Search Results (508)

To address the insufficient fusion of electromechanical impedance (EMI) response features from multiple sensors and the limited characterization of spatial relationships between sensors and bolt nodes in four-bolt connection structures, this study proposes an improved graph convolutional network (GCN) model integrating Batch Normalization (BN) and Distance Weighting (DW) strategies for bolt preload-loss state identification. First, PZT sensor nodes and bolt nodes are jointly represented as a graph structure, and the correlation coefficient deviation (CCD) is extracted as the EMI response feature. Then, a weighted adjacency matrix is constructed according to the geometric distances between sensor nodes and bolt nodes to describe the spatial coupling relationships among different nodes. Subsequently, the weighted adjacency matrix and node features are input into the GCN, and a BN layer is introduced after the graph convolutional layers to reduce the influence of multi-channel feature distribution variations on model training stability. Experimental results on a four-bolt connection structure show that the proposed GCN-BN-DW model outperforms the Basic GCN, GCN-BN, GCN-DW, and several benchmark models in terms of prediction accuracy and stability. Under the strict five-fold cross-validation protocol, the proposed model achieves a test MAE of $2.400\pm 0.100$, RMSE of $3.302\pm 0.239$, MASE of $0.300\pm 0.013$, and $R^2$ of $0.821\pm 0.033$. These results indicate that the proposed model can effectively integrate multi-sensor EMI features and sensor–bolt spatial relationships, providing a feasible graph-based modeling approach for bolt preload-loss state identification. Full article

Satellites are critical components of modern space information systems. During long-term on-orbit operation, satellite telemetry often exhibits multi-scale temporal dynamics, heterogeneous channel behavior, and time-varying inter-variable dependencies, which pose substantial challenges to anomaly detection. Existing methods remain limited in adaptively representing anomaly patterns across temporal scales, jointly modeling temporal evolution and dynamic asymmetric channel dependencies, and preventing over-generalized reconstruction of anomalous inputs. To address these limitations, this paper proposes MSGMamba, a multi-scale graph state space model for satellite telemetry anomaly detection. First, a multi-scale temporal patch decomposition and gated fusion mechanism partitions telemetry sequences into patches of different granularities and adaptively integrates their representations at each temporal position, enabling the joint modeling of short-term transients and relatively slow-varying patterns. Second, a graph–sequence alternating propagation mechanism couples selective state space updates with dynamic graph interaction. At each temporal patch, a directed and asymmetric dependency graph with self-connection priors is generated from the temporally encoded features, allowing temporal evolution and time-varying cross-channel dependencies to be modeled within a unified framework. Third, an orthogonal memory-augmented anomaly discrimination mechanism introduces an orthogonality-constrained memory bank to reduce redundancy among nominal prototypes and constrain the reconstruction space. A dual-pathway anomaly score further combines signal-space reconstruction error with encoder–memory discrepancy to improve the separability of nominal and anomalous samples. Experiments on the SMAP, MSL, and EIRSAT-1 datasets show that MSGMamba outperforms representative baseline methods in terms of average PA-F1 and AFF-F1. Full article

Gas-sensor-based air quality forecasting is important for short-term pollutant concentration prediction and environmental monitoring support. However, practical monitoring records are affected by complex interactions among gaseous pollutants, metal oxide sensor responses, and available meteorological variables, while missing observations, abnormal fluctuations, and observation-quality variations may reduce forecasting reliability. Focusing on the UCI Air Quality Dataset, this study proposes an Interpretable Environmental Multi-scale Temporal Network (IEMTN) for multivariate gaseous pollutant forecasting. The proposed model uses historical pollutant concentrations, metal oxide sensor responses, and meteorological variables to support one-step, multi-step, and multi-target prediction of CO(GT), ${\mathrm{NO}}_x$(GT), ${\mathrm{NO}}_2$(GT), and C₆H₆(GT), which are the reference concentration targets provided in the dataset. Specifically, IEMTN constructs a dynamic environmental variable graph to characterize time-varying coupling relationships among pollutant variables, sensor response signals, and meteorological factors. It further introduces an observation-quality-aware temporal representation module to incorporate missing-value masks, missing-duration information, and temporal-deviation indicators, thereby reducing the influence of incomplete or unreliable observations. In addition, an adaptive multi-period temporal modeling module is designed to capture short-term fluctuations, diurnal variations, accumulation effects, and longer-range temporal patterns. Gradient-based attribution and perturbation-based analysis are also incorporated to improve prediction transparency. Experimental results show that IEMTN achieves the best one-step forecasting performance among the compared models, with average MAE, RMSE, ${\mathrm{MAPE}}_{ϵ}$, and $R^2$ values of 8.040, 12.721, 8.99%, and 0.956, respectively. For 24-step forecasting, IEMTN obtains MAE and RMSE values of 13.680 and 23.100, respectively, and maintains strong performance in multi-pollutant joint prediction. Ablation and interpretability analyses further confirm the contribution of the proposed modules. Overall, IEMTN provides a robust and interpretable modeling framework for pollutant concentration forecasting within the current gas-sensor-based monitoring dataset, while broader validation on multi-station datasets, additional pollutant types, and richer meteorological variables is still required. Full article

When natural disasters strike, the destruction of terrestrial communication infrastructure creates urgent demands for emergency networks. Efficient UAV deployment in capsule airport–UAV hierarchical networks has emerged as a critical challenge due to limited aerial resources and stringent quality-of-service requirements. This paper develops a QoS-aware joint optimization model for UAV deployment, integrating air-to-ground (A2G) channel modeling with resource allocation, where upper-level position optimization is coordinated with lower-level frequency allocation and power control through a hierarchical decomposition strategy. The proposed QoS-TLK-VNS-K algorithm combines graph coloring for interference mitigation with iterative power control for SINR guarantee. Empirical evaluation using multi-scenario simulations demonstrates that the proposed approach significantly outperforms the traditional distance-based coverage method. Statistical validation over 30 independent runs demonstrates significant improvements in QoS satisfaction ($+23.8\%$, $p<0.001$), average SINR ($+104.0\%$, $p<0.001$), minimum user rate ($+194.9\%$, $p<0.001$), and Jain’s fairness index ($+16.2\%$, $p<0.001$) compared to the distance-based baseline. These results demonstrate that the framework effectively addresses the trade-off between interference suppression and network connectivity in multi-UAV emergency communication systems. Full article

Camera localization aims to estimate the six-degree-of-freedom camera pose from a single RGB image and is essential for robotics, autonomous navigation, and augmented reality. Despite recent progress in learning-based localization, robust pose estimation remains challenging under large viewpoint changes, occlusions, repetitive textures, and complex scene layouts. Existing methods mainly rely on local feature matching or independent feature regression, while the structural dependencies among multi-scale visual representations are not fully explored. To address this issue, we propose Uncertainty-aware Bidirectional Graph Learning (UBGL) for RGB-based camera localization. UBGL extracts hierarchical visual features and converts them into graph-structured representations, where nodes describe scene information at different semantic levels. A bidirectional graph learning module is introduced to exchange information between low-level geometric cues and high-level contextual features, enabling joint modeling of local correspondences and global scene structure. In addition, an uncertainty-aware relation modeling strategy estimates the reliability of graph connections and helps reduce the influence of unstable feature interactions during graph reasoning. The refined graph representations are then projected into dense scene-coordinate maps, and the final camera pose is recovered using a differentiable pose solver. Experiments on the 7Scenes and Cambridge Landmarks datasets show that UBGL achieves competitive localization accuracy, especially improving rotation estimation on the 7Scenes benchmark while maintaining comparable performance on Cambridge Landmarks. Ablation studies further demonstrate the effectiveness of bidirectional graph interaction and uncertainty-aware relation modeling. Full article

In 3D integrated circuits, a placement decision that looks acceptable from a 2D wirelength view can still create a local thermal or stress problem after stacking. This issue becomes more visible as the number of tiers and the density of vertical interconnects increase. We propose ThermIC, a placement framework that brings thermal and mechanical risk estimates into the placement loop rather than treating them only as post-layout checks. The novelty of ThermIC does not lie in treating graph neural networks, reinforcement learning, uncertainty-aware learning, or physics-informed regularization as individually new techniques. Instead, ThermIC contributes a placement-time coupling mechanism in which physically typed graph propagation, dense multi-constraint risk prediction, and action-level reinforcement learning feedback are jointly organized for stacked 3D-IC placement. ThermIC uses a heterogeneous graph encoder to carry thermal, stress, timing, and congestion information through the netlist; a constraint head to estimate local hotspot, stress-risk, timing-violation, and congestion probabilities; and a sequential placement policy trained with physics-informed penalties. We evaluate the method on ThermIC-Bench, a simulated corpus with more than 30,000 finite-element samples from 18 heterogeneous 3D-IC designs with 4–8 tiers. Because the present study does not include proprietary industrial circuits, silicon measurements, or a tape-out case, the experimental results are interpreted as simulation-based benchmark evidence rather than final industrial qualification. ThermIC connects the heat-kernel branch to the discretized heat-conduction equation and the stress-filter branch to linear thermo-elastic equilibrium, providing a mechanism-level basis for physical interpretability. The analysis distinguishes offline simulation/training cost from online deployment cost and reports complexity, runtime, and memory scaling for practical large-scale use. Under joint DRC, thermo-mechanical stress, and thermally coupled timing checks, ThermIC obtains an $82.1\%$ physical verification pass rate. The peak-temperature error is $3.1$ °C, the hotspot localization IoU is 0.89, and the number of placement-closure iterations is reduced by $3.7\times$ relative to the heuristic baseline. Together, these benchmark results indicate that early, differentiable multi-physics feedback can make 3D placement less dependent on late correction cycles. Full article

How can one test for a multiplicative topological difference between two structured network populations whose fixed-scale additive Betti summaries agree? We model each population as a probability law over finite graphs, considered up to isomorphism, and read each graph through its clique complex. At the working scale, the ordinary summary is the joint Betti vector $B=(b_0,b_1,b_2)$, recording connected components, loops, and voids. The comparison is deliberately single scale: B is the vector of Betti counts at a fixed working scale, not the full persistence diagram of a filtration. We show that this additive summary can be identical under two non-degenerate graph laws while a multiplicative cohomology-ring statistic differs: the cup product, a multiplicative operation recording when two one-dimensional cohomology classes have a nonzero product in degree two, occurs with different frequency under the two laws. Consequently any procedure whose input is only this single-scale B-summary has no power beyond its size against the constructed alternatives, while a simple cup-product statistic separates them. We define a ring-frequency distance, prove finite-sample concentration for its plug-in estimator, and give a consistent two-sample test. The theory is aimed at structured, ring-rich graph complexes—surface-like meshes and coverage complexes—where the cup product is active; we give a deterministic mechanism under which it is vacuous, together with numerical evidence that it can be uninformative in generic random-graph regimes. Numerical illustrations confirm that the ring test detects the difference while calibrated B-only tests stay blind; those same B-only tests have power when the Betti law itself changes. Real-data case studies on surface meshes and nanoporous frameworks illustrate, respectively, the intended ring-rich regime and a cup-vacuous scope boundary. Full article

Inverse kinematics (IK) is fundamental to robot motion planning. Classical analytical solvers require complete Denavit–Hartenberg (DH) parameters that are often proprietary or degraded by mechanical wear, and numerical solvers based on damped least squares (DLS) are sensitive to initialization, particularly near singularities. We propose XGNN, an explainable graph neural network positioned as a model-free, interpretable warm-start initializer for downstream numerical IK refinement rather than as a standalone replacement for analytical solvers. Each IK query is encoded as a 12-node graph in which six pose nodes and six joint nodes are connected through bipartite pose-to-joint attention edges and chain edges along the kinematic structure. GATv2 message passing aggregates information at each joint node; two ablation-validated design contributions (a learnable node-type embedding and an angle-aware composite loss) enable training to convergence. Evaluated on 300,000 trajectory-style samples generated from the ABB IRB 2400 kinematic model, XGNN achieves ${3.66}^{\circ }$ joint mean absolute error (MAE), comparable to a multilayer perceptron baseline (${3.09}^{\circ }$) and a bidirectional LSTM (${3.14}^{\circ }$) under identical training. The standalone joint accuracy of all learned models is too coarse for direct industrial use, but XGNN provides the strongest warm start for DLS refinement: the convergence rate improves from $98.4\%$ to $100\%$, mean iterations drop from 14.6 to 3.2, and wall-clock time per pose drops $5.0\times$ on the IRB 2400. The benefit transfers cross-platform to the Universal Robots UR5 collaborative manipulator (convergence rate $82.2\%$ to $100\%$, $10.0\times$ speedup) and survives DH parameter perturbation of up to $\pm 10\%$, simulating calibration drift or mechanical wear. The GATv2 attention coefficients additionally provide an interpretability signal at zero inference cost. XGNN therefore complements analytical and numerical IK methods as an interpretable, calibration-robust warm start when DH parameters are unavailable, proprietary, or degraded. Full article

Continuous monitoring of climatic variables is essential for precision viticulture and data-driven decision support systems. However, agricultural sensor networks are frequently affected by missing data due to hardware failures, communication issues, or maintenance interruptions. In this work, we propose a spatio-temporal graph-based autoencoder for reconstructing missing temperature and relative humidity time series collected from a five-node vineyard sensor network over a two-year period. The model combines a GRU-based temporal encoder, augmented with a time-decay imputation mechanism applied to the input data, with a GraphSAGE spatial module, enabling the joint exploitation of temporal dynamics and inter-node spatial correlations. Experimental results on real-world data show that the proposed approach achieves accurate reconstruction under controlled missing-data scenarios generated through structured artificial masking. For moderate corruption levels ($p=0.3$), the model attains reconstruction losses of $0.003$ for temperature and $0.005$ for humidity using short temporal windows (L = 36~3 h), corresponding to MAE values below 0.03 °C and 0.1%, respectively. Even at higher corruption levels ($p=0.7$), performance remains stable, with losses below $0.008$ and $0.011$, and MAE values within 0.05 °C and 0.17%. The results highlight a trade-off between temporal context and reconstruction accuracy: shorter windows yield lower absolute errors under moderate corruption whereas, under extreme data loss ($p=0.9$), the longer windows (L = 144~12 h) reduce the composite temperature reconstruction loss from 0.027 to 0.021. Additionally, temperature is consistently reconstructed more accurately than humidity, reflecting its smoother dynamics and stronger spatial coherence. Full article

Repurposing existing natural gas pipelines for hydrogen service requires an assessment of their current technical condition and remaining lifetime, especially those that may have reached or exceeded their design life. In this study, the strength of welded joints in the X52 steel gas pipeline after 36 years of operation and in the as-received state was investigated, focusing on circumferential welded joints. Hardness distributions in the welded joint zones (the weld metal, the heat-affected zone and the base metal) were determined, and the values of the material’s strength and plasticity characteristics were estimated based on the correlation equations. This enables assessment of the stress–strain relationships for the metal from different zones of welded joints, which were compared with the experimental results determined from uniaxial tensile testing. Finite element models of welded joints were developed, in which the relevant material zones were defined in accordance with established stress–strain relationships, and the stress–strain distributions in the welded joints subjected to simulated tensile loading were determined, identifying the areas under the greatest stress. For the welded joint after 36 years of operation, the normalized graphs show higher relative extreme values of σ₁₁/σ_ys = 1.25 compared to the as-received state, where σ₁₁/σ_ys = 1.1. In the as-received welded joint, strain concentration was observed for a stress load about 5% lower than the σ_ys of the base metal, while in the operated one, a local strain increase was observed for a load even 11% lower than the σ_ys of the base metal. Full article

We develop a unified information-theoretic framework for the analysis of cancer transcriptomic dysregulation across measurement modalities. Three functionals capture distributional, network-aware, and joint-dependence aspects of expression: the Shannon entropy with a Miller–Madow correction, the signalling entropy rate over the protein interaction graph, and the Gaussian total correlation on a principal-component projection. A closed-form algebraic expression yields a linear-time algorithm for the signalling entropy rate. A Compositional Dilution Lemma decomposes bulk entropy into intrinsic and compositional contributions, and a Cross-Modality Invariance Proposition provides an empirically falsifiable null hypothesis. Validation uses 700,202 single cells and 3942 bulk samples across five cancer types. Pan-cancer tumour elevation is significant at $p<{10}^{-7}$, and cross-modality testing on 4230 observations does not reject the interaction null at $p>0.5$. The invariance conclusion is corroborated by cancer-level paired sign-flip permutation, cancer-block bootstrap, and empirical distribution function tests, and the prognostic Cox regressions satisfy proportional-hazards diagnostics with cross-validation concordance of $0.696\pm 0.018$. Immune deconvolution against the LM22 signature validates cell-type-specific predictions, partitioning cancers into myeloid-driven and lymphoid-driven classes. Breast cancer Cox regressions instantiate the predicted orthogonality of distributional and network-aware functionals after immune adjustment. Full article

Human Digital Twins (HDTs) rely on reliable context estimation to support personalized services, adaptive decision-making, and context-aware interaction, yet local ego sensing can be noisy, intermittent, or ambiguous. This study investigates whether Social Internet of Things (SIoT)-enabled opportunistic recruitment of external sources can improve HDT context estimation under partial observability. A controlled synthetic simulator is developed in which the SIoT layer is represented as a typed object graph supporting graph-constrained candidate discovery, bounded relationship-guided discovery, and cost-aware recruitment. The evaluation compares ego-only sensing, a high-coverage opportunistic-all reference, SIoT-aware bounded recruitment, and privacy-aware SIoT recruitment across nominal conditions, degraded ego sensing, ambiguous local context, and noisy/untrusted external sources. Performance is assessed with strict joint overall context accuracy, mean variable accuracy, per-variable Macro-F1, operational cost, effective recovery cost, source-cap-matched baselines, discovery-mode comparisons, and graph-size scalability. The results show that opportunistic-all recruitment gives the highest raw OCA because it recruits many sources, whereas bounded SIoT-aware policies provide lower-cost operating points and preserve nearly the same accuracy as exhaustive SIoT discovery in the discovery-mode comparison. The findings are therefore framed as accuracy–cost–privacy–scalability trade-offs in a synthetic, reproducible testbed rather than as deployment-level claims of universal policy superiority. Full article

Continuous and complete meteorological observations are essential for reliable climate analysis and environmental assessment. However, missing values caused by sensor malfunctions and transmission failures can introduce systematic biases and increase uncertainty in downstream applications. Meteorological variables can be modeled as functional data and typically exhibit nonlinear inter-variable dependencies alongside temporal smoothness; these properties provide valuable prior information for missing data recovery. To address this issue, we propose HSIC-DIMFMC, a multi-view functional matrix completion method for meteorological data imputation that integrates the Hilbert–Schmidt Independence Criterion (HSIC) and dual-information graph regularization. Within a unified framework of functional data analysis and multi-view learning, HSIC is utilized to capture nonlinear dependencies across multiple views, while dual-information graph regularization preserves local structural relationships and temporal smoothness. This joint modeling strategy significantly improves latent representation learning and enhances imputation performance. Experiments on real meteorological datasets demonstrate that the proposed method consistently outperforms several state-of-the-art baselines, especially for strongly correlated variable pairs such as temperature–dew point and wind speed–maximum wind speed. Compared with seven representative approaches—ranging from traditional spatial interpolation to advanced functional matrix completion models—HSIC-DIMFMC achieves average reductions of 43.97–73.59% in RMSE. The results indicate that HSIC-DIMFMC effectively exploits nonlinear cross-view dependencies and structural information, providing a robust solution for collaborative meteorological data imputation. Full article

The evaluation of optimization algorithms for electric vehicle routing problems depends strongly on the quality of the benchmark instances used during experimentation. However, many synthetic instances simplify the joint effects of geometry, topography, operation, and energy, which can distort algorithmic assessment. This article proposes a modular and reproducible pipeline for generating synthetic instances of the Electric Vehicle Steiner Traveling Salesman Problem (EV-STSP), calibrated from a real urban reference network based on publicly available Madrid data. The pipeline combines directed graph construction, geometric control, attribute enrichment, charging-infrastructure placement, structured export, and explicit traceability mechanisms. To assess the realism of the generated instances, a three-level validation protocol is introduced, covering marginal distributional similarity, physical coherence among dependent variables, and structural–operational consistency. A controlled ablation design is then used to quantify the contribution of individual modules to overall benchmark realism. Within the experimental domain explored here, the results show that benchmark realism is not supported uniformly by all modules; instead, it depends primarily on arc-length generation, topographic alignment, and energy modeling. The proposed framework therefore offers not only a reproducible way to generate EV-STSP benchmarks, but also an explicit methodology for verifying whether such benchmarks are suitable for comparative algorithmic experimentation. Full article

Targeting the joint challenges posed by sparse graph topology, limited semantic expressiveness, and scarce annotation resources that commonly afflict knowledge graphs in the oil and gas pipeline safety domain, this paper presents a Multi-Information Fusion Unsupervised Entity Alignment model (MIF-UEA). The proposed method constructs high-quality initial alignment pairs by integrating multi-source similarity computation with a structure-aware seed generation mechanism and performs representation learning by fusing structural features and semantic attribute information. Furthermore, a pseudo-label augmentation and denoising strategy is introduced to enhance the effectiveness of self-training. Finally, entity matching is achieved through an optimal transport model. Experimental results confirm that MIF-UEA surpasses existing baselines across both the specialized oil and gas pipeline safety dataset and multiple general-domain benchmarks, demonstrating its effectiveness and generalization capability. Full article