Search Results (373)

The topology identification (TI) of low-voltage distribution networks (LVDNs) is the foundation for their intelligent operation and lean management. However, the existing identification methods may produce inconsistent results under measurement noise, missing data, and heterogeneous load behaviors. Without principled multiple method fusion and meter-level confidence quantification, the reliability of the identification results is questionable in the absence of ground-truth topology. To address these challenges, a confidence-aware TI (Ca-TI) method for the LVDN based on weakly supervised learning (WSL) and Dempster–Shafer (D-S) evidence theory is proposed, aiming to infer each meter’s latent topology connectivity label and quantify the meter-level confidence without ground truth by fusing different identification methods. Specifically, within the framework of data programming (DP) in WSL, different TI methods were modeled as labeling functions (LFs), and a weakly supervised label model (WSLM) was adopted to learn each method’s error pattern and each meter’s posterior responsibility; within the framework of D-S evidence theory, an uncertainty-aware basic probability assignment (BPA) was constructed from each meter’s posterior responsibility, with posterior uncertainty allocated to ignorance, and was further discounted according to the missing data rate; subsequently, a consensus-calibrated conflict-gated (CCCG)-enhanced D-S fusion rule was proposed to aggregate the TI results of multiple methods, producing the final TI decisions with meter-level confidence. Finally, the test was carried out in both simulated and actual low-voltage distribution transformer areas (LVDTAs), and the robustness of the proposed method under various measurement noise and missing data was tested. The results indicate that the proposed method can effectively integrate the performances of various TI methods, is not adversely affected by extreme bias from any single method, and provides the meter-level confidence for targeted on-site verification. Further, an engineering deployment scheme with cloud–edge collaboration is further discussed to support scalable implementation in utility environments. Full article

Byzantine failures remain a critical threat to Federated Learning (FL), where malicious clients inject adversarial updates to disrupt global model convergence. From the perspective of symmetry, benign client updates typically exhibit statistical symmetry around the global consensus, whereas Byzantine attacks function as “symmetry-breaking” events that introduce skewness and distributional anomalies. Existing defenses often rely on unrealistic assumptions or fail to capture these asymmetric deviations under high-dimensional non-IID settings. In this paper, we propose a symmetry-aware Byzantine-resilient FL framework driven by a Dual-Channel Attention-Driven Anomaly Detector (DAAD). Specifically, DAAD transforms inter-client behaviors into geometrically symmetric interaction matrices—encoding Gradient Cosine Similarities and Loss Euclidean Distances—to construct dual-channel spatial representations. These representations are processed via a Convolutional Neural Network (CNN) enhanced with Squeeze-and-Excitation (SE) attention blocks, which leverage the inherent symmetry of benign consensus to extract robust adversarial signatures. The detector is pre-trained offline on a synthetic dataset incorporating a diverse portfolio of simulated attacks (e.g., Gaussian noise and label flipping). Crucially, this pre-trained model is seamlessly embedded into the online FL loop to filter updates without requiring ground-truth labels. By jointly encoding client behaviors and learning cross-modal attack signatures, our framework enables reliable detection even when over half of the clients are Byzantine. Extensive experiments on MNIST, CIFAR-10, and FEMNIST datasets demonstrate that DAAD consistently outperforms existing robust aggregation baselines in both anomaly detection accuracy and global model performance, especially under high Byzantine ratios and non-IID conditions. Full article

Serial flow cytometry was recently introduced as a method that can estimate measurement uncertainty (i.e., imprecision, the coefficient of variation of repeated measurements of individual particles) independent from population characteristics. Replication of light sources and detectors at multiple sites along a flow cytometer’s microchannel requires more equipment and can complicate detector synchronization. Here, we introduce amplitude modulation to encode each region of a serial cytometer with a unique carrier frequency, which enables demultiplexing of the combined signal incident on a single photodetector by fast Fourier transform (FFT) peak magnitude. To facilitate validation of detection, matching, and uncertainty quantification of fluorescence signals, we designed a microfluidic amplitude modulation (AM) serial flow cytometer that has ground truth detectors on individual regions (serial cytometry) in parallel with the combined channel detection for AM demultiplexing. With this report, we present metrics for event detection and dynamic range, prevalence and processing of overlapping detections, region-decoding accuracy, process yield, and uncertainty quantification on a brightness ladder of calibration microspheres. Despite being operated with reduced light intensities, the AM cytometer was capable of high-fidelity performance in comparison to conventional serial cytometry. For events above the detection limit, over 97% were analyzed. Both conventional and AM serial cytometers achieved median imprecisions in the range of 0.53% to 2.1% after outlier removal, which was well below the inherent intensity distribution of any of the microsphere subpopulations. Overall, AM cytometry supports uncertainty quantification and temporal analyses of serial cytometry data with a reduced number of photodetectors, which offers simplification of chip design with multiple measurement regions and wide-field detectors. Full article

Soil salinity mapping in heterogeneous irrigation districts faces a dual challenge: the high dimensionality of hyperspectral data leads to redundancy, while the scarcity of ground-truth samples restricts the generalization of data-driven models. Traditional regression methods often struggle to capture non-linear spectral responses under such “small-sample” conditions. To address these limitations, this study proposes a semi-supervised retrieval framework coupling Optimal Band Combination Analysis (OBCA) with a Spectral Wasserstein GAN with Gradient Penalty (S-WGAN-GP). We constructed a robust feature set via cross-scenario evaluation and developed a rigorous “Uncertainty-Aware Filtering” protocol to screen synthetic samples generated by a teacher mechanism. The OBCA screening revealed that salinity-sensitive features are robustly clustered in the Green (550–570 nm) and Near-Infrared (NIR, 880–950 nm) regions, with NIR bands demonstrating superior stability across different sites. The proposed S-WGAN-GP successfully densified the feature manifold by generating 1186 high-fidelity synthetic samples. By incorporating these augmented data, the inversion accuracy was substantially improved: the R² of the optimal SVR model increased from 0.36 (baseline) to 0.60 (+66.7%), and the RMSE decreased from 7.06 to 5.57 dSm⁻¹. This study confirms that physically constrained generative augmentation, when combined with rigorous quality control, effectively bridges the distribution gap in limited datasets. The proposed framework offers a transferable and accurate solution for fine-scale soil salinity monitoring in data-scarce arid regions. Full article

Background: In temporal lobe epilepsy (TLE), locally reduced glucose metabolism (i.e., hypometabolism) is indicative of the epileptogenic onset zone (EZ). Here, we investigate the potential value of resting-state fMRI (rs-fMRI) for localizing the EZ with fluorodeoxyglucose positron emission tomography (FDG-PET) as ground truth. Methods: Twelve PET-positive patients (34.1 ± 13.1 y; 5 females) with unilateral drug-resistant TLE were included. FDG-PET and rs-fMRI were acquired simultaneously at a hybrid 3T PET-MR scanner. Hypometabolic regions were identified on the FDG-PET images by a nuclear medicine expert. The FDG-PET images were compared with a clinical FDG-PET control dataset with normal glucose uptake distribution. The output z-score maps were thresholded at z < −2 to produce a binary mask of the significantly hypometabolic regions. The hypometabolism masks were mirrored onto the contralateral hemisphere for the asymmetry comparison. Regional homogeneity (ReHo), amplitude of low-frequency fluctuations (ALFF), and fractional ALFF (fALFF) were calculated from the rs-fMRI in conventional (0.01–0.1 Hz) and slow-3 (0.073–0.198 Hz) frequency bands. Asymmetry indices (AIs) were calculated using the ipsilateral and contralateral hypometabolic masks in the PET-positive subjects and assessed via the one-sample Wilcoxon test and Spearman correlation coefficients. Results: The AIs of conventional fALFF were significantly lower in the hypometabolic zone (p < 0.05). A significant negative correlation was found between the AIs of FDG-PET and fALFF in the slow-3 band (r = −0.62; p < 0.05). Conclusions: Conventional and slow-3 band fALFF showed a potential to mimic the FDG-PET findings in terms of EZ localization. Further research with extended cohorts and histopathological validation is required to determine the clinical value. Full article

Object detection is a fundamental task in computer vision. Bounding box regression (BBR) losses are critical to detector performance. However, evaluation measures that rely on the Intersection over Union (IoU) between the predicted and ground truth boxes are highly sensitive to positional deviations, which can hinder optimization. To alleviate this issue, we propose ATDIoU, a novel arctangent-differential loss for bounding-box regression. ATDIoU computes distance similarity between a predicted and a ground truth box by modeling the distances between their corresponding vertices as a two-dimensional arctangent differential distribution (ATD). This arctangent differential-based design mitigates bounding box drift and reduces sensitivity to localization errors. As a result, it guides the model to learn target positions more effectively. We evaluate ATDIoU by integrating it into YOLOv6 and conducting experiments on PASCAL VOC and VisDrone2019. The results demonstrate that ATDIoU yields improvements of 1.4% and 0.7% in mean average precision (mAP) relative to MPDIoU. Full article

Estimating individual tree Above-Ground Biomass (AGB) is essential for assessing ecological functions and carbon storage in both forest and urban environments. Traditional field-based methods, such as plot measurements, are costly and impractical for large-scale applications. However, satellite- and aerial-based techniques lack the spatial resolution for individual-tree-level analysis. Unmanned Aerial Vehicle (UAV) Light Detection and Ranging (LiDAR) data, combined with machine learning (ML), offers a powerful alternative for detailed tree structure measurement and AGB estimation. Leveraging advances in deep-learning-based individual tree detection and geometric structure estimation including Height (H), Surface Area (SA), Volume (V), and Crown Width (CW), this study develops ML regression models for estimating individual tree AGB. We explore three objectives: (1) evaluating four regression models including Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Feed-Forward Neural Network (FFNN); (2) sensitivity assessment of different geometric feature combinations on model accuracy; and (3) improving model robustness using Synthetic Minority Over-sampling Technique (SMOTE) data augmentation for addressing imbalanced data. Results show that the RF model outperforms others that achieved the lowest RMSE and most balanced residual distribution. CW was the strongest single predictor of AGB and, in combination with H, yielded to the most accurate results. This combination improved RMSE and R² by 14.2% and 89.3% with respect to single-variable-based models. The integration of SMOTE and RF further improved model performance since it lowered RMSE by 225.6 kg (~22.1%) and increased R² by 0.76 (~49.0%). This was particularly evident in underrepresented low and high AGB ranges. The proposed RF-SMOTE approach is a cost-effective and scalable approach for generating high-quality ground truth data to enable large-scale satellite-based biomass estimation and help forest carbon accounting and planning in cities and forests. Full article

Monitoring agricultural production in developing nations is essential for assessing food security. Nevertheless, persistent cloud cover in tropical regions severely limits optical satellite observations, and ground-truth data for classification validation are typically unavailable. This study developed a remote sensing methodology to classify agricultural land in southern Uasin Gishu County, Kenya, using weather-independent Synthetic Aperture Radar (SAR) imagery without requiring in situ training data. We processed 29 Sentinel-1 C-band VH-polarized scenes through the Alaska Satellite Facility’s Radiometric Terrain Correction pipeline. We computed the Coefficient of Variation (CV) across the 2017 time series to quantify temporal backscatter variance. VH polarization was selected over VV because a preliminary analysis showed that VV sensitivity to water surface dynamics confounded the CV algorithm. Preprocessing masks excluded water bodies, urban areas, and edge pixels to reduce classification errors from non-agricultural sources of temporal variability. Unsupervised ISO Cluster classification partitioned the CV raster into land-cover classes, and a Python-based statistical analysis determined optimal threshold values. Active agriculture pixels (n = 581,807) exhibited a mean CV of 0.469 (SD = 0.087), while non-agricultural pixels (n = 623,484) showed a mean CV of 0.274 (SD = 0.049). The optimal classification threshold of 0.357, determined by the intersection of fitted normal distributions, achieved an overall accuracy of 87.5% (Kappa = 0.73) when validated against Sentinel-2 reference imagery. User’s accuracy for agriculture was 96.6%, indicating that pixels classified as agricultural were highly reliable, while omission errors reducing producer’s accuracy to 84.6% were primarily attributable to edge pixels and land cover types where preprocessing masks or threshold placement excluded pixels exhibiting intermediate temporal dynamics. The classification identified approximately 810 km² of actively cultivated land (54% of the southern study area), corresponding to an estimated 69,500 to 162,200 metric tonnes (assuming 30–70% maize fraction) of potential maize production based on FAO yield data. The methodology provides a replicable, cost-effective tool for food security monitoring in cloud-prone regions where ground-truth data are unavailable. Full article

Super-resolution technology significantly enhances the visual quality of low-resolution medical images, resulting in ultra-high-resolution clear images. Super-resolution technology based on artificial intelligence has achieved great success in reconstruction quality. However, like the image restoration task, super-resolution is also an ill-posed problem, and current work lacks consideration of trustworthiness. Medical image super-resolution needs to ensure clarity and, more importantly, to ensure that the output image is reliable and does not produce false details and mislead the diagnosis. To address the trustworthy issue of medical image super-resolution, we design a novel hybrid loss that combines a hinge-based adversarial term with a PSNR-based regularization. In the designed loss function, the adversarial term makes the reconstructed result close to the distribution of the true high-resolution image, thus generating more refined high-frequency textures, while the PSNR-based regularization term explicitly reduces the deviation from the ground truth. We apply this loss in the global-token U-Net backbone network and add a lightweight VGG as the discriminator for adversarial terms. We empirically verify that integrating the proposed methods can enhance the trustworthiness of medical image super-resolution technology while maintaining high reconstruction quality. Full article

Accurate and timely monitoring of soil salinity is essential for the sustainable management and remediation of coastal salinization. This study utilized a UAV-based remote sensing platform to collect multispectral imagery and concurrent in situ soil salinity samples from an experimental zone within the Yellow River Delta National Nature Reserve in July 2024. We constructed multiple spectral indices and employed advanced feature selection methods—namely VIP, MultiSURF, and PSO-SFLA—to identify the most informative index combination. We established a soil salinity retrieval model utilizing a stacking ensemble framework. This architecture integrated TabPFN, SVM, and Ridge regression as the base learners, while employing XGBoost as the meta-learner to synthesize the final predictions. Model interpretability was assessed using SHAP (SHapley Additive explanations) values, while predictive performance was evaluated using the coefficient of determination (R²), Standardized Root Mean Square Error (S_RMSE), and the Ratio of Performance to Deviation (RPD). Results indicate that the stacking model, when coupled with PSO-SFLA for feature selection, outperformed all other model configurations. It achieved the highest prediction accuracy on the test set, with an R² of 0.754, S_RMSE of 0.310, and RPD of 1.941. The resulting soil salinity distribution map exhibited a high degree of spatial agreement with the ground-truth survey data. This study demonstrates that leveraging a stacking algorithm with UAV multispectral data provides an accurate and reliable method for monitoring soil salinity in coastal wetlands, offering valuable technical support for effective soil salinization management. Full article

In urban environments, autonomous vehicles face critical challenges in localization and perception under extreme lighting conditions, including rapid illumination changes, high contrast, and nighttime low-light scenarios. To address the performance degradation of traditional LiDAR-inertial odometry systems under such conditions, this study proposes a high-precision FAST-LIO2-EC algorithm that fuses event cameras into the FAST-LIO2 framework. Event cameras, with their microsecond temporal resolution and 140 dB dynamic range, provide asynchronous edge information that complements LiDAR point clouds and IMU measurements. We validate the proposed system through real-world road tests conducted on public roads and closed test tracks, covering three typical extreme lighting scenarios: tunnel entrance/exit transitions, high-contrast shadow boundaries, and nighttime sparse-lighting conditions. The experimental platform is equipped with a 32-beam LiDAR, a 6-axis IMU, a DVS event camera, and an RTK-GNSS system for ground truth trajectory acquisition. Real-world results demonstrate that the FAST-LIO2-EC system achieves significant improvements in localization accuracy and robustness. In illumination change scenarios, the Absolute Trajectory Error (ATE) is reduced by 32.5% compared to the baseline FAST-LIO2 system, with zero tracking loss events. The point cloud quality is substantially enhanced, with more uniform distribution and clearer obstacle boundaries. In high-contrast scenarios, both systems maintain comparable performance with ATE below 0.15 m. However, in nighttime scenarios, the fusion system shows moderate improvement (15.3% ATE reduction) but reveals sensitivity to event camera noise, indicating the need for adaptive thresholding strategies. Supplementary simulation experiments validate the system’s robustness under varying speeds and sensor noise levels. This work provides a practical solution for autonomous vehicle deployment in complex urban lighting environments, with a comprehensive analysis of real-world performance boundaries and deployment considerations. Full article

Chlorophyll-a (Chl-a), a proxy for phytoplankton biomass, plays an important indicator in monitoring trophic states of inland waters. This study proposes a comprehensive framework that utilizes two convolutional neural networks (CNNs) for AC (ConvNet-AC) and Chl-a estimation (ConvNet-CHL) in the eutrophic lakes of Hanoi city (Vietnam) using Landsat-8 images. Satellite-based Chl-a retrieval algorithms have been established based on water remote sensing reflectance ($R_{rs}\left(\lambda \right)$). However, existing atmospheric correction (AC) models often struggle to efficiently extract $R_{rs}\left(\lambda \right)$ due to the complex optical properties of turbid lakes, leading to significant errors in Chl-a retrieval. In this study, a total of 45,764 $R_{rs}\left(\lambda \right)$ and 13,561 Chl-a samples are synthesized using radiative transfer AC and regional Chl-a retrieval algorithms to address the scarcity of their data. A two-stage training strategy combined with hyperparameter tuning is utilized to automatically optimize the architecture of both networks. Model validation and testing are performed using a subset of synthesized data and an in situ dataset. In the comparative analysis, numerous AC approaches, including atmospheric correction for OLI “lite”, Case-2 Regional Coast Color, Image Correction for Atmospheric Effects, Landsat-8 Surface Reflectance Code, QUick Atmospheric Correction, and Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH), and the existing regional Chl-a retrieval algorithm are implemented. Results indicate that ConvNet-AC achieves an average $R^2$ = 0.72 and RMSE = 0.0024 sr⁻¹ for $R_{rs}\left(\lambda \right)$ prediction across five spectral bands, outperforming other AC candidates. The ConvNet-CHL achieves $R^2$ = 0.73 and RMSE = 40.40 mg·m⁻³ for Chl-a estimation within a range between 50 mg·m⁻³ and 300 mg·m⁻³, representing a 43% improvement over the existing regional Chl-a retrieval algorithm with RMSE = 71.99 mg·m⁻³. Furthermore, the proposed framework successfully captures the spatial and seasonal patterns of the Chl-a concentration distributions, demonstrating the effectiveness of integrating CNN-based AC and Chl-a retrieval, offering a robust and transferable solution for monitoring inland water quality with limited ground-truth data. Full article

Accurate broiler weight estimation in commercial farms is hindered by noisy scale data and multi-broiler occupancy. To address this challenge, we propose a KDE-based framework enhanced with systematic preprocessing, including coefficient of variation (CV), relative change (ROC), and absolute change (AC). In this study, kernel density estimation (KDE) is employed not as a predictive model, but as a distributional tool to robustly extract representative flock weight from noisy, high-frequency scale measurements under commercial farm conditions. In the absence of physical ground-truth, our evaluation focused on the framework’s ability to consistently detect the single, representative peak in the KDE distribution. Weekly thresholds were empirically optimized for the preprocessing filters. Results show that the combined ROC + AC method consistently produced unimodal peak distributions and improved the Peak Detection Rate (PDR) from 91.2% (raw data) to 97.9%. Single-Entity Filtering, assisted by cameras, further mitigated density distortions caused by prolonged occupancy, while CV-only and ROC-only filtering yielded less stable representative values. These findings demonstrate that rigorous preprocessing is essential for reliable KDE-based weight estimation under real-world farm conditions. The proposed framework not only improves data quality and stabilizes distributions but also provides a practical foundation for real-time monitoring and AI-driven precision livestock farming models. Full article

Unmanned Aerial Vehicle (UAV) imagery has emerged as a critical data source in remote sensing, playing an important role in vehicle detection for intelligent traffic management and urban monitoring. Deep learning–based detectors rely heavily on large-scale, high-quality annotated datasets, however, collecting and labeling real-world UAV data are both costly and time-consuming. Owing to its controllability and scalability, synthetic data has become an effective supplement to address the scarcity of real data. Nevertheless, the significant domain gap between synthetic data and real data often leads to substantial performance degradation during real-world deployment. To address this challenge, this paper proposes a high-fidelity synthetic data generation framework designed to reduce the Sim2Real gap. First, UAV oblique photogrammetry is utilized to reconstruct real-world 3D model, ensuring geometric and textural authenticity; second, diversified rendering strategies that simulate real-world illumination and weather variations are adopted to cover a wide range of environmental conditions; finally, an automated ground-truth generation algorithm based on semantic masks is developed to achieve pixel-level precision and cost-efficient annotation. Based on this framework, we construct a synthetic dataset named UAV-SynthScene. Experimental results show that multiple mainstream detectors trained on UAV-SynthScene achieve competitive performance when evaluated on real data, while significantly enhancing robustness in long-tail distributions and improving generalization on real datasets. Full article

Mitral valve orifice area is a key functional metric that depends on complex geometric features, motivating a systematic assessment of the relative influence of these parameters. In this study, the mitral valve geometry is parameterized using twelve geometric variables, and a global sensitivity analysis based on Sobol indices is performed to quantify their relative importance. Because global sensitivity analysis requires many simulations, a Gaussian Process regressor is developed to efficiently predict the orifice area from the geometric inputs. Structural simulations of the mitral valve are carried out in Abaqus, focusing exclusively on the valve mechanics. The predicted distribution of orifice areas obtained from the Gaussian Process shows strong agreement with the ground-truth simulation results, and similar agreement is observed when only the most influential geometric parameters are varied. The analysis identifies a subset of geometric parameters that dominantly govern the mitral valve orifice area and can be reliably extracted from medical imaging modalities such as echocardiography. These findings establish a direct link between echocardiographic measurements and physics-based simulations and provide a framework for patient-specific assessment of mitral valve mechanics, with potential applications in guiding interventional strategies such as MitraClip placement. Full article