Search Results (1,006)

Accurate and reliable multi-scene positioning remains a critical challenge in autonomous driving systems, as conventional fixed-noise fusion strategies struggle to handle the dynamic error characteristics of heterogeneous sensors in complex operational environments. This paper proposes a novel noise-adaptive fusion framework integrating Global Navigation Satellite System (GNSS) and Inertial Navigation System (INS) measurements. Our key innovation lies in developing a dual noise estimation model that synergizes priori weighting with posterior variance compensation. Specifically, we establish an a priori weighting model for satellite pseudorange errors based on elevation angles and signal-to-noise ratios (SNRs), complemented by a Helmert variance component estimation for posterior refinement. For INS error modeling, we derive a bias instability noise accumulation model through Allan variance analysis. These adaptive noise estimates dynamically update both process and observation noise covariance matrices in our Error-State Kalman Filter (ESKF) implementation, enabling real-time calibration of GNSS and INS contributions. Comprehensive field experiments demonstrate two key advantages: (1) The proposed noise estimation model achieves 37.7% higher accuracy in quantifying GNSS single-point positioning uncertainties compared to conventional elevation-based weighting; (2) in unstructured environments with intermittent signal outages, the fusion system maintains an average absolute trajectory error (ATE) of less than 0.6 m, outperforming state-of-the-art fixed-weight fusion methods by 36.71% in positioning consistency. These results validate the framework’s capability to autonomously balance sensor reliability under dynamic environmental conditions, significantly enhancing positioning robustness for autonomous vehicles. Full article

Hyperspectral sparse unmixing (SU) networks have recently received considerable attention due to their model hyperspectral images (HSIs) with a priori spectral libraries and to capture nonlinear features through deep networks. This method effectively avoids errors associated with endmember extraction, and enhances the unmixing performance via nonlinear modeling. However, two major challenges remain: the use of large spectral libraries with high coherence leads to computational redundancy and performance degradation; moreover, certain feature extraction models, such as Transformer, while exhibiting strong representational capabilities, suffer from high computational complexity. To address these limitations, this paper proposes a hyperspectral unmixing dual-branch network integrating an adaptive hop-aware GCN and neighborhood offset Mamba that is termed DGMNet. Specifically, DGMNet consists of two parallel branches. The first branch employs the adaptive hop-neighborhood-aware GCN (AHNAGC) module to model global spatial features. The second branch utilizes the neighborhood spatial offset Mamba (NSOM) module to capture fine-grained local spatial structures. Subsequently, the designed Mamba-enhanced dual-stream feature fusion (MEDFF) module fuses the global and local spatial features extracted from the two branches and performs spectral feature learning through a spectral attention mechanism. Moreover, DGMNet innovatively incorporates a spectral-library-pruning mechanism into the SU network and designs a new pruning strategy that accounts for the contribution of small-target endmembers, thereby enabling the dynamic selection of valid endmembers and reducing the computational redundancy. Finally, an improved ESS-Loss is proposed, which combines an enhanced total variation (ETV) with an $l_{1/2}$ sparsity constraint to effectively refine the model performance. The experimental results on two synthetic and five real datasets demonstrate the effectiveness and superiority of the proposed method compared with the state-of-the-art methods. Notably, experiments on the Shahu dataset from the Gaofen-5 satellite further demonstrated DGMNet’s robustness and generalization. Full article

The standard treatment for patients with locally advanced non-small cell lung cancer (NSCLC) is concurrent chemoradiation. However, clinical responses are heterogeneous and generally not known until after the completion of therapy. Multiple studies have investigated imaging predictors (radiomics) for different cancer histologies, but little exists for NSCLC. The objective of this study was to develop a multivariate CT-based radiomics model to a priori predict responses to definitive chemoradiation in patients with lung adenocarcinoma. Methods: Patients diagnosed with locally advanced unresectable lung adenocarcinoma who had undergone chemoradiotherapy followed by at least one dose of maintenance durvalumab were included. The PyRadiomics Python library was used to determine statistical, morphological, and textural features from normalized patient pre-treatment CT images and their wavelet-filtered versions. A nested leave-one-out cross-validation was used for model building and evaluation. Results: Fifty-seven patients formed the study cohort. The clinical stage was IIIA-C in 98% of patients. All but one received 6000–6600 cGy of radiation in 30–33 fractions. All received concurrent platinum-based chemotherapy. Based on RECIST 1.1, 20 (35%) patients were classified as responders (R) to chemoradiation and 37 (65%) patients as non-responders (NR). A three-feature model based on a KNN k = 1 machine learning classifier was found to have the best performance, achieving a recall, specificity, accuracy, balanced accuracy, precision, negative predictive value, F1-score, and area under the curve of 84%, 70%, 80%, 77%, 84%, 70%, 84%, and 0.77, respectively. Conclusions: Our results suggest that a CT-based radiomics model may be able to predict chemoradiation response for lung adenocarcinoma patients with estimated accuracies of 77–84%. Full article

Background: Cognitive heterogeneity in Parkinson’s disease (PD) remains a diagnostic and prognostic challenge, particularly in early stages. In this cross-sectional study, we aimed to identify clinically relevant cognitive subtypes in early PD by integrating neuropsychological profiles with regional brain atrophy assessed via visual MRI scales. Methods: Eighty-one de novo PD patients (≤36 months from diagnosis) and twenty healthy controls underwent 3T MRI with visual atrophy ratings and completed an extensive neuropsychological battery. Results: Using a mixed a priori–a posteriori approach, we defined eight anatomocognitive subtypes reflecting distinct patterns of regional vulnerability: frontosubcortical, posterior cortical, left/right hippocampal, global, and preserved cognition. Specific MRI markers correlated with cognitive deficits in executive, visuospatial, memory, and language domains. Cluster analyses supported subtype validity (AUC range: 0.68–0.95). Conclusions: These results support a practical classification model linking cognitive performance to brain structural changes in early PD. This scalable approach may improve early patient stratification and guide personalized management strategies. Longitudinal studies are needed to assess progression patterns and therapeutic implications. Full article

As an indispensable piece of production equipment in the industrial field, wire rope is directly related to personnel safety and the normal operation of equipment. Therefore, it is necessary to perform broken wire detection. Deep learning has powerful feature-learning capabilities and is characterized by high accuracy and efficiency, and the YOLOv8 object detection model has been adopted to detect wire breaks in electromagnetic signal images of wire rope, achieving better results. Nevertheless, the black box problem of the model brings a new trust challenge, and it is difficult to determine the correctness of the model’s decision and whether it has any potential problems, so an interpretability study needed to be carried out. In this work, a perturbation-based interpretability method—ESTC (Eliminating Splicing and Truncation Compensation)—is proposed, which distinguishes itself from other methods of the same type by targeting the signaling object instead of the ordinary object. ESTC is compared with other model-agnostic interpretable methods, LIME, RISE, and D-RISE, using the same model on the same test set. The results indicate that our proposed method is objectively superior to the others, and the interpretability analysis shows that the model predicts in a way that is consistent with the priori knowledge of the manual rope inspection. This not only increases the credibility of using the object detection model for broken wire detection but also has important implications for the practical application of using object detection model to detect wire breaks. Full article

The rising prevalence of elderly obesity in developed countries poses a public health challenge, since body composition changes during aging are associated with higher risks of chronic diseases. We cross-sectionally explored the relationship between diet, physical activity, and sex-specific differences in body composition among 378 elderly previously enrolled in the Florence European Prospective Investigation into Cancer and Nutrition (EPIC) cohort. Information on dietary habits and lifestyle was collected through validated questionnaires. Adherence to the Italian Mediterranean Index (IMI), Dietary Approaches to Stop Hypertension (DASH), and Greek Modified Mediterranean Diet (GMMD) a priori dietary patterns was calculated. Anthropometric measures were taken by trained personnel, and body composition parameters were estimated via bioelectrical impedance. In age- and energy-intake-adjusted regression models, adherence to the DASH and IMI patterns was associated with healthier body composition among women, while no significant relationship emerged among men. Fitness activities and total recreational physical activity revealed positive associations with healthier body composition (lower % fat mass, higher % muscle mass, and reduced waist circumference) in both sexes. These findings highlight the synergistic effect of diet and physical activity on body composition in the elderly and underscore the need for sex-specific interventions for promoting healthy aging. Full article

Airborne radar-based ground moving target tracking faces challenges such as low detection rates and high clutter density. While lowering the detection threshold can improve detection performance, it introduces significant false alarms, thereby degrading tracking performance. To address these challenges, this paper proposes a novel multi-information assisted Joint Detection and Tracking (JDT) framework for ground moving targets. This study enhances detection and tracking performance by integrating multi-source information, specifically echo information, road network data, and velocity limits, enabling bidirectional data exchange between the detector and tracker for multiple ground targets. An adaptive threshold detector is developed by incorporating a priori information and tracker feedback. Additionally, we innovatively propose an improved Variable Structure Interacting Multiple Model (VS-IMM) filter that leverages road network constraints and detector outputs for tracking, featuring an enhanced model probability calculation to significantly reduce computational time. Simulation results demonstrate that the proposed method significantly improves data association accuracy and tracking precision. Full article

Half-cell potential (HCP) is widely acknowledged as a nondestructive method for assessing the durability of concrete, although the variability in environmental and material conditions compromises its accuracy. The reliability of traditional prediction models, which are often derived from limited data, is questionable under various conditions. This study employed a Bayesian-enhanced probabilistic model to predict corrosion reinforcement using HCP, addressing both known and unknown uncertainties. Constructed as a piecewise function, the model integrates insights from the literature with the results of an accelerated corrosion experiment conducted by the research team, thereby validating the effectiveness of the probabilistic approach. This study also examines the influence of prior knowledge on the accuracy of predictions. The findings revealed a biphasic relationship between HCP and the corroded mass reduction ratio. HCP decreased exponentially with a corroded mass reduction ratio below 15%, whereas beyond this threshold, the decline became more pronounced, modeled by a combination of exponential and cubic polynomial functions. These results underscore the critical role of employing a piecewise function to accurately define the relationship between HCP and corrosion in reinforced concrete, thereby providing a solid foundation for future durability assessments. Full article

The advancement of computational genomics has significantly enhanced the use of data-driven solutions in disease prediction and precision medicine. Yet, challenges such as data scarcity, privacy constraints, and biases persist. Synthetic data generation offers a promising solution to these issues. However, existing approaches based on generative artificial intelligence often fail to incorporate biological knowledge, limiting the realism and utility of generated samples. In this work, we present BioGAN, a novel generative framework that, for the first time, incorporates graph neural networks into a generative adversarial network architecture for transcriptomic data generation. By leveraging gene regulatory and co-expression networks, our model preserves biological properties in the generated transcriptomic profiles. We validate its effectiveness on E. coli and human gene expression datasets through extensive experiments using unsupervised and supervised evaluation metrics. The results demonstrate that incorporating a priori biological knowledge is an effective strategy for enhancing both the quality and utility of synthetic transcriptomic data. On human data, BioGAN achieves a 4.3% improvement in precision and an up to 2.6% higher correlation with real profiles compared to state-of-the-art models. In downstream disease and tissue classification tasks, our synthetic data improves prediction performance by an average of 5.7%. Results on E. coli further confirm BioGAN’s robustness, showing consistently strong recall and predictive utility. Full article

We study the impact on the cosmic microwave background (CMB) landscape of peculiar rotational general relativistic effects. These effects, on galactic scales, do not possess a Newtonian analogue, and therefore could a priori impact CMB analysis. We find that the velocity inferred from the CMB dipole, under the kinematic interpretation, coincides with that measured by a stationary observer within the Milky Way and not with the one measured by the zero angular momentum observer. We show that the galaxy peculiar frame-dragging effects do not impact the standard CMB analysis, as these modify the multipole coefficients only at higher orders with respect to the dominant terms. Moreover, we prove that no general relativistic framework at the galactic scale patched within the standard cosmological model can account for the current tension on the CMB quadrupole amplitude. Full article

The extension of high-speed rail (HSR) lines around the world is increasing. The largest network today is in China, followed by Spain, Japan, France, and Italy; currently, new lines are being built in Morocco and Saudi Arabia. The goal of the new lines built is to drastically reduce the time distances between the extreme railway terminals by intervening on the two main components of time: space and speed. The two components have been investigated in various fields of engineering for design conditions (ex ante/a priori). In the literature, there is no analysis of what happened in the realization of the projects (ex post/retrospective). The research problem that arises is to analyze the high-speed lines built in order to verify, given a pair of extreme terminals, how much the length is reduced by passing from a conventional line to a high-speed line, and to verify how this length is getting closer and closer to the distance as the crow flies. The reduction of spatial distance produces direct connections between two territories, making the railway system (HSR) more competitive compared to other transport alternatives (e.g., air travel). To address the problem posed, information and data are collected on European HSR lines, which constitute a sufficiently homogeneous set in terms of railway and structural standards. The planimetric characteristics of specially built lines such as HSR are examined. A test method is proposed, consisting of a model that is useful to compare the length along the HSR line, with direct lengths, and existing conventional lines. The results obtained from the elaborations offer a first answer to the problem posed, demonstrating that in the HSR lines realized the spatial distances approach the distance as the crow flies between the cities located at the extremes, and are always shorter than the lengths of conventional lines. The final indications that can be drawn concern the possibility of using the results obtained as a reference for decision-makers and planners involved in the transport planning process at national and international level. Future research directions should study the values of the indicators in other large HSR networks, such as those built in Asia, and more generally study all the elements of the lines specially built to allow better sustainable planning, reducing the negative elements found and increasing the positive ones. Full article

A sufficient number of sensors installed in all structural components is a prerequisite for obtaining the full-field temporal–spatial displacement and is essential for large-scale structure health monitoring. In this paper, a novel lightweight vision-based temporal–spatial deflection measurement method is proposed to measure the full-field temporal–spatial displacement of slender structures. First, the geometric and mechanical properties of slender members are introduced as the priori information to vision-based measurement. Then, a slice template matching model is proposed by deploying a one-dimensional template matching model in every pixel column of each image frame, based on traditional digital image correlation (DIC) method. An indoor experiment was carried out to verify the proposed method, and experiment results show that measurement precision of STMM agrees well with the theory and the laser ranger, with a maximum measurement error of 0.03 pixels and the root-mean-square error (RMSE) of 0.052 mm, for transient beam deflection curve; with the correlation coefficient and coefficient of determination of 0.9994 and 0.9986, for dynamic deflection–time history curves at the middle-span point. Finally, further investigation reveals that brightness inconstancy is the source of STMM measurement error. Full article

Background: Clarithromycin is a commonly used macrolide antibiotic. Infection is a major source of mortality and morbidity in critical care units. Pharmacokinetics may vary during critical illness and suboptimal antimicrobial exposure has been shown to be associated with treatment failure. The pharmacokinetics of intravenous clarithromycin in critical illness have not previously been described. Methods: Pharmacokinetic, clinical and demographic data were collected from critically ill adults receiving intravenous clarithromycin. Drug concentrations were measured using high-performance liquid chromatography/mass spectrometry. Population pharmacokinetic analysis was performed using NONMEM version 7.5.1. Allometric weight scaling was added, and periods of renal replacement therapy were excluded a priori. Simulations of 10,000 patients were performed to assess pharmacokinetic–pharmacodynamic (PKPD) target attainment. Results: The analysis included 121 samples taken from 19 participants. A two-compartment model was found to provide the best fit. The addition of covariates did not improve model fit. There was no evidence of auto-inhibition in this population. Population parameter estimates of clearance and volume of distribution were lower than previously reported, with high interindividual variability. Simulations suggested reasonable pharmacokinetic–pharmacodynamic (PKPD) target attainment with current dosing regimens for most organisms that clarithromycin is used to treat with known clinical breakpoints. Conclusions: To our knowledge, this is the first study to describe the pharmacokinetics of intravenous clarithromycin in humans. Although our simulations suggest reasonable target attainment, further investigation into appropriate PKPD targets and clinical breakpoints for clarithromycin may enable dosing optimisation in this population. Full article

In this study, laminates based on polyetherimide (PEI) with contents of carbon fibers (CFs) from 55 to 70 wt.% were fabricated by thermoforming (TF) and ultrasonic additive manufacturing (UAM) methods. The UAM laminates with CF contents above 55 wt.% possessed shear strengths lower by 40% in comparison with those of the TF ones, due to insufficient amounts of the binder in the prepregs to form reliable interlaminar joints. For enhancing the shear strength of the laminates with a CF content of 70 wt.%. up to the levels of the TF ones, extra resin layers with thicknesses of 50, 100, and 150 μm were deposited. By ranking the UAM parameters using the Taguchi method, it was possible to increase the shear strengths by 30% as compared to those of the trial laminates. Further improvements were achieved by artificial neural network (ANN) modeling. As a result, the use of the 50 µm thick extra resin layer made it possible to increase the shear strengths up to 50% relative to those of the trial laminates at a CF content of 70 wt.%. This improvement was achieved via minimizing the number of defects at the interlaminar interfaces. The dependences of both mechanical and structural characteristics of the laminates on the UAM parameters were essentially nonlinear. For their analysis and optimization of the UAM parameters, the direct propagation neural networks with the minimal architecture were utilized. Under the ultra-small sample conditions, the use of a priori knowledge enabled us to predict the results rather accurately. Full article

A theoretical model is presented for the accurate detection of a gas leak source through a pinhole in a cylindrical storage vessel using the acoustic emission (AE) technique. Pinholes of various diameters ranging from 0.20 to 1.2 mm were installed as leak sources, and safe N₂ was used as a filler gas. AE signals were measured and analyzed in terms of AE parameters (such as frequency, amplitude and RMS) as a function of angle and axial distance. Among them, the amplitude characteristic was the most important parameter to determine the leakage dynamics of AE with a continuous waveform. The simulation of AE amplitude was performed using the theoretical model for AE. For practical applications, the theoretical formula was modified into two semi-empirical equations by introducing the normalization method to fit the angular and axial characteristics of the observed AE amplitude, respectively. The main finding of this study is that the semi-empirical equations provide an accurate solution for leak source localization in the cylindrical vessel. As a priori knowledge, the value of ${\kappa }_{\eta }$ in Green’s function, which determines the angular and axial dependence of the AE amplitude, was determined by applying external excitation to the cylinder surface. The proposed formulas provide a suitable approach for practical application in the localization of leak sources in cylindrical storage tanks. Full article