Search Results (771)

High-resolution, long-term gridded meteorological datasets from in situ observations are crucial for ecosystem monitoring, soil diagnostics, hydrological modelling, and Earth system model evaluation. This study presents two enhanced real-time adaptations of Thornton’s Daymet V4 interpolation method. Daymet4-r1 uses a traditional calibration strategy with exhaustive parameter search, while Daymet4-r2 applies a global optimization algorithm (find_min_global from the dlib library) to adjust parameters automatically at each time step. Both methods were tested over Tuscany using high-resolution terrain and a dense observation network. Validation with leave-one-out method was carried out for the period 1995–2011 for both versions, while Daymet4-r2 underwent extended evaluation from 1991 to 2024 to assess seasonal dynamics and long-term variability. Results show that Daymet4-r2 outperforms Daymet4-r1 and the original Daymet V4 for all variables (mean absolute error of 1.24 mm, 1.06 °C, 1.29 °C, 6.26%, 0.78 m/s, and 2.04 hPa for precipitation, maximum and minimum temperature, relative humidity, wind speed, and sea level pressure, respectively). The largest improvement was observed in minimum temperature due to an enhanced approach for detecting and modelling thermal inversions. The high performance, flexibility, and ability of Daymet4-r2 to operate without prior calibration highlight its potential for model verification, real-time environmental monitoring, and integration into climate services. Full article

Remote tower operations require air traffic controllers to maintain continuous visual monitoring and integrate information from panoramic displays, radar data, flight strips, and voice communication. Such screen-mediated and sustained surveillance tasks may lead to covert fatigue, which is difficult to capture using a single physiological or behavioral signal. To address this issue, this study proposes a Gated EEG–Eye Fusion Network (GEEF-Net) for window-level fatigue detection in remote tower controllers. EEG and eye-tracking signals were synchronously collected during simulated remote tower tasks and segmented into 5 s windows with a 2 s step. For each window, 53 EEG features and 47 eye-tracking features were extracted to construct a 100-dimensional multimodal representation. GEEF-Net adopts a lightweight modality-gating mechanism to adaptively weight EEG and eye-tracking representations before fatigue classification. Under the main subject-dependent validation setting, GEEF-Net achieved an Accuracy of 0.883, an F1-score of 0.788, and a ROC-AUC of 0.944, outperforming EEG-only, eye-only, and early-fusion baselines in most overall metrics. The gating analysis indicated that eye-tracking features received a higher average weight than EEG features, suggesting the importance of visual behavior in remote tower fatigue detection. Cross-subject validation showed that individual differences remain a major challenge, while few-shot subject-specific calibration improved model adaptation when limited target-subject samples were available. These findings suggest that EEG–eye-tracking fusion with lightweight modality gating is a feasible approach for fatigue detection in simulated remote tower tasks. However, larger datasets and operationally realistic validation considering shift work, circadian effects, and operational pressure are still required before the approach can be considered operationally reliable. Full article

Microsatellites operate in highly dynamic thermal environments due to severe physical constraints, making temperature telemetry a critical onboard health indicator. Conventional threshold-based monitoring fails to distinguish normal operational mode transitions from genuine faults, causing excessive false alarms. To address this, we propose a two-stage framework integrating unsupervised thermal mode discovery with mode-specific deep learning prediction. Raw temperature telemetry is downsampled and segmented into orbital cycles. Unsupervised clustering identifies two nominal thermal regimes and four canonical fault-type libraries (step, spike, drift, and noise), each corresponding to distinct in-orbit failure mechanisms. For each nominal mode, a Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) is trained on 7-day historical windows to forecast 3-day temperature evolution. Post-downlink, incoming cycle mode is inferred via nearest-neighbor DTW classification; anomalies are flagged when prediction residuals exceed mode-adaptive thresholds. Validation on Macau Science Satellite-1B (MSS-1B, COSPAR 2023-069-B, NORAD 56732) in-orbit telemetry from a 41° inclination low-Earth orbit—where solar illumination dominates external thermal loading and internal heat from the data-communication module and scientific payload constitutes the primary internal thermal source—shows the method reduces anomaly flags by 96.6% and improves prediction mean absolute error by 51.3% compared to a non-classified global baseline under nominal operating conditions, correctly detecting a known operational transient while suppressing spurious alarms. A synthetic fault injection experiment with four anomaly types and five baseline methods further confirms the framework’s detection capability, achieving an overall F1 score of 0.725 vs. 0.258 for the global baseline—a 2.8× improvement driven primarily by a 4× precision gain. Sensitivity analysis reveals that the two-stage advantage is most pronounced for low-magnitude and short-duration faults, where mode-specific context is essential. This work advances microsatellite autonomous health management by providing reliable anomaly detection with quantified fault detection performance. Full article

Background: Cataract diagnosis and management pose a significant global health challenge, contributing to 17 million cases of blindness and over 83 million cases of vision impairment worldwide in 2020. This issue is particularly acute in regions lacking adequate ophthalmological services, where a shortage of eye care clinicians and specialized equipment like slit-lamp cameras leads to late diagnoses. To address this accessibility gap, we developed a computer-assisted cataract grading system using smartphone-acquired external eye photographs. This approach utilizes image processing and deep learning on a standard, hardware-free smartphone, offering a low-cost and portable alternative to traditional equipment. Methods: The study introduces a new advanced algorithm to stratify cataract severity into three distinct stages: normal, pre-mature, and mature. The methodology was developed using a combined dataset of 799 images sourced from the Cataract v01 Computer Vision Project and the Indian Institute of Technology, Delhi. A key step is isolating the iris and lens using a region of interest (ROI) extraction procedure powered by the open-source MediaPipe framework. Key to the algorithm’s efficacy is the use of transfer learning, adapting four customized ResNet architectures (ResNet-18, ResNet-34, ResNet-50, and ResNet-101) to address medical image analysis intricacies. These models were fine-tuned with specific modifications, including dropout layers and the Adam optimizer, for analyzing the digital periocular images. Results: Evaluation of the models shows varied performance across the various architectures when classifying cataract stages. While the simpler ResNet-18 model exhibited the lowest performance, the deeper models showed significant improvement. The ResNet-50 architecture achieved the highest accuracy of 94%. This model also demonstrated excellent precision (94%), recall (95%), and an F1-score of 95% in multi-class classification, outperforming the other tested models. Its depth enables precise cataract classification, positioning it as a robust and reliable tool for potential medical diagnostic deployment. Conclusions: Deep learning-based analysis of smartphone-acquired external eye images demonstrated feasibility for cataract detection in this study. This method could be a scalable and easy-to-use addition to screening, especially in places where resources are limited. Further work is needed to expand the dataset and to validate the algorithm against established clinical grading systems before broader clinical implementation. Full article

As the growing presence of antibiotic residues in environmental water bodies poses an increasing risk to ecological safety and human health, developing simple and efficient methods for the targeted detection of antibiotics is of particular importance. In this study, we propose a simple method for the one-step hydrothermal synthesis of N, S-co-doped carbon dots (N, S-CDs) using disulfide bonds from discarded badminton shuttlecocks. We investigated the effects of different synthesis temperatures on its performance and confirmed the method’s excellent performance in detecting tetracycline (TC) concentrations, with results demonstrating that varying synthesis temperatures affect the degree and distribution of carbonization, thereby influencing fluorescence intensity. Consequently, employing N, S-CDs-180, which exhibits optimal photoluminescence properties, as the sensing probe for the detection of TC solutions at varying concentrations yielded an excellent linear equation for fluorescence quenching and the detection limit is 1.963 mg/L. Additionally, the fluorescence stability of N,S-CDs-180 was investigated in laboratory water, tap water, seawater, lake water, and industrial wastewater, all of which demonstrated exceptional environmental adaptability. Furthermore, a systematic investigation into the target selectivity of N, S-CDs-180 toward various antibiotics revealed that this material exhibits a sensitive quenching response specifically to tetracycline-class antibiotics while showing no quenching effect on non-tetracycline antibiotics, collectively indicating that the as-prepared N, S-CDs can serve as potential fluorescent probes for the highly selective detection of tetracycline-class antibiotics in complex aqueous systems. Full article

Wind turbine main bearings are critical drivetrain components whose operating status directly affects the stability and safety of the entire unit. However, traditional unsupervised health monitoring methods suffer from difficulty in capturing early weak faults, low anomaly detection sensitivity, and inability to fully exploit axial–radial vibration coupling characteristics. To address these issues, this paper proposes an Axial–Radial Coupling-aware Informer (ARC-Informer) for unsupervised main bearing health monitoring. First, 20 time-frequency domain features are extracted from each of the axial and radial vibration signals and concatenated into a 40-dimensional coupled health feature vector. A cross-attention-based coupling enhancement module with residual fusion explicitly models the dynamic interaction between the two directions. Second, a self-attention channel-gating mechanism adaptively reweights the feature channels, and an Informer backbone captures long-range temporal dependencies for multistep prediction of the coupled features. At last, a health index (HI) is constructed from the prediction residuals, with a 99.7% quantile threshold and a six-step consecutive exceedance criterion for anomaly alarm triggering. Experimental results on real wind turbine data show that the proposed ARC-Informer achieves MSE of 0.180–0.257 across prediction horizons 1–16, with its advantage over TPE-optimized baselines (GRU, LSTM, RNN, TCN) growing from negligible at short horizons to 8.1% MSE reduction at H = 16, validating the effectiveness of the coupling enhancement for long-range forecasting. A cross-turbine case study on 10 healthy segments from five wind turbines confirms zero false alarms, and a simulated fault experiment successfully triggers an early warning, demonstrating practical unsupervised health monitoring capability. Full article

Precise detection of cotton apical buds is the primary step toward achieving intelligent topping operations. Existing object detection models still struggle to accurately recognize dense small targets under complex field conditions. In this study, we propose an improved model, MCA-YOLO, based on YOLOv11n, and optimize it from three aspects: feature extraction, computational efficiency, and multi-scale feature fusion. First, we introduce the MLCA attention mechanism into the PSABlock to construct the C2PSA_MLCA module, enhancing the model’s capability to represent both local and global features. Second, a CSPHet module is reconstructed using heterogeneous convolution (HetConv) combined with a dual-path design to reduce convolutional redundancy and improve feature extraction efficiency. Finally, the original YOLOv11n detection head is replaced with an ASFFHead, enabling adaptive multi-scale feature fusion, thereby improving detection performance for small, dense, and scale-varying targets. Experimental results show that MCA-YOLO achieves Precision, Recall, mAP@0.5, and F1-score of 89.0%, 83.1%, 90.6%, and 85.9%, corresponding to improvements of 3.0, 8.1, 7.1, and 5.8 percentage points over YOLOv11n. Compared with YOLOv11n, the parameters and GFLOPs increase by 50.0% and 31.7%. Even with this increase in model complexity, MCA-YOLO achieves 75 FPS with a model size of 7.76 MB, indicating that it maintains real-time detection capability while improving detection accuracy. Full article

Additive manufacturing (AM) monitoring is fundamentally constrained by the severe scarcity of annotated data for layer-wise segmentation. This paper addresses this bottleneck by introducing a scalable, high-fidelity synthetic data generation pipeline built on the Slice-100K dataset, capable of producing large volumes of layer-wise semantic segmentation masks. Through analysis of this large-scale synthetic data, we identify a systemic foreground–background class imbalance (1:24 ratio) inherent to AM monitoring, which causes standard Dice loss formulations to diverge catastrophically into a phenomenon we formalize as the “Dice Crash.” To effectively leverage large amounts of unlabeled data, we adapt the Meta Pseudo-Labeling (MPL) framework for industrial segmentation. We evaluate MPL’s true marginal utility by integrating it with both a standard U-Net and a robust state-of-the-art nnU-Net architecture. Experimental outputs show that while MPL yields substantial performance gains (+15.2%) on weak baselines, integrating it with an optimally configured strong baseline consistently improves segmentation accuracy and suppresses false foreground detections, thereby mitigating confirmation bias. These findings demonstrate that semi-supervised learning via continuous bilevel optimization offers a practical and robust enhancement to data-scarce additive manufacturing monitoring. Because any hidden defects in the topmost layer will be permanently buried by subsequent extrusion, this foundational layer-wise segmentation step is the most critical primitive of the monitoring pipeline. Full article

We present a composable, pipeline-based rules engine for detecting application-level intrusions in HTTP traffic with adaptive rule generation capabilities. Rules are expressed in JSON chain multi-step decoders (Base64, hex, XOR, zlib, gzip) with matching primitives (word boundaries, regular expressions, substring sets) to detect obfuscated payloads. To enable adaptation to novel attack patterns, we integrate a large language model (LLM) component as a second-opinion layer that automatically generates validated detection rules for previously unseen threats, combining the adaptability of machine learning with the interpretability of explicit rules. We evaluate the system on two standard benchmarks (CSIC 2010 and HttpParamsDataset) and present a head-to-head comparison with ModSecurity and the OWASP Core Rule Set, achieving 98.1% and 98.3% detection rates with F1 scores above 0.97 on both datasets while maintaining false positive rates below 0.51%. Full article

Anchor-based bipartite graph methods provide scalable solutions for multi-view clustering, but most of them construct graphs in the original feature space, where high dimensionality distorts the proximity between samples and anchors and degrades graph quality. In addition, the K-means step commonly used to discretize spectral embeddings may produce different cluster assignments across random seeds. To address these limitations, this paper proposes projection-enhanced bipartite graph learning (PEBGL), which first projects each view onto a compact PCA subspace and then jointly performs bipartite graph construction, consensus graph fusion with adaptive view weighting, spectral embedding, and discrete label assignment within an alternating optimization framework. Most subproblems admit closed-form or efficient projection-based updates, and the final labels are obtained by connected-component detection on the learned consensus graph, reducing the dependence on K-means post-processing. Experiments on six benchmark datasets demonstrate that PEBGL achieves competitive clustering performance against recent graph-based and bipartite graph-based methods. These results validate the effectiveness of the proposed framework. Full article

Lower-limb amputation remains a significant clinical and socio-economic challenge, while the high cost of microprocessor-controlled prostheses (MPKs) limits their widespread accessibility. This paper presents the design and preliminary laboratory-scale evaluation of a low-cost microprocessor-controlled ankle prosthesis intended as a feasibility-oriented alternative platform for future active prosthetic system development. Building upon the previously developed V1 mechanical architecture, an updated CAD model was created in the SolidWorks 2024 environment, and the kinematic configuration was refined using a ball-screw transmission (SFU1204-300) driven by a NEMA 17 stepper motor. The electronic control system integrates an ESP32 microcontroller, an MPU9250 inertial measurement unit (IMU), a limit switch for initial-position detection, and a WiFi-based REST API interface for communication and control. Laboratory no-load experiments demonstrated controlled positional behavior, repeatable angular response, and successful operation of the homing procedure within a motion range of 0–4200 motor steps. The prototype actively generated dorsiflexion–plantar flexion motion in the sagittal plane, while a passive inversion–eversion mechanism was incorporated and intended to improve structural adaptability. IMU-based measurements enabled preliminary monitoring of angular displacement and positional behavior during the experiments. The presented prototype represents an initial engineering feasibility study of a low-cost active ankle actuation architecture and provides a foundation for future investigations involving load-bearing experiments, biomechanical gait analysis, and closed-loop control implementation. Full article

As unmanned aerial vehicles (UAVs) are increasingly deployed in mission-critical domains such as military operations, infrastructure inspection, and disaster response, the threat of GPS and network spoofing attacks has emerged as a fundamental challenge to operational continuity. Existing intrusion detection systems based on threshold rules or shallow machine learning models are inherently limited in their ability to identify the latent onset of sophisticated, gradually intensifying spoofing campaigns—a gap that motivates the present work. This study proposes a deep learning-based early detection and network resilience prediction framework that employs Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) architectures operating on three spatio-temporal network features—Hop Count Spike Rate (HCS), Packet Drop Volatility (PDV), and Spatial Disconnect Density (SDD)—proposed in this study. To reflect realistic adversarial conditions, we design a Gradual Adaptive Attacker model in which the spoofing intensity escalates progressively across six operational phases, including a second-stage adaptive attack that modulates its gradient upon detecting initial countermeasures. Both models are trained on 1000 simulated runs using sliding-window time-series sequences and evaluated across 500 independent test runs with paired statistical testing. The GRU model achieves a mean ROC-AUC of 0.9915 (±0.0091) and a mean F1-Score of 0.9099 (±0.0462), outperforming LSTM across all metrics with statistical significance at p < 0.001 under both the paired t-test and the Wilcoxon signed-rank test. Critically, GRU detects spoofing onset with an average latency of 0.503 time steps—approximately 29.4% faster than LSTM (0.712 steps)—a difference confirmed as statistically significant (p < 0.001, Cohen’s d = 0.41). Network resilience simulations further demonstrate that integrating GRU-based autonomous evasion maintains a Connectivity Ratio (CR) above 80% even under severe attack phases, whereas passive networks experience total connectivity collapse (CR = 0%). These findings establish GRU as the superior architecture for real-time UAV edge deployment and affirm that the proposed pipeline extends beyond threat alerting to actively preserving mission continuity under adversarial spoofing conditions. Full article

Steel surface quality critically determines the service safety and structural reliability of industrial products. Defects such as cracks, inclusions, patches, pitting, rolled-in scale, and scratches severely compromise product safety, making accurate and efficient detection a key step in quality control. However, the native A2C2f module in YOLOv13 exhibits insufficient multi-scale feature extraction for tiny defects and weak robustness under complex industrial backgrounds, hindering the detection of these six defect types. To address these gaps, we propose a multi-scale denoising enhanced module, A2C2f-MSDE, which constructs a multi-scale multi-kernel fusion branch (MSKF) with learnable adaptive weights, integrates a lightweight SEL channel attention and a DE denoising module, and employs a dual learnable residual scaling structure, while preserving the original multi-scale fusion architecture. We embed A2C2f-MSDE into the YOLOv13 backbone, perform ablation studies to verify each component’s contribution, compare it with mainstream advanced detectors on the public NEU-DET dataset, and conduct generalization tests on the GC10-DET dataset. Experiments on NEU-DET show that the improved YOLOv13n achieves mAP50-95 of 0.454 (9.4% relative gain over baseline, absolute gain 0.039), with mAP50 and mAP75 reaching 0.774 and 0.466, at an inference speed of 555 FPS, respectively, outperforming the compared mainstream models. On GC10-DET, mAP50 reaches 0.704, comparable to the baseline, maintaining stable overall detection capability, while mAP75 and mAP50-95 improve by 0.033 and 0.019, verifying the module’s performance advantages under high localization accuracy requirements and its cross-dataset generalization ability. The proposed module effectively balances detection accuracy and lightweight characteristics, providing a high-performance solution for industrial steel defect detection. Full article

There are differences in imaging characteristics between infrared and visible light images: visible light images can provide rich texture and color information, but imaging is limited in harsh weather conditions. Infrared images are based on the target’s thermal radiation characteristics and have the ability to resist environmental interference but lack details and background information. Effectively integrating the two can significantly enhance scene understanding ability and improve environmental perception and target recognition performance in applications such as intelligent driving. However, existing fusion methods still face challenges, especially in complex scenes where it is difficult to balance the full preservation of target information with the complete presentation of background details, often resulting in difficulties in extracting differentiated features from different modalities. This article proposes a target detection method based on the visible light infrared fusion diffusion model. This method introduces the Stable Diffusion architecture and designs a target perception spatial fusion weight module that can adaptively generate a spatial fusion weight map based on modal differences. By implementing a multi-stage dynamic fusion strategy, the fusion ratio is automatically adjusted at different diffusion stages. A full-step multi-step prediction mechanism is adopted to improve fusion quality and stability. Compared with existing methods, the method proposed in this article has significant advantages. Experiments on multiple publicly available datasets have shown that this method outperforms existing mainstream methods in key metrics such as Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE), and ean Absolute Error (MAE) and also demonstrates good detection performance in downstream tasks for object detection. Full article

Background: Children with juvenile idiopathic arthritis (JIA) exhibit gait abnormalities, postural instability, and compensatory movement strategies due to joint pain, inflammation, and reduced neuromuscular control. These alterations negatively affect functional mobility and movement efficiency. Although gait retraining is commonly recommended in rehabilitation, objective evidence on its short-term biomechanical effects remains limited. This study aimed to evaluate the immediate impact of a single-session standardized movement training intervention on gait biomechanics in children with JIA. Methods: Seventeen children with JIA underwent pre–post gait assessments using the Xsens MVN Awinda wearable motion capture system. The intervention focused on step symmetry, stride length, heel–toe progression, and upright trunk posture, delivered by an experienced physiotherapist following a standardized protocol. Scalar kinematic outcomes were analyzed using paired statistical tests, and time-normalized kinematic waveforms were compared with healthy reference data from 25 age-matched participants derived from the COMPWALK-ACL dataset. Results: Significant improvements were observed in multiple gait parameters following the intervention. Trunk lateral lean decreased significantly (p = 0.0002; d = −1.35), indicating enhanced postural stability. Significant changes were also found in ankle dorsiflexion–plantarflexion (p = 0.0081; d = 0.83) and knee flexion–extension (p = 0.0252; d = 0.68). Waveform analyses showed increased similarity to healthy patterns, particularly in trunk and knee kinematics. Spatiotemporal parameters reflected a slower, more controlled gait pattern, with increased stride time and stance duration. Conclusions: A single session of standardized movement training can produce immediate improvements in gait biomechanics in children with JIA, especially in trunk control and lower-limb kinematics. Wearable motion analysis provides a sensitive tool for detecting these short-term adaptations and supports the inclusion of structured movement training in pediatric JIA rehabilitation. Full article