Search Results (7,172)

Accurate weld defect detection is critical for ensuring structural safety and evaluating welding quality in industrial applications. Manual inspection methods have inherent limitations, including inefficiency and inadequate sensitivity to subtle defects. Existing detection models, primarily designed for natural images, struggle to adapt to the characteristic challenges of weld X-ray images, such as high noise, low contrast, and inter-defect similarity, particularly leading to missed detections and false positives for small defects. To address these challenges, a multi-dimensional feature fusion model (MADet), which is a multi-branch deep fusion network for weld defect detection, was proposed. The framework incorporates two key innovations: (1) A multi-scale feature fusion network integrated with lightweight attention residual modules to enhance the perception of fine-grained defect features by leveraging low-level texture information. (2) An anchor-based feature-selective detection head was used to improve the discrimination and localization accuracy for five typical defect categories. Extensive experiments on both public and proprietary weld defect datasets demonstrated that MADet achieved significant improvements over the state-of-the-art YOLO variants. Specifically, it surpassed the suboptimal model by 7.41% in mAP@0.5, indicating strong industrial applicability. Full article

The accelerated evolution of remote sensing technology has intensified the demand for real-time tile map generation, highlighting the limitations of conventional mapping approaches that rely on manual cartography and field surveys. To address the critical need for rapid cartographic updates, this study presents a novel multi-stage generative framework that synergistically integrates Generative Adversarial Networks (GANs) with Diffusion Denoising Models (DMs) for high-fidelity map generation from remote sensing imagery. Specifically, our proposed architecture first employs GANs for rapid preliminary map generation, followed by a cascaded diffusion process that progressively refines topological details and spatial accuracy through iterative denoising. Furthermore, we propose a hybrid attention mechanism that strategically combines channel-wise feature recalibration with coordinate-aware spatial modulation, enabling the enhanced discrimination of geographic features under challenging conditions involving edge ambiguity and environmental noise. Quantitative evaluations demonstrate that our method significantly surpasses established baselines in both structural consistency and geometric fidelity. This framework establishes an operational paradigm for automated, rapid-response cartography, demonstrating a particular utility in time-sensitive applications including disaster impact assessment, unmapped terrain documentation, and dynamic environmental surveillance. Full article

Background/Objectives: This study aimed to create a ‘carbapenem resistance score’ with the risk factors of carbapenem-resistant Gram-negative bacterial infections (GNBIs) in patients with hematological malignancies. Methods: Patients with carbapenem-resistant and susceptible GNBIs were included in this study and compared in terms of risk factors. Three models of “carbapenem resistance risk scores” were created with statistically significant variables. Results: The study included 154 patients with hospital-acquired GNBIs, of whom 64 had carbapenem-resistant GNBIs and 90 had carbapenem-susceptible GNBIs. Univariate and multivariate analyses identified several statistically significant risk factors for carbapenem resistance, including transfer from another hospital or clinic (p = 0.038), prior use of antibiotics like fluoroquinolones (p = 0.009) and carbapenems (p = 0.001), a history of carbapenem-resistant infection in the last six months (p < 0.001), rectal Klebsiella pneumoniae colonization (p < 0.001), hospitalization for ≥30 days (p = 0.001), and the presence of a urinary catheter (p = 0.002). Notably, the 14-day mortality rate was significantly higher in the carbapenem-resistant group (p < 0.001). Based on these findings, three risk-scoring models were developed. Common factors in all three models were fluoroquinolone use in the last six months, rectal K. pneumoniae colonization, and the presence of a urinary catheter. The fourth variable was transfer from another hospital (Model 1), a history of carbapenem-resistant infection (Model 2), or hospitalization for ≥30 days (Model 3). All models demonstrated strong discriminative power (AUC for Model 1: 0.830, Model 2: 0.826, Model 3: 0.831). For all three models, a cutoff value of >2.5 was adopted as the threshold to identify patients at high risk for carbapenem resistance, a value which yielded high positive and negative predictive values. Conclusions: This study successfully developed three practical risk-scoring models to predict carbapenem resistance in patients with hematological malignancies using common clinical risk factors. A cutoff score of >2.5 proved to be a reliable threshold for identifying high-risk patients across all models, providing clinicians with a valuable tool to guide appropriate empirical antibiotic therapy. Full article

Tea cultivation faces significant threats from red spider mite (RSM: Oligonychus coffeae) infestations, which reduce yields and economic viability in major tea-producing regions. Current automated detection methods rely on supervised deep learning models requiring extensive labeled data, limiting scalability for smallholder farmers. This article proposes AIM-Net (AI-based Infestation Mapping Network) by evaluating SwAV (Swapping Assignments between Views), a self-supervised learning framework, for classifying RSM infestation severity (Mild, Moderate, Severe) using a geo-referenced, field-acquired dataset of RSM infested tea-leaves, Cam-RSM. The methodology combines SwAV pre-training on unlabeled data with fine-tuning on labeled subsets, employing multi-crop augmentation and online clustering to learn discriminative features without full supervision. Comparative analysis against a fully supervised ResNet-50 baseline utilized 5-fold cross-validation, assessing accuracy, F1-scores, and computational efficiency. Results demonstrate SwAV’s superiority, achieving 98.7% overall accuracy (vs. 92.1% for ResNet-50) and macro-average F1-scores of 98.3% across classes, with a 62% reduction in labeled data requirements. The model showed particular strength in Mild_RSM-class detection (F1-score: 98.5%) and computational efficiency, enabling deployment on edge devices. Statistical validation confirmed significant improvements (p < 0.001) over baseline approaches. These findings establish self-supervised learning as a transformative tool for precision pest management, offering resource-efficient solutions for early infestation detection while maintaining high accuracy. Full article

The increasing penetration of renewable energy into power systems has intensified transient power quality (PQ) disturbances, demanding efficient detection and classification methods to enable timely operational decisions. This paper introduces a hybrid framework combining an Improved Adaptive S-Transform (IAST) with a Random Forest (RF) classifier to address these challenges. The IAST employs a globally adaptive Gaussian window as its kernel function, which automatically adjusts window length and spectral resolution based on real-time frequency characteristics, thereby enhancing time–frequency localization accuracy while reducing algorithmic complexity. To optimize computational efficiency, window parameters are determined through an energy concentration maximization criterion, enabling rapid extraction of discriminative features from diverse PQ disturbances (e.g., voltage sags and transient interruptions). These features are then fed into an RF classifier, which simultaneously mitigates model variance and bias, achieving robust classification. Experimental results show that the proposed IAST–RF method achieves a classification accuracy of 99.73%, demonstrating its potential for real-time PQ monitoring in modern grids with high renewable energy penetration. Full article

Background: Type 2 diabetes (T2D) is a global health epidemic with rising prevalence within Asian populations, particularly amongst individuals with high visceral adiposity and ectopic organ fat, the so-called Thin-Outside, Fat-Inside phenotype. Metabolomic and microbiome shifts may herald T2D onset, presenting potential biomarkers and mechanistic insight into metabolic dysregulation. However, multi-omics datasets across ethnicities remain limited. Methods: We performed cross-sectional multi-omics analyses on 171 adults (99 Asian Chinese, 72 European Caucasian) from the New Zealand-based TOFI_Asia cohort at 4-years follow-up. Paired plasma and faecal samples were analysed using untargeted metabolomic profiling (polar/lipid fractions) and shotgun metagenomic sequencing, respectively. Sparse multi-block partial least squares regression and discriminant analysis (DIABLO) unveiled signatures associated with ethnicity, glycaemic status, and sex. Results: Ethnicity-based DIABLO modelling achieved a balanced error rate of 0.22, correctly classifying 76.54% of test samples. Polar metabolites had the highest discriminatory power (AUC = 0.96), with trigonelline enriched in European Caucasians and carnitine in Asian Chinese. Lipid profiles highlighted ethnicity-specific signatures: Asian Chinese showed enrichment of polyunsaturated triglycerides (TG.16:0_18:2_22:6, TG.18:1_18:2_22:6) and ether-linked phospholipids, while European Caucasians exhibited higher levels of saturated species (TG.16:0_16:0_14:1, TG.15:0_15:0_17:1). The bacteria Bifidobacterium pseudocatenulatum, Erysipelatoclostridium ramosum, and Enterocloster bolteae characterised Asian Chinese participants, while Oscillibacter sp. and Clostridium innocuum characterised European Caucasians. Cross-omic correlations highlighted negative correlations of Phocaeicola vulgatus with amino acids (r = −0.84 to −0.76), while E. ramosum and C. innocuum positively correlated with long-chain triglycerides (r = 0.55–0.62). Conclusions: Ethnicity drove robust multi-omic differentiation, revealing distinctive metabolic and microbial profiles potentially underlying the differential T2D risk between Asian Chinese and European Caucasians. Full article

Multimodal sentiment analysis (MSA) faces key challenges such as incomplete modality inputs, long-range temporal dependencies, and suboptimal fusion strategies. To address these, we propose MGMR-Net, a Mamba-guided multimodal reconstruction and fusion network that integrates modality-aware reconstruction with text-centric fusion within an efficient state-space modeling framework. MGMR-Net consists of two core components: the Mamba-collaborative fusion module, which utilizes a two-stage selective state-space mechanism for fine-grained cross-modal alignment and hierarchical temporal integration, and the Mamba-enhanced reconstruction module, which employs continuous-time recurrence and dynamic gating to accurately recover corrupted or missing modality features. The entire network is jointly optimized via a unified multi-task loss, enabling simultaneous learning of discriminative features for sentiment prediction and reconstructive features for modality recovery. Extensive experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that MGMR-Net consistently outperforms several baseline methods under both complete and missing modality settings, achieving superior accuracy, robustness, and generalization. Full article

In response to the problem of complex and variable loads on wind turbine gearbox bearing in working conditions, as well as the limited amount of sound data making fault identification difficult, this study focuses on sound signals and proposes an intelligent diagnostic method using deep learning. By adding the CBAM module in ResNeXt to enhance the model’s attention to important features and combining it with the Arcloss loss function to make the model learn more discriminative features, the generalization ability of the model is strengthened. We used a fine-tuning transfer learning strategy, transferring pre-trained model parameters to the CBAM-ResNeXt50-ArcLoss model and training with an extracted Mel spectrogram of sound signals to extract and classify audio features of the wind turbine gearbox. Experimental validation of the proposed method on collected sound signals showed its effectiveness and superiority. Compared to CNN, ResNet50, ResNeXt50, and CBAM-ResNet50 methods, the CBAM-ResNeXt50-ArcLoss model achieved improvements of 13.3, 3.6, 2.4, and 1.3, respectively. Through comparison with classical algorithms, we demonstrated that the research method proposed in this study exhibits better diagnostic capability in classifying wind turbine gearbox sound signals. Full article

Accurate cloud segmentation is critical for astronomical observations and solar forecasting. However, traditional threshold- and texture-based methods suffer from limited accuracy (65–80%) under complex conditions such as thin cirrus or twilight transitions. Although the deep-learning segmentation method based on U-Net effectively captures low-level and high-level features and achieves significant progress in accuracy, current methods still lack interpretability and multi-scale feature integration and usually produce fuzzy boundaries or fragmented predictions. In this paper, we propose multi-scale CAM, an explainable AI (XAI) framework that integrates class activation mapping (CAM) with hierarchical feature fusion to quantify pixel-level attention across hierarchical features, thereby enhancing the model’s discriminative capability. To achieve precise segmentation, we integrate CAM into an improved U-Net architecture, incorporating multi-scale CAM attention for adaptive feature fusion and dilated residual modules for large-scale context extraction. Experimental results on the SWINSEG dataset demonstrate that our method outperforms existing state-of-the-art methods, improving recall by 3.06%, F1 score by 1.49%, and MIoU by 2.21% over the best baseline. The proposed framework balances accuracy, interpretability, and computational efficiency, offering a trustworthy solution for cloud detection systems in operational settings. Full article

The phase-sensitive optical time-domain reflectometry (Φ-OTDR) system has shown substantial potential in distributed acoustic sensing applications. Accurate event classification is crucial for effective deployment of Φ-OTDR systems, and various methods have been proposed for event classification in Φ-OTDR systems. However, most existing methods typically rely on sufficient labeled signal data for model training, which poses a major bottleneck in applying these methods due to the expensive and laborious process of labeling extensive data. To address this limitation, we propose CLWTNet, a novel contrastive representation learning method enhanced with wavelet transform convolution for event classification in Φ-OTDR systems. CLWTNet learns robust and discriminative representations directly from unlabeled signal data by transforming time-domain signals into STFT images and employing contrastive learning to maximize inter-class separation while preserving intra-class similarity. Furthermore, CLWTNet incorporates wavelet transform convolution to enhance its capacity to capture intricate features of event signals. The experimental results demonstrate that CLWTNet achieves competitive performance with the supervised representation learning methods and superior performance to unsupervised representation learning methods, even when training with unlabeled signal data. These findings highlight the effectiveness of CLWTNet in extracting discriminative representations without relying on labeled data, thereby enhancing data efficiency and reducing the costs and effort involved in extensive data labeling in practical Φ-OTDR system applications. Full article

Cancer metabolic reprogramming plays a critical role in tumor progression and therapeutic resistance, underscoring the need for advanced analytical strategies. Metabolomics, leveraging mass spectrometry and nuclear magnetic resonance (NMR) spectroscopy, offers a comprehensive and functional readout of tumor biochemistry. By enabling both targeted metabolite quantification and untargeted profiling, metabolomics captures the dynamic metabolic alterations associated with cancer. The integration of metabolomics with machine learning (ML) approaches further enhances the interpretation of these complex, high-dimensional datasets, providing powerful insights into cancer biology from biomarker discovery to therapeutic targeting. This review systematically examines the transformative role of ML in cancer metabolomics. We discuss how various ML methodologies—including supervised algorithms (e.g., Support Vector Machine, Random Forest), unsupervised techniques (e.g., Principal Component Analysis, t-SNE), and deep learning frameworks—are advancing cancer research. Specifically, we highlight three major applications of ML–metabolomics integration: (1) cancer subtyping, exemplified by the use of Similarity Network Fusion (SNF) and LASSO regression to classify triple-negative breast cancer into subtypes with distinct survival outcomes; (2) biomarker discovery, where Random Forest and Partial Least Squares Discriminant Analysis (PLS-DA) models have achieved >90% accuracy in detecting breast and colorectal cancers through biofluid metabolomics; and (3) prognostic modeling, demonstrated by the identification of race-specific metabolic signatures in breast cancer and the prediction of clinical outcomes in lung and ovarian cancers. Beyond these areas, we explore applications across prostate, thyroid, and pancreatic cancers, where ML-driven metabolomics is contributing to earlier detection, improved risk stratification, and personalized treatment planning. We also address critical challenges, including issues of data quality (e.g., batch effects, missing values), model interpretability, and barriers to clinical translation. Emerging solutions, such as explainable artificial intelligence (XAI) approaches and standardized multi-omics integration pipelines, are discussed as pathways to overcome these hurdles. By synthesizing recent advances, this review illustrates how ML-enhanced metabolomics bridges the gap between fundamental cancer metabolism research and clinical application, offering new avenues for precision oncology through improved diagnosis, prognosis, and tailored therapeutic strategies. Full article

Hepatocellular carcinoma (HCC) is the most prevalent subtype of liver cancer with an increasing incidence worldwide. Single nucleotide polymorphisms (SNPs) may influence disease risk and serve as predictive markers. This study aimed to evaluate the association of PNPLA3 (rs738409 and rs2294918), GCKR (rs780094), MBOAT7 (rs641738), NCAN (rs2228603), and TM6SF2 (rs58542926) SNPs with the risk of developing HCC in a Mexican population. A case-control study was conducted in unrelated Mexican individuals. Cases were 173 adults with biopsy-confirmed HCC and 346 were healthy controls. Genotyping was performed using TaqMan allelic discrimination assay. Logistic regression was applied to evaluate associations under codominant, dominant, and recessive inheritance models. p-values were corrected using the Bonferroni test (pC). Haplotype and gene–gene interaction were also analyzed. The GG homozygous of rs738409 and rs2294918 of PNPLA3, TT, and TC genotypes of GCKR, as well as the TT genotype of MBOAT7, were associated with a significant increased risk to HCC under different inheritance models (~Two folds in all cases). The genotypes of NCAN and TM6SF2 did not show differences. The haplotype G-G of rs738409 and rs2294918 of PNPLA3 was associated with an increased risk of HCC [OR (95% CI) = 2.2 (1.7–2.9)]. There was a significant gene–gene interaction between PNPLA3 (rs738409), GCKR (rs780094), and MBOAT7 (rs641738) (Cross-validation consistency (CVC): 10/10; Testing accuracy = 0.6084). This study demonstrates for the first time that PNPLA3 (rs738409 and rs2294918), GCKR (rs780094), and MBOAT7 (rs641738) are associated with an increased risk of developing HCC from multiple etiologies in Mexican patients. Full article

The transition to efficient production requires innovative water control techniques to maximize irrigation efficiency and minimize waste. Analyzing and optimizing irrigation practices is essential to improve water use and reduce environmental impact. The aim of the research was to identify a discrimination method to analyze the different hydration levels in baby-leaf products. The species being researched was spinach, harvested at the baby leaf stage. Utilizing a large dataset of 261 wavelengths from the hyperspectral imaging system, the feature selection minimum redundancy maximum relevance (FS-MRMR) algorithm was applied, leading to the development of a neural network-based prediction model. Finally, a mathematical classification model K-NN (k-nearest neighbors type) was developed in order to identify a transfer function capable of discriminating the hyperspectral data based on a threshold value of absolute leaf humidity. Five significant wavelengths were identified for estimating the moisture content of baby leaves. The resulting model demonstrated a high generalization capability and excellent correlation between predicted and measured data, further confirmed by the successful training, validation, and testing of a K-NN-based statistical classifier. The construction phase of the statistical classifier involved the use of the experimental dataset and the critical humidity threshold value of 0.83 (83% of leaf humidity) was considered, below which the baby-leaf crop requires the irrigation intervention. High percentages of correct classification were achieved for data within two humidity classes. Specifically, the statistical classifier demonstrated excellent performance, with 81.3% correct classification for samples below the threshold and 99.4% for those above it. The application of advanced spectral analysis and artificial intelligence methods has led to significant progress in leaf moisture analysis and prediction, yielding substantial implications for both agriculture and biological research. Full article

Malware evolution presents growing security threats for resource-constrained Internet of Medical Things (IoMT) devices. Conventional federated learning (FL) often suffers from slow convergence, high communication overhead, and fairness issues in dynamic IoMT environments. In this paper, we propose FedGCL, a secure and efficient FL framework integrating contrastive graph representation learning for enhanced feature discrimination, a Jain-index-based fairness-aware aggregation mechanism, an adaptive synchronization scheduler to optimize communication rounds, and secure aggregation via homomorphic encryption within a Trusted Execution Environment. We evaluate FedGCL on four benchmark malware datasets (Drebin, Malgenome, Kronodroid, and TUANDROMD) using 5 to 15 graph neural network clients over 20 communication rounds. Our experiments demonstrate that FedGCL achieves 96.3% global accuracy within three rounds and converges to 98.9% by round twenty—reducing required training rounds by 45% compared to FedAvg—while incurring only approximately 10% additional computational overhead. By preserving patient data privacy at the edge, FedGCL enhances system resilience without sacrificing model performance. These results indicate FedGCL’s promise as a secure, efficient, and fair federated malware detection solution for IoMT ecosystems. Full article

Geographic object-based image analysis (GEOBIA) has demonstrated substantial utility in remote sensing tasks. However, its integration with deep learning remains largely confined to image-level classification. This is primarily due to the irregular shapes and fragmented boundaries of segmented objects, which limit its applicability in semantic segmentation. While convolutional neural networks (CNNs) excel at local feature extraction, they inherently struggle to capture long-range dependencies. In contrast, Transformer-based models are well suited for global context modeling but often lack fine-grained local detail. To overcome these limitations, we propose GOFENet (Geo-Object Feature Enhanced Network)—a hybrid semantic segmentation architecture that effectively fuses object-level priors into deep feature representations. GOFENet employs a dual-encoder design combining CNN and Swin Transformer architectures, enabling multi-scale feature fusion through skip connections to preserve both local and global semantics. An auxiliary branch incorporating cascaded atrous convolutions is introduced to inject information of segmented objects into the learning process. Furthermore, we develop a cross-channel selection module (CSM) for refined channel-wise attention, a feature enhancement module (FEM) to merge global and local representations, and a shallow–deep feature fusion module (SDFM) to integrate pixel- and object-level cues across scales. Experimental results on the GID and LoveDA datasets demonstrate that GOFENet achieves superior segmentation performance, with 66.02% mIoU and 51.92% mIoU, respectively. The model exhibits strong capability in delineating large-scale land cover features, producing sharper object boundaries and reducing classification noise, while preserving the integrity and discriminability of land cover categories. Full article