Search Results (1,176)

Cross-regional enterprise financial distress can undermine long-term corporate viability, weaken regional industrial resilience, and amplify systemic risk, making robust early-warning tools essential for sustainable financial governance. This study investigates the problem of cross-regional enterprise delisting-related distress identification under heterogeneous economic structures and highly imbalanced risk samples. We propose a cross-domain learning framework that aims to deliver stable, interpretable, and transferable risk signals across regions without requiring access to labeled data from the target domain. Using a multi-source empirical dataset covering Beijing, Shanghai, Jiangsu, and Zhejiang, we conduct leave-one-domain-out evaluations that simulate real-world regulatory deployment. The results demonstrate consistent improvements over representative sequential and graph-based baselines, indicating stronger cross-regional generalization and more reliable identification of borderline and noisy cases. By linking cross-domain stability with uncertainty-aware risk screening, this work contributes a practical and economically meaningful solution for sustainable corporate oversight, offering actionable value for policy-oriented financial supervision and regional economic sustainability. Full article

Ultra-Wideband (UWB) technology enables centimeter-level indoor positioning, but it remains highly sensitive to channel dynamics, multipath and Non-Line-of-Sight (NLoS) propagation. Recent studies increasingly apply Machine Learning (ML) methods to address these issues by modeling nonlinear channel behavior and mitigating ranging bias. This paper presents a comprehensive review and provides a critical synthesis of 169 research works published between 2020 and 2024, offering an integrated overview of how ML techniques are incorporated into UWB-based Indoor Positioning Systems (IPSs). The studies are grouped according to their functional objective, learning algorithm, network architecture, evaluation metrics, dataset, and experimental setting. The results indicate that most approaches apply ML to channel classification and ranging error mitigation, with Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and hybrid CNN–Long Short-Term Memory (LSTM) architectures being among the most common choices due to their ability to capture spatial and temporal patterns in the Channel Impulse Response (CIR). Despite the reported accuracy improvements, scalability and cross-environment generalization remain open challenges, largely due to the scarcity of public datasets and the lack of standardized evaluation protocols. Emerging research trends highlight growing interest in transfer learning, domain adaptation, and federated learning, along with lightweight and explainable models suitable for embedded and multi-sensor systems. Overall, this review summarizes the progress made in ML-driven UWB localization, identifies current gaps, and outlines promising directions toward more robust and generalizable indoor positioning frameworks. Full article

The atmospheric reentry of hypersonic vehicles generates a plasma sheath enveloping the vehicle surface. This fluid medium moves at velocities distinct from the vehicle body, significantly altering its electromagnetic scattering properties. This paper introduces a Multi-Frame Lorentz Transformation Finite-Difference Time-Domain (FDTD) method, which incorporates a spatially varying velocity field into the computational scheme. The proposed algorithm maintains velocity synchronization in electromagnetic field updates and employs a near-to-far-field transformation for far-zone analysis. We systematically investigate the scattering characteristics of a plasma-sheath-covered hypersonic vehicle across a range of velocities and analyze the effect of velocity on the Radar Cross-Section (RCS) under different polarization conditions. Full article

Recent studies have highlighted that network traffic may be influenced by various external factors such as weather conditions and user behavior, making it challenging to achieve precise predictions using only historical traffic data. To address this limitation, this study proposes a multivariate time series prediction model that incorporates environmental variables, such as meteorological information, to improve the accuracy of network traffic forecasting. Five deep learning models—RNN, GRU, LSTM, CNN, and Transformer—were evaluated under the same experimental conditions. Performance was assessed using metrics such as MSE, RMSE, MAE, R², and MAPE. In addition, ANOVA and Tukey HSD post hoc tests were conducted to analyze the statistical significance of performance differences between models, and the contribution of each environmental variable was evaluated using the Permutation Importance method, which demonstrated a significant impact on model performance. Experimental results indicated that the GRU and RNN models achieved the best overall prediction accuracy. Additionally, some weather variables, such as temperature and sunlight duration, positively impacted performance improvement. This study empirically demonstrates the generalization capabilities of simple recurrent architectures and the effectiveness of integrating environmental variables. Furthermore, it suggests future research directions, including cross-domain model adaptation and the application of large language model (LLM)-based time series forecasting frameworks. Full article

This work presents an experimental evaluation of a high-speed analog-to-digital conversion method based on passive reference waveform crossings combined with time-to-digital converter (TDC) time-tagging. Unlike conventional level-crossing event-driven analog-to-digital converters (ADCs) that require dynamically updated digital-to-analog converters (DACs), the proposed architecture compares the input waveform against a broadband periodic sampling function without active threshold control. Crossing instants are detected by a high-speed comparator and converted into rising and falling edge timestamps using a multi-channel TDC. A commercial ScioSense GPX2-based time-tagger with 30 ps single-shot precision was used for validation. A range of test signals—including 5 MHz sine, sawtooth, damped sine, and frequency-modulated chirp waveforms—were acquired using triangular, sinusoidal, and sawtooth sampling functions. Stroboscopic sampling was demonstrated using reference frequencies lower than the signal of interest, enabling effective undersampling of periodic radio frequency (RF) waveforms. The method achieved effective bandwidths approaching 100 MHz, with amplitude reconstruction errors of 0.05–0.30 RMS for sinusoidal signals and 0.15–0.40 RMS for sawtooth signals. Timing jitter showed strong dependence on the relative slope between the acquired waveform and sampling function: steep regions produced jitter near 5 ns, while shallow regions exhibited jitter up to 20 ns. The study has several limitations, including the bandwidth and dead-time constraints of the commercial TDC, the finite slew rate and noise of the comparator front-end, and the limited frequency range of the generated sampling functions. These factors influence the achievable timing precision and reconstruction accuracy, especially in low-gradient signal regions. Overall, the passive waveform-crossing method demonstrates strong potential for wideband, sparse, and rapidly varying signals, with natural scalability to multi-channel systems. Potential application domains include RF acquisition, ultra-wideband (UWB) radar, integrated sensing and communication (ISAC) systems, high-speed instrumentation, and wideband timed antenna arrays. Full article

The fusion of synthetic aperture radar (SAR) and visible images offers complementary spatial and spectral information, enabling more reliable and comprehensive scene interpretation. However, SAR speckle noise and the intrinsic modality gap pose significant challenges for existing methods in extracting consistent and complementary features. To address these issues, we propose VGSRF-Net, a Retinex-guided SAR reconstruction-driven fusion network that leverages visible-image priors to refine SAR features. This approach effectively reduces modality discrepancies before fusion, enabling improved multi-modal representation. The cross-modality reconstruction module (CMRM) reconstructs SAR features guided by visible priors, effectively reducing modality discrepancies before fusion and enabling improved multi-modal representation. The multi-modal feature joint representation module (MFJRM) enhances cross-modal complementarity by integrating global contextual interactions and local dynamic convolution, thereby achieving further feature alignment. Finally, the feature enhancement module (FEM) refines multi-scale spatial features and selectively enhances high-frequency details in the frequency domain, improving structural clarity and texture fidelity. Extensive experiments on diverse real-world remote sensing datasets demonstrate that VGSRF-Net surpasses state-of-the-art methods in denoising, structural preservation, and generalization under varying noise and illumination conditions. Full article

This study presents a controlled benchmarking analysis of min–max scaling, Z-score normalization, and an adaptive preprocessing pipeline that combines percentile-based ROI cropping with histogram standardization. The evaluation was conducted across four public chest X-ray (CXR) datasets and three convolutional neural network architectures under controlled experimental settings. The adaptive pipeline generally improved accuracy, F1-score, and training stability on datasets with relatively stable contrast characteristics while yielding limited gains on MIMIC-CXR due to strong acquisition heterogeneity. Ablation experiments showed that histogram standardization provided the primary performance contribution, with ROI cropping offering complementary benefits, and the full pipeline achieving the best overall performance. The computational overhead of the adaptive preprocessing was minimal (+6.3% training-time cost; 5.2 ms per batch). Friedman–Nemenyi and Wilcoxon signed-rank tests confirmed that the observed improvements were statistically significant across most dataset–model configurations. Overall, adaptive normalization is positioned not as a novel algorithmic contribution, but as a practical preprocessing design choice that can enhance cross-dataset robustness and reliability in chest X-ray classification workflows. Full article

Change detection plays a crucial role in geological disaster tasks such as landslide identification, post-earthquake building reconstruction assessment, and unstable rock mass monitoring. However, real-world scenarios often pose significant challenges, including complex surface backgrounds, illumination and seasonal variations between temporal phases, and diverse change patterns. To address these issues, this paper proposes a multi-stage model for geological disaster change detection, termed MSMCD, which integrates strategies of global dependency modeling, local difference enhancement, edge constraint, and frequency-domain fusion to achieve precise perception and delineation of change regions. Specifically, the model first employs a DualTimeMamba (DTM) module for two-dimensional selective scanning state-space modeling, explicitly capturing cross-temporal long-range dependencies to learn robust shared representations. Subsequently, a Multi-Scale Perception (MSP) module highlights fine-grained differences to enhance local discrimination. The Edge–Change Interaction (ECI) module then constructs bidirectional coupling between the change and edge branches with edge supervision, improving boundary accuracy and geometric consistency. Finally, the Frequency-domain Change Fusion (FCF) module performs weighted modulation on multi-layer, channel-joint spectra, balancing low-frequency structural consistency with high-frequency detail fidelity. Experiments conducted on the landslide change detection dataset (GVLM-CD), post-earthquake building change detection dataset (WHU-CD), and a self-constructed unstable rock mass change detection dataset (TGRM-CD) demonstrate that MSMCD achieves state-of-the-art performance across all benchmarks. These results confirm its strong cross-scenario generalization ability and effectiveness in multiple geological disaster tasks. Full article

Background: Ankle sprains affect approximately 8% of the general population, and recurrence occurs in as many as 80% of patients participating in high-risk sports. The aim of this review was to assess the impact of physiotherapy interventions on chronic ankle stability (CAI), providing evidence for the effectiveness of clinical treatment and care for patients with CAI. Methods: A systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Randomized controlled trials (RCTs) evaluating the effectiveness of physiotherapy interventions in athletes with CAI following injury were analyzed. PubMed, Embase, PEDro, and Cochrane electronic databases were searched. A modified McMaster Critical Review Form for quantitative studies was used to assess the methodological quality of the included studies, in accordance with the guidelines. Results: The literature search yielded 316 results, of which 13 articles met all required eligibility criteria and were included in the study. The RCTs included 490 athletes with CAI. Interventions included various types of exercises, including balance training (BT), plyometric training, CrossFit, and neuromuscular training. The duration of the intervention was 4–12 weeks. Both subjective and objective measures were used to assess the effectiveness of the therapy in the following seven domains: Dynamic Balance, Static Balance, Patient-Reported Outcomes, Kinematic Outcomes, Proprioception, Body-Composition, and Strength Assessment. Conclusions: The evidence supports the effectiveness of rehabilitation interventions in athletes with CAI. Further large-scale randomized controlled trials, incorporating control groups and long-term follow-up, are needed to better determine the robust impact of conservative management on improving both the physical and psychological health of patients with CAI. Full article

This study explored language control in phonological encoding during L1 (Chinese) and L2 (English) production via two retrieval-induced forgetting (RIF) experiments and two bilingual picture–word interference (PWI) experiments with Chinese–English bilinguals. RIF results showed that performance on a target language phonological judgement task can be facilitated by prior picture naming in either the target language or a non-target language in both L2 and L1 production. Bilingual PWI results revealed cross-language phonological facilitation effects in L2 and L1 production. Domain-general cognitive control only moderated effects in L2 tasks. Findings confirmed non-selective phonological activation of translation equivalents and cross-language phonologically related words and supported the Language-Specific Selection Model as the primary language control mechanism in phonological encoding, which restricts competition to the target language. Full article

Graph representation learning (GRL) has emerged as a unifying paradigm for modeling the relational and heterogeneous nature of battery energy storage systems (BESS), yet a systematic synthesis focused on data-scarce (few-shot) battery scenarios is still lacking. Graph representation learning offers a natural way to describe the structure and interaction of battery cells, modules and packs. At the same time, battery applications often suffer from very limited labeled data, especially for new chemistries, extreme operating conditions and second-life use. This review analyzes how graph representation learning can be combined with few-shot learning to support key battery management tasks under such data-scarce conditions. We first introduce the basic ideas of graph representation learning, including models based on neighborhood aggregation, contrastive learning, autoencoders and transfer learning, and discuss typical data, model and algorithm challenges in few-shot scenarios. We then connect these methods to battery state estimation problems, covering state of charge, state of health, remaining useful life and capacity. Particular attention is given to approaches that use graph neural models, meta-learning, semi-supervised and self-supervised learning, Bayesian deep networks, and federated learning to extract transferable features from early-cycle data, partial charge–discharge curves and large unlabeled field datasets. Reported studies show that, with only a small fraction of labeled samples or a few initial cycles, these methods can achieve state and life prediction errors that are comparable to or better than conventional models trained on full datasets, while also improving robustness and, in some cases, providing uncertainty estimates. Based on this evidence, we summarize the main technical routes for few-shot battery scenarios and identify open problems in data preparation, cross-domain generalization, uncertainty quantification and deployment on real battery management systems. The review concludes with a research outlook, highlighting the need for pack-level graph models, physics-guided and probabilistic learning, and unified benchmarks to advance reliable graph-based few-shot methods for next-generation intelligent battery management. Full article

This study was conducted to address the demand for interpretable intelligent recognition of fruit tree diseases in smart horticultural environments. A KAD-Former framework integrating an agricultural knowledge graph with a visual Transformer was proposed and systematically validated through extensive cross-regional, multi-variety, and multi-disease experiments. The primary objective of this work was to overcome the limitations of conventional deep models, including insufficient interpretability, unstable recognition of weak disease features, and poor cross-regional generalization. In the experimental evaluation, the model achieved significant advantages across multiple representative tasks: in the overall performance comparison, KAD-Former reached an accuracy of $0.946$, an F1-score of $0.933$, and a mAP of $0.938$, outperforming classical models such as ResNet50, EfficientNet, and Swin-T. In the cross-regional generalization assessment, a DGS of $0.933$ was obtained, notably surpassing competing models. In terms of explainability consistency, a Consistency@5 score of $0.826$ indicated strong alignment between the model’s attention regions and expert annotations. The ablation experiments further demonstrated that the three core modules—AKG (agricultural knowledge graph), SAM (semantic alignment module), and KGA (knowledge-guided attention)—each contributed substantially to final performance, with the complete model exhibiting the best results. These findings collectively demonstrate the comprehensive advantages of KAD-Former in disease classification, symptom localization, model interpretability, and cross-domain transfer. The proposed method not only achieved state-of-the-art performance in pure visual tasks but also advanced knowledge-enhanced and interpretable reasoning by emulating the diagnostic logic employed by agricultural experts in real orchard scenarios. Through the integration of the agricultural knowledge graph, semantic alignment, and knowledge-guided attention, the model maintained stable performance under challenging conditions such as complex illumination, background noise, and weak lesion features, while exhibiting strong robustness in cross-region and cross-variety transfer tests. Furthermore, the experimental results indicated that the approach enhanced fine-grained recognition capabilities for various fruit tree diseases, including apple ring rot, brown spot, powdery mildew, and downy mildew. Full article

Background: Sarcopenia is a progressive skeletal muscle disorder associated with adverse outcomes. Although the association between sarcopenia and quality of life (QoL) has been discussed, the specific relationship between different stages of sarcopenia severity—particularly distinguishing between muscle mass loss and functional impairment—and health-related quality of life (HRQoL) remains unclear. Method: This cross-sectional study enrolled 100 elderly participants from a geriatric outpatient clinic. Participants were categorized into four groups (normal, possible sarcopenia, sarcopenia and severe sarcopenia) based on the 2019 Asian Working Group for Sarcopenia (AWGS) criteria. HRQoL was assessed using the Short-Form 36-Item (SF-36) questionnaire. Result: The severe sarcopenia group was significantly older and had lower calf circumference compared to the normal group. Notably, the possible sarcopenia group presented with the highest body mass index and body fat percentage, resembling a “dynapenic obesity” phenotype. In terms of QoL, participants with confirmed sarcopenia did not exhibit significant differences compared to the normal group. However, the severe sarcopenia group demonstrated significantly lower scores across almost all SF-36 domains compared to the normal group. Multivariate linear regression analysis revealed that severe sarcopenia was independently and significantly negatively associated with multiple QoL domains, including physical functioning, general health and vitality. Additionally, age, social activity and body fat were identified as independent correlates of specific QoL domains. Conclusions: Our findings suggest a non-linear relationship between sarcopenia and HRQoL. A comprehensive decline in HRQoL is strongly linked to the severity of sarcopenia (functional impairment) rather than the diagnosis of muscle mass loss alone. These results highlight the clinical importance of preserving physical performance and suggest that categorizing different severities of sarcopenia and stage-specific management strategies are necessary to improve quality of life in older adults. Full article

Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems face significant challenges due to limited labeled data availability and persistent domain gaps between synthetic and measured imagery. This paper presents a comprehensive self-supervised learning (SSL) framework that eliminates dependency on synthetic data while achieving state-of-the-art performance through multi-task pretext training and extensive downstream classifier evaluation. We systematically evaluate our SSL framework across diverse downstream classifiers spanning different computational paradigms and architectural families. Our study encompasses traditional machine learning approaches (SVM, Random Forest, XGBoost, Gradient Boosting), deep convolutional neural networks (ResNet, U-Net, MobileNet, EfficientNet), and a generative adversarial network. We conduct extensive experiments using the SAMPLE dataset with rigorous evaluation protocols. Results demonstrate that SSL significantly improves SAR ATR performance, with SVM achieving 99.63% accuracy, ResNet18 reaching 97.40% accuracy, and Random Forest demonstrating 99.26% accuracy. Our multi-task SSL framework employs nine carefully designed pretext tasks, including geometric invariance, signal robustness, and multi-scale analysis. Cross-validation experiments validate the generalizability and robustness of our findings. Rigorous comparison with SimCLR baseline validates that task-based SSL outperforms contrastive learning for SAR ATR. This work establishes a new paradigm for SAR ATR that leverages inherent radar data structure without synthetic augmentation, providing practical guidelines for deploying SSL-based SAR ATR systems and a foundation for future domain-specific self-supervised learning research in remote sensing applications. Full article

Mature soybean pods exhibit high homogeneity in color and texture relative to straw and dead leaves, and instances are often densely occluded, posing significant challenges for accurate field segmentation. To address these challenges, this paper constructs a high-quality field-based mature soybean dataset and proposes an adaptive Transformer-based network, PodFormer, to improve segmentation performance under homogeneous backgrounds, dense distributions, and severe occlusions. PodFormer integrates three core innovations: (1) the Adaptive Wavelet Detail Enhancement (AWDE) module, which strengthens high-frequency boundary cues to alleviate weak-boundary ambiguities; (2) the Density-Guided Query Initialization (DGQI) module, which injects scale and density priors to enhance instance detection in both sparse and densely clustered regions; and (3) the Mask Feedback Gated Refinement (MFGR) layer, which leverages mask confidence to adaptively refine query updates, enabling more accurate separation of adhered or occluded instances. Experimental results show that PodFormer achieves relative improvements of 6.7% and 5.4% in mAP50 and mAP50-95, substantially outperforming state-of-the-art methods. It further demonstrates strong generalization capabilities on real-world field datasets and cross-domain wheat-ear datasets, thereby providing a reliable perception foundation for structural trait recognition in intelligent soybean harvesting systems. Full article