Search Results (7,376)

With the advancement of electromagnetic interference and counter-interference technology, complex and unpredictable interference signals greatly reduce radar detection, tracking, and recognition performance. In multi-interference environments, the overlap of interference cross-correlation peaks can mask target signals, weakening radar interference suppression capability. To address this, we propose a joint waveform and filter design method called Multi-Interference Suppression Network (MISNet) for effective interference suppression. First, we develop a design criterion based on suppression coefficients for different interferences, minimizing both cross-correlation energy and interference peak models. Then, for the non-smooth, non-convex optimization problem, we use complex neural networks and gating mechanisms, transforming it into a differentiable problem via end-to-end training to optimize the transmit waveform and receive filter efficiently. Simulation results show that compared to traditional algorithms, MISNet effectively reduces interference cross-correlation peaks and autocorrelation sidelobes in single interference environments; it demonstrates excellent robustness in multi-interference environments, significantly outperforming CNN, PSO, and ANN comparison methods, effectively improving radar interference suppression performance in complex multi-interference scenarios. Full article

With the continuous scaling-down of integrated circuit feature sizes, inverse lithography technology (ILT), as the most groundbreaking resolution enhancement technique (RET), has become crucial in advanced semiconductor manufacturing. By directly optimizing mask patterns through inverse computation rather than rule-based local corrections, ILT can more accurately approximate target design patterns while extending the process window. However, current mainstream ILT approaches—whether machine learning-based or gradient descent-based—all face the challenge of balancing mask optimization quality and computational time. Moreover, ILT often faces a trade-off between imaging fidelity and manufacturability; fidelity-prioritized optimization leads to explosive growth in mask complexity, whereas manufacturability constraints require compromising fidelity. To address these challenges, we propose an iterative deep learning-based ILT framework incorporating a lightweight model, ghost and adaptive attention U-net (EAAUnet) to accelerate runtime and reduce computational overhead while progressively improving mask quality through multiple iterations based on the pre-trained network model. Compared to recent state-of-the-art (SOTA) ILT solutions, our approach achieves up to a 39% improvement in mask quality metrics. Additionally, we introduce a mask constraint scheme to regulate complex SRAF (sub-resolution assist feature) patterns on the mask, effectively reducing manufacturing complexity. Full article

Background: To report a deep learning-based algorithm for automated segmentation of geographic atrophy (GA) among patients with age-related macular degeneration (AMD). Methods: Validation of a deep learning algorithm was performed using optical coherence tomography (OCT) images from patients in routine clinical care diagnosed with GA, with and without concurrent nAMD. For model construction, a 3D U-Net architecture was used with the output modified to generate a 2D mask. Accuracy of the model was assessed relative to the manual labeling of GA with the Dice similarity coefficient (DSC) and correlation r² scores. Results: The OCT data set included 367 scans from the Spectralis (Heidelberg, Germany) from 55 eyes in 33 subjects; 267 (73%) scans had concurrent nAMD. In parallel, 348 scans were collected using the Cirrus (Zeiss), from 348 eyes in 326 subjects; 101 (29%) scans had concurrent nAMD. For Spectralis data, the mean DSC score was 0.83 and r² was 0.91. For Cirrus data, the mean DSC score was 0.82 and r² was 0.88. Conclusions: The reported deep learning algorithm demonstrated strong agreement with manual grading of GA secondary to AMD on the OCT data set from routine clinical practice. The model performed well across two OCT devices as well as amongst patients with GA with concurrent nAMD, suggesting applicability in the clinical space. Full article

We propose a phase-aware complex-spectrogram autoencoder (AE) for preprocessing raw vibration signals of rotating electrical machines. The AE reconstructs normal components and separates fault components as residuals, guided by an input-phasor phase-orthogonality regularization that defines parallel/orthogonal residuals with respect to the local signal phase. We use a U-Net-based AE with a mask-bias head to refine local magnitude and phase. Decisions are based on residual features—magnitude/shape, frequency distribution, and projections onto the normal manifold. Using the AI Hub open dataset from field ventilation motors, we evaluate eight representative motor cases (2.2–5.5 kW: misalignment, unbalance, bearing fault, belt looseness). The preprocessing yielded clear residual patterns (low-frequency floor rise, resonance-band peaks, harmonic-neighbor spikes), and achieved an area under the receiver operating characteristic curve (ROC-AUC) = 0.998–1.000 across eight cases, with strong leave-one-file-out generalization and good calibration (expected calibration error (ECE) ≤ 0.023). The results indicate that learning to remove normal structure while enforcing phase consistency provides an unsupervised front-end that enhances fault evidence while preserving interpretability on field data. Full article

The simulation of multidimensional wave propagation with variable material parameters is a computationally intensive task, with applications from seismology to electromagnetics. While quantum computers offer a promising path forward, their algorithms are often analyzed in the abstract oracle model, which can mask the high gate-level complexity of implementing those oracles. We present a framework for constructing a quantum algorithm for the multidimensional wave equation with a variable speed profile. The core of our method is a decomposition of the system Hamiltonian into sets of mutually commuting Pauli strings, paired with a dedicated diagonalization procedure that uses Clifford gates to minimize simulation cost. Within this framework, we derive explicit bounds on the number of quantum gates required for Trotter–Suzuki-based simulation. Our analysis reveals significant computational savings for structured block-model speed profiles compared to general cases. Numerical experiments in three dimensions confirm the practical viability and performance of our approach. Beyond providing a concrete, gate-level algorithm for an important class of wave problems, the techniques introduced here for Hamiltonian decomposition and diagonalization enrich the general toolbox of quantum simulation. Full article

Ensuring the structural continuity and completeness of road networks in high-resolution remote sensing imagery remains a major challenge for current deep learning methods, especially under conditions of occlusion caused by vegetation, buildings, or shadows. To address this, we propose a novel post-processing enhancement framework that improves the connectivity and accuracy of initial road extraction results produced by any segmentation model. The method employs a dual-stream encoder architecture, which jointly processes RGB images and preliminary road masks to obtain complementary spatial and semantic information. A core component is the MAF (Multi-Modal Attention Fusion) module, designed to capture fine-grained, long-range, and cross-scale dependencies between image and mask features. This fusion leads to the restoration of fragmented road segments, the suppression of noise, and overall improvement in road completeness. Experiments on benchmark datasets (DeepGlobe and Massachusetts) demonstrate substantial gains in precision, recall, F1-score, and mIoU, confirming the framework’s effectiveness and generalization ability in real-world scenarios. Full article

Urban streetscapes are among the most frequently encountered spatial environments in daily life, and their restorative visual features have a significant impact on well-being. Although existing studies have revealed the relationship between streetscape environments and perceived restorativeness, there remains a lack of scalable, data-driven methods for quantifying such perception at the street level. This study proposes an interpretable and replicable framework for predicting streetscape restorativeness by integrating semantic segmentation, perceptual evaluation, and machine learning techniques. Taking Liwan District of Guangzhou as a case study, street-view images (SVIs) were collected and processed using the Mask2Former model to extract the following five key visual metrics: greenness, openness, enclosure, walkability, and imageability. Based on the Perceived Restorativeness Scale (PRS), an online questionnaire was designed from four dimensions (fascination, being away, compatibility, and extent) to score a random sample of images. A random forest model was then trained to predict the perceptual levels of the full dataset, followed by K-means clustering to identify spatial distribution patterns. The results revealed that there were significant differences in visual characteristics among high, medium, and low restorativeness street types. The proposed framework enables scalable, data-driven evaluation of perceived restorativeness across diverse urban streetscapes. By embedding perceptual metrics into large-scale urban analysis, the framework offers a replicable and efficient approach for identifying streets with low restorative potential—thus providing urban planners and policymakers with a novel tool for prioritizing street-level renewal, improving public well-being, and supporting perception-oriented urban design without the need for labor-intensive fieldwork. Full article

High-voltage switchgear is an important component of the power system, and its operation safety will directly affect the reliability of the power supply of the power system. At present, the operation and maintenance decision-making of the switchgear mainly relies on manual work, which has problems such as low efficiency and poor reliability of judgment results. Therefore, this paper proposes an intelligent operation and maintenance auxiliary method for high-voltage switchgear based on the combination of the Ripplenet algorithm and knowledge graph, which ensures high efficiency while improving the reliability of the results. Among them, the knowledge graph is mainly based on the Bidirectional Encoder Representations from Transformers-Whole Word Masking (BERT-wwm) algorithm, and it is constructed in a bottom-up and top-down manner. It consists of 240 nodes and 960 relationships. Based on this knowledge graph, the intelligent operation and maintenance auxiliary method of high-voltage switchgear based on Ripplenet is studied. Based on textual information such as on-site information and fault reports, the judgment reasoning of the fault type of the high-voltage switchgear and recommendations for operation and maintenance solutions are realized. The diagnostic accuracy of this method for high-voltage switchgear faults can reach 95.96%. Full article

As a major contributor to environmental pollution in recent years, solid waste has become an increasingly significant concern in the realm of sustainable development. Unmanned Aerial Vehicle (UAV) imagery, known for its high spatial resolution, has become a valuable data source for solid waste detection. However, manually interpreting solid waste in UAV images is inefficient, and object detection methods encounter serious challenges due to the patchy distribution, varied textures and colors, and fragmented edges of solid waste. In this study, we proposed an improved instance segmentation approach called Watershed Mask Network for Solid Waste (WMNet-SW) to accurately retrieve solid waste with precise edges from UAV images. This approach combined the well-established Mask R-CNN segmentation framework with the watershed transform edge detection algorithm. The benchmark Mask R-CNN was improved by optimizing the anchor size and Region of Interest (RoI) and integrating a new mask head of Layer Feature Aggregation (LFA) to initially detect solid waste. Subsequently, edges of the detected solid waste were precisely adjusted by overlaying the segments generated by the watershed transform algorithm. Experimental results show that WMNet-SW significantly enhances the performance of Mask R-CNN in solid waste retrieval, increasing the average precision from 36.91% to 58.10%, F1-score from 0.5 to 0.65, and AP from 63.04% to 64.42%. Furthermore, our method efficiently detects the details of solid waste edges, even overcoming the limitations of training Ground Truth (GT). This study provides a solution for retrieving solid waste with precise edges from UAV images, thereby contributing to the protection of the regional environment and ecosystem health. Full article

This study investigates the microenvironment under face masks and respirators, focusing on the influence of material and design characteristics on carbon dioxide (CO₂) concentration, temperature, and relative humidity. Masks and respirators were selected from the three main types of personal protective equipment—textile non-medical masks, surgical masks and respirators. Experimental measurements were conducted to assess how geometric parameters (thickness, bulk density), mass (mass per unit area), and structural parameters (air permeability, face cover area) influence the microclimatic conditions during wear. The results show that thickness, mass per unit area, and bulk density have a significant effect on temperature but negligible influence on CO₂ concentration and humidity. In contrast, air permeability and face cover area play a key role in CO₂ and moisture accumulation: higher permeability significantly reduces both, while larger coverage tends to increase them. These findings support the need for an integrated design approach that balances filtration efficiency with respiratory and thermophysiological comfort, contributing to improved protective performance and user acceptance. Full article

Time-domain signal models have been widely applied to single-channel music source separation tasks due to their ability to overcome the limitations of fixed spectral representations and phase information loss. However, the high acoustic similarity and synchronous temporal evolution between vocals and accompaniment make accurate separation challenging for existing time-domain models. These challenges are mainly reflected in two aspects: (1) the lack of a dynamic mechanism to evaluate the contribution of each source during feature fusion, and (2) difficulty in capturing fine-grained temporal details, often resulting in local artifacts in the output. To address these issues, we propose an attention-driven time-domain convolutional network for vocal and accompaniment source separation. Specifically, we design an embedding attention module to perform adaptive source weighting, enabling the network to emphasize components more relevant to the target mask during training. In addition, an efficient convolutional block attention module is developed to enhance local feature extraction. This module integrates an efficient channel attention mechanism based on one-dimensional convolution while preserving spatial attention, thereby improving the ability to learn discriminative features from the target audio. Comprehensive evaluations on public music datasets demonstrate the effectiveness of the proposed model and its significant improvements over existing approaches. Full article

In image classification tasks, models may occasionally produce incorrect predictions, which can lead to severe consequences in safety-critical applications. For instance, if a model mistakenly classifies a red traffic light as green, it could result in a traffic accident. Therefore, it is essential to assess the confidence level associated with each prediction. Predictions accompanied by high confidence scores are generally more reliable and can serve as a basis for informed decision-making. To address this, the present paper extends the block-scaling approach—originally developed for estimating classifier accuracy on unlabeled datasets—to compute confidence scores for individual samples in image classification. The proposed method, termed block masking confidence (BMC), applies a sliding mask filled with random noise to occlude localized regions of the input image. Each masked variant is classified, and predictions are aggregated across all variants. The final class is selected via majority voting, and a confidence score is derived based on prediction consistency. To evaluate the effectiveness of BMC, we conducted experiments comparing it against Monte Carlo (MC) dropout and a vanilla baseline across image datasets of varying sizes and distortion levels. While BMC does not consistently outperform the baselines under standard (in-distribution) conditions, it shows clear advantages on distorted and out-of-distribution (OOD) samples. Specifically, on the level-3 distorted iNaturalist 2018 dataset, BMC achieves a median expected calibration error (ECE) of 0.135, compared to 0.345 for MC dropout and 0.264 for the vanilla approach. On the level-3 distorted Places365 dataset, BMC yields an ECE of 0.173, outperforming MC dropout (0.290) and vanilla (0.201). For OOD samples in Places365, BMC achieves a peak entropy of 1.43, higher than the 1.06 observed for both MC dropout and vanilla. Furthermore, combining BMC with MC dropout leads to additional improvements. On distorted Places365, the median ECE is reduced to 0.151, and the peak entropy for OOD samples increases to 1.73. Overall, the proposed BMC method offers a promising framework for uncertainty quantification in image classification, particularly under challenging or distribution-shifted conditions. Full article

Background/Objectives: In patients with malignancy, fluid electrolyte imbalance and renal dysfunction have been demonstrated to increase mortality and morbidity. The objective of this study was to evaluate body composition, and clinical and laboratory tests at baseline and at 3 months during chemotherapy and standard fluid therapy in patients with malignancy. Methods: This study included patients with an ECOG performance status of 0–1 who did not have clinically evident organ failure, brain tumors, or a need for intensive care treatment. All received standard fluid therapy and chemotherapy. Examinations, routine laboratory tests, and body composition measurements were performed at the beginning of chemotherapy and again after three months. Results: The number of hypervolemic patients increased. Although the body mass index (BMI) did not change compared to the baseline, serum levels of B-type natriuretic peptide (BNP), calcium, albumin, total cholesterol, high-density lipoprotein (HDL) cholesterol, and triglycerides increased at the second measurement. By month three, the frequency of overhydration (OH) increased. There was a significant, positive, moderate correlation between the difference in OH and the difference in BNP (p = 0.001). The leukocyte, neutrophil, neutrophil-to-lymphocyte ratio, and neutrophil-to-albumin ratio decreased (p < 0.05 for all). Body composition monitor (BCM) measurements revealed that the extracellular fluid/intracellular fluid ratio (E/I) increased at the second measurement (p = 0.001). Conclusions: The frequency of OH and BNP levels increased at three months. An initial fluid deficit or OH was associated with mortality. OH may mask sarcopenia in patients. Therefore, objective assessment of body composition is important for patient management to avoid OH and predict mortality. However, more studies with larger patient populations and long-term follow-up are needed. Full article

This study reports the development of a fiber-optic localized surface plasmon resonance (FO-LSPR) sensor incorporating a three-dimensional micropillar array functionalized with gold nanoparticles. The micropillar structures were fabricated on the fiber facet using a single-mask imprint lithography process, followed by nanoparticle immobilization to create a composite plasmonic surface. Compared with flat polymer-coated fibers, the micropillar array markedly increased the effective sensing surface and enhanced light trapping by providing anti-reflective conditions at the interface. Consequently, the sensor demonstrated superior performance in refractive index sensing, yielding a sensitivity of 4.54 with an R² of 0.984, in contrast to 3.13 and 0.979 obtained for the flat counterpart. To validate its biosensing applicability, Interleukin-8 (IL-8), a cancer-associated cytokine, was selected as a model analyte. Direct immunoassays revealed quantitative detection across a broad dynamic range (0.1–1000 pg/mL) with a limit of detection of 0.013 pg/mL, while specificity was confirmed against non-target proteins. The proposed FO-LSPR platform thus offers a cost-effective and reproducible route to overcome the surface-area limitations of conventional designs, providing enhanced sensitivity and stability. These results highlight the potential of the micropillar-based FO-LSPR sensor for practical deployment in point-of-care diagnostics and real-time biomolecular monitoring. Full article

In this study, we present a cost-effective approach for fabricating nanopores on single-crystal silicon using a silver–alumina–silver (Ag/AAO/Ag) metal–insulator–metal (MIM) structured mask. Self-ordered porous anodic aluminum oxide (AAO) films were prepared via two-step anodization and coated with silver layers on both sides to form the MIM structure. When irradiated with a 532 nm nanosecond laser, the MIM mask excites surface plasmon polaritons (SPPs), resulting in a localized field enhancement that enables the etching of nanopores into the silicon substrate. This method successfully produced nanopores with diameters as small as 50 nm and depths up to 28 nm. The laser-induced SPP-assisted machining significantly enhances the specific surface area of the processed surface, making it promising for applications in catalysis, biosensing, and microcantilever-based devices. For instance, an increased surface area can improve catalytic efficiency by providing more active sites, and enhance sensor sensitivity by amplifying response signals. Compared to conventional lithographic or focused ion beam techniques, this method offers simplicity, low cost, and scalability. The proposed technique demonstrates a practical and efficient route for the large-area subwavelength nanostructuring of silicon surfaces. Full article