Search Results (12,418)

Surrogate modeling has been rapidly evolving in the field of aerospace engineering, further reducing the cost of computational analyses. These models often require large amounts of information to learn the underlying process, which is at odds with obtaining and using the highest-fidelity data. This study assesses the efficacy of multi-fidelity modeling (MFM) to improve simulation accuracy while reducing computational cost. A database of hovering rotor simulations with perturbations of the rotor design and operating conditions was first generated using two different fidelity levels of the OVERFLOW 2.4D Computational Fluid Dynamics software. MFM was then used to quantify the effectiveness of this approach for the development of accurate surrogate models. Multi-fidelity models based on Gaussian Process Regression (GPR) were derived for hovering rotor performance prediction given the geometric rotor blade inputs that currently include twist, planform, airfoil, and the collective pitch angle. The MFM approach was consistently more accurate at predicting the hold-out test data than the surrogate model with high-fidelity data alone. An MFM using just 20% of the available high-fidelity training data was as accurate as a solely high-fidelity model trained on 80% of the available data, representing an approximate fourfold reduction in computational cost. Full article

Single-image super-resolution (SISR) plays a critical role in enhancing visual quality for real-world applications, including industrial inspection and embedded vision systems. While deep learning-based approaches have made significant progress in SR, existing lightweight SR models often fail to accurately reconstruct high-frequency textures, especially under complex degradation scenarios, resulting in blurry edges and structural artifacts. To address this challenge, we propose a Dense Residual Fused Attention Network (DRFAN), a novel lightweight hybrid architecture designed to enhance high-frequency texture recovery in challenging degradation conditions. Moreover, by coupling convolutional layers and attention mechanisms through gated interaction modules, the DRFAN enhances local details and global dependencies with linear computational complexity, enabling the efficient utilization of multi-level spatial information while effectively alleviating the loss of high-frequency texture details. To evaluate its effectiveness, we conducted ×4 super-resolution experiments on five public benchmarks. The DRFAN achieves the best performance among all compared lightweight models. Visual comparisons show that the DRFAN restores more accurate geometric structures, with up to +1.2 dB/+0.0281 SSIM gain over SwinIR-S on Urban100 samples. Additionally, on a domain-specific rice grain dataset, the DRFAN outperforms SwinIR-S by +0.19 dB in PSNR and +0.0015 in SSIM, restoring clearer textures and grain boundaries essential for industrial quality inspection. The proposed method provides a compelling balance between model complexity and image reconstruction fidelity, making it well-suited for deployment in resource-constrained visual systems and industrial applications. Full article

Ghost imaging (GI) facilitates image acquisition under low-light conditions through single pixel measurements, thus holding tremendous potential across various fields such as biomedical imaging, remote sensing, defense and military applications, and 3D imaging. However, in order to reconstruct high-resolution images, GI typically requires a large number of single-pixel measurements, which imposes practical limitations on its application. Parallel ghost imaging addresses this issue by utilizing each pixel of a position-sensitive detector as a bucket detector to simultaneously perform tens of thousands of ghost imaging measurements in parallel. In this work, we explore the non-local characteristics of ghost imaging in depth, and by constructing a large speckle space, we achieve a reconstruction result in parallel ghost imaging where the field of view surpasses the limitations of the reference arm detector. Using a computational ghost imaging framework, after pre-recording the speckle patterns, we are able to complete X-ray ghost imaging at a speed of 6 min per sample, with image dimensions of 14,000 × 10,000 pixels (4.55 mm × 3.25 mm, millimeter-scale field of view) and a pixel resolution of 0.325 µm (sub-micron pixel resolution). We present this framework to enhance efficiency, extend resolution, and dramatically expand the field of view, with the aim of providing a solution for the practical implementation of ghost imaging. Full article

This paper proposes a speed-adaptive autonomous driving path-tracking framework based on the soft actor–critic (SAC) and pure pursuit (PP) methods, named the SACPP controller. The framework first analyzes the obstacles around the vehicle and plans an obstacle-free reference path with the minimum curvature using the hybrid A* algorithm. Next, based on the generated reference path, the current state of the vehicle, and the vehicle motor energy efficiency diagram, the optimal speed is calculated in real time, and the vehicle dynamics preview point at the future moment—specifically, the look-ahead distance—is predicted. This process relies on the learning of the SAC network structure. Finally, PP is used to generate the front wheel angle control value by combining the current speed and the predicted preview point. In the second layer, we carefully designed the evaluation function in the tracking process based on the uncertainties and performance requirements that may occur during vehicle driving. This design ensures that the autonomous vehicle can not only quickly and accurately track the path, but also effectively avoid surrounding obstacles, while keeping the motor running in the high-efficiency range, thereby reducing energy loss. In addition, since the entire framework uses a lightweight network structure and a geometry-based method to generate the front wheel angle, the computational load is significantly reduced, and computing resources are saved. The actual running results on the i7 CPU show that the control cycle of the control framework exceeds 100 Hz. Full article

Background/Objectives: Atrial fibrillation (AF) is a prevalent arrhythmia associated with a high risk of major adverse cardiovascular events (MACEs). This study aimed to compare the predictive ability of an ML model and the CHA₂DS₂-VASc score in predicting MACEs in AF patients using machine learning (ML) techniques. Methods: A cohort of 40,297 individuals aged 65–95 from the Terres de l’Ebre region (Catalonia, Spain) and diagnosed with AF between 2015 and 2016 was analyzed. ML algorithms, particularly AdaBoost, were used to predict MACEs, and the performance of the models was evaluated through metrics such as recall, area under the ROC curve (AUC), and accuracy. Results: The AdaBoost model outperformed CHA₂DS₂-VASc, achieving an accuracy of 99.99%, precision of 0.9994, recall of 1, and an AUC of 99.99%, compared to CHA₂DS₂-VASc’s AUC of 81.71%. A statistically significant difference was found using DeLong’s test (p = 0.0034) between the models, indicating the superior performance of the AdaBoost model in predicting MACEs. Conclusions: The AdaBoost model provides significantly better prediction of MACE in AF patients than the CHA₂DS₂-VASc score, demonstrating the potential of ML algorithms for personalized risk assessment and early detection in clinical settings. Further validation and computational resources are necessary to enable broader implementation. Full article

With the growing global demand for clean energy, the accuracy of wind-power forecasting plays a vital role in ensuring the stable operation of power systems. However, wind-power generation is significantly influenced by meteorological conditions and is characterized by high uncertainty and multiscale fluctuations. Traditional recurrent neural network (RNN) and long short-term memory (LSTM) models, although capable of handling sequential data, struggle with modeling long-term temporal dependencies due to the vanishing gradient problem; thus, they are now rarely used. Recently, Transformer models have made notable progress in sequence modeling compared to RNNs and LSTM models. Nevertheless, when dealing with long wind-power sequences, their quadratic computational complexity (O(L²)) leads to low efficiency, and their global attention mechanism often fails to capture local periodic features accurately, tending to overemphasize redundant information while overlooking key temporal patterns. To address these challenges, this paper proposes a wind-power forecasting method based on dimension-transformed collaborative multidimensional multiscale attention (DTCMMA). This method first employs fast Fourier transform (FFT) to automatically identify the main periodic components in wind-power data, reconstructing the one-dimensional time series as a two-dimensional spatiotemporal representation, thereby explicitly encoding periodic features. Based on this, a collaborative multidimensional multiscale attention (CMMA) mechanism is designed, which hierarchically integrates channel, spatial, and pixel attention to adaptively capture complex spatiotemporal dependencies. Considering the geometric characteristics of the reconstructed data, asymmetric convolution kernels are adopted to enhance feature extraction efficiency. Experiments on multiple wind-farm datasets and energy-related datasets demonstrate that DTCMMA outperforms mainstream methods such as Transformer, iTransformer, and TimeMixer in long-sequence forecasting tasks, achieving improvements in MSE performance by 34.22%, 2.57%, and 0.51%, respectively. The model’s training speed also surpasses that of the fastest baseline by 300%, significantly improving both prediction accuracy and computational efficiency. This provides an efficient and accurate solution for wind-power forecasting and contributes to the further development and application of wind energy in the global energy mix. Full article

Hydrogen is a promising zero-carbon fuel for internal combustion engines; however, the geometric optimization of injectors for low-pressure direct-injection (LPDI) systems under lean-burn conditions remains underexplored. This study presents a high-fidelity optimization framework that couples a validated computational fluid dynamics (CFD) combustion model with a surrogate-assisted multi-objective genetic algorithm (MOGA). The CFD model was validated using particle image velocimetry (PIV) data from non-reacting flow experiments conducted in an optically accessible research engine developed by Sandia National Laboratories, ensuring accurate prediction of in-cylinder flow structures. The optimization focused on two critical geometric parameters: injector hole count and injection angle. Partial indicated mean effective pressure (pIMEP) and in-cylinder NO_x emissions were selected as conflicting objectives to balance performance and emissions. Adaptive mesh refinement (AMR) was employed to resolve transient in-cylinder flow and combustion dynamics with high spatial accuracy. Among 22 evaluated configurations including both capped and uncapped designs, the injector featuring three holes at a 15.24° injection angle outperformed the baseline, delivering improved mixture uniformity, reduced knock tendency, and lower NO_x emissions. These results demonstrate the potential of geometry-based optimization for advancing hydrogen-fueled LPDI engines toward cleaner and more efficient combustion strategies. Full article

Aerosol uniformity in the mixing chamber is one of the key factors in evaluating performance of aerosol samplers and accuracy of aerosol monitors which could output the direct reading of particle size or concentration. For obtaining high uniformity and a stable test aerosol sample during evaluation, a portable mixing chamber, where the sample and clean air were dual-vortex turbulent mixed, was designed. By using computational fluid dynamics (CFD), particle motion within the mixing chamber was illustrated or explained. By adjusting critical structure parameters of chamber such as height and diameter, the flow field structure was optimized to improve particle mixing characteristics. Accordingly, a novel portable aerosol mixing chamber with length and inner diameter of 0.7 m and 60 mm was developed. Through a combination of simulations and experiments, the operating conditions, including working flow rate, ratio of carrier/dilution clean air, and mixture duration, were studied. Finally, by using the optimized parameters, a mixing chamber with high spatial uniformity where variation is less than 4% was obtained for aerosol particles ranging from 0.3 μm to 10 μm. Based on this chamber, a standardized testing platform was established to verify the sampling efficiency of aerosol samplers with high flow rate (28.3 L·min⁻¹). The obtained results were consistent with the reference values in the sampler’s manual, confirming the reliability of the evaluation system. The testing platform developed in this study can provide test aerosol particles ranging from sub-micrometers to micrometers and has significant engineering applications, such as atmospheric pollution monitoring and occupational health assessment. Full article

The rapid growth of Internet of Things (IoT) environments has increased security challenges due to heightened exposure to cyber threats and attacks. A key problem is the class imbalance in attack traffic, where critical yet underrepresented attacks are often overlooked by intrusion-detection systems (IDS), thereby compromising reliability. We propose Feature-Importance GAN SMOTE (FIGS), an innovative, realistic intrusion-detection framework designed for IoT environments to address this challenge. Unlike other works that rely only on traditional oversampling methods, FIGS integrates sensitivity-based feature-importance analysis, Generative Adversarial Network (GAN)-based augmentation, a novel imbalance ratio (GIR), and Synthetic Minority Oversampling Technique (SMOTE) for generating high-quality synthetic data for minority classes. FIGS enhanced minority class detection by focusing on the most important features identified by the sensitivity analysis, while minimizing computational overhead and reducing noise during data generation. Evaluations on the CICIoMT2024 and CICIDS2017 datasets demonstrate that FIGS improves detection accuracy and significantly lowers the false negative rate. FIGS achieved a 17% improvement over the baseline model on the CICIoMT2024 dataset while maintaining performance for the majority groups. The results show that FIGS represents a highly effective solution for real-world IoT networks with high detection accuracy across all classes without introducing unnecessary computational overhead. Full article

Fagonia cretica, a medicinal herb from the Zygophyllaceae family, is traditionally utilized to treat various conditions such as hepatitis, gynecological disorders, tumors, urinary tract issues, and diabetes. The present study aimed to evaluate the therapeutic potential of Fagonia cretica in treating polycystic ovarian syndrome (PCOS) induced in female rats. PCOS, a complex hormonal disorder, was experimentally induced by administering Letrozole (1 mg/kg) in combination with a high-fat diet for 21 days. The affected rats were then treated with hydro-alcoholic extracts of Fagonia cretica at doses of 100 mg/kg, 200 mg/kg, and 300 mg/kg for 20 days. Key biochemical parameters—including serum testosterone, insulin, fasting blood glucose, insulin resistance (HOMA-IR), cholesterol, triglycerides, and lipoprotein levels—were measured. Ultrasound imaging and histopathological analysis of ovarian tissues were also performed. The data were analyzed using computer-based statistical tools, including one-way ANOVA, Cohen’s d effect size, and Tukey’s HSD test, with graphical representations generated using Python 3.10 on the Kaggle platform. Results demonstrated a significant reduction in serum testosterone, insulin, cholesterol, and triglyceride levels (p < 0.05) in treated groups, along with improved ovarian morphology. These findings support the therapeutic potential of Fagonia cretica as a natural treatment for PCOS. Full article

In this paper, we aim to develop an efficient algorithm for the solving Tensor Robust Principal Component Analysis (TRPCA) problem, which focuses on obtaining a low-rank approximation of a tensor by separating sparse and impulse noise. A common approach is to minimize the convex surrogate of the tensor rank by shrinking its singular values. Due to the existence of various definitions of tensor ranks and their corresponding convex surrogates, numerous studies have explored optimal solutions under different formulations. However, many of these approaches suffer from computational inefficiency primarily due to the repeated use of tensor singular value decomposition in each iteration. To address this issue, we propose a novel TRPCA algorithm that introduces a new convex relaxation for the tensor norm and computes low-rank approximation more efficiently. Specifically, we adopt the tensor average rank and tensor nuclear norm, and further relax the tensor nuclear norm into a sum of the tensor Frobenius norms of the factor tensors. By alternating updates of the truncated factor tensors, our algorithm achieves efficient use of computational resources. Experimental results demonstrate that our algorithm achieves significantly faster performance than existing reference methods known for efficient computation while maintaining high accuracy in recovering low-rank tensors for applications such as color image recovery and background subtraction. Full article

Random Forests are powerful machine learning models widely applied in classification and regression tasks due to their robust predictive performance. Nevertheless, traditional Random Forests face computational challenges during tree construction, particularly in high-dimensional data or on resource-constrained devices. In this paper, a novel node-splitting algorithm, BayesSplit, is proposed to accelerate decision tree construction via a Bayesian-based impurity estimation framework. BayesSplit treats impurity reduction as a Bernoulli event with Beta-conjugate priors for each split point and incorporates two main strategies. First, Dynamic Posterior Parameter Refinement updates the Beta parameters based on observed impurity reductions in batch iterations. Second, Posterior-Derived Confidence Bounding establishes statistical confidence intervals, efficiently filtering out suboptimal splits. Theoretical analysis demonstrates that BayesSplit converges to optimal splits with high probability, while experimental results show up to a 95% reduction in training time compared to baselines and maintains or exceeds generalization performance. Compared to the state-of-the-art MABSplit, BayesSplit achieves similar accuracy on classification tasks and reduces regression training time by 20–70% with lower MSEs. Furthermore, BayesSplit enhances feature importance stability by up to 40%, making it particularly suitable for deployment in computationally constrained environments. Full article

Aluminium alloy 6082 is widely used in the automotive and aerospace industries due to its high strength-to-weight ratio. However, its structural integrity can sometimes be affected by an early fatigue failure. This study investigates the fatigue performance of extruded 6082-T6 samples through a series of fatigue tests conducted at varying stress levels. The material showed significant variability under identical fatigue conditions, suggesting the presence of microstructural defects. Scanning electron microscopy with energy-dispersive spectroscopy (SEM/EDS) and scanning transmission electron microscopy (S/TEM) were used to identify the nature and location of the defects and evaluate the underlying mechanisms influencing the fatigue performance. Computer tomography (CT) also confirmed the presence of oxide inclusions on the fracture surface and near the edges of the samples. These oxide inclusions are distributed throughout the material heterogeneously and in the form of broken oxide films, suggesting that they might have originated during the material’s early processing stages. These oxides acted as stress concentrators, initiating microcracks that led to catastrophic and unpredictable early failure, ultimately reducing the fatigue life of micro-oxide-containing samples. These results highlight the need for better casting control and improved post-processing techniques to minimise the effect of oxide presence in the final components, thus enhancing their fatigue life. Full article

The electrocatalytic CO₂ reduction reaction (CO₂RR) offers an energy-saving and environmentally friendly approach to producing hydrocarbon fuels. The use of a gas diffusion electrode (GDE) flow cell has generally improved the rate of CO₂RR, while the gas diffusion layer (GDL) remains a significant challenge. In this study, we successfully engineered a novel metal–organic framework (MOF) heterojunction through the controlled coating of zeolitic imidazolate framework (ZIF-L) on ultrathin nickel—metal–organic framework (Ni-MOF) nanosheets. This innovative architecture simultaneously integrates GDL functionality and exposes abundant solid–liquid–gas triple-phase boundaries. The resulting Ni-MOF@ZIF-L heterostructure demonstrates exceptional performance, achieving a formate Faradaic efficiency of 92.4% while suppressing the hydrogen evolution reaction (HER) to 6.7%. Through computational modeling of the optimized heterojunction configuration, we further elucidated its competitive adsorption behavior and electronic modulation effects. The experimental and theoretical results demonstrate an improvement in electrochemical CO₂ reduction activity with suppressed hydrogen evolution for the heterojunction because of its hydrophobic interface, good electron transfer capability, and high CO₂ adsorption at the catalyst interface. This work provides a new insight into the rational design of porous crystalline materials in electrocatalytic CO₂RR. Full article

Blind and visually impaired (BVI) people face significant challenges in perception, navigation, and safety during travel. Existing infrastructure (e.g., blind lanes) and traditional aids (e.g., walking sticks, basic audio feedback) provide limited flexibility and interactivity for complex environments. To solve this problem, we propose a real-time travel assistance system based on deep learning. The hardware comprises an NVIDIA Jetson Nano controller, an Intel D435i depth camera for environmental sensing, and SG90 servo motors for feedback. To address embedded device computational constraints, we developed a lightweight object detection and segmentation algorithm. Key innovations include a multi-scale attention feature extraction backbone, a dual-stream fusion module incorporating the Mamba architecture, and adaptive context-aware detection/segmentation heads. This design ensures high computational efficiency and real-time performance. The system workflow is as follows: (1) the D435i captures real-time environmental data; (2) the processor analyzes this data, converting obstacle distances and path deviations into electrical signals; (3) servo motors deliver vibratory feedback for guidance and alerts. Preliminary tests confirm that the system can effectively detect obstacles and correct path deviations in real time, suggesting its potential to assist BVI users. However, as this is a work in progress, comprehensive field trials with BVI participants are required to fully validate its efficacy. Full article