Search Results (211)

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

In satellite and space debris laser ranging, photon-counting time-of-flight sequences exhibit spatio-temporal echo coherence and deterministic orbital constraints. We propose an unsupervised framework exploiting this spatial-kinematic coupling to extract weak returns under high background noise. First, a fuzzy clustering regression employs a dynamic energy functional and cross-entropy-regularized photon attribution, guided by target motion priors. To enhance low signal-to-noise ratio sensitivity, we introduce a low-gradient sampling strategy that theoretically guarantees a signal-to-background ratio exceeding 1/2. Furthermore, a dual-stream autoencoder fuses orbital kinematic parameters and multi-scale echo densities via noise-adaptive latent gating. Validation on 88 satellite and 24 debris datasets achieves F1-scores of 0.73 and 0.93, respectively. The sampling strategy reduces computational latency by ∼5.2% with no loss in tracking precision. This label-free, physically grounded approach enables robust weak signal detection in ground-based photon-counting lidar. Full article

High-speed maneuvering flight vehicles operating in the subsonic-to-transonic regime (250–500 m/s) pose severe challenges to defense interception systems due to their rapid and unpredictable maneuvering behaviors. Accurate short-term trajectory prediction is essential for effective terminal-phase interception guidance. This paper proposes DSGF-Net (Dual-Stream Gated Fusion Network), a hybrid deep learning architecture for 3D trajectory prediction that simultaneously exploits frequency-domain and temporal-domain information through independent parallel streams. DSGF-Net employs two Temporal Convolutional Networks (TCNs) as parallel encoders: a frequency stream processes Wavelet Packet Decomposition (WPD) features (24-dimensional, db4 wavelet, level-3 decomposition), and a temporal stream processes raw 3D coordinates. An adaptive sigmoid gating module dynamically fuses the two independently encoded streams at each time step and feature dimension, followed by an LSTM sequence learner and a single-step fully connected decoder. Experiments on a simulated dataset covering five representative maneuvering modes (cruise, dive, climb, serpentine, composite) reveal a three-level performance hierarchy. First, incorporating raw 3D coordinates alongside WPD features substantially improves clean-data accuracy over WPD-only baselines: DSGF-Net achieves ADE = 3.476 ± 0.010 m (5 random seeds) versus TCN-LSTM (WPD-only) at 3.938 ± 0.103 m (11.7% improvement). Second, a single-stream concatenation baseline (Concat-TCNLSTM) using identical inputs achieves comparable clean-data accuracy (3.333 ± 0.009 m), confirming that input information—rather than fusion mechanism—drives clean-data gains. Third, and most critically, DSGF-Net’s independently encoded dual-stream architecture enables adaptive suppression of degraded sensor inputs: under multi-sensor noise (complementary radar/GPS profiles), DSGF-Net achieves ADE = 13.91 m versus TCN-LSTM’s 21.32 m (34.9% advantage)—a substantially larger margin than on clean data—a capability structurally unavailable to concatenation-based models. With 300K parameters and a 4.96 ms inference time on an A100 GPU, DSGF-Net meets real-time terminal interception requirements (<10 ms). Full article

To address the challenges of low detection accuracy and weak generalization in identifying mining-induced ground fissures from UAV imagery, caused by their slender and discontinuous morphology, complex background clutter, and multi-scale surface features, this paper proposes an enhanced deep semantic segmentation model, SAG-DeepLabV3+ (with Spatial Vision Transformer, Attention mechanisms, and Adaptive Gated Fusion). Specifically, to enhance global context modeling and fine boundary delineation, we introduce a Spatial Vision Transformer (SVT) branch within the Atrous Spatial Pyramid Pooling (ASPP) module. We further employ a dual attention mechanism, sequentially combining Squeeze-and-Excitation (SE) and a Convolutional Block Attention Module (CBAM), for progressive channel and spatial feature refinement. Moreover, an Adaptive Gated Fusion (AGF) module is designed to dynamically optimize the fusion of multi-level decoder features. Experiments on a dedicated UAV-based mining fissure dataset comprising 1280 annotated images show that SAG-DeepLabV3+ achieves a state-of-the-art mean Intersection over Union (mIoU) of 79.52% (with Xception backbone) and 79.19% (with lightweight MobileNetV2 backbone), surpassing DeepLabV3+, U-Net, and PSPNet by a significant margin. Furthermore, by leveraging transfer learning (pre-training on the public CrackVision12K dataset and fine-tuning on our mining fissure dataset), the model’s mIoU is further elevated to 82.04%, demonstrating superior generalization capability. The proposed SAG-DeepLabV3+ effectively balances high accuracy with operational efficiency, fulfilling the potential demand for lightweight automated fissure monitoring under resource-limited field deployments, and lays a foundation for subsequent real-time on-site deployment verification. Full article

Insider threats are difficult to detect and investigate because risky behavior can occur through valid accounts, develop slowly, and leave mixed behavioral traces. We study an analyst support architecture that links anomaly detection with evidence-based triage. Rather than treating insider threat analysis as a single classification task, the architecture organizes it as a workflow that combines behavior modeling, evidence retrieval, rule interpretation, and constrained reasoning. For anomaly detection, we build a multi-view representation over subject time windows and design a heterogeneous dual-branch network (HDBN) that fuses semantic and statistical branches through confidence-gated fusion. The detector captures temporal event patterns and statistical deviations while retaining structured alert clues for downstream investigation. For investigation, we construct a dual-track evidence infrastructure for LLM-assisted reasoning: a star schema data mart supports structured fact verification and a rule tree index supports policy and rule interpretation. An intent-aware hybrid retrieval mechanism routes sub-questions to the relevant evidence source and aligns structured facts with unstructured rules. We also design a constrained reasoning agent based on a controlled reasoning and acting workflow. Action-space constraints, evidence-completeness gating, and state recovery are used to limit reasoning drift and unsupported decisions when enterprise evidence is incomplete. On the CERT r4.2 dataset, the HDBN reaches 96.8% recall at the selected operating point. In the constructed investigation tasks, the constrained ReAct agent reaches 91.8% end-to-end triage accuracy compared to an unconstrained LLM agent baseline under the same tool access setting. The results support the feasibility of traceable detection-to-investigation workflows in the evaluated benchmark setting, while deployment on real enterprise data and adversarial scenarios remains to be validated. Full article

Valve leakage in marine oil and gas pipelines is a critical failure mode that threatens operational safety, ecological integrity and production economic benefits, creating an urgent demand for accurate, real-time and robust fault diagnosis systems. Acoustic Emission (AE) technology captures transient acoustic signatures generated by leakage to enable non-intrusive online monitoring, while deep learning supports intelligent analysis through automatic signal feature extraction. Nevertheless, traditional AE-based leakage diagnosis methods rely heavily on manual feature engineering and fixed signal processing rules. Existing AE-driven deep learning methods fail to simultaneously deliver high detection accuracy, low inference latency and strong noise immunity, hindering their practical deployment on offshore platforms. To address these limitations, this paper proposes a Parameter-free Star-shaped Attention Fusion Network (SAFNet) for lightweight valve leakage localization using AE signals. Centered on the Temporal Pyramid Encoder (TPE) and Progressive Lightweight Star-shaped Attention (PLSA) module, SAFNet integrates Dual Bilinear Star Mapping (DBSM), Energy-Driven Feature Refiner (EDFR) and Multi-Scale Gated Attention Fusion (MS-GAF) modules. This architecture achieves efficient multi-scale temporal feature extraction, parameter-free nonlinear enhancement, noise-resistant refined feature processing and adaptive hierarchical feature fusion. The proposed method is applicable to valve leakage diagnosis of marine oil and gas pipelines under variable pressure and complex marine noise conditions. Comprehensive experiments are conducted on a dataset constructed by combining laboratory controlled leakage signals with real marine background noise recorded from the Liwan 3-1 offshore platform. The experimental results reveal that SAFNet balances high detection accuracy, compact model size and low inference latency simultaneously. Specifically, the network maintains a stable detection accuracy above 95% under pipeline pressures ranging from 2 MPa to 5 MPa, and exhibits excellent stability under extreme heavy noise environments. Ablation experiments further validate the synergistic performance gain brought by all core modules. The presented network delivers an efficient lightweight solution for valve leakage localization under simulated marine acoustic conditions, promotes the development of intelligent monitoring technologies for marine pipeline systems, and comprehensively improves offshore operational safety and marine ecological protection capacity. Full article

Current digital twin frameworks focused on human–robot collaboration rarely take into account the sensory degradation of real industrial environments, nor do they integrate the operator as an active agent within the system. This research presents a multimodal digital twin framework for a dual-arm collaborative robot at an assembly station; the system was developed using ROS 2 Jazzy and CoppeliaSim as the simulator. The architecture integrates three main components: the first is a perception layer that captures voice commands using Whisper ASR and the state of the workspace using a hybrid YOLO + ViT visual pipeline, both with per-channel metadata; the second consists of a Confidence-Weighted Late Fusion engine that dynamically adjusts the weight of each modality based on real-time signal quality, so that each fusion decision can be reconstructed from the signals that generated it; and the third component is a Reference Resolver that grounds linguistic intent within the visual context of the scene and in the fusion weights, using a local instance of Llama 3.1 8B that does not transmit audio, transcripts, or images outside the system. The framework was evaluated using 210 iterations distributed across seven degradation conditions of increasing severity, comparing adaptive fusion against a baseline of fixed weights (0.5/0.5). Under clean conditions and under visual degradation of any severity, both configurations achieved 100% accuracy. Under severe auditory degradation (SNR 0 dB), adaptive fusion activated the safety gate and refrained from executing most commands (13.3% accuracy), while the fixed-weight baseline executed more commands (60% accuracy) but made three incorrect object selections; under severe dual degradation, the pattern repeated (13.3% vs. 40%, with five incorrect selections in the baseline). The adaptive system made no grounding errors in the 210 executions, compared to eight in the baseline, substituting incorrect execution with conservative abstention when no modality provided a reliable signal. The implementation, featuring a versioned degradation protocol and a fixed seed, provides a reproducible benchmark for evaluating multimodal fusion strategies in human–cobot interaction. Full article

Gas concentration in coal mine return-air corners is affected by ventilation, mining disturbance and gas drainage conditions, and it shows strong nonstationarity, local fluctuation and dynamic multi-point correlations. To improve frequency information separation, monitoring point relationship modeling, and short-term prediction accuracy, a variational mode decomposition (VMD)-based dual-branch spatiotemporal graph method is proposed. Gas concentrations from four key monitoring points are used as inputs, and the return-air corner gas concentration is taken as the output. First, the raw series are decomposed by VMD and reconstructed into low- and high-frequency components. Then, two branches are built for different frequency components. The low-frequency branch combines adaptive graph learning, graph convolution and gated recurrent units to extract global variation features, while the high-frequency branch combines graph attention and gated recurrent units to capture local disturbance features. Finally, a feature-fusion module generates multi-step predictions, and a lightweight short-term warning strategy is developed based on the predicted values. The proposed model achieves MAE, RMSE and R² values of 0.0338, 0.0471 and 0.9499 in one-step prediction, respectively, and outperforms GRU, LSTM, GCN-GRU, GAT-GRU, VMD-GRU, Informer and STGCN under three-step and six-step conditions. Cross-dataset validation and inference time analysis indicate good adaptability and online prediction potential. Full article

Acute respiratory distress syndrome (ARDS) is associated with mortality rates up to 46% and remains challenging to diagnose early due to overlapping clinical presentations. We propose a dual-system framework for multimodal ARDS diagnosis that integrates a Mamba-Bi-LSTM primary discrimination system with a TreeSHAP-based verification system whose attribution outputs iteratively refine the primary system’s feature selection gate. The primary system processes heterogeneous clinical inputs—ventilator parameters, blood gas indices, chest imaging, and EEG signals—through a selective state-space Mamba module and bidirectional LSTM layers. The verification system applies TreeSHAP attribution to independently cross-validate primary outputs, provide clinically interpretable evidence, and supply ${\ell }_1$-normalised attribution vectors that directly modulate the Mamba feature selection gate weights during offline refinement. A confidence-and-consistency decision mechanism governs final output, and high-confidence predictions are incorporated as curriculum-filtered signals to iteratively recalibrate both systems through a confidence-gated offline refinement protocol. Evaluated on 3742 held-out patients from MIMIC-IV (internal test) and 2594 patients from the eICU Collaborative Research Database across 208 US hospitals (external validation), the complete system achieves 92.8% accuracy and an F1 score of 0.889 after offline iterative recalibration on the internal test set, with 91.6% accuracy and F1 of 0.871 on external validation, extending early warning time from 5.2 to 9.7 h. The P/F ratio consistently ranks as the top predictive feature in alignment with the Berlin definition. Ablation experiments confirm that EEG integration independently contributes a 2.7 percentage point accuracy gain and a 1.9-h extension of the warning window (McNemar ${\chi }^2=27.0$, $p<0.001$). All performance improvements over single-modality baselines and over existing methods are statistically significant ($p<0.001$, Bonferroni-corrected). End-to-end processing latency of 350 ms per case is compatible with real-time ICU deployment. Full article

Pure inertial dead reckoning during short GNSS outages causes rapid drift on low-cost MEMS GNSS/IMU platforms. Most learning-based compensators upgrade a single predictor and rarely address late-outage drift or cross-domain bias mismatch. This paper proposes two enhancements over a Transformer baseline (TF-Base) plus a lightweight inference-time fusion strategy. MGTR (Motion-Guided Transformer with Tail-aware Readout) adds residual motion gating and a tail-aware readout for hard-segment and late-outage response. TAMS (Temporal Attention Multi-Scale) replaces global average pooling with learnable temporal attention and a short-window dual head. Delayed-Switch selects among TF-Base, MGTR, and TAMS without retraining backbones; its classifier needs a one-pass target-domain calibration, so it is not zero-shot. On real 5 Hz GNSS/IMU recordings under a three-tier protocol, where dead reckoning yields a 40.02 m mean RMSE on cross-domain segments, MGTR cuts the 90th-percentile 2D-RMSE by 20.3% over TF-Base, and Delayed-Switch reaches 30.32 m mean RMSE (24.2% below dead reckoning, 9.5% below TF-Base), within 0.51 m of the better-of-two upper bound. Against two recent baselines under the same protocol, only the AT-LSTM gain is significant after multiple-comparison correction; the margins over the strongest predictors are numerically favorable but not significant at this sample size, with gains concentrated on a few hard segments. Full article

In intensive aquaculture, non-invasive real-time monitoring of morphological traits and body weight of largemouth bass (Micropterus salmoides) is essential for precision feeding and yield estimation. Manual measurement is laborious and stressful, whereas vision-based methods are challenged by insufficient dual-view feature fusion, poor robustness to underwater noise, and over-parameterized models unsuitable for edge deployment. To address these issues, a lightweight framework, MECT-MobileViT, is proposed based on MobileViT-xxs. A Morphometric-Guided Multi-Scale Fusion module is designed to couple physical priors with dual-branch visual features, strengthening shape–weight association. An ECA-NL attention block employing instance normalization, GLU gating, and threshold filtering is embedded to enhance feature robustness against visual disturbances typical in aquaculture and to accentuate critical morphological features. A three-stage synergistic pruning strategy—attention head pruning, structured channel pruning, and depthwise separable attention substitution—is applied to achieve substantial compression while preserving representational capacity. Experiments on a self-built lateral–dorsal dual-view dataset show that the proposed model significantly outperforms mainstream benchmarks. The pruned version attains an R² of 0.8266 and an RMSE of 16.4201, with less than 2% accuracy degradation relative to the best unpruned model, and contains only 7.34 M parameters. This study demonstrates a promising prototype for contactless, stress-free weight estimation in largemouth bass and offers new technical insights into feature fusion, noise suppression, and collaborative model compression for aquaculture visual perception. Full article

The accumulation of training and competition loads represents a critical determinant of musculoskeletal injury risk in professional team sports, yet contemporary monitoring systems remain limited by their reliance on single-domain temporal analysis that overlooks the multi-scale rhythmic patterns inherent in athletic workload signals. This study introduces FDTM (frequency-aware dual-stream temporal model), a deep learning framework that jointly encodes time-domain dependencies and frequency-domain spectral signatures from digital athlete monitoring streams to predict individual injury risk over a forward-looking seven-game horizon. The framework integrates a stacked bidirectional long short-term memory branch augmented with temporal self-attention pooling, a spectral encoding branch employing discrete Fourier transform decomposition across high-frequency (weekly), mid-frequency (bi-weekly), and low-frequency (seasonal) bands, and a cross-modal gated attention fusion module that adaptively balances temporal and spectral representations conditioned on player context. We evaluate FDTM on three heterogeneous public sports datasets spanning basketball (NBA game-log corpus 2013–2023), Australian rules football (AFL Player Workload Dataset), and soccer (SoccerMon open monitoring corpus), comprising 612 athletes and 247,830 player-game observations across ten competitive seasons. FDTM achieves AUC-ROC values of 0.858, 0.833, and 0.821 on the three datasets respectively, outperforming the strongest deep-learning baseline (FEDformer) by 2.0 to 3.3 percentage points and the strongest non-spectral baseline (TCN) by 3.2 to 4.5 percentage points while maintaining a Brier score below 0.04. Ablation studies confirm that the spectral branch contributes 5.1 percent to overall discriminative performance. SHAP attribution analyses identify high-frequency weekly components as the dominant injury-relevant signal, followed by low-frequency seasonal trends and the cumulative acute-to-chronic workload temporal feature, with gating-weight visualizations revealing dynamic modality contributions consistent with established sports science theory. Direct spectral analysis of the raw workload signal confirms that injury-preceding windows exhibit significantly elevated weekly-band power across all three datasets (Mann–Whitney U test, p < 1 × 10⁻⁷), and the architectural advantage is shown to be robust across 30 independent training seeds. These findings suggest that frequency-aware modeling may serve as a transferable methodology for sports engineering applications in injury prevention, return-to-play planning, and individualized rehabilitation, pending further external validation in female athletes and additional team sports. Full article

Digital watermarking secures electroencephalogram (EEG) data in distributed Brain–Computer Interface (BCI) environments. However, existing single-domain deep learning schemes struggle to maintain robustness against clinical signal processing attacks due to EEG’s joint time–frequency nature. We introduce the Dual-Stream Frequency–Time Attention Network (DS-FTAN), utilizing an adaptive Spectral Gating Mechanism to embed information within robust, high-energy EEG spectral regions. A robustness simulation layer—encompassing resampling, spectral dropout, and band-pass filtering—is incorporated during training. Validations confirm DS-FTAN balances imperceptibility (PSNR > 36 dB) with reliable recovery. Specifically, it achieves >99.99% accuracy under no-attack conditions and maintains 86.52–98.77% accuracy across complex attacks (e.g., 50% cropping, band-pass filtering). This significantly outperforms time-domain baselines. Furthermore, DS-FTAN exhibits excellent zero-shot cross-channel generalization. It preserves diagnostic integrity, causing merely a 0.42% accuracy drop in downstream EEGNet intention recognition. Ultimately, this framework provides a reliable solution for privacy-preserving EEG data sharing. Full article

Rapid, low-cost ethanol quantification is vital for beverage quality control, biofuel production, and pharmaceutical applications, yet current approaches are costly, reagent- or label-dependent, or rely on spectroscopy with substantial sample preparation. We introduce a purely cell-based, label-free biosensor that exploits temperature-gradient-induced spontaneous detachment of Saccharomyces cerevisiae from a chip surface. The readout is the detachment half-time, t_d50, derived from time-resolved changes in interfacial thermal resistance, R_th, at the solid–liquid interface. Cells were pre-exposed to ethanol (0–70% v/v) and the detachment kinetics monitored using the heat transfer method (HTM). Under these conditions, cells display a pronounced non-monotonic t_d50 response with a peak around 20% v/v ethanol. Overall, the t_d50 rises from ~45 min (0% ethanol) to ≳10 h (20%) and then decreases, with no detachment at 60% and beyond. Critically, cell quality gates the detachment window. Fresh yeast responds up to ~50%, whereas aged yeast ceases to detach above ~8%, demonstrating a dual-function assay. Complementary measurements show that ethanol decreases surface tension monotonically, as expected, while optical/SEM imaging reveals aggregation above the detachment window. Requiring only a heater and a temperature probe, this platform offers a compact and low-cost strategy for ethanol sensing. Its applicability in a complex matrix is further demonstrated using whiskey diluted to selected alcohol concentrations, which produced responses consistent with the ethanol calibration trend. Potentially, it also offers a thermal assay for real-time monitoring of microbial cell quality across biotechnology and bioengineering applications. Considering ethanol as a proxy for drugs, the strategy may also support label-free drug screening on cells. At a fundamental level, the non-monotonic effect of ethanol, and especially the sharp maximum at 20%, remains unresolved and invites further studies. Full article

Air pollution negatively impacts human health and environmental sustainability, particularly in areas with high industrial activity. This study comparatively evaluated deep learning-based models for estimating PM₁₀ and SO₂ pollutants in Dilovası and Ereğli (Turkey), industrial areas with high pollutant loads. The study utilized Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), an RNN–GRU stacked hybrid model, an attention-based hybrid model, and the proposed GRU–LSTM dual-path hybrid model. The proposed method consists of four main stages: data conversion into a time-series format, data preprocessing and feature generation, model architecture development, and model training and performance evaluation. The dataset consisted of 365 daily PM₁₀ and SO₂ observations obtained from the Air Monitoring Center for the Dilovası and Ereğli monitoring stations. Model performance was evaluated using the coefficient of determination (R²), training time, root mean squared error (RMSE), mean squared error (MSE), and mean absolute error (MAE) metrics. The findings showed that the hybrid models provided higher accuracy compared to the single-track models. Specifically, the proposed GRU–LSTM dual-path hybrid model produced the highest R² and lowest error values for both pollutant parameters in both the Dilovası and Ereğli regions. In Dilovası, this model achieved R² = 0.97 for SO₂ and R² = 0.96 for PM₁₀; in Ereğli, it reached R² = 0.92 for SO₂ and R² = 0.98 for PM₁₀. Thus, it has been shown that the GRU–LSTM dual-path hybrid model, which models short-term and long-term temporal dependencies in parallel, is an effective and reliable method for air pollutant forecasting in industrial areas. These findings demonstrate the potential of the proposed model to support air quality monitoring, early warning systems, and environmental decision-making in industrial regions. Full article