Search Results (2,529)

With the advancement of contactless biometric technologies, improving recognition accuracy and robustness in unconstrained environments remains a significant challenge. To address insufficient feature representation caused by modality discrepancies, as well as non-compact feature distributions, we propose HDC-Net, a contactless palmprint and palm vein fusion recognition model based on a heterogeneous dual-stream network and supervised contrastive learning. Specifically, a heterogeneous dual-stream feature extraction architecture is designed to learn modality-specific representations from palmprint and palm vein images. Supervised contrastive learning is introduced to enhance intra-class compactness and improve inter-class separability. Furthermore, a cross-modal interaction fusion module is developed to facilitate complementary feature learning across modalities. Experimental results on Tongji, CASIA-MS, and the self-built SCAU-PM dataset demonstrate that the proposed method achieves equal error rates (EERs) of 0.05%, 0.21%, and 0.02%, respectively. These results indicate that the proposed method achieves reliable recognition performance across different datasets and provides a feasible approach for contactless palmprint and palm vein fusion recognition. Full article

Following the occurrence of a substation fault, alarm systems frequently exhibit issues such as high-density redundancy, spurious alerts, undetected alarms, and temporal inconsistencies. In addition, the effective integration of heterogeneous multi-source data—including fault waveform records and phasor measurement unit (PMU) streams—remains a nontrivial challenge, further impeding the accuracy of fault diagnosis. To address these limitations, this paper proposes an enhanced framework for multi-source fault event modeling and candidate scenario generation based on an extended temporal constraint network. First, protection operations, circuit breaker status transitions, transient waveform features, and PMU-derived dynamic parameters are abstracted as fault event nodes. On this basis, an event representation model is constructed, incorporating event type, associated equipment, temporal attributes, data source identifiers, and reliability coefficients. Second, the conventional temporal constraint network is refined by jointly embedding temporal constraints, distance constraints, and event confidence metrics, thereby enabling the characterization of uncertain causal-temporal dependencies between fault origins and multi-source observations. Third, a dynamic time-window mechanism is introduced to perform online event clustering, followed by reverse temporal reasoning to generate a set of candidate fault scenarios. These scenarios are subsequently verified, merged, and ranked with reference to waveform and PMU data, facilitating the identification of false alarms, missing alarms, and timestamp anomalies. Finally, case studies conducted on a 220 kV substation and its interconnected transmission network demonstrate that the proposed method achieves a correct scenario coverage rate of 96.8%, a candidate scenario compression rate of 68.7%, and an abnormal alarm recognition accuracy of 89.5%, while sustaining an average scenario generation time of 0.28 s. Full article

Methane partial oxidation (POM) offers a promising pathway for syngas production, but achieving optimal catalyst performance requires precise control of promoter loading. We systematically investigated cerium (Ce) promotion on nickel-based catalysts supported on aluminum oxide (Ni/Al₂O₃) catalysts across 1–3 wt.% loadings and identified a critical discovery: catalyst performance exhibits a pronounced non-monotonic response to Ce concentration. The 1 wt.% Ce-promoted catalyst (Ni+1Ce/Al) achieved the superior performance with 65% methane conversion and 60% hydrogen yield at 650 °C, maintaining stable output over 275 min time-on-stream. This smaller Ce amount tunes NiO reducibility, oxygen mobility, and metal–support interactions, resulting in improved activity performance of Ni+1Ce/Al. Notably, Ce promotion shifts the H₂/CO ratio from 2.5 to 2.9, with the increased hydrogen yield arising from enhanced water–gas shift chemistry and indirect oxidation pathways. Excess cerium (2–3 wt.%) causes performance deterioration, Ni particle agglomeration, and thus loss of Ni active sites, demonstrating that Ce operates as a structural promoter with a well-defined appropriate concentration window. Moreover, the best performing catalyst (Ni+1Ce/Al) remained stable during 20-h long-term POM. An artificial neural network model achieved exceptional predictive accuracy (R = 0.9758 overall), validating the experimental findings. These results indicate that the best Ce loading for industrial application is 1 wt.% and the traditional alumina supports can be competitive in performance with the advantage of thermal stability and cost-effectiveness when doped with rare-earth elements. Full article

Adaptive bitrate streaming over HTTP relies on carefully constructed bitrate ladders and ordered sets of bitrate–resolution pairs to deliver optimal perceptual quality under fluctuating network conditions. While content-aware methods based on convex hull optimisation have substantially improved ladder efficiency for Video-on-Demand, they require exhaustive multi-resolution pre-encoding that is computationally prohibitive under the real-time constraints of live streaming. This challenge is compounded by the H.266/Versatile Video Coding (VVC) standard, which offers approximately 50% compression gains over HEVC at 8–10× the encoding complexity. This paper presents LiveCH-VVC, a latency-aware dynamic bitrate ladder prediction framework for VVC-encoded live streaming over Low-Latency DASH (LL-DASH) with CMAF packaging. The framework introduces four integrated modules: (i) a Lightweight Dual-Path CNN (LDP-CNN), obtained via teacher–student knowledge distillation (∼5 M parameters, 148 ms GPU inference), that jointly extracts spatial–temporal features from raw frames and compression-domain statistics from a fast VVC probe encode; (ii) an adaptive scene change detector with exponential moving average thresholding (F1 = 0.925) that triggers ladder updates only upon significant complexity shifts; (iii) a temporally augmented XGBoost multi-label classifier that predicts latency-constrained Pareto-optimal bitrate–resolution pairs; and (iv) an online adaptation engine that integrates Common Media Client Data (CMCD) feedback from CDN edge servers for continuous closed-loop refinement. Comprehensive evaluation on 81 UHD sequences (∼4050 CMAF segments) from three benchmark datasets demonstrates an average BD-Rate of $+0.68\%$ relative to the per-segment oracle convex hull $5.4\times$ better than the state-of-the-art ARTEMIS framework ($+3.67\%$) while achieving 73.3% encoding time savings, 2.37 s end-to-end latency, and a QoE score of 81.6 in live simulation with 100 concurrent clients. Ablation analysis confirms that the dual-path compression-domain branch ($+0.44$ pp) and temporal context augmentation ($+0.35$ pp) are the primary performance drivers, while the online adaptation mechanism provides $42\%$ relative improvement over extended streaming sessions. Full article

Fused deposition modeling (FDM) is a material-extrusion additive manufacturing technology that is widely used in rapid prototyping, complex product modeling, and functional part fabrication. However, process-parameter drift and environmental disturbances may induce underfilling, overfilling, warping, delamination, and other defects, thereby reducing part quality or interrupting the manufacturing process. Since FDM is characterized by point-wise extrusion and layer-by-layer deposition, layer-surface images naturally contain both spatial morphology and temporal evolution information. Existing image-based diagnostic methods often treat layer images as independent samples, and the selection of the image-stream length is still insufficiently supported by experimental evidence. Moreover, spatial compression in spatiotemporal neural networks may remove local defect information that is important for distinguishing similar process-parameter drifts. This study provides a deployment-oriented analysis of FDM image-stream diagnosis by systematically examining how layer-window length, spatial feature preservation, and strict data partitioning influence process-parameter drift recognition. To address these issues, this paper studies ConvLSTM-based FDM image-stream process-parameter drift diagnosis. Continuous region-of-interest image streams are constructed for one nominal condition and six process-parameter drift conditions. In this paper, the time step T denotes the number of consecutive layer-surface images, or, equivalently, the number of consecutive printed layers, contained in one diagnostic image stream. A ConvLSTM-Flatten baseline is first developed to preserve complete spatial feature maps and to evaluate the effect of different time-step lengths. Then, a ConvLSTM model with adaptive spatial pooling and temporal attention (ASP-TA) is constructed to analyze the influence of spatial pooling granularity and temporal feature fusion. The experiments show that the ConvLSTM-Flatten model achieves the highest average test accuracy of 0.7288 at $T=9$, whereas $T=3$ is identified as a practical optimal time step when test accuracy, image-frame computation, diagnosis latency, and convergence behavior are considered together. The paired trial-wise accuracy difference between $T=9$ and $T=3$ is small and not statistically significant over ten repeated trials. Thus, the diagnostic window corresponding to $T=3$ covers three consecutive deposited layers; after the initial window is available, stride-one stream construction allows the diagnosis to be updated with each newly acquired layer image. ASP-TA with a pooling size of eight consistently outperforms ASP-TA with a pooling size of four, but both are lower than the Flatten baseline, indicating that preserving sufficient spatial information is essential for distinguishing FDM process-parameter drift states. The results reveal the non-monotonic influence of time-step length and clarify the tradeoff between spatial feature preservation and model compactness in FDM image-stream process-parameter drift diagnosis. Full article

Hyperspectral unmixing aims to extract pure endmembers and their corresponding abundance from mixed pixels. Existing deep learning-based unmixing methods predominantly rely on convolutional neural networks (CNNs) or Transformer architectures. However, CNNs suffer from limited receptive fields and struggle to capture long-range spectral dependencies across the entire spectral sequence. While Transformers possess global modeling capabilities, they are constrained by quadratic computational complexity and lack the ability to adaptively filter redundant noise in consecutive spectral bands. To address these limitations, this paper proposes a dynamic hyperspectral unmixing network integrating a spectral sequence Mamba with local spatial–spectral awareness. Specifically, the network features a novel asymmetric dual-stream collaborative architecture. The first branch, the spectral sequence Mamba, models hyperspectral data as a one-dimensional continuous sequence and employs the selective state space model to perform global scanning with linear complexity. This adaptively filters redundant spectral bands to accurately extract high-purity global spectral semantics. The second branch, dedicated to local spatial–spectral awareness, uses an attention-augmented CNN to capture local continuous spectral variations and spatial textures, providing fine-grained geometric boundary constraints for abundance estimation. Furthermore, a spatially adaptive gated fusion module is designed to dynamically balance global spectral semantics and local spatial–spectral details according to the pixel mixing complexity of varying spatial regions. Extensive experiments on multiple public hyperspectral datasets demonstrate that the proposed method achieves significant improvements in unmixing accuracy over comparative methods. Full article

Mobile robots used in edge-assisted Industrial Internet-of-Things (IIoT) settings generate coupled motion, LiDAR, edge-compute, and network telemetry. Public datasets that place these streams in one tabular format, with scenario labels suitable for machine-learning experiments, are still limited. This data descriptor presents a pilot-real-calibrated indoor robotic IoT benchmark dataset with 120,000 records sampled at 2 Hz across nominal navigation and nine anomaly scenarios. The benchmark rows are generated from physically constrained simulation rules and are explicitly labeled as synthetic benchmark data. Real pilot evidence is included separately: ROS Noetic runs on a TurtleBot3 Burger, successful LD08 LiDAR bringup after resolving a driver mismatch, and NVIDIA Jetson Nano tegrastats logs under normal-navigation workloads. The calibrated file aligns normal-navigation LiDAR and edge-compute distributions with these pilot measurements while keeping the multi-scenario structure needed for controlled anomaly-detection experiments. The package includes CSV files, metadata, a data dictionary, validation reports, baseline scripts, ROS collection utilities, and a plan for future fully physical data collection. The complete dataset is openly available on Zenodo. Full article

The recovery of low- and medium-temperature waste heat using Organic Rankine Cycles (ORCs) is increasingly important for improving the efficiency and sustainability of industrial and energy systems. In compact ORC turboexpanders, high specific power output and large pressure ratios often require single- or two-stage turbines operating in transonic or supersonic regimes. Under these conditions, stator blade design is complicated by strong compressible-flow effects and, for organic working fluids, by real-gas thermodynamic behavior. Conventional supersonic stator design methods, such as the method of characteristics, are mainly applicable to the diverging supersonic portion of the blade passage, while the converging region is typically defined using empirical or heuristic prescriptions. This paper presents a physics-informed neural-network-based design method for supersonic turbine stator blades. The proposed framework generates the complete inter-blade passage, including both the converging and diverging regions, starting from a prescribed mean-line geometry and Mach number distribution. The velocity field is obtained by solving the governing equations of steady, inviscid, adiabatic, irrotational compressible flow within a PINN formulation. A hard boundary-condition strategy is used to impose the specified mean-line velocity distribution exactly, while real-fluid thermodynamic effects are incorporated through lookup tables for the speed of sound and density. The blade contours are then reconstructed from stream-function isolines predicted from the computed velocity field. The method is demonstrated for two working fluids: air, treated as a perfect gas, and toluene undergoing transcritical expansion. The resulting blade passages are first validated using inviscid CFD simulations, which show close agreement between the prescribed and computed mean-line Mach number distributions. Turbulent CFD simulations of the final blade cascades confirm smooth acceleration through the inter-blade passage, with no strong internal shocks and only weak fishtail shocks downstream of the trailing edge. For both fluids, the post-expansion ratio is approximately unity and the exit flow angle remains close to the prescribed blade metal angle, indicating well-matched supersonic stator designs. The results demonstrate that the proposed PINN-based design method provides a physically consistent approach for generating supersonic stator blade profiles for both ideal-gas and real-gas turbine applications. Full article

Outdoor industrial sites, including logistics terminals, construction yards, and civil infrastructure worksites, increasingly require supervisory systems for monitoring autonomous mobile units under variable wireless and operational conditions. This study presents an edge-cloud telemetry platform that connects V2X on-board and roadside units to a normalized data pipeline and an operator dashboard. The architecture assigns frame reception and data validation to the edge layer, while cloud services perform stream ingestion, storage, querying, and visualization using a Kafka-Elasticsearch-Grafana stack. A fixed supervisory schema was defined for position, heading, speed, mission state, battery level, and error flags so that virtual fields used in early validation can later be replaced by measured signals without changing downstream interfaces. Physical field validation was conducted using a single test vehicle in a construction-site emulation environment to evaluate communication continuity and dashboard refresh behavior. Multi-unit applicability was examined at the architecture and schema levels, and a preliminary payload-level capacity estimate was derived using the telemetry frequency and payload-length assumptions. Under the tested site conditions, the system maintained continuous reception and visualization over an approximately 700 m distance from the RSU-side reference location. The measured end-to-end display delay averaged 0.78 s, with a standard deviation of 0.059 s and a maximum of 0.96 s. Under a 10 Hz status-message condition, the estimated pure-payload traffic was approximately 23 kbps per mobile unit. These results indicate that V2X-based edge-cloud telemetry can provide a practical baseline for supervisory monitoring in outdoor industrial sites, while simultaneous multi-vehicle validation, detailed network-load evaluation, and long-term field testing remain necessary future work. Full article

Short-term airport traffic forecasting faces a structural gap: temporal ensemble models ignore route-network dependencies that shape hub operations, while deep graph neural networks require synchronised multi-airport operational data streams unavailable to single-airport operators, who have access only to their own operational records and publicly available route topology. To our knowledge, this study provides the first systematic evaluation of three graph representation classes—centrality measures, DeepWalk, and Node2Vec—as structural augmentations to Random Forest (RF), XGBoost, and LightGBM for hourly aircraft movement prediction at King Khalid International Airport (RUH), using a two-hop aviation graph combining RUH operational data with the OpenFlights database. Across all three ensemble families, random-walk graph augmentations consistently reduce MAE by approximately 9–17% relative to temporal-only baselines, whereas handcrafted centrality measures provide smaller and less consistent gains. Diebold–Mariano tests confirm that both RF+DeepWalk and RF+Node2Vec significantly outperform all nine baseline models ($p<0.05$), while no statistically significant difference is observed between the two embedding methods within any ensemble family, indicating that the benefit arises from the class of random-walk representations rather than a specific algorithm. RF+DeepWalk achieves the lowest observed MAE of 1.810 (RMSE = 2.481, sMAPE = 6.17%). SHAP analysis indicates that graph embedding dimensions rank among the top predictors, suggesting that they capture structural signal absent from temporal features. Full article

Low-slow-small (LSS) target recognition using multi-dimensional radar remains challenging due to weak signatures, similar kinematics, and overlapping short-term Doppler patterns. Digital-array radar provides continuous, complementary Doppler-spectrum and kinematic measurements; however, their heterogeneity in dimension, distribution, and physical meaning often makes direct fusion under-exploit discriminative complementarity and inadequately model temporal track evolution. To address this, we propose a Doppler-Kinematic Spatio-Temporal Graph Learning framework named Dual-Stream Spatio-Temporal Cross-Attention Graph Convolutional Network (DS-STCAGCN) for LSS target recognition using multi-dimensional radar observations. The method separately encodes Doppler-spectrum and kinematic features to preserve their modality-specific characteristics, fuses them through bidirectional cross-attention, captures long-range temporal dependencies via self-attention, and aggregates local frame-to-frame correlations through graph convolution on a time-ordered observation graph. On the public L-band digital-array dataset LSS-DAUR-1.0, DS-STCAGCN achieves 99.73% mean accuracy and maintains 98.64% at 5 dB signal-to-noise ratio (SNR). On the passive-radar dataset LSS-PR-1.0, it reaches 99.86% mean accuracy, demonstrating strong cross-modal generalization. This work provides an effective spatio-temporal modelling framework for multi-dimensional radar sensing and robust LSS target recognition. Full article

Flooding poses a serious challenge in rapidly growing mountain cities, where steep relief, wadi networks, and expanding urban surfaces concentrate runoff along narrow drainage pathways. This study applies a terrain-based Height Above Nearest Drainage (HAND) workflow within a GIS environment to map flood susceptibility and infrastructure exposure across the Abha, Khamis Mushait, and Ahad Rafidah catchment in the Aseer Region of Saudi Arabia. A 30 m digital elevation model was processed in PCRaster to derive flow direction, flow accumulation, stream networks, subcatchments, and HAND surfaces under four contributing-area thresholds of 1, 5, 10, and 20 km². The scenario design evaluates how drainage-representation uncertainty affects susceptibility and exposure estimates. Susceptibility was summarized for cumulative HAND classes of ≤5, ≤10, ≤20, and ≤30 m, then intersected with filtered building footprints and the road network to estimate infrastructure exposure. The analysis shows that mapped susceptibility varies with drainage representation, but the most critical building and road exposure remains concentrated within the same low-lying urban–wadi zone across all scenarios. The mapped extent of the HAND ≤ 5 m class declined from 367 km² under the 1 km² scenario to 99 km² under the 20 km² scenario. Buildings within HAND ≤ 5 m decreased from 26,449 to 5633, while road segments within the same class declined from 8758 to 1393. Even under more conservative stream thresholds, exposure remains focused within this same urbanized drainage belt, indicating persistent localized susceptibility. The findings show that HAND can be used as a practical first-pass screening tool for identifying flood-susceptible terrain and prioritizing exposed infrastructure in data-scarce environments, while the scenario-based threshold testing improves confidence in identifying robust hotspots for follow-up hydraulic modeling and urban risk management. Full article

Distinguishing authentic gold products from high-quality counterfeits is a challenging fine-grained computer vision problem; counterfeit items are engineered to replicate surface texture, hallmark engravings, color, and geometry with remarkable fidelity, making visual discrimination unreliable even for trained professionals. In this paper, we address the problem of visual gold authentication from unconstrained smartphone imagery in three main contributions. First, we introduce GoldNet, a public benchmark dataset designed for this task, comprising 2127 real-world images of authentic and counterfeit gold items collected under diverse real-world conditions. Second, we evaluate fourteen classification architectures spanning classical handcrafted texture descriptors, convolutional neural networks (CNNs), and vision transformers under a rigorous transfer learning protocol, establishing the first comprehensive baseline for this problem. Third, we propose GoldFormer, a hybrid dual-stream algorithm that combines the local texture representations of ResNet-50 with the global contextual modeling capability of the Swin Transformer (Swin-T) through a newly designed Texture-Aware Attention Gate (TAAG) module. The TAAG dynamically modulates Swin feature dimensions using CNN-derived texture energy, providing improved discriminability and per-prediction interpretability without requiring post hoc attribution. Experimental results show that, under matched-resolution 5-fold cross-validation, the proposed GoldFormer attains the highest overall accuracy (95.02%, F1-score 0.9502) at roughly half the FLOPs of its higher-resolution setting, statistically tied with the strongest individual backbone (ViT-B/16, 94.31%; McNemar $p=0.23$) and on par with a training-free soft-voting ensemble (94.92%), while significantly improving on its own Swin-T backbone (93.65%) and adding built-in, attribution-free texture-gate interpretability. GoldFormer surpasses trained human-expert performance (89.80%) by approximately 5 percentage points. 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

Network intrusion detection systems (IDS) operate in high-dimensional feature spaces under evolving attack patterns and asymmetric misclassification costs, where false negatives represent a critical security risk. Reinforcement learning (RL) offers a natural mechanism for encoding domain-specific misclassification costs directly into the learning signal through reward shaping, enabling cost-sensitive policy optimization in adaptive streaming environments. However, the integration of variational quantum models into RL-based IDS remains insufficiently explored. This work investigates a variational quantum reinforcement learning (VQRL) framework for intrusion detection, in which parameterized quantum circuits are employed to model the policy function. We adopt an RL formulation primarily as a principled cost-sensitive optimization approach rather than to exploit sequential state dependencies, and we employ Instantaneous Quantum Polynomial (IQP) embedding as a quantum feature encoding strategy. The study analyzes how embedding expressivity interacts with varying levels of dimensionality reduction via principal component analysis (PCA) on the CICIDS2017 dataset. Experiments demonstrate that VQRL-IQP achieves high recall and reduces false negative rates in moderately high-dimensional feature spaces compared to a classical RL baseline. This improvement is accompanied by an increase in false positive rates, reflecting a trade-off shaped jointly by the reward structure and the structural properties of IQP encoding. Statistical validation across five independent runs confirms the consistency of these trends. Importantly, no general quantum advantage in accuracy or computational efficiency is claimed; rather, the results indicate that VQRL-IQP offers a distinct error trade-off that is operationally valuable in security-critical scenarios where minimizing missed attacks is the primary objective. Full article