Search Results (963)

Style transfer technology has seen substantial attention in image synthesis, notably in applications like oil painting, digital printing, and Chinese landscape painting. However, it is often difficult to generate migrated images that retain the essence of paper-cutting art and have strong visual appeal when trying to apply the unique style of Chinese paper-cutting art to style transfer. Therefore, this paper proposes a new method for Chinese paper-cutting style transformation based on the Transformer, aiming at realizing the efficient transformation of Chinese paper-cutting art styles. Specifically, the network consists of a frequency-domain mixture block and a multi-level feature contrastive learning module. The frequency-domain mixture block explores spatial and frequency-domain interaction information, integrates multiple attention windows along with frequency-domain features, preserves critical details, and enhances the effectiveness of style conversion. To further embody the symmetrical structures and hollowed hierarchical patterns intrinsic to Chinese paper-cutting, the multi-level feature contrastive learning module is designed based on a contrastive learning strategy. This module maximizes mutual information between multi-level transferred features and content features, improves the consistency of representations across different layers, and thus accentuates the unique symmetrical aesthetics and artistic expression of paper-cutting. Extensive experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches in both qualitative and quantitative evaluations. Additionally, we created a Chinese paper-cutting dataset that, although modest in size, represents an important initial step towards enriching existing resources. This dataset provides valuable training data and a reference benchmark for future research in this field. Full article

Image dehazing technology is a crucial component in the fields of intelligent transportation and autonomous driving. However, most existing dehazing algorithms only process images in the spatial domain, failing to fully exploit the rich information in the frequency domain, which leads to residual haze in the images. To address this issue, we propose a novel Frequency-domain Information Guided Symmetric Dual-branch Dehazing Network (FIGD-Net), which utilizes the spatial branch to extract local haze features and the frequency branch to capture the global haze distribution, thereby guiding the feature learning process in the spatial branch. The FIGD-Net mainly consists of three key modules: the Frequency Detail Extraction Module (FDEM), the Dual-Domain Multi-scale Feature Extraction Module (DMFEM), and the Dual-Domain Guidance Module (DGM). First, the FDEM employs the Discrete Cosine Transform (DCT) to convert the spatial domain into the frequency domain. It then selectively extracts high-frequency and low-frequency features based on predefined proportions. The high-frequency features, which contain haze-related information, are correlated with the overall characteristics of the low-frequency features to enhance the representation of haze attributes. Next, the DMFEM utilizes stacked residual blocks and gradient feature flows to capture local detail features. Specifically, frequency-guided weights are applied to adjust the focus of feature channels, thereby improving the module’s ability to capture multi-scale features and distinguish haze features. Finally, the DGM adjusts channel weights guided by frequency information. This smooths out redundant signals and enables cross-branch information exchange, which helps to restore the original image colors. Extensive experiments demonstrate that the proposed FIGD-Net achieves superior dehazing performance on multiple synthetic and real-world datasets. Full article

Background/Objectives: Wolf–Hirschhorn syndrome (WHS; OMIM #194190) is a rare neurodevelopmental disorder, caused by deletions in the distal short arm of chromosome 4. It is characterized by developmental delay, epilepsy, intellectual disability, and distinctive facial dysmorphism. Clinical presentation varies widely, complicating prognosis and individualized care. Methods: We assembled a cohort of 140 individuals with genetically confirmed WHS from Spain and Latin-America, and developed and validated a multidimensional, Clinician-Reported Outcome Assessment (ClinRO) based on the Global Functional Assessment of the Patient (GFAP), derived from standardized clinical questionnaires and weighted by HPO (Human Phenotype Ontology) term frequencies. The GFAP score quantitatively captures key functional domains in WHS, including neurodevelopment, epilepsy, comorbidities, and age-corrected developmental milestones (selected based on clinical experience and disease burden). Results: Higher GFAP scores are associated with worse clinical outcomes. GFAP showed strong correlations with deletion size, presence of additional genomic rearrangements, sex, and epilepsy severity. Ward’s clustering and discriminant analyses confirmed GFAP’s discriminative power, classifying over 90% of patients into clinically meaningful groups with different prognoses. Conclusions: Our findings support GFAP as a robust, WHS-specific ClinRO that may aid in stratification, prognosis, and clinical management. This tool may also serve future interventional studies as a standardized outcome measure. Beyond its clinical utility, GFAP also revealed substantial social implications. This underscores the broader socioeconomic burden of WHS and the potential value of GFAP in identifying high-support families that may benefit from targeted resources and services. Full article

The MAM domain-containing glycosylphosphatidylinositol anchor 1 (MDGA1) gene, which encodes a protein involved in synaptic inhibition, has been identified as a potential risk gene for restless legs syndrome. A recent study in the Chinese population described increased MDGA1 methylation levels in patients with idiopathic RLS (iRLS) compared to healthy controls. In this study, we investigated the possible association between the most common variants in the MDGA1 gene and the risk for iRLS in a Caucasian Spanish population. We assessed the frequencies of MDGA1 rs10947690, MDGA1 rs61151079, and MDGA1 rs79792089 genotypes and allelic variants in 263 patients with idiopathic RLS and 280 healthy controls using a specific TaqMan-based qPCR assay. We also analyzed the possible influence of the genotype frequencies on several variables, including age at the onset of RLS, gender, a family history of RLS, and response to drugs commonly used in the treatment of RLS. The frequencies of the genotypes and allelic variants of the three common missense SNVs studied did not differ significantly between RLS patients and controls, neither in the whole series nor when analyzing each gender separately; were not correlated with age at onset and the severity of RLS assessed by the International Restless Legs Syndrome Study Group Rating Scale (IRLSSGRS); and were not related to a family history of RLS or the pharmacological response to dopamine agonists, clonazepam, or gabaergic drugs. Our findings suggest that common missense SNVs in the MDGA1 gene are not associated with the risk of developing idiopathic RLS in Caucasian Spanish people. Full article

This study proposes MSFF-Net, a lightweight deep learning framework for bearing fault diagnosis based on frequency-domain multi-sensor fusion. The vibration and acoustic signals are initially converted into the frequency domain using the fast Fourier transform (FFT), enabling the extraction of temporally invariant spectral features. These features are processed by a compact one-dimensional convolutional neural network, where modality-specific representations are fused at the feature level to capture complementary fault-related information. The proposed method demonstrates robust and superior performance under both full and scarce data conditions, as verified through experiments on a publicly available dataset. Experimental results on a publicly available dataset indicate that the proposed model attains an average accuracy of 99.73%, outperforming state-of-the-art (SOTA) methods in both accuracy and stability. With only about 70.3% of the parameters of the SOTA model, it offers faster inference and reduced computational cost. Ablation studies confirm that multi-sensor fusion improves all classification metrics over single-sensor setups. Under few-shot conditions with 20 samples per class, the model retains 94.69% accuracy, highlighting its strong generalization in data-limited scenarios. The results validate the effectiveness, computational efficiency, and practical applicability of the model for deployment in data-constrained industrial environments. Full article

Respiratory diseases present significant global health challenges. Recent advances in respiratory sound analysis (RSA) have shown great potential for automated disease diagnosis and patient management. The International Conference on Biomedical and Health Informatics 2017 (ICBHI2017) database stands as one of the most authoritative open-access RSA datasets. This review systematically examines 135 technical publications utilizing the database, and a comprehensive and timely summary of RSA methodologies is offered for researchers and practitioners in this field. Specifically, this review covers signal processing techniques including data resampling, augmentation, normalization, and filtering; feature extraction approaches spanning time-domain, frequency-domain, joint time–frequency analysis, and deep feature representation from pre-trained models; and classification methods for adventitious sound (AS) categorization and pathological state (PS) recognition. Current achievements for AS and PS classification are summarized across studies using official and custom data splits. Despite promising technique advancements, several challenges remain unresolved. These include a severe class imbalance in the dataset, limited exploration of advanced data augmentation techniques and foundation models, a lack of model interpretability, and insufficient generalization studies across clinical settings. Future directions involve multi-modal data fusion, the development of standardized processing workflows, interpretable artificial intelligence, and integration with broader clinical data sources to enhance diagnostic performance and clinical applicability. Full article

Hydraulic concrete is a critical infrastructure material, with its surface condition playing a vital role in quality assessments for water conservancy and hydropower projects. However, images taken in complex hydraulic environments often suffer from degraded quality due to low lighting, shadows, and noise, making it difficult to distinguish defects from the background and thereby hindering accurate defect detection and damage evaluation. In this study, following systematic analyses of hydraulic concrete color space characteristics, we propose a Dual-Branch Luminance–Chrominance Attention Network (DBLCANet-HCIE) specifically designed for low-light hydraulic concrete image enhancement. Inspired by human visual perception, the network simultaneously improves global contrast and preserves fine-grained defect textures, which are essential for structural analysis. The proposed architecture consists of a Luminance Adjustment Branch (LAB) and a Chroma Restoration Branch (CRB). The LAB incorporates a Luminance-Aware Hybrid Attention Block (LAHAB) to capture both the global luminance distribution and local texture details, enabling adaptive illumination correction through comprehensive scene understanding. The CRB integrates a Channel Denoiser Block (CDB) for channel-specific noise suppression and a Frequency-Domain Detail Enhancement Block (FDDEB) to refine chrominance information and enhance subtle defect textures. A feature fusion block is designed to fuse and learn the features of the outputs from the two branches, resulting in images with enhanced luminance, reduced noise, and preserved surface anomalies. To validate the proposed approach, we construct a dedicated low-light hydraulic concrete image dataset (LLHCID). Extensive experiments conducted on both LOLv1 and LLHCID benchmarks demonstrate that the proposed method significantly enhances the visual interpretability of hydraulic concrete surfaces while effectively addressing low-light degradation challenges. Full article

Recent advances in hyperspectral image (HSI) classification have demonstrated the effectiveness of hybrid architectures that integrate convolutional neural networks (CNNs) and Transformers, leveraging CNNs for local feature extraction and Transformers for global dependency modeling. However, existing fusion approaches face three critical challenges: (1) insufficient synergy between spectral and spatial feature learning due to rigid coupling mechanisms; (2) high computational complexity resulting from redundant attention calculations; and (3) limited adaptability to spectral redundancy and noise in small-sample scenarios. To address these limitations, we propose HyperTransXNet, a novel CNN-Transformer hybrid architecture that incorporates adaptive spectral-spatial fusion. Specifically, the proposed HyperTransXNet comprises three key modules: (1) a Hybrid Spatial-Spectral Module (HSSM) that captures the refined local spectral-spatial features and models global spectral correlations by combining depth-wise dynamic convolution with frequency-domain attention; (2) a Mixture-of-Experts Routing (MoE-R) module that adaptively fuses multi-scale features by dynamically selecting optimal experts via Top-K sparse weights; and (3) a Spatial-Spectral Tokens Enhancer (SSTE) module that ensures causality-preserving interactions between spectral bands and spatial contexts. Extensive experiments on the Indian Pines, Houston 2013, and WHU-Hi-LongKou datasets demonstrate the superiority of HyperTransXNet. Full article

With the rapid development of video encoding technology in the field of computer vision, the demand for tasks such as video frame reconstruction, denoising, and super-resolution has been continuously increasing. However, traditional video encoding methods typically focus on extracting spatial or temporal domain information, often facing challenges of insufficient accuracy and information loss when reconstructing high-frequency details, edges, and textures of images. To address this issue, this paper proposes an innovative LadderConv framework, which combines discrete wavelet transform (DWT) with spatial and channel attention mechanisms. By progressively recovering wavelet subbands, it effectively enhances the video frame encoding quality. Specifically, the LadderConv framework adopts a stepwise recovery approach for wavelet subbands, first processing high-frequency detail subbands with relatively less information, then enhancing the interaction between these subbands, and ultimately synthesizing a high-quality reconstructed image through inverse wavelet transform. Moreover, the framework introduces spatial and channel attention mechanisms, which further strengthen the focus on key regions and channel features, leading to notable improvements in detail restoration and image reconstruction accuracy. To optimize the performance of the LadderConv framework, particularly in detail recovery and high-frequency information extraction tasks, this paper designs an innovative ResGroup module. By using multi-layer convolution operations along with feature map compression and recovery, the ResGroup module enhances the network’s expressive capability and effectively reduces computational complexity. The ResGroup module captures multi-level features from low level to high level and retains rich feature information through residual connections, thus improving the overall reconstruction performance of the model. In experiments, the combination of the LadderConv framework and the ResGroup module demonstrates superior performance in video frame reconstruction tasks, particularly in recovering high-frequency information, image clarity, and detail representation. Full article

Background: Parkinson’s disease (PD) presents a significant challenge due to its wide range of motor, non-motor, and treatment-related symptoms. Non-invasive interventions like transcranial magnetic stimulation (TMS) are being explored for potential therapeutic benefits. This study aimed to assess if a high-frequency repetitive TMS protocol (HF-rTMS) consisting of 10 trains of 100 pulses of rTMS at 25 Hz over the motor cortex (M1) at 80% of the resting motor threshold could be effective in treating motor or non-motor symptoms in patients with PD with levodopa-induced dyskinesias. Methods: A randomized, single-blinded, placebo-controlled pilot trial was conducted with eleven PD patients. Nine patients received HF-rTMS, while two received sham stimulation. Patients were exhaustively evaluated using validated clinical scales to assess motor and non-motor symptoms. The study followed a rigorous protocol to avoid bias, with assessments conducted by a neurologist specialized in single-blinded movement disorder. Results: The HF-rTMS group experienced a statistically significant slight worsening in both motor and non-motor symptoms, particularly in the mood/cognition and gastrointestinal domains. However, positive effects were observed in some non-motor symptoms, specifically reduced excessive sweating and weight. No adverse effects were reported. Conclusions: Although HF-rTMS did not produce significant motor improvements, its potential benefit on specific non-motor symptoms, such as autonomic regulation, warrants further investigation. Full article

Traditional relaxation techniques such as meditation and slow breathing often rely on subjective self-assessment, making it difficult to objectively monitor physiological changes. Electrocardiograms (ECG), which are commonly used by clinicians, provide one-dimensional signals to interpret cardiovascular activity. In this study, we introduce a visual interpretation framework that transforms heart rate variability (HRV) time series into fuzzy recurrence plots (FRPs). Unlike ECGs’ linear traces, FRPs are two-dimensional images that reveal distinctive textural patterns corresponding to autonomic changes. These visually rich patterns make it easier for even non-experts with minimal training to track changes in relaxation states. To enable automated detection, we propose a multi-domain feature fusion framework suitable for wearable systems. HRV data were collected from 60 participants during spontaneous and slow-paced breathing sessions. Features were extracted from five domains: time, frequency, non-linear, geometric, and image-based. Feature selection was performed using the Fisher discriminant ratio, correlation filtering, and greedy search. Among six evaluated classifiers, support vector machine (SVM) achieved the highest performance, with 96.6% accuracy and 100% specificity using only three selected features. Our approach offers both human-interpretable visual feedback through FRP and accurate automated detection, making it highly promising for objectively monitoring real-time stress and developing biofeedback systems in wearable devices. Full article

Process anomaly detection in financial services systems is crucial for operational compliance and risk management. However, traditional process mining techniques frequently neglect the detection of significant low-frequency abnormalities due to their dependence on frequency and the inadequate incorporation of domain-specific knowledge. Therefore, we develop an enhanced process mining algorithm by incorporating a domain-specific follow-relationship matrix derived from standard operating procedures (SOPs). We empirically evaluated the effectiveness of the proposed algorithm based on real-world event logs from a corporate account-opening process conducted from January to December 2022 in a Chinese commercial bank. Additionally, we employed large language models (LLMs) for root cause analysis and process optimization recommendations. The empirical results demonstrate that the E-Heuristic Miner significantly outperforms traditional machine learning methods and process mining algorithms in process anomaly detection. Furthermore, the integration of LLMs provides promising capabilities in semantic reasoning and offers explainable optimization suggestions, enhancing decision-making support in complex financial scenarios. Our study significantly improves the precision of process anomaly detection in financial contexts by incorporating banking-specific domain knowledge into process mining algorithms. Meanwhile, it extends theoretical boundaries and the practical applicability of process mining in intelligent, semantic-aware financial service management. Full article

Background: Asymmetrical brain oscillations may be characteristic of Parkinson’s disease (PD). We investigated differences in oscillation asymmetry between individuals with PD and healthy controls and explored associations between the asymmetry and clinical features. Methods: Clinical and resting-state EEG data from 37 patients and 24 controls were cross-sectionally analyzed. EEG asymmetry indices were calculated for the delta, theta, alpha, and beta frequencies in the frontal, central, and parietal regions. Independent t-tests and linear regression models were employed. Results: Patients exhibited lower alpha asymmetry than controls in the parietal region (t(59) = 2.12, p = 0.03). In the frontal alpha asymmetry models, there were associations with time since diagnosis (β = −0.042) and attention/orientation (β = 0.061), and with Movement Disorder Society-Unified Parkinson’s Disease Rating Scale (MDS-UPDRSIII)-posture (β = 0.136) and MDS-UPDRSIII-rest-tremor persistence (β = −0.111). In the central alpha model, higher asymmetry was associated with the physical activity levels (International Physical Activity Questionnaire) IPAQ-active (β = 0.646) and IPAQ-very active (β = 0.689), (Timed Up and Go) TUG dual-task cost (β = 0.023), MDS-UPDRSII-freezing (β = 0.238), and being male (β = 0.535). In the parietal alpha asymmetry model, MDS-UPDRSII-gait/balance was inversely associated with alpha asymmetry (β = −0.156), while IPAQ-active (β = −0.247) and being male (β = −0.191) were associated with lower asymmetry. Conclusions: Our findings highlight the potential role of alpha asymmetry as a neurophysiological marker of PD’s motor symptoms, mainly rest tremor, gait/balance, freezing, and specific cognitive domains such as attention/orientation. The models stressed the relationship between disease progression and reduced alpha asymmetry. Brazilian Registry of Clinical Trials (RBR-7zjgnrx, 9 June 2022). Full article

The transient operation of pump turbines generates significant flow-induced instabilities, prompting a comprehensive numerical investigation using the SST $k-\omega$ turbulence model to examine these instability effects throughout the complete operating range in turbine mode. This study specifically analyzes the evolutionary mechanisms of unsteady flow dynamics under ten characteristic off-design conditions while simultaneously characterizing the pressure fluctuation behavior within the vaneless space (VS). The results demonstrate that under both low-speed conditions and near-zero-discharge conditions, the VS and its adjacent flow domains exhibit pronounced flow instabilities with highly turbulent flow structures, while the pressure fluctuation amplitudes remain relatively small due to insufficient rotational speed or flow rate. Across the entire turbine operating range, the blade passing frequency (BPF) dominates the VS pressure fluctuation spectrum. Significant variations are observed in both low-frequency components (LFCs) and high-frequency, low-amplitude components (HF-LACs) with changing operating conditions. The HF-LACs exhibit relatively stable amplitudes but demonstrate significant variation in the frequency spectrum distribution across different operating conditions, with notably broader frequency dispersion under runaway conditions and adjacent operating points. The LFCs demonstrate significantly higher spectral density and amplitude magnitudes under high-speed, low-discharge operating conditions while exhibiting markedly reduced occurrence and diminished amplitudes in the low-speed, high-flow regime. This systematic investigation provides fundamental insights into the flow physics governing pump-turbine performance under off-design conditions while offering practical implications for optimizing transient operational control methodologies in hydroelectric energy storage systems. Full article

In the recognition of fruit leaf diseases, image recognition technology based on deep learning has received increasing attention. However, deep learning models often perform poorly in complex backgrounds, and in some cases, they even outperform traditional algorithms. To address this issue, this paper proposes a Frequency-Adaptive Attention (FA-attention) mechanism that leverages the significance of frequency-domain features in fruit leaf disease regions. By enhancing the processing of frequency domain features, the recognition performance in complex backgrounds is improved. Specifically, FA-attention combines Fourier transform with the attention mechanism to extract frequency domain features as key features. Then, this mechanism is integrated with the Unet model to obtain feature maps strongly related to frequency domain features. These feature maps are fused with multi-scale convolutional feature maps and then used for classification. Experiments were conducted on the Plant Village (PV) dataset and the Plant Pathology (PP) dataset with complex backgrounds. The results indicate that the proposed FA-attention mechanism achieves significant effects in learning frequency domain features. Our model achieves a recognition accuracy of 99.91% on the PV dataset and 89.59% on the PP dataset. At the same time, the convergence speed is significantly improved, reaching 94% accuracy with only 20 epochs, demonstrating the effectiveness of this method. Compared with classical models and state-of-the-art (SOTA) models, our model performs better on complex background datasets, demonstrating strong generalization capabilities. Full article