Radiology report generation (RRG) converts chest X-rays into structured findings and impressions, but autoregressive systems can propagate early entity, negation, or anatomical errors, and language-model-based systems may rely on language priors when visual evidence is weak. We propose SEDRRG, structured evidence-guided discrete diffusion for radiology report generation, an image-conditioned framework that refines the whole report sequence through discrete token denoising. SEDRRG combines Swin-V2 hierarchical global and patch-level evidence with denoising-time global-local gating, and uses multi-factor structured supervision to align token recovery with report-derived medical token/phrase cues, image-text alignment, and section organization. Experiments on IU X-Ray and MIMIC-CXR show competitive benchmark-level performance against representative autoregressive, knowledge-enhanced, expert-token-based, and language-model-assisted baselines under reproduced and literature-reported comparison settings. A complementary CheXbert-based 14-observation clinical-efficacy evaluation on MIMIC-CXR yields precision of 0.322, recall of 0.375, and F1 of 0.346. Ablation and controlled analyses support the contributions of hierarchical evidence encoding, gated conditioning, and structured supervision. These results position SEDRRG as a benchmark-oriented algorithmic framework, not as evidence of clinical deployment readiness.

Soft sensing technology plays a crucial role in the real-time monitoring and optimization of key industrial variables. Recently, Transformers have emerged as a promising tool for soft sensor development, owing to natural advantages in dealing with long-range temporal correlations and complex nonlinearities. However, the conventional Transformer-based soft sensors are developed in a global learning framework, suffering from performance degradation in processes with multiple working conditions. To address this limitation, a conditional Gaussian mixture model (CGMM)-guided Transformer is developed in this article. Specifically, a CGMM, differentiating the physical properties and distributional discrepancies of manipulated and process variables, is first designed for high-accuracy recognition of the working conditions. Then, a condition-adaptive Transformer is proposed to accommodate variations in working conditions by capturing localized spatial-temporal characteristics based on the CGMM. Experimental results on both a numerical example and an industrial case demonstrate the superiority of the CGMM-Transformer over baseline models.

Orthogonal time frequency space (OTFS) modulation has emerged as a transformative technology for enabling reliable wireless communications in high-mobility scenarios (such as low-altitude wireless networks) by leveraging signal processing in the delay-Doppler (DD) domain. Furthermore, integrating OTFS with multiple-input multiple-output (MIMO) technology unlocks spatial flexibility, significantly enhancing system performance. This paper introduces the novel precoding design for multi-user MIMO-OTFS systems, aimed at maximizing the weighted sum rate (WSR) while addressing critical computational complexity challenges. We first develop a comprehensive transceiver framework for joint delay-Doppler-spatial (DDS) domain multiplexing and formulate the WSR maximization problem. Next, we systematically explore various precoding algorithms, starting with a weighted minimum mean-square error (WMMSE)-based benchmark that reveals significant computational bottlenecks in practical implementations. Then, we propose an innovative low-complexity singular value decomposition (SVD)-based algorithm to effectively mitigate inter-user interference. To reduce the computational complexity associated with performing SVD on high-dimensional channel state information (CSI) matrices, we focus on an approximated dominant line-of-sight (LoS) channel. The SVD of the LoS channel can be derived analytically by leveraging the structural properties of the DD and spatial domains, thereby significantly lowering the computational burden. Extensive simulations demonstrate that the proposed low-complexity SVD-based algorithm not only achieves competitive WSR performance but also reduces computational overhead by orders of magnitude compared to conventional methods. Moreover, it requires only partial (LoS-only) CSI, making it highly suitable for practical deployment in next-generation high-mobility wireless systems.

Pulse wave diagnosis is not only the basis of modern clinical assessment but also has a history of several thousand years in China. This study proposes a pulse-taking pressure sensor based on surface acoustic wave (SAW), designs a novel balloon-type sensing structure, conducts structural simulation using the finite element method (FEM), and finally performs temperature compensation through machine learning algorithms. First, a balloon-type three-point structure was designed to monitor pulse pressure at the three positions of "Cun," "Guan," and "Chi" through SAW sensors. A polytetrafluoroethylene (PTFE) sphere with a radius of 7.5 mm was selected to simulate the fingertip. Second, COMSOL FEM revealed localized strain concentration and a linear correlation between applied pressure and frequency shift. Finally, to mitigate temperature drift, a model of dingo optimization algorithm-assisted support vector regression (SVR) (DOA-SVR) is developed, which reduced average measurement error to 0.52% over a 0-3-N pressure range and 20 degrees C-40 degrees C temperature span. Experimental pulse waveform measurements under light, moderate, and heavy pressures exhibited distinct "floating," "medium," and "deep" pulse characteristics, demonstrating the sensor's potential for objective and standardized pulse diagnosis.

Scaling test-time compute enhances long chain-of-thought (CoT) reasoning, yet existing approaches face a fundamental trade-off between computational cost and coverage quality: either incurring high training expense or yielding redundant trajectories. We introduce The Geometric Reasoner (TGR), a training-free framework that performs manifold-informed latent foresight search under strict memory bounds. At each chunk boundary, TGR scores candidate latent anchors via a lightweight look-ahead estimate combined with soft geometric regularizers that encourage smooth trajectories and diverse exploration. Chunk-wise KV cache resets keep memory linear in chunk length. On challenging math and code benchmarks, TGR improves robust trajectory coverage, measured by the area under the Pass@k curve (AUC), by up to 13 points on Qwen3-8B, with negligible overhead of about 1.1–1.3 times.

Map generation from remote sensing imagery is a critical task in urban planning and Earth observation. Recently, deep learning-based style transfer methods have emerged as a transformative approach due to the ability to handle complex image features and significantly enhance production efficiency. Unlike existing surveys that broadly cover general image-to-image translation, this paper provides a uniquely targeted review focusing explicitly on the intersection of style transfer algorithms and geographical map synthesis. We systematically trace the evolutionary path from traditional map-making methods and conventional image style transfer techniques to advanced deep learning models, explicitly linking how general feature extraction architectures have been adapted for the strict spatial constraints of remote sensing data. Furthermore, we critically analyze the evolution of generative adversarial networks (GANs)-based style transfer methods and the application in generating map images, categorizing them into text-free and text-annotated generation tasks – a crucial distinction representing the latest innovative frontier in this field. In this paper, the inherent disadvantages of current methods for generating map images from remote sensing imagery, such as incomplete retention of topological map information, blurred road edges, and unstable GAN training, are comprehensively evaluated. Finally, possible solutions and future research directions are proposed to offer new perspectives for advancing highly accurate and practically applicable map image generation through remote sensing style transfer.

To address the flexible regulation requirements of integrated energy systems with high renewable penetration, this study investigates the nonlinear coordination between Vehicle-to-Grid (V2G) and the electricity–hydrogen chain. A Stackelberg-game-based bi-level optimization model is developed, in which the upper level optimizes electricity pricing and incentive signals, while the lower level performs coordinated charging/discharging and multi-energy conversion scheduling. The objective function incorporates electricity trading cost, battery degradation cost, hydrogen-related operating cost, and carbon cost. To quantify whether the joint deployment of the two flexibility resources creates additional value beyond their standalone effects, a synergistic gain index, Δ, is introduced. A nested GA-MILP framework is adopted to solve the resulting problem, providing a tractable and practically implementable strategy for the nonlinear upper-level decisions and the lower-level dispatch problem. Based on 2019 load and electricity-price data together with representative renewable-generation scenarios, the model is evaluated through operational analysis, parameter sensitivity experiments, multi-season robustness tests, and an additional renewable-generation forecast-error stress test. The results show that, within the examined case-study settings, the coordinated use of V2G and the electricity–hydrogen chain achieves the most favorable synergistic outcome when the renewable penetration coefficient is 2.0 and the carbon-cost weight is 1.0, with the best joint capacity configuration occurring at an EV capacity multiplier of 3.0 and a hydrogen-chain capacity multiplier of 1.5. The study provides a quantitative framework for evaluating and scheduling multiple flexibility resources in integrated energy systems.

This paper presents a yarn tension sensor based on Surface Acoustic Waves (SAW). To enhance the detection accuracy of the sensor, an improved beam structure is designed for tension measurement, along with intelligent algorithms for temperature compensation. Firstly, regarding the sensor structure, a simply supported beam with a hyperbolic surface is designed to achieve stress concentration by reducing the section modulus at the beam's midpoint. Secondly, by incorporating an unbalanced split-electrode Interdigital Transducer (IDT) design, the sensor effectively suppresses signal sidelobe interference and significantly improves the structure's tension sensitivity. Finally, in terms of signal processing, to eliminate the influence of environmental temperature fluctuations on measurements, a temperature-compensation algorithm based on Bayesian Optimization Least Squares Support Vector Machine (BO-LSSVM) with Gaussian Process regression is proposed. Experimental results show that the tension sensitivity of the improved structure was 8.2% higher than that of the doubly clamped beam and 12.7% higher than that of the cantilever beam. For temperature compensation, the BO-LSSVM model reduced the Mean Relative Error (MRE) by 5.67 percentage points relative to raw data and by 2.04 percentage points relative to the fixed-parameter LSSVM model, lowering the temperature sensitivity coefficient from 4.09 (& times;10-3/degrees C) to 0.41 (10-3/degrees C).

With the rapid development of IoT and 5G technologies, edge computing has become a critical infrastructure for intelligent applications. However, the openness and heterogeneity of edge computing environments pose severe security challenges: malicious edge nodes may steal sensitive data or tamper with computation results. Existing task scheduling algorithms primarily focus on performance optimization, lacking comprehensive consideration of security and trust. To address these challenges, this paper proposes GraphMatch, a security-aware task scheduling framework based on Graph Convolutional Network (GCN). GraphMatch models task scheduling as a constrained graph matching problem and achieves multi-objective optimization of security, trust, and performance through four synergistic modules: (1) Multi-hop Trust Propagation that expands trust coverage by discovering indirect trust paths; (2) Trust-Guided GCN that learns optimal task-device matching by fusing five scoring mechanisms; (3) NSGA-III-based Multi-objective Optimization that explores Pareto optimal solutions among makespan, trust, and security objectives; (4) Laplacian Load Balancing that achieves workload distribution through spectral graph diffusion. Experimental results demonstrate that GraphMatch achieves a trust score of 0.8869, representing a 10.0% improvement over the state-of-the-art SecDS algorithm. GraphMatch attains 100% malicious device avoidance rate and sensitive task protection rate while maintaining competitive makespan performance. Scalability experiments verify the algorithm's stability across 50-250 device scales, and robustness experiments confirm its reliability under 5%-30% malicious node ratios. GraphMatch provides an effective solution for security-sensitive task scheduling in edge computing.

Indoor fire smoke degrades visible-light cameras and near-infrared Lidar through wavelength-dependent absorption and scattering, threatening robotic navigation safety. Existing path planners either ignore sensor degradation or rely on empirical penalties lacking a physical basis. To address these issues, this paper proposes Quality Cost A* (QC-A*), which maps Fire Dynamics Simulator (FDS) visibility fields to sensor perception quality via the Koschmieder and Beer-Lambert physical laws, embedding a cost function that drives paths away from high-attenuation regions. A multi-sensor fusion layer provides fault tolerance under sensor-specific failure conditions. The method is validated through FDS-based simulations across four smoke scenarios in a 20 m × 6 m corridor with 21 obstacles, using 50 start-goal pairs per scenario. Perception quality derives from Beer-Lambert optical transmittance, while the hazard-zone proportion quantifies path segments with visibility below 5 m. Across the Symmetric and Asymmetric scenarios, QC-A* reduces the low-visibility hazard-zone proportion from 40.7% to 19.6% and improves worst-case perception quality from 0.067 to 0.177, with a 15.3% path length increase, while remaining close to traditional A* in light-smoke conditions. Under constructed sensor failure tests, QC-A* maintains a 96-100% planning success rate versus 48% for Camera-Only and 70% for Lidar-Only. QC-A* shifts sensor degradation modeling from empirical penalty to physical mechanism, achieving a favorable safety-efficiency balance prioritizing perceptual safety, and provides an interpretable, generalizable framework for robotic fire-environment path planning.

In modern industry, it is of great significance to employ data-driven virtual metrology technique to improve production efficiency and quality by predicting key quality variables in an economical and reliable way. Among data-driven algorithms, the transformer is yielding promising results in predicting time series data and handling vast amounts of complex industrial data, due to the superior attention mechanism. In this paper, a novel target adaptive attention (TAA) mechanism is first developed for guiding transformer to focus more on characteristics relating quality variables, by ensuring that the encoder would adaptively identify and capture features with higher correlation with the target quality variables. To handle large-scale industrial data while both the dimensionality and scale of data expanding, the number of encoder layers would increase accordingly, such that the predictive performance of the model would decline; thus successively, the inter-level fusion attention (IFA) mechanism is proposed to add the weighted evaluation of interlevel correlations among different encoder layers to transformer for improving capabilities of feature extraction and enhancing prediction accuracy. Experiments on virtual metrology tasks on the DC process and the primary reformer process illustrate the merits of the proposed method in a sense that the target quality variable is accurately predicted.

Objective Collaborative edge computing (CEC) addresses the service quality issues that arise from the limited resources of a single node in traditional edge computing architectures by integrating resources from multiple edge nodes. However, ensuring reliable task offloading in this collaborative environment remains a significant challenge. Existing solutions often struggle to balance the intelligence and trustworthiness of offloading decisions effectively. This imbalance can lead to poor performance and reduced task success rates, especially if tasks are offloaded to malicious nodes.Methods To tackle these challenges, this paper proposes a trust-enabled decentralized task offloading scheme that combines blockchain technology and deep reinforcement learning (DRL). First, we introduce a blockchain-based reputation mechanism within the CEC architecture to facilitate trusted collaboration among nodes, utilizing smart contracts for reputation management. Next, we propose a beta distribution-based three-factor reputation update (BTRU) algorithm to enhance the accuracy of reputation evaluation. Finally, we present a decentralized and trust-enabled task offloading (DTTO) algorithm based on DRL, which uses on-chain reputation data to guide agents in learning trustworthy task offloading policies, thereby maximizing offloading trustworthiness and task success rates.Result To thoroughly assess the effectiveness and practicality of our proposed scheme, we develop a testbed for CEC task offloading based on Kubernetes and Ethereum. Experimental results demonstrate that the BTRU algorithm effectively distinguishes malicious nodes, reducing their average reputation by 97.54%, with an improvement of 9.94% compared to competitive algorithms. Meanwhile, the DTTO algorithm significantly enhances the efficiency and reliability of task offloading, raising the task success rate by at least 3.04%, especially when the proportion of malicious nodes reaches 40%, its task success rate is at least 5.41% higher than that of competitive algorithms.Conclusion The proposed trust-enabled decentralized task offloading scheme successfully combines blockchain-based reputation management with DRL to achieve both intelligent and trustworthy task offloading in the CEC environments. The experimental validation confirms the scheme's effectiveness in identifying malicious nodes and improving task success rates under various system conditions.

In symbiotic radio (SR), the secondary system not only shares the spectrum and power of the primary system but also enhances its performance by providing multipath gains, fostering a cooperative mutualism between the two systems. However, in high-mobility channels, time-frequency selective fading presents significant challenges for reliable SR communications. The recently introduced orthogonal time-frequency space (OTFS) technique, which processes signals in the delay-Doppler (DD) domain, is expected to improve SR communication performance in high-speed mobile scenarios. In this paper, we propose embedding primary information symbols in the DD domain using amplitude-phase modulation, while employing a combinatorial frequency (CF) modulation strategy for secondary information transmission. To obtain channel state information (CSI) and detect secondary symbols, for some special scenarios, we propose an off-grid sparse Bayesian learning (SBL)-based method. This method first estimates the equivalent CSI and then detects the symbols by leveraging the highly structured Doppler shifts. For more general scenarios, we introduce a model-driven equivalent CSI estimation-net (ECSIEst-Net) and a data-driven secondary symbol detection-Net (SSymDet-Net). Numerical results are provided to guide parameter selection and demonstrate the effectiveness of the proposed methods.

This paper presents a design method for a continuous tension detection sensor based on a cantilever beam structure and compensates for the temperature drift of a SAW sensor based on a neural network algorithm. Firstly, a novel cantilever beam roller structure is proposed to significantly enhance the sensitivity of the transmission of silk thread tension to a SAW tension sensor. Secondly, to improve the sensitivity of the SAW tension sensor, the COMSOL finite element method (FEM) is employed for simulation to determine the optimal IDT placement. An unbalanced split IDT design is utilized to suppress potential parasitic responses. Finally, the designed sensor is tested, and a GA-PSO-BP algorithm is employed to fit the test data for temperature compensation. The experimental results demonstrate that the temperature sensitivity coefficient of the data optimized by the GA-PSO-BP algorithm is reduced by an order of magnitude compared to the raw data, with reductions of 6.0409×10−3 °C−1 and 3.0312×10−3 °C−1 compared to the BP neural network and the PSO-BP algorithm, respectively. The average output error of the optimized data is reduced by 5.748% compared to the sensor measurement data, and it is also lower than both the BP neural network and the PSO-BP algorithm. It provides new design ideas for the development of tension sensors.

This paper proposes an Adam-optimized Deep Belief Networks (Adam-DBNs) denoising method for throat-attached piezoelectric signals. The method aims to process mechanical vibration signals captured through polyvinylidene fluoride (PVDF) sensors attached to the throat region, which are typically contaminated by environmental noise and physiological noise. First, the short-time Fourier transform (STFT) is utilized to convert the original signals into the time–frequency domain. Subsequently, the masked time–frequency representation is reconstructed into the time domain through a diagonal average-based inverse STFT. To address complex nonlinear noise structures, a Deep Belief Network is further adopted to extract features and reconstruct clean signals, where the Adam optimization algorithm ensures the efficient convergence and stability of the training process. Compared with traditional Convolutional Neural Networks (CNNs), Adam-DBNs significantly improve waveform similarity by 6.77% and reduce the local noise energy residue by 0.099696. These results demonstrate that the Adam-DBNs method exhibits substantial advantages in signal reconstruction fidelity and residual noise suppression, providing an efficient and robust solution for throat-attached piezoelectric sensor signal enhancement tasks.

In recent years, with the development of technologies such as computer vision, machine learning, and deep learning, as well as the popularity of large-scale data collection devices, 3D point cloud processing has become increasingly important. 3D point cloud processing can be widely used in fields such as object recognition, robot navigation, building information modeling (BIM), and urban planning. With more and more 3D point cloud data acquired, it has become a challenge for present 3D point cloud processing models to accurately and efficiently process this data. To improve the accuracy of point cloud classification and segmentation tasks, this study proposes an improved point cloud classification and segmentation model based on neighborhood aware information fusion. The model includes a Fusion Neighbor Information Feature Enhancement (FNIFE) module, which connects points in the local neighborhood and obtains the features of the current point through the feature relationships between the points in the neighborhood. By enhancing the feature expression of the point, it reduces the feature loss caused by the feature extraction operation and improves the accuracy of point cloud classification. Additionally, the model includes a Reverse Transmission of Point Features (RToPF) module, in which interpolation parameters are adjusted to ensure that the enhanced feature information can be effectively transmitted, thereby improving the accuracy and computing speed of the model. Finally, to further improve classification accuracy further, a module containing the X-Conv operator is utilized in the model to replace the max-pooling in the original network and reduce the feature loss generated during feature extraction. Comparative experiments are conducted on ModelNet40, ShapeNet, S3DIS datasets and ScanNet datasets. The experimental results show that the overall accuracy of proposed model reaches 92.4%. The average accuracy reaches 90.2% in the point cloud classification task, and the average intersection ratio reaches 84.5% in the point cloud segmentation task, achieving superior performance in classification and segmentation tasks compared with the state-of-the-art models.

Water color remote sensing is vital for the monitoring and quantification of marine suspended sediment dynamics and their distributions. Yet validations of these observables in coastal regions and deltaic estuaries, including the Hangzhou Bay in the East China Sea, remain challenging, primarily due to the pronounced complex oceanic dynamics that exhibit high spatiotemporal variability in the signals of the suspended sediment concentration (SSC) in the ocean. Here, we integrate satellite images from the sun-synchronous satellites, China’s Huanjing (Chinese for environmental, HJ)-1A/B (charged couple device) CCD (30 m), and from Korea’s Geostationary Ocean Color Imager GOCI (500 m) to the spatiotemporal scale effects to validate SSC remote sensing-retrieved data products. A multi-scale validation framework based on coefficient of variation (CV)-based zoning was developed, where high-resolution HJ CCD SSC data were resampled to the GOCI scale (500 m), and spatial variability was quantified using CV values within corresponding HJ CCD windows. Traditional validation, comparing in situ point measurements directly with GOCI pixel-averaged data, introduces significant uncertainties due to pixel heterogeneity. The results indicate that in regions with high spatial heterogeneity (CV > 0.10), using central pixel values significantly weakens correlations and increases errors, with performance declining further in highly heterogeneous areas (CV > 0.15), underscoring the critical role of spatial averaging in mitigating scale-related biases. This study enhances the quantitative assessment of uncertainties in validating medium-to-low-resolution water color products, providing a robust approach for high-dynamic oceanic environment estuaries and bays.

Hyperuricemia has seen a continuous increase in incidence and a trend towards younger patients in recent years, posing a serious threat to human health and highlighting the urgency of using technological means for disease risk prediction. Existing risk prediction models for hyperuricemia typically include two major categories of indicators: routine blood tests and biochemical tests. The potential of using routine blood tests alone for prediction has not yet been explored. Therefore, this paper proposes a hyperuricemia risk prediction model that integrates Particle Swarm Optimization (PSO) with machine learning, which can accurately assess the risk of hyperuricemia by relying solely on routine blood data. In addition, an interpretability method based on Explainable Artificial Intelligence(XAI) is introduced to help medical staff and patients understand how the model makes decisions. This paper uses Cohen's d value to compare the differences in indicators between hyperuricemia and non-hyperuricemia patients and identifies risk factors through multivariate logistic regression. Subsequently, a risk prediction model is constructed based on the parameter optimization of five machine learning models using the PSO algorithm. The accuracy and sensitivity of the proposed particle swarm fusion Stacking model reach 97.8% and 97.6%, marking an improvement in accuracy of over 11% compared to the state-of-the-art models. Finally, a sensitivity analysis of factors affecting the prediction results is conducted using the XAI method. This paper has also developed a Health Portrait Platform that integrates the proposed risk prediction models, enabling real-time online health risk assessment. Since only routine blood test data are used, the new model has better feasibility and scalability, providing a valuable reference for assessing the risk of hyperuricemia occurrence.

To effectively account for the impact of fluctuations in the power generation efficiency of renewable energy sources such as photovoltaics (PVs) and wind turbines (WTs), as well as the uncertainties in load demand within an integrated energy system (IES), this article develops an IES model incorporating power generation units such as PV, WT, microturbines (MTs), Electrolyzer (EL), and Hydrogen Fuel Cell (HFC), along with energy storage components including batteries and heating storage systems. Furthermore, a demand response (DR) mechanism is introduced to dynamically regulate the energy supply–demand balance. In modeling uncertainties, this article utilizes historical data on PV, WT, and loads, combined with the adjustability of decision variables, to generate a large set of initial scenarios through the Monte Carlo (MC) sampling algorithm. These scenarios are subsequently reduced using a combination of the K-means clustering algorithm and the Simultaneous Backward Reduction (SBR) technique to obtain representative scenarios. To further manage uncertainties, a distributionally robust optimization (DRO) approach is introduced. This method uses 1-norm and ∞-norm constraints to define an ambiguity set of probability distributions, thereby restricting the fluctuation range of probability distributions, mitigating the impact of deviations on optimization results, and achieving a balance between robustness and economic efficiency in the optimization process. Finally, the model is solved using the column and constraint generation algorithm, and its robustness and effectiveness are validated through case studies. The MC sampling method adopted in this article, compared to Latin hypercube sampling followed by clustering-based scenario reduction, achieves a maximum reduction of approximately 17.81% in total system cost. Additionally, the results confirm that as the number of generated scenarios increases, the optimized cost decreases, with a maximum reduction of 1.14%. Furthermore, a comprehensive cost analysis of different uncertainties modeling approaches is conducted, demonstrating that the optimization results lie between those obtained from stochastic optimization (SO) and robust optimization (RO), effectively balancing conservatism and economic efficiency.