Search Results (2,653)

Conventional methods for calculating sortie mission reliability of shipborne vehicle layouts suffer from excessive computational overhead, long runtimes, and large labeled data requirements. To address these limitations, this work proposes a specialized graph neural network architecture tailored for limited-data small-sample scenarios, denoted as the Small-Sample Graph Neural Network (SS-GNN). The proposed SS-GNN integrates multi-relational graph convolutional layers, an adaptive attention weighting mechanism, small-sample regularization techniques, and an uncertainty quantification module to accurately capture the heterogeneous multidimensional dependencies between vehicles. To further improve learning performance under data-scarce conditions, we employ a hybrid training strategy combining meta-learning-based pretraining, contrastive learning for representation enhancement, knowledge distillation, and transfer learning. Experimental results demonstrate that SS-GNN substantially outperforms traditional reliability calculation methods, classical machine learning models, and state-of-the-art GNN baselines across three key dimensions: predictive accuracy, computational efficiency, and generalization robustness, while also providing theoretically grounded uncertainty estimates for all predictions. This work provides both a theoretical foundation and a practical technical framework for shipborne vehicle reliability prediction and offers a generalizable solution for small-sample graph regression tasks in industrial domains. Future work will focus on extending the approach to extremely low-data regimes via specialized few-shot learning algorithms, incorporating dynamic relation modeling for time-varying sortie processes, and integrating domain knowledge graphs to broaden its operational applicability. Full article

With the rapid growth of fashion e-commerce, fashion attribute recognition has emerged as a critical research area in computer vision. Existing methods face two primary problems: (1) building multi-task models, leading to complex network architectures; (2) the overlooking of semantic relationships and spatial positional dependencies between fashion attributes. To address these issues, this paper proposes SLAR-Net, a novel hierarchical multi-label classification network that effectively fuses spatial and semantic information for improved recognition performance. Specifically, SLAR-Net adopts a progressive, hierarchical architecture. Firstly, we introduce a lightweight backbone network enhanced with a custom-designed attention mechanism to extract low-level image features. Secondly, we innovatively construct an adjacency matrix to represent the relative spatial orientations of attributes, which is then employed by a graph convolutional network to model mid-level spatial positional features. Thirdly, we design a graph embedding matrix that captures attribute dependency relationships, leveraging a neural network to learn high-level semantic representations. Finally, we propose a custom multi-head attention mechanism to fuse spatial and semantic features, facilitating enhanced feature interaction and improving recognition performance. Experimental results on fashion attribute and benchmark datasets demonstrate that SLAR-Net outperforms state-of-the-art methods in recognition accuracy, validating the effectiveness of the proposed hierarchical architecture and fusion strategy. Full article

Global Digital Elevation Models (DEMs) exhibit systematic biases constrained by acquisition geometry and surface penetration. This study aims to evaluate whether the increasing complexity of geometric deep learning (e.g., Graph Neural Networks, GNNs) is justified by performance gains over established feature engineering paradigms (e.g., XGBoost) under the constraints of sparse altimetry supervision. We established a rigorous comparative framework across four mainstream products—ALOS World 3D, Copernicus DEM, SRTM GL1, and TanDEM-X—using Sichuan Province, China, as a representative natural laboratory. Our results reveal a fundamental scale mismatch (where the ~485 m average spacing of sampled altimetry footprints dwarfs the local terrain resolution): despite their topological complexity, Hybrid GNN models fail to establish a statistically significant accuracy advantage over the systematically optimized XGBoost baseline, demonstrating RMSE parity. Mechanistically, we uncover a critical divergence in decision logic: XGBoost relies on a stable “Physics Skeleton” consistently dominated by deterministic features (terrain aspect and vegetation density), whereas GNNs exhibit severe “Attribution Stochasticity” ($\rho \approx$ 0.63–0.77). The GNN component acts as a residual-dependent latent feature learner rather than discovering universal topological laws. We conclude that for geospatial regression tasks relying on sparse supervision, “Physics Trumps Geometry.” A “Feature-First” paradigm that prioritizes robust, domain-knowledge-based physical descriptors outweighs the indeterminate complexity of “Black Box” architectures. This study underscores the imperative of prioritizing explanatory stability over marginal accuracy gains to foster trusted Geo-AI. Full article

The Chengdu–Chongqing Twin-City Economic Circle (CC-TCEC), located in the Sichuan Basin, frequently experiences persistent winter PM_2.5 pollution due to basin-constrained ventilation and strong meteorology–emission coupling. Using daily PM_2.5 observations from 113 monitoring stations with a strict two-year training and one-year testing split, we develop hybrid spatiotemporal forecasting models that couple a graph neural network (GCN/GAT) for inter-station spatial dependence learning with a temporal backbone (LSTM/Transformer) for evolving concentration dynamics. We adopt a rolling one-day-ahead forecasting scheme using a 7-day look-back window. Across 12-month, 6-month, and 3-month evaluation windows, the meteorology-augmented Multi-GAT-Transformer shows a slight but consistent advantage over the other tested variants, suggesting potential benefits of attention-based spatial weighting and long-range temporal self-attention under nonstationary basin pollution regimes. Spatiotemporal mappings derived from the best-performing configuration suggest that elevated winter PM_2.5 is mainly associated with low-lying areas such as the Chengdu Plain, industry clusters, and dense urban cores, with peaks that also coincide with the New Year and the pre-Lunar New Year period, suggesting a possible contribution from elevated traffic and production activity. These impacts are amplified by winter stagnation (low winds, high humidity, limited precipitation). From a policy perspective, the results support sustainability-oriented winter haze management by enabling early episode warning and hotspot prioritization. Full article

The analysis of brain data through electroencephalography (EEG) has become essential in neuroscience, affective computing, and brain–computer interfaces. Recent work associates EEG features with artificial neurotransmitter models, simulating emotions and rational–emotional decision-making using complexity theory. However, current methods face limitations: (1) linear temporal representations lacking memory and anticipation, (2) limited contextual adaptation, (3) difficulty with paradoxical affective states, and (4) absence of ethical reasoning in decision-making. We present a framework based on Sophimatics, using complex time ($t=t_{real}+i\cdot t_{imag}\in \mathbb{C}$) where $t_{real}$ represents chronology and $t_{imag}$ encodes experiential dimensions including memory depth and anticipatory imagination. The Super Time Cognitive Neural Network (STCNN) architecture enables the parallel processing of objective time sequences and subjective cognitive experiences. Our Sophimatics-assisted EEG analysis achieves: (1) two-dimensional temporal coherence integrating past experiences and future projections, (2) context-sensitive adaptation via ontological knowledge graphs, (3) interpretable symbolic reasoning compatible with clinical psychology, (4) mechanisms for resolving affective paradoxes, and (5) ethical constraints ensuring value-based decision-making. Across three case studies (emotion recognition, meditation-induced transitions, and brain–computer interface decision support), integrated Sophimatics models outperform traditional machine learning (15–22% accuracy improvement) and complexity theory models (8–14% improvement), while offering greater cognitive richness and immunity to incomplete data. Results establish a post-generative AI framework with computational wisdom: relationally interactive, ethically informed, and temporally consistent with human cognitive and affective life. The framework outlines paths toward next-generation neuromorphic systems achieving genuine understanding beyond pattern recognition. Full article

Stock-ranking prediction is an important task in quantitative finance because it directly influences portfolio construction and alpha generation. Recent Graph Neural Network (GNN) models provide a promising way to describe inter-stock dependencies, but many existing methods still have difficulty balancing rapidly changing market interactions with relatively stable structural relationships. They are also easily affected by financial micro-structure noise. To address these issues, this paper proposes USTGCN, a Unified Spatio-Temporal Graph Convolutional Network for stock-ranking prediction. USTGCN adopts a dual-stream temporal encoder based on ALSTM and GRU to capture short-term dynamic patterns and longer-horizon structural information, respectively. We further introduce a rolling-window correlation smoothing strategy to build a more stable dynamic graph, and then integrate the dynamic and structural graph views through a shared fusion layer. Skip connections are used to preserve original temporal information during spatial aggregation. Experiments on the CSI100 and CSI300 benchmark datasets show that USTGCN achieves IC values of 0.141 and 0.154, respectively, and exhibits improved drawdown control during stressed market periods, indicating its practical value for quantitative trading. Full article

Graph Neural Networks (GNNs) have emerged as the standard for learning representations from graph-structured data. While traditional architectures relying on message-passing mechanisms excel in homophilic settings, they essentially function as fixed low-pass filters. However, this smoothing operation limits their ability to generalize to heterophilic graphs, where connected nodes often exhibit dissimilar labels and high-frequency signals are crucial for discrimination. Furthermore, existing Mixture-of-Experts (MoE) methods for graphs often suffer from local-view routing, failing to capture global structural context during expert selection. To address these challenges, this paper proposes SS-AdaMoE, a novel Spatio-Spectral Adaptive Mixture of Experts framework designed for robust node classification across diverse graph patterns. Specifically, a Dual-Domain Expert System is constructed, integrating heterogeneous spatial aggregators with learnable spectral filters based on Bernstein polynomials. This allows the model to adaptively capture arbitrary frequency responses—including high-pass and band-pass signals—which are overlooked by standard GNNs. To resolve the locality bias, a Hierarchical Global-Prior Gating Network augmented by a Linear Graph Transformer is introduced, ensuring that expert selection is guided by both local node features and global topological awareness. Extensive experiments are conducted on five benchmark datasets spanning both homophilic and heterophilic networks. The results demonstrate that SS-AdaMoE consistently outperforms baselines, achieving accuracy improvements of up to 2.65% on Chameleon and 1.41% on Roman-empire over the strongest MoE baseline, while surpassing traditional GCN architectures by margins exceeding 28% on heterophilic datasets such as Texas. These findings validate that the synergy of learnable spectral priors and global gating effectively bridges the gap between spatial aggregation and spectral filtering. Full article

Multistep-ahead prediction of critical states in the iron ore sintering process is essential for maintaining production stability, enhancing energy efficiency, and reducing industrial emissions. However, large time delays, strong coupling, and condition drifts challenge existing spatiotemporal graph neural networks (STGNNs). This paper proposes Process-aware Mixed Dynamic Graph Network (ProMix-DGNet), which integrates a Decoupled Two-Stream Topology Learning mechanism—fusing Adaptive Static Graph with a Radial Basis Function (RBF)-driven Dynamic Graph Constructor—to ensure robust spatial modeling under high-noise conditions. Furthermore, Process-View Global Mixer explicitly captures long-range process coupling across the entire sintering strand, overcoming the receptive field limitations of traditional graph convolutions. In the decoding phase, a future control-informed module utilizes a bidirectional Long Short-Term Memory (BiLSTM) and a global mixer to align known future control setpoints with the system’s spatial topology. These features are integrated via a gated residual mechanism that dynamically modulates the interaction between control intents and historical representations. Extensive experiments conducted on two real-world industrial datasets, Sinter-A and Sinter-B, demonstrate that ProMix-DGNet consistently outperforms mainstream baselines across multiple metrics, including Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results verify the model’s higher accuracy and robustness in complex large-time-delay systems, offering a reliable framework for the intelligent monitoring and closed-loop optimization of sintering process. Full article

As a key metering device in the smart grid, the clock battery status of smart meters directly affects the operational efficiency and economy of the grid. In response to the limitations of current evaluation methods in feature correlation analysis and model interpretability, this study proposes a knowledge-and-data-driven low battery voltage status prediction method. We systematically dissected the physical mechanisms underlying battery undervoltage faults and constructed a status features knowledge graph comprising 17 state features across four dimensions. By employing Pearson correlation analysis and association rule mining techniques, we achieved a quantitative correlation analysis between multi-source heterogeneous features and battery status. Building on this foundation, we developed an interpretable model framework based on XGBoost-SHAP. Empirical studies utilized a dataset of 939,000 faulty meters recalled by a provincial power company in 2023, with 9.87% of outlier samples eliminated using the Isolation Forest algorithm during preprocessing. Results demonstrate that the proposed model achieved an R² of 0.851 and a Mean Squared Error (MSE) of 0.0088 on the test set. The prediction performance significantly surpassed that of Random Forest (R² = 0.692) and MLP+BP neural networks (R² = 0.583), thereby validating the effectiveness of the approach in combining predictive accuracy with decision transparency. Full article

Dissolved oxygen (DO) is a crucial indicator for characterizing water quality and ecosystem status in freshwater lakes, and its concentration is closely correlated with the surrounding aquatic environment, particularly meteorological conditions. However, traditional DO prediction methods struggle to effectively capture the intricate coupling relationships between multi-station meteorological factors and DO concentration time series, limiting the prediction accuracy. This study proposes a multi-scale spatio-temporal graph neural network with integrated multi-meteorological factors. Taking Taihu Lake and its surrounding cities as the study area, a meteorological graph is constructed based on the geographic proximity between meteorological stations, and a dual-stage “local–global” modeling strategy is adopted to capture the spatio-temporal dependencies of DO concentration under meteorological forcing. Using R², RMSE, MAE and MAPE as evaluation metrics, we conducted single-step and multi-step DO prediction experiments on the 2023–2024 Taihu Tuoshan water quality dataset and compared the proposed model with commonly used prediction models. In the single-step prediction task, the proposed model improved R² by 2.12–20.84% and reduced RMSE, MAE, and MAPE by 3.05–40.80%, 14.97–53.26%, and 6.91–55.62%, respectively. In the 6-step-ahead and 12-step-ahead prediction tasks, RMSE and MAE were reduced by 3.79–15.75% and 6.68–23.09%, and by 5.03–10.39% and 7.13–16.46%, respectively. The experimental results provide quantitative evidence for the superiority of the proposed model in single-step and multi-step DO prediction. This study offers a novel data-driven tool for lake water quality early warning and drinking water safety, and the proposed framework can serve as a reference for water quality prediction studies driven by multi-source environmental factors. Full article

Maritime heterogeneous wireless networks are characterized by dynamic topology and significant heterogeneity in bandwidth, latency, and coverage across communication paradigms, rendering traditional terrestrial routing protocols inadequate. To address these challenges, this paper proposes a unified multi-radio access fusion infrastructure featuring a gateway that enables protocol conversion and collaborative resource management across heterogeneous systems. Building upon this infrastructure, we introduce CMPGNN-DQN, an intelligent routing algorithm that integrates Contrastive Message Passing Graph Neural Networks with Deep Reinforcement Learning. Specifically, the algorithm employs k-hop neighbor aggregation to expand the receptive field for routing decisions, and utilizes a dual-view contrastive learning mechanism—encompassing both homogeneous and heterogeneous perspectives—to enhance representation robustness against dynamic topology perturbations. By deeply fusing network topology features with real-time state information, including bandwidth, delay, and queue length, the agent makes hop-by-hop routing decisions via an ε-greedy policy within the DQN framework. Extensive simulations conducted across various scales of dynamic maritime communication scenarios demonstrate that CMPGNN-DQN outperforms state-of-the-art benchmark algorithms, including AODV, DQN, and GCN, across key metrics such as packet delivery ratio, transmission latency, and bandwidth utilization. Quantitatively, compared to the best-performing alternative (MPNN-DQN), our algorithm achieves throughput improvements of 2.06–5.04% under standard traffic loads and 6.6–27.1% under partial link failure conditions, while converging within merely 25 training episodes. Notably, under heavy network loads (40% load rate) or partial link failures, the algorithm maintains stable communication performance, demonstrating strong adaptability to complex dynamic environments. Full article

In real-world applications, the prevalence of heterogeneous graph data has driven the development of heterogeneous graph neural networks (HGNNs) as an effective solution for modeling intricate semantic relationships. A widely adopted strategy involves using meta-paths as high-level structural motifs to direct neighborhood aggregation in HGNNs. Nevertheless, the semantic content inherent in meta-paths themselves is often not fully exploited, even though they are typically employed as guiding signals. This paper introduces a new HGNN architecture that utilizes meta-path sequences, integrating the intrinsic information of meta-paths directly into the semantic fusion mechanism. By representing meta-paths as sequential data—similar to sequences in natural language processing—we are able to capture more detailed semantic patterns through the sequential order of node types in heterogeneous graphs. Using sequence modeling methods, our approach embeds meta-path semantics into the graph neural network, offering not only additional structural insights but also enabling the training of specialized embeddings for node types. We perform extensive experiments, comprising comparative and ablation analyses, on a custom-built dataset and three publicly available medium-scale heterogeneous graph benchmarks. The experimental outcomes validate the efficacy of our method in utilizing sequential characteristics of meta-paths to improve representation learning. Full article

The screw pump is a critical device for elevating downhole petroleum to the surface, and screw pump failure can significantly disrupt the production of oil wells. Due to the complex structure of the screw pump, the same pump fault can cause different changes in the monitoring parameters, and different faults can also cause the same parameter change. In consequence of the complexity, it requires a large amount of labeled data for a diagnosis model to achieve fault diagnosis of a screw pump in practical application. Aiming for this kind of condition, we discovered the dynamic coupling effect between multi-source information through detailed research on the collected data of screw pumps. To fully leverage the information dynamic coupling (IDC) effect, a semi-supervised learning graph attention network (SSL-GAT) fault diagnosis method is proposed. This approach integrates the semi-supervised learning framework and graph attention neural network for the fault diagnosis of a screw pump. The experimental validation of the SSL-GAT method demonstrates its outstanding performance in screw pump fault diagnosis. Full article

Forecasting monthly precipitation in mountainous terrain poses challenges that push conventional deep learning approaches to their limits: convective processes operate locally while orographic effects span entire drainage basins. We compare three architecture families on precipitation prediction across the Colombian Andes: ConvLSTM (convolutional recurrent), FNO-ConvLSTM (spectral–temporal), and GNN-TAT (graph attention LSTM). Using CHIRPS v2.0 and SRTM topography for Boyacá department (61 × 65 grid, 3965 nodes), we evaluate 39 configurations across feature bundles (BASIC, KCE elevation clusters, and PAFC autocorrelation lags) and horizons from 1 to 12 months. GNN-TAT matches ConvLSTM accuracy ($R^2$: 0.628 vs. 0.642; RMSE: 82.29 vs. 79.40 mm) with 95% fewer parameters (∼98K vs. 2.1M). Across configurations, GNN-TAT produces a lower mean RMSE (92.12 vs. 112.02 mm; $p=0.015$) and a 74.7% lower variance. The explicit graph structure, with edges weighted by elevation similarity, appears to reduce sensitivity to hyperparameter choices. Pure FNO struggles with precipitation’s spatial discontinuities ($R^2=0.206$), though adding a ConvLSTM decoder recovers much of the lost skill ($R^2=0.582$). Elevation clustering improves GNN-TAT significantly ($p=0.036$) but not ConvLSTM, suggesting that feature design should match the spatial encoding paradigm. ConvLSTM achieves peak accuracy on local patterns; GNN-TAT provides robust predictions with interpretable spatial reasoning. These complementary strengths motivate stacking ensembles that combine grid-based and graph-based representations. Full article

Improving absolute accuracy in industrial manipulators remains difficult because rigid-body kinematic calibration cannot fully represent configuration-dependent non-geometric effects. Drawing inspiration from biological brain–body co-adaptation, this study presents an Evolutionary Neuro-Physical Hybrid (Evo-NPH) framework in which rigid geometric parameters and neural compensator weights are treated as a single co-evolving decision vector. In the offline phase, a Dual-Strategy Adaptive Differential Evolution (DS-ADE) optimizer performs global joint identification using complementary exploration–exploitation behaviors and success-history inheritance, analogous to morphology-control co-evolution in biological systems. In the online phase, a Neuro-Physical Hybrid Jacobian (NPHJ) solver augments the analytical Jacobian with gradients from a Graph Kolmogorov–Arnold Network (GKAN), enabling sensorimotor-like real-time compensation on the learned physical manifold. Experiments on an ABB IRB 120 manipulator with 600 configurations (500 training, 100 testing) report a testing distance-residual RMSE of 0.62 mm, STD of 0.59 mm, and MAX of 0.83 mm. Relative to the uncalibrated baseline, RMSE is reduced by 86.75%; compared with the strongest published baseline, RMSE improves by 23.46%. Ablation results show that joint DS-ADE optimization outperforms a sequential pipeline by 32.6%, and the graph-structured KAN outperforms a parameter-matched MLP by 26.2%. Wilcoxon signed-rank tests ($p<0.001$) confirm statistical significance. Full article