Search Results (6,482)

Accurate arrival picking of acoustic emission (AE) data is essential for AE event localization and hydraulic fracture characterization in true triaxial hydraulic fracturing experiments. However, conventional arrival picking methods are highly sensitive to manually defined thresholds, whereas existing deep learning models are constrained by low signal-to-noise ratios (SNRs) and limited AE dataset sizes. To address these challenges, this study proposes an attention-based deep learning method for AE arrival picking. The proposed method introduces an attention mechanism into the PhaseNet framework to suppress noise feature transmission in the skip connections. In addition, a kernel density estimation (KDE)-based label smoothing strategy was adopted to alleviate label imbalance and account for arrival-time uncertainty. The results demonstrate that the proposed method reduced the mean absolute error (MAE) by 10.58%, 92.92%, and 98.25% compared with PhaseNet, STA/LTA, and AR-AIC, respectively. The proposed method exhibited superior picking accuracy, robustness, and computational efficiency relative to the other methods, providing a reliable foundation for AE event localization and high-precision AE monitoring in hydraulic fracturing experiments. Full article

With the widespread adoption of intelligent terminals, edge devices, and distributed information systems in the financial domain, financial security sensing data exhibit multisource heterogeneity, dynamic temporal patterns, and high privacy sensitivity. Traditional centralized anomaly detection methods are no longer able to simultaneously satisfy the requirements of cross-institutional or cross-node collaborative modeling, client data privacy protection, and robust monitoring of transaction and system anomalies. To address this challenge, a data-local federated deep anomaly detection framework has been proposed for distributed financial security sensing systems. Initially, a local deep financial security sensing representation module is constructed to perform temporal encoding and attention-based modeling on multisource financial signals, including terminal operation status, network transaction communication, backend server operation, identity authentication, and anomaly alerts, thereby extracting representations relevant to anomalous behaviors. Subsequently, a data-local federated optimization and personalized aggregation mechanism is developed to enable cross-node knowledge sharing without transmitting raw transaction or client data, while local personalized detection heads are employed to adapt to non-independent and identically distributed (non-IID) financial institution data. Furthermore, an adversarially robust security detection and trust-aware aggregation strategy is introduced to enhance model stability under input noise, feature masking, anomaly camouflage, and potential malicious client updates. Experimental results demonstrate that the proposed method achieves an Accuracy of $92.37\%$, a Precision of $89.41\%$, a Recall of $88.26\%$, an F1-score of $88.83\%$, an AUC of $93.06\%$, and a PR-AUC of $89.15\%$ in the primary financial anomaly detection task, significantly outperforming baseline methods such as Isolation Forest, Autoencoder, LSTM, Transformer, FedAvg, FedProx, SCAFFOLD, and MOON. In robustness experiments, the method attains F1-scores of $87.95\%$, $86.42\%$, $86.88\%$, $84.57\%$, $86.73\%$, and $83.91\%$ under Gaussian noise, feature masking, temporal shift, adversarial perturbation, and $20\%$ and $30\%$ malicious client scenarios, respectively. Ablation studies further confirm the effectiveness of local representation learning, personalized federated optimization, adversarial training, and trust-aware aggregation mechanisms. Overall, the proposed approach provides an efficient intelligent anomaly detection solution for financial AI security monitoring scenarios characterized by data localization requirements, node heterogeneity, and attack perturbations. Full article

Endometrial cancer is the most common gynecologic malignancy in developed countries and remains challenging in terms of risk stratification, treatment monitoring, and early detection of recurrence. Liquid biopsy provides a minimally invasive approach for the dynamic assessment of tumor-derived biomarkers and may complement tissue-based diagnosis and molecular classification. This narrative review summarizes current evidence on circulating biomarkers in endometrial cancer, including circulating tumor DNA (ctDNA), circulating tumor cells (CTCs), extracellular vesicles (EVs), circulating microRNAs, and tumor-educated platelets, with attention to validity, applicability, and implementation barriers. Among these biomarkers, ctDNA currently has the strongest evidence base, especially for longitudinal monitoring, prognostic stratification, molecular residual disease assessment, and early detection of relapse in high-risk or recurrent disease. However, its sensitivity remains limited in early-stage, low-volume, and low-shedding tumors. CTCs, EVs, microRNAs, and platelet-derived signatures are promising but still largely investigational. Artificial intelligence may support multimodal biomarker validation, although clinical adoption will require external validation, locked algorithms, standardized workflows, and prospective utility trials. Overall, liquid biopsy represents a promising adjunct to tissue-based diagnosis and molecular classification in endometrial cancer, particularly for monitoring and follow-up. Prospective studies are now needed to demonstrate whether liquid-biopsy-informed decisions can improve outcomes or safely reduce overtreatment. Full article

Selective laser melting (SLM) equipment operates as a complex cyber–physical system, wherein strong implicit coupling among internal subsystems presents significant challenges for condition monitoring and fault diagnosis. Existing deep learning methods often suffer from feature submersion when processing multi-source heterogeneous data and lack the capability for system-level topological causal inference. To address these issues, we propose a multisystem coupling modeling and anomaly traceability method based on a decoupled graph attention network (ST-DBGAE). Independent local spatiotemporal feature alignment modules are constructed to map heterogeneous sensory data into a unified latent space. This eliminates dimensional discrepancies while strictly maintaining the feature independence of underlying hardware subsystems, such as optical and gas circuits. A dynamic graph attention mechanism with sparse priors is subsequently introduced to adaptively capture time-varying coupling weights triggered by implicit interactions (e.g., thermal fluids), bypassing the need for predefined rigid physical connections. Furthermore, a dual-branch two-stage decoupled optimization architecture is designed. By blocking the cross-interference of global backpropagation, this architecture outputs a continuous equipment health index (HI) based on reconstruction errors and employs a topological difference matrix inference mechanism to reversely anchor the root-cause nodes responsible for cross-system cascading degradation. Experimental results based on over 310,000 real operational monitoring records from industrial SLM equipment demonstrate that the proposed model achieves a comprehensive diagnostic Macro-F1 score of 96.5% across eight operating states. The single-class detection rates (ACCs) of specific underlying anomalies are significantly improved. This method not only enables high-precision equipment health warnings but also provides a physically interpretable microscopic fault propagation mapping for predictive maintenance. Full article

Objective: Preanalytical errors account for the vast majority of preanalytical incidents and remain a fundamental threat to the reliability of test results. Although the types and frequencies of these errors have been extensively studied in the literature, their time-dependent variability has received comparatively little attention. This study aimed to evaluate how preanalytical specimen rejection rates vary across intraday time intervals and to assess the independent influence of time on preanalytical quality. Methods: This retrospective observational study included a total of 579,845 specimens accepted by the central laboratory of Istanbul Atlas University Hospital between January 2024 and December 2025. Specimens were analyzed with respect to preanalytical rejection reasons, the distribution and rate of these reasons across clinical units, and time of day. Each day was divided into six equal four-hour intervals: Z1 (00:00–04:00), Z2 (04:00–08:00), Z3 (08:00–12:00), Z4 (12:00–16:00), Z5 (16:00–20:00), and Z6 (20:00–24:00). Statistical analyses were performed using the Pearson chi-square test, and effect sizes were quantified using Cramér’s V coefficient. Results: Of the 579,845 specimens examined, 4365 were rejected, yielding an overall rejection rate of 0.79%. Rejection rates were found to be non-uniformly distributed across the day (p < 0.001). The highest rejection rate was observed during the Z2 interval (04:00–08:00) at 1.98%, whereas the lowest was recorded during Z3 (08:00–12:00) at 0.45%. Negative binomial regression analysis identified the Z2 interval as the only time period independently associated with an increased rejection risk Incidence Rate Ratio (IRR) = 1.63; 95% Confidence Interval (CI): 1.22–2.19. Among clinical units, the highest rejection rate was recorded in the emergency department (1.92%). Analysis of error types revealed that the majority of rejections were attributable to hemolysis (47.5%) and clotted specimens (26.3%). Hemolysis rates peaked in the emergency department, while clotted specimens occurred more frequently within intensive care units. Analysis of time and error interactions revealed that clotted specimens peaked during Z1 and Z2, whereas hemolysis became the primary cause of rejection during Z3 and Z4. Conclusions: Preanalytical specimen rejection rates exhibited significant variation according to time of day, clinical unit, and error type, with time emerging as a factor independently associated with preanalytical quality. The coexistence of elevated rejection risk during Z2 (04:00–08:00) and markedly low rejection rates during Z3 (08:00–12:00) indicates that the relationship between workload and error frequency is not linear. Although hemolysis and clotted specimens constituted the dominant error types, their distribution followed distinct patterns depending on the clinical unit and time interval. These results underscore the necessity of time-based monitoring to pinpoint unit-specific risks, providing a clear roadmap for targeted quality improvement interventions. Full article

With the occurrence of global climate change and the depletion of agricultural water resources, there is a growing need to develop rapid, non-destructive, and autonomous plant health monitoring systems. As an economically valuable crop, Ocimum basilicum L. (basil) is sensitive to changes in water availability and may exhibit stress-related morphological variations under drought and over-irrigation conditions. However, due to the visual similarity of leaf symptoms under drought stress, waterlogging stress, and optimal irrigation conditions, accurately distinguishing these conditions remains challenging in practical applications. To address this challenge, this paper presents an attention-based dual-branch deep learning framework designed to extract both subtle leaf details and channel-related features from high-resolution plant images. By combining the Convolutional Block Attention Module (CBAM) and Squeeze-and-Excitation (SE) mechanism in a parallel structure, the proposed network improves the analysis of high-resolution images with an input size of 720 × 720 pixels. Under controlled environmental conditions, with ground-truth labels obtained using soil moisture sensor measurements, the proposed model was compared with eight deep learning architectures, including DenseNet121, InceptionV3, and VGG16. The proposed model achieved a hold-out evaluation accuracy of 99.54%, outperforming the second-best model, DenseNet121, which achieved 96.43%. In addition, the proposed model reached a class-specific precision value of 100% for the Drought Stress category and achieved an area under the receiver operating characteristic curve of 1.00 under the controlled experimental setting. Taylor Diagram analysis also indicated that the model closely preserved the variability pattern of the reference data. These results suggest that the proposed application-specific framework may support non-destructive basil water-stress detection under controlled conditions. After further validation with larger datasets, different cultivars, variable environmental conditions, and real-world agricultural scenarios, the proposed approach may contribute to precision irrigation management and sustainable agricultural production. The contribution of this study should be interpreted as an application-specific implementation and evaluation of complementary attention mechanisms for controlled-environment basil water-stress classification, rather than as the introduction of a fundamentally new deep learning methodology. Full article

Mining-subsidence-induced surface cracks pose substantial risks to ecological systems, infrastructure stability, and mining safety. Their thin, elongated, discontinuous, and low-contrast characteristics make accurate detection from unmanned aerial vehicle (UAV) imagery challenging, particularly under complex environmental conditions. This study proposes an enhanced YOLO11n framework for detecting surface cracks in mining subsidence areas. Switchable Atrous Convolution (SAConv) was incorporated to strengthen multi-scale feature extraction, while Cascaded Group Attention (CGA) was introduced to suppress background interference and improve feature discrimination, and Shape-IoU loss was adopted to enhance the localization of slender crack targets. The model was evaluated using 5000 annotated UAV images collected in the Zhungeer mining area. It achieved a precision of 85.6%, a recall of 77.9%, an mAP@0.5 of 84.3%, and an F1-score of 81.6%. Compared with the baseline YOLO11n, precision, recall, and mAP@0.5 increased by 1.4, 4.6, and 3.2 percentage points, respectively. Cross-dataset evaluation on the public Crack500 dataset further demonstrated improved robustness under domain variation. These results indicate that the proposed framework improves the detection and localization of slender and discontinuous cracks in complex mining environments, supporting its application in UAV-based geological hazard monitoring. Full article

Rolling bearing fault diagnosis remains challenging due to environmental noise, insufficient information sharing between diagnosis and prediction tasks, and poor model generalization ability. To address these issues, this paper proposes a fault diagnosis and severity prediction method integrating probabilistic principal component analysis (PPCA) and empirical mode decomposition (EMD) with a one-dimensional convolutional neural network (1DCNN) and bidirectional gated recurrent unit (BiGRU). The proposed model consists of two parallel branches for fault diagnosis and fault severity prediction. A self-attention mechanism is integrated into both branches to enhance feature extraction via adaptive feature weighting. In addition, parameter sharing and weighted loss functions are adopted to improve the training efficiency and collaborative learning between the two tasks. PPCA and EMD are employed for signal denoising and reconstruction while preserving fault-related features. Experiments on public datasets and industrial production-line data show that the proposed method improves the fault classification accuracy from 92.43% to 99.71% under different load conditions, while achieving 98.99% accuracy in fault severity prediction. Noise interference tests further demonstrate the effectiveness of the model. A production-line case study further illustrates the feasibility of applying the proposed method to real monitoring signals. These results confirm the effectiveness and practical potential of the proposed method for rolling bearing fault diagnosis and health assessment. Full article

Metal oxide semiconductor (MOS) gas sensors are an important part of electronic nose technology because they are sensitive, cheap, and work well with microfabrication for system integration. But sensor drift makes them less useful for long-term, continuous gas monitoring. Changes in how sensors respond over time make pattern recognition models that were trained at first less accurate. This review looks at new ways to deal with sensor drift, with a focus on transfer learning and deep learning methods that have been developing continuously in the last five years. It emphasizes the shift from conventional recalibration and component correction to sophisticated methodologies, including deep domain adaptation, contrastive representation learning, and attention-based models. The review does not just list these methods; it also analyzes their pros and downsides, especially in situations where there is not much labeled data, drift is hard to anticipate, or the computational resources are limited, which is often the case with edge sensors. Full article

Impaction of the mandibular third molar in proximity to the mandibular canal increases the risk of inferior alveolar nerve injury. Panoramic radiography is routinely used to assess this relationship. Automated classification of molar–canal overlap could support clinical triage and reduce unnecessary CBCT referrals, while Federated Learning (FL) enables multi-center collaboration without sharing patient data. We compared Local Learning (LL), FL, and Centralized Learning (CL) for binary overlap/no-overlap classification on cropped panoramic radiographs partitioned across eight independent labelers in a simulated heterogeneous multi-center setting. A pretrained ResNet-34 was trained under each paradigm and evaluated using per-client metrics with locally optimized thresholds and pooled test performance with a global threshold. Performance was assessed using area under the receiver operating characteristic curve (AUC) and threshold-based metrics, alongside training dynamics, Grad-CAM visualizations, and server-side aggregate monitoring signals. On the test set, CL achieved the highest performance (AUC 0.831; accuracy ≈ 0.782), FL showed intermediate performance (AUC 0.757; accuracy ≈ 0.703), and LL generalized poorly across clients (AUC range ≈ 0.619–0.734; mean ≈ 0.672). Training curves suggested overfitting, particularly in LL models, and Grad-CAM indicated more anatomically focused attention in CL and FL. Overall, centralized training provided the strongest performance, while FL offers a privacy-preserving alternative that outperforms LL. Full article

Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for computer-assisted diagnosis, treatment planning, and disease monitoring. However, brain tumors usually exhibit irregular, heterogeneous, and multi-scale spatial patterns with complex and ambiguous boundaries. At the same time, the performance of deep segmentation models is often constrained by the limited availability of voxel-level annotations, which are expensive and time-consuming to obtain. To address these challenges, this paper proposes Semi-SwinUNeTR, a semi-supervised framework for 3D brain tumor segmentation with limited annotated data. The proposed method adopts SwinUNeTR as the segmentation backbone, enabling hierarchical volumetric representation learning through shifted-window self-attention while preserving the encoder–decoder structure required for dense prediction. On top of this backbone, we introduce a dual-consistency semi-supervised learning strategy, consisting of mean teacher-based model consistency and interpolation consistency-based data consistency. In addition, voxel-wise consistency weights are used to redistribute semi-supervised supervision toward structurally complex and boundary-irregular tumor regions without changing the SwinUNeTR backbone. Experiments on the BraTS 2019 benchmark demonstrate that the proposed framework achieves strong performance across different annotation ratios. The original Semi-SwinUNeTR achieves Dice scores of 84.93%, 86.25%, 87.05%, and 87.83% under the 10%, 20%, 40%, and 80% labeled-data settings, respectively. With the weighted consistency extension, the Dice scores are further improved to 85.64%, 87.94%, and 88.59% under the 10%, 20%, and 80% labeled-data settings, respectively, while the corresponding HD${}_{95}$ values are reduced to 8.9826, 8.1854, and 7.4533. These results indicate that combining a SwinUNeTR backbone with complementary model consistency, data consistency, and voxel-wise consistency weighting is an effective strategy for semi-supervised volumetric medical image segmentation under limited annotation. Full article

In recent years, China’s urban underground rail transit has developed rapidly, and the development of underground space has become increasingly complex, exposing the system to multiple operational risks such as structural instability, excessive deformation, equipment failures and emergencies. Existing studies often evaluate individual hazards or isolated stakeholder risks, while insufficient attention has been paid to how sudden events interact and propagate as disaster chains. To address this gap, this study develops a disaster-chain network framework for operational risk management in underground rail transit. Twenty sudden disaster risk events are first identified through literature review, expert consultation, system investigation, and HAZOP (Hazard and Operability) analysis. A database of 595 historical events is then used to construct co-occurrence and adjacency matrices. And the Jaccard index is used only to quantify association strength, while temporal order, HAZOP-based causal screening, and expert verification are introduced to distinguish plausible triggering relationships from simple correlations. Network indicators, including degree, betweenness, modified clustering coefficient, path length, connectivity, and edge vulnerability, are applied to identify critical nodes and propagation paths. The results indicate that functional failure of civil structures, fire, and crowd stampede are the dominant risk nodes. The proposed framework provides a transparent and replicable basis for prioritizing monitoring, emergency response, and link-cutting mitigation measures. The findings are intended as system-specific decision support rather than universal risk rankings and should be updated when new local operational data become available. Full article

Aero-engine predictive maintenance is challenged by heterogeneous operating conditions, complex degradation patterns, and the need for interpretable maintenance alerts rather than solely numerical life estimates. This study investigates a condition-aware data-driven framework for jet engine health assessment using the NASA C-MAPSS dataset, which contains four benchmark subsets (FD001–FD004) with different operating conditions and fault modes. Instead of formulating the task as conventional remaining useful life regression, this study reformulates degradation assessment as a three-class health state classification problem, including Normal, Warning, and Fault. A unified preprocessing pipeline is developed, incorporating condition-wise normalization, first-order differential feature construction, and per-unit sliding window segmentation to reduce operating-condition bias, capture degradation dynamics, and prevent data leakage. Five representative models are evaluated under the same framework, including XGBoost, LightGBM, Random Forest, a context-aware multi-scale temporal attention convolutional neural network, and a bidirectional long short-term memory network. The results show that the proposed framework achieves consistently high classification accuracy across all four subsets, with the best results of 0.9841 on FD001, 0.9764 on FD002, 0.9891 on FD003, and 0.9832 on FD004. In addition, Bi-LSTM outperforms MSTA-CNN on all subsets, for example improving accuracy from 0.9614 to 0.9747 on FD002 and from 0.9773 to 0.9806 on FD004, which is consistent with the importance of long-term temporal dependency modeling for this task. These findings suggest that the proposed framework provides an effective and maintenance-decision-aligned solution for C-MAPSS-based health monitoring, where the three-class alert output offers clearer operational meaning than a single numerical life estimate. Full article

COVID-19, caused by the SARS-CoV-2 virus, has become a global public health crisis with diverse clinical manifestations affecting multiple organ systems, including the integumentary system. One notable cutaneous manifestation, referred to as “COVID toes,” involves the development of pernio-like chilblains, characterized by red-to-violet macules, plaques, or nodules, primarily on toes and fingers. This characteristic clinical feature gained significant attention due to its apparent association with COVID-19, especially during the early stages of the pandemic when individuals with mild or asymptomatic cases exhibited these symptoms. Concurrently, digital platforms such as Google Trends have emerged as tools for tracking public interest in health-related topics, offering insights into real-time patterns of disease awareness. Previous research has demonstrated that Google Trends data may correlate with the incidence of infectious diseases, suggesting that search interest can be a proxy for disease outbreaks. In this study, we sought to explore the potential relationship between public interest in COVID toes, as reflected in Google Trends, and the incidence and mortality rates of COVID-19. Specifically, we examined whether peaks in search interest for “COVID toes” corresponded with surges in COVID-19 cases and deaths. By analyzing trends in search data, we aimed to assess the utility of digital platforms as an epidemiological tool for monitoring disease progression and public awareness. Our findings provide insights into the potential role of digital search data in forecasting outbreaks and highlight the interplay between public perception and the clinical burden of COVID-19, emphasizing the importance of real-time data in public health surveillance and response. Full article

Signals generated during tool wear are nonlinear, non-stationary, and easily affected by machining noise, which makes reliable tool condition monitoring difficult in intelligent manufacturing. To address this issue, this study proposes a tool wear degree classification framework, FCTrans-CA, that fuses time-domain and frequency-domain information through a lightweight cross-attention (CA) bridge. Fast Fourier transform (FFT) is first used to obtain frequency-domain representations. The raw time-domain signals are processed by a multi-scale one-dimensional convolutional neural network (MS-CNN) to extract temporal wear features, while the FFT-derived representations provide complementary spectral cues. These two feature streams are fused by an asymmetric CA module in which frequency-domain features guide the selection of wear-sensitive temporal features. K-means clustering is used to divide the measured flank wear (VB) trajectory of each tool into initial-, normal-, and severe-wear stages, thereby reducing subjectivity in label generation. Experiments on the PHM2010 milling dataset show that FCTrans-CA achieves 99.43% classification accuracy on 40,648 test samples. The results indicate that cross-domain feature interaction improves the separability of wear states and provides a reproducible data-driven route for tool wear monitoring. Full article