laboratory results with a long-horizon recurrent memory unit that models gradual temporal trends. The approach was trained and internally validated on the publicly available eICU Collaborative Research Database, which includes more than 200,000 admissions from 208 hospitals across the United States. Results: The model achieved a mean area under the receiver operating characteristic curve of 0.91 across six critical outcomes, with in-hospital mortality reaching 0.96, outperforming logistic regression, temporal long short-term memory networks, and calibrated Transformer-based architectures. Feature attribution analysis using SHAP and temporal contribution mapping identified lactate trajectories, creatinine fluctuations, and vasopressor administration as dominant determinants of risk, consistent with established clinical understanding while revealing additional temporal dependencies overlooked by existing scoring systems. Conclusions: These findings demonstrate that adaptive graph construction combined with multi-horizon temporal reasoning improves predictive reliability and interpretability in heterogeneous intensive care populations, offering a transparent and reproducible foundation for future research in clinical machine learning. Full article

Efficient spectrum allocation and telecom traffic steering in densified heterogeneous maritime communication networks remains a critical challenge due to user mobility, dynamic interference, and congestion across terrestrial, aerial, and sea-based transmitters. This paper introduces the Moving Colorable Graph (MCG) framework, a dynamic graph-theoretical representation of interferences that extends conventional graph coloring to capture the spatiotemporal evolution of heterogeneous wireless links under varying channel and traffic conditions. The formulated spectrum allocation problem is inherently non-convex, as it involves discrete frequency assignments, mobility-induced dependencies, and interference coupling among multiple transmitters and users, thus requiring suboptimal yet computationally efficient solvers. The proposed approach models resource assignment as a time-dependent coloring problem, targeting to optimally support users’ diverse demands in dense port-area networks. Considering a realistic port-area network with coastal, sea and Unmanned Aerial Vehicle (UAV) radio coverage, we design and evaluate three MCG-based algorithm variants that dynamically update frequency assignments, highlighting their adaptability to fluctuating demands and heterogeneous coverage domains. Simulation results demonstrate that the selective reuse-enabled MCG scheme significantly decreases network outage and improves user demand satisfaction, compared with static, greedy and heuristic baselines. Overall, the MCG framework may act as a flexible scheme for mobility-aware and congestion-resilient resource management in densified and heterogeneous maritime networks. Full article

Forecasting real-world time series in domains with strong event sensitivity and regional variability poses unique challenges, as predictive models must account for sudden disruptions, heterogeneous contextual factors, and structural differences across locations. In tackling these challenges, we draw on the concept of symmetry that refers to the balance and invariance patterns across temporal, multimodal, and structural dimensions, which help reveal consistent relationships and recurring patterns within complex systems. This study is based on two multimodal datasets covering 12 tourist regions and more than 3 years of records, ensuring robustness and practical relevance of the results. In many applications, such as monitoring economic indicators, assessing operational performance, or predicting demand patterns, short-term fluctuations are often triggered by discrete events, policy changes, or external incidents, which conventional statistical and deep learning approaches struggle to model effectively. To address these limitations, we propose an event-aware multimodal time-series forecasting framework with graph-based regional transfer built upon an enhanced PatchTST backbone. The framework unifies multimodal feature extraction, event-sensitive temporal reasoning, and graph-based structural adaptation. Unlike Informer, Autoformer, FEDformer, or PatchTST, our model explicitly addresses naive multimodal fusion, event-agnostic modeling, and weak cross-regional transfer by introducing an event-aware Multimodal Encoder, a Temporal Event Reasoner, and a Multiscale Graph Module. Experiments on diverse multi-region multimodal datasets demonstrate that our method achieves substantial improvements over eight state-of-the-art baselines in forecasting accuracy, event response modeling, and transfer efficiency. Specifically, our model achieves a 15.06% improvement in the event recovery index, a 15.1% reduction in MAE, and a 19.7% decrease in event response error compared to PatchTST, highlighting its empirical impact on tourism event economics forecasting. Full article

Ultra-short-term photovoltaic (PV) cluster power prediction (PCPP) is crucial for intra-day energy dispatch. However, it faces significant challenges due to the chaotic nature of atmospheric systems and errors in meteorological forecasting. To address this, we propose a novel ultra-short-term PCPP strategy that introduces a dynamic smoothing mechanism for PV clusters. This strategy introduces a smoothing convergence function to quantify sequence fluctuations and employs dynamic clustering based on this function to identify PV stations with complementary smoothing effects. We model the similarities in fluctuation amplitude, trend correlation, and degree correlation among sub-cluster nodes using a spatiotemporal heterogeneous dynamic graph convolutional neural network (STHDGCN). Three dynamic heterogeneous graphs are constructed to represent these spatiotemporal evolutionary relationships. Furthermore, a bidirectional temporal convolutional neural network (BITCN) is integrated to capture the temporal dependencies within each sub-cluster, ultimately predicting the output of each node. Experimental results using real-world data demonstrate that the proposed method reduces the normalized root mean square error (NRMSE) and normalized mean absolute error (NMAE) by an average of 6.90% and 4.15%, respectively, while improving the coefficient of determination (R²) by 34.36%, compared to conventional cluster prediction approaches. 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

The increasing integration of renewable energy sources (RESs) introduces significant uncertainties in both generation and demand, presenting critical challenges to the convergence, feasibility, and real-time performance of optimal power flow (OPF). To address these challenges, a multi-agent deep reinforcement learning (DRL) model is proposed to solve the OPF while ensuring constraints are satisfied rapidly. A heterogeneous multi-agent proximal policy optimization (H-MAPPO) DRL algorithm is introduced for multi-area power systems. Each agent is responsible for regulating the output of generation units in a specific area, and together, the agents work to achieve the global OPF objective, which reduces the complexity of the DRL model’s training process. Additionally, a graph neural network (GNN) is integrated into the DRL framework to capture spatiotemporal features such as RES fluctuations and power grid topological structures, enhancing input representation and improving the learning efficiency of the DRL model. The proposed DRL model is validated using the RTS-GMLC test system, and its performance is compared to MATPOWER with the interior-point iterative solver. The RTS-GMLC test system is a power system with high spatial–temporal resolution and near-real load profiles and generation curves. Test results demonstrate that the proposed DRL model achieves a 100% convergence and feasibility rate, with an optimal generation cost similar to that provided by MATPOWER. Furthermore, the proposed DRL model significantly accelerates computation, achieving up to 85 times faster processing than MATPOWER. Full article

With the proliferation of mobile devices and payment systems in modern financial services, there is an increasing need to process and analyze continuous streams of transaction data for credit risk assessment. Leveraging the inherent symmetries in financial markets and data structures, this paper introduces DeepCreditRisk, a symmetry-aware deep learning framework that addresses key challenges while maintaining critical invariance properties in financial data representation. The framework incorporates three main components: an adaptive temporal fusion mechanism, a heterogeneous graph neural network, and an attention-based interpretable output layer. The temporal fusion mechanism effectively models both short-term fluctuations and long-term trends in financial time series, while the heterogeneous graph neural network captures intricate relationships within the financial ecosystem. The framework maintains important symmetrical properties in both temporal and structural representations, ensuring balanced feature learning and invariant risk assessment. The attention-based output layer preserves representation symmetry while enhancing model interpretability. Extensive experiments on a large-scale credit risk dataset demonstrate DeepCreditRisk’s superior performance, achieving a 7.2% improvement in the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) and an 18.6% improvement in the Kolmogorov–Smirnov (KS) statistic over state-of-the-art baseline models. The framework maintains high predictive power across various time horizons and provides interpretable insights into feature importance. DeepCreditRisk represents a significant advancement in applying deep learning to credit risk assessment, offering financial institutions a more accurate, robust, and transparent approach for evaluating creditworthiness and managing risk. Full article

The modeling and analysis of epidemic processes in networks have attracted much attention over the past few decades. A major underlying assumption is that the recovery process and infection process are homogeneous, allowing the associated theoretical studies to be conducted in a convenient manner. However, the recovery and infection processes usually exhibit heterogeneous rates in the real world, which makes it difficult to characterize the general relations between the dynamics and the underlying network structure. In this work, we focus on the susceptible–infected–susceptible (SIS) epidemic process with heterogeneous recovery rates in a finite-size complete graph. Specifically, we study the metastable-state statistical properties of SIS epidemic dynamics with two different nodal recovery rates in complete graphs. We propose approximate solutions to the metastable-state expectation and the variance in the number of infected nodes within the framework of the mean-field approximation method. We also derive several upper and lower bounds of the steady-state probability that a node is in the infected state. We verify the proposed approximate solutions of the mean and variance via simulations. This work provides insights into the fluctuations in the statistical properties of epidemic processes with complex dynamical behaviors in networks. Full article

Traffic crashes have become one of the key public health issues, triggering significant apprehension among citizens and urban authorities. However, prior studies have often been limited by their inability to fully capture the dynamic and complex nature of spatiotemporal instability in urban traffic crashes, typically focusing on static or purely spatial effects. Addressing this gap, our study employs a novel methodological framework that integrates an Integrated Nested Laplace Approximation (INLA)-based Stochastic Partial Differential Equation (SPDE) model with spatially adaptive graph structures, which enables the effective handling of vast and intricate geospatial data while accounting for spatiotemporal instability. This approach represents a significant advancement over conventional models, which often fail to account for the fluid interplay between time-varying weather conditions, geographical attributes, and crash severity. We applied this methodology to analyze traffic crashes across three major U.S. cities—New York, Los Angeles, and Houston—using comprehensive crash data from 2016 to 2019. Our findings reveal city-specific disparities in the factors influencing severe traffic crashes, which are defined as incidents resulting in at least one person sustaining serious injury or death. Despite some universal trends, such as the risk-enhancing effect of cold weather and pedestrian crossings, we find marked differences across cities in relation to factors like temperature, precipitation, and the presence of certain traffic facilities. Additionally, the adjustment observed in the spatiotemporal standard deviations, with values such as 0.85 for New York and 0.471 for Los Angeles, underscores the varying levels of annual temporal instability across cities, indicating that the fluctuation in crash severity factors over time differs markedly among cities. These results underscore the limitations of traditional modeling approaches, demonstrating the superiority of our spatiotemporal method in capturing the heterogeneity of urban traffic crashes. This work has important policy implications, suggesting a need for tailored, location-specific strategies to improve traffic safety, thereby aiding authorities in better resource allocation and strategic planning. Full article

The Susceptible–Infected–Susceptible (SIS) model in complex networks is one of the critical models employed in the modeling of virus spread. The study of the heterogeneous SIS model with a non-homogeneous nodal infection rate in finite-size networks has attracted little attention. Investigating the statistical properties of heterogeneous SIS epidemic dynamics in finite networks is thus intriguing. In this paper, we focus on the measure of variability in the number of infected nodes for the heterogeneous SIS epidemic dynamics in finite-size bipartite graphs and star graphs. Specifically, we investigate the metastable-state variance of the number of infected nodes for the SIS epidemic process in finite-size bipartite graphs and star graphs with heterogeneous nodal infection rates. We employ an extended individual-based mean-field approximation to analyze the heterogeneous SIS epidemic process in finite-size bipartite networks and star graphs. We derive the approximation solutions of the variance of the infected number. We verify the proposed theory by simulations. The proposed theory has the potential to help us better understand the fluctuations of SIS models like epidemic dynamics with a non-homogeneous infection rate. Full article