Search Results (13,000)

Accurate cerebral vasculature segmentation using digital subtraction angiography (DSA) is critical for diagnosing and treating cerebrovascular diseases. However, conventional single-frame analysis methods often fail to capture fine vascular structures due to background noise, overlapping anatomy, and dynamic contrast flow. In this study, we propose a novel vessel-enhancing preprocessing technique using temporal differencing of DSA sequences to improve cerebrovascular segmentation accuracy. Our method emphasizes contrast flow dynamics while suppressing static background components by computing absolute differences between sequential DSA frames. The enhanced images were input into state-of-the-art deep learning models, U-Net++ and DeepLabv3+, for vascular segmentation. Quantitative evaluation of the publicly available DIAS dataset demonstrated significant segmentation improvements across multiple metrics, including the Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and Vascular Connectivity (VC). Particularly, DeepLabv3+ with the proposed preprocessing achieved a DSC of 0.83 ± 0.05 and VC of 44.65 ± 0.63, outperforming conventional methods. These results suggest that leveraging temporal information via input enhancement substantially improves small and complex vascular structure extraction. Our approach is computationally efficient, model-agnostic, and clinically applicable for DSA. Full article

Predicting driver injury severity is critical for enhancing road safety, but it is complicated because fatal accidents inherently create class imbalance within datasets. This study conducts a comparative analysis of machine-learning (ML) and deep-learning (DL) models for multi-class driver injury severity prediction using a comprehensive dataset of 107,195 traffic accidents from the Adana, Mersin, and Antalya provinces in Turkey (2018–2023). To address the significant imbalance between fatal, injury, and non-injury classes, the hybrid SMOTE-ENN algorithm was employed for data balancing. Subsequently, feature selection techniques, including Relief-F, Extra Trees, and Recursive Feature Elimination (RFE), were utilized to identify the most influential predictors. Various ML models (K-Nearest Neighbors (KNN), XGBoost, Random Forest) and DL architectures (Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN)) were developed and rigorously evaluated. The findings demonstrate that traditional ML models, particularly KNN (0.95 accuracy, 0.95 F1-macro) and XGBoost (0.92 accuracy, 0.92 F1-macro), significantly outperformed DL models. The SMOTE-ENN technique proved effective in managing class imbalance, and RFE identified a critical 25-feature subset including driver fault, speed limit, and road conditions. This research highlights the efficacy of well-preprocessed ML approaches for tabular crash data, offering valuable insights for developing robust predictive tools to improve traffic safety outcomes. Full article

Fog computing is increasingly preferred over cloud computing for processing tasks from Internet of Things (IoT) devices with limited resources. However, placing tasks and allocating resources in distributed and dynamic fog environments remains a major challenge, especially when trying to meet strict Quality of Service (QoS) requirements. Deep reinforcement learning (DRL) has emerged as a promising solution to these challenges, offering adaptive, data-driven decision-making in real-time and uncertain conditions. While several surveys have explored DRL in fog computing, most focus on traditional centralized offloading approaches or emphasize reinforcement learning (RL) with limited integration of deep learning. To address this gap, this paper presents a comprehensive and focused survey on the full-scale application of DRL to the task offloading problem in fog computing environments involving multiple user devices and multiple fog nodes. We systematically analyze and classify the literature based on architecture, resource allocation methods, QoS objectives, offloading topology and control, optimization strategies, DRL techniques used, and application scenarios. We also introduce a taxonomy of DRL-based task offloading models and highlight key challenges, open issues, and future research directions. This survey serves as a valuable resource for researchers by identifying unexplored areas and suggesting new directions for advancing DRL-based solutions in fog computing. For practitioners, it provides insights into selecting suitable DRL techniques and system designs to implement scalable, efficient, and QoS-aware fog computing applications in real-world environments. Full article

This study presents the development of a noise-monitoring system for the storage ring at the Siam Photon Source, designed to detect and classify noise patterns in real time using beam position monitor (BPM) data. Noise patterns were categorized into four classes: broad peak, multipeak, normal peak, and no beam. Two BPMs located at the multipole wiggler section, BPM-MPW1 and BPM-MPW2, were selected for detailed monitoring based on consistent noise trends observed across the ring. The dataset was organized in two complementary formats: two-dimensional (2D) images used for training and validating the models and one-dimensional (1D) CSV files containing the corresponding raw numerical signal data. Pre-trained deep learning and 1D convolutional neural network (CNN) models were employed to classify these patterns, achieving an overall classification accuracy of up to 99.83%. The system integrates with the EPICS control framework and archiver log data, enabling continuous data acquisition and long-term analyses. Visualization and monitoring features were developed using CS-Studio/Phoebus, providing both operators and beamline scientists with intuitive tools to track beam quality and investigate noise-related anomalies. This approach highlights the potential of combining beam diagnostics with machine learning to enhance operational stability and optimize the synchrotron radiation performance for user experiments. Full article

Change detection technology holds significant importance in disciplines such as urban planning, land utilization tracking, and hazard evaluation, as it can efficiently and accurately reveal dynamic regional change processes, providing crucial support for scientific decision-making and refined management. Although deep learning methods based on computer vision have achieved remarkable progress in change detection, they still face challenges including reducing dynamic background interference, capturing subtle changes, and effectively fusing multi-temporal data features. To address these issues, this paper proposes a novel change detection model called OFNet. Building upon existing Siamese network architectures, we introduce an optical flow branch module that supplements pixel-level dynamic information. By incorporating motion features to guide the network’s attention to potential change regions, we enhance the model’s ability to characterize and discriminate genuine changes in cross-temporal remote sensing images. Additionally, we innovatively propose a dual-domain attention mechanism that simultaneously models discriminative features in both spatial and frequency domains for change detection tasks. The spatial attention focuses on capturing edge and structural changes, while the frequency-domain attention strengthens responses to key frequency components. The synergistic fusion of these two attention mechanisms effectively improves the model’s sensitivity to detailed changes and enhances the overall robustness of detection. Experimental results demonstrate that OFNet achieves an IoU of 83.03 on the LEVIR-CD dataset and 82.86 on the WHU-CD dataset, outperforming current mainstream approaches and validating its superior detection performance and generalization capability. This presents a novel technical method for environmental observation and urban transformation analysis tasks. Full article

The precise mapping of rock joint traces is fundamental to the design and safety assessment of foundations, retaining structures, and underground cavities in building and civil engineering. Existing deep learning approaches either impose prohibitive computational demands for on-site deployment or disrupt the topological continuity of subpixel lineaments that govern rock mass behavior. This study presents BATNet-Lite, a lightweight encoder–decoder architecture optimized for joint segmentation on resource-constrained devices. The encoder introduces a Boundary-Aware Token-Mixing (BATM) block that separates feature maps into patch tokens and directionally pooled stripe tokens, and a bidirectional attention mechanism subsequently transfers global context to local descriptors while refining stripe features, thereby capturing long-range connectivity with negligible overhead. A complementary Multi-Scale Line Enhancement (MLE) module combines depth-wise dilated and deformable convolutions to yield scale-invariant responses to joints of varying apertures. In the decoder, a Skeletal-Contrastive Decoder (SCD) employs dual heads to predict segmentation and skeleton maps simultaneously, while an InfoNCE-based contrastive loss enforces their topological consistency without requiring explicit skeleton labels. Training leverages a composite focal Tversky and edge IoU loss under a curriculum-thinning schedule, improving edge adherence and continuity. Ablation experiments confirm that BATM, MLE, and SCD each contribute substantial gains in boundary accuracy and connectivity preservation. By delivering topology-preserving joint maps with small parameters, BATNet-Lite facilitates rapid geological data acquisition for tunnel face mapping, slope inspection, and subsurface digital twin development, thereby supporting safer and more efficient building and underground engineering practice. Full article

Pipelines play a vital role in material transportation within industrial settings. This review synthesizes detection technologies for early-stage small gas leaks from pipelines in the industrial sector, with a focus on acoustic-based methods, optical gas imaging (OGI), and multimodal fusion approaches. It encompasses detection principles, inherent challenges, mitigation strategies, and the state of the art (SOTA). Small leaks refer to low flow leakage originating from defects with apertures at millimeter or submillimeter scales, posing significant detection difficulties. Acoustic detection leverages the acoustic wave signals generated by gas leaks for non-contact monitoring, offering advantages such as rapid response and broad coverage. However, its susceptibility to environmental noise interference often triggers false alarms. This limitation can be mitigated through time-frequency analysis, multi-sensor fusion, and deep-learning algorithms—effectively enhancing leak signals, suppressing background noise, and thereby improving the system’s detection robustness and accuracy. OGI utilizes infrared imaging technology to visualize leakage gas and is applicable to the detection of various polar gases. Its primary limitations include low image resolution, low contrast, and interference from complex backgrounds. Mitigation techniques involve background subtraction, optical flow estimation, fully convolutional neural networks (FCNNs), and vision transformers (ViTs), which enhance image contrast and extract multi-scale features to boost detection precision. Multimodal fusion technology integrates data from diverse sensors, such as acoustic and optical devices. Key challenges lie in achieving spatiotemporal synchronization across multiple sensors and effectively fusing heterogeneous data streams. Current methodologies primarily utilize decision-level fusion and feature-level fusion techniques. Decision-level fusion offers high flexibility and ease of implementation but lacks inter-feature interaction; it is less effective than feature-level fusion when correlations exist between heterogeneous features. Feature-level fusion amalgamates data from different modalities during the feature extraction phase, generating a unified cross-modal representation that effectively resolves inter-modal heterogeneity. In conclusion, we posit that multimodal fusion holds significant potential for further enhancing detection accuracy beyond the capabilities of existing single-modality technologies and is poised to become a major focus of future research in this domain. Full article

The growing complexity and size of healthcare systems have rendered fraud detection increasingly challenging; however, the current literature lacks a holistic view of the latest machine learning (ML) techniques with practical implementation concerns. The present study addresses this gap by highlighting the importance of machine learning (ML) in preventing and mitigating healthcare fraud, evaluating recent advancements, investigating implementation barriers, and exploring future research dimensions. To further address the limited research on the evaluation of machine learning (ML) and hybrid approaches, this study considers a broad spectrum of ML techniques, including supervised ML, unsupervised ML, deep learning, and hybrid ML approaches such as SMOTE-ENN, explainable AI, federated learning, and ensemble learning. The study also explored their potential use in enhancing fraud detection in imbalanced and multidimensional datasets. A significant finding of the study was the identification of commonly employed datasets, such as Medicare, the List of Excluded Individuals and Entities (LEIE), and Kaggle datasets, which serve as a baseline for evaluating machine learning (ML) models. The study’s findings comprehensively identify the challenges of employing machine learning (ML) in healthcare systems, including data quality, system scalability, regulatory compliance, and resource constraints. The study provides actionable insights, such as model interpretability to enable regulatory compliance and federated learning for confidential data sharing, which is particularly relevant for policymakers, healthcare providers, and insurance companies that intend to deploy a robust, scalable, and secure fraud detection infrastructure. The study presents a comprehensive framework for enhancing real-time healthcare fraud detection through self-learning, interpretable, and safe machine learning (ML) infrastructures, integrating theoretical advancements with practical application needs. Full article

This study presents a novel deep learning framework for classifying visual images based on brain responses recorded through electroencephalogram (EEG) signals. The primary challenge in EEG-based visual pattern recognition lies in the inherent spatiotemporal variability of neural signals across different individuals and recording sessions, which severely limits the generalization capabilities of classification models. Our work specifically addresses the task of identifying which image category a person is viewing based solely on their recorded brain activity. The proposed methodology incorporates three primary components: first, a brain hemisphere asymmetry-based dimensional reduction approach to extract discriminative lateralization features while addressing high-dimensional data constraints; second, an advanced channel selection algorithm utilizing Fisher score methodology to identify electrodes with optimal spatial representativeness across participants; and third, a Dynamic Temporal Warping (DTW) alignment technique to synchronize temporal signal variations with respect to selected reference channels. Comprehensive experimental validation on a visual image classification task using a publicly available EEG-based visual classification dataset, ImageNet-EEG, demonstrates that the proposed disambiguation framework substantially improves classification accuracy while simultaneously enhancing model convergence characteristics. The integrated approach not only outperforms individual component implementations but also accelerates the learning process, thereby reducing training data requirements for EEG-based applications. These findings suggest that systematic spatiotemporal disambiguation represents a promising direction for developing robust and generalizable EEG classification systems across diverse neurological and brain–computer interface applications. Full article

The graphite mineral processing workshop involves complex procedures and generates a large amount of dust and smoke during operation. This particulate matter significantly degrades the quality of indoor surveillance video frames, thereby affecting subsequent tasks such as image segmentation and recognition. Existing image dehazing algorithms often suffer from insufficient feature extraction or excessive computational cost, which limits their real-time applicability and makes them unsuitable for deployment in graphite processing environments. To address this issue, this paper proposes a CNN-based dehazing algorithm tailored for dust and haze removal in graphite mineral processing workshops. Experimental results on a synthetic haze dataset constructed for graphite processing scenarios demonstrate that the proposed method achieves higher PSNR and SSIM compared to existing deep learning-based dehazing approaches, resulting in improved visual quality of dehazed images. Full article

In recent years, solar energy has emerged as a pillar of sustainable development. However, maintaining panel efficiency under extreme environmental conditions remains a persistent hurdle. This study introduces an automated defect detection pipeline that leverages deep learning and computer vision to identify five standard anomaly classes: Non-Defective, Dust, Defective, Physical Damage, and Snow on photovoltaic surfaces. To build a robust foundation, a heterogeneous dataset of 8973 images was sourced from public repositories and standardized into a uniform labeling scheme. This dataset was then expanded through an aggressive augmentation strategy, including flips, rotations, zooms, and noise injections. A YOLOv11-based model was trained and fine-tuned using both fixed and adaptive learning rate schedules, achieving a mAP@0.5 of 85% and accuracy, recall, and F1-score above 95% when evaluated across diverse lighting and dust scenarios. The optimized model is integrated into an interactive dashboard that processes live camera streams, issues real-time alerts upon defect detection, and supports proactive maintenance scheduling. Comparative evaluations highlight the superiority of this approach over manual inspections and earlier YOLO versions in both precision and inference speed, making it well suited for deployment on edge devices. Automating visual inspection not only reduces labor costs and operational downtime but also enhances the longevity of solar installations. By offering a scalable solution for continuous monitoring, this work contributes to improving the reliability and cost-effectiveness of large-scale solar energy systems. Full article

Credit card fraud remains a major cause of financial loss around the world. Traditional fraud detection methods that rely on supervised learning often struggle because fraudulent transactions are rare compared to legitimate ones, leading to imbalanced datasets. Additionally, the models must be retrained frequently, as fraud patterns change over time and require new labeled data for retraining. To address these challenges, this paper proposes an ensemble unsupervised learning approach for credit card fraud detection that combines Autoencoders (AEs), Self-Organizing Maps (SOMs), and Restricted Boltzmann Machines (RBMs), integrated with an Adaptive Reconstruction Threshold (ART) mechanism. The ART dynamically adjusts anomaly detection thresholds by leveraging the clustering properties of SOMs, effectively overcoming the limitations of static threshold approaches in machine learning and deep learning models. The proposed models, AE-ASOMs (Autoencoder—Adaptive Self-Organizing Maps) and RBM-ASOMs (Restricted Boltzmann Machines—Adaptive Self-Organizing Maps), were evaluated on the Kaggle Credit Card Fraud Detection and IEEE-CIS datasets. Our AE-ASOM model achieved an accuracy of 0.980 and an F1-score of 0.967, while the RBM-ASOM model achieved an accuracy of 0.975 and an F1-score of 0.955. Compared to models such as One-Class SVM and Isolation Forest, our approach demonstrates higher detection accuracy and significantly reduces false positive rates. In addition to its performance, the model offers considerable computational efficiency with a training time of 200.52 s and memory usage of 3.02 megabytes. Full article

Efficient and explainable vehicle damage inspection is essential due to the increasing complexity and volume of vehicular incidents. Traditional manual inspection approaches are not time-effective, prone to human error, and lead to inefficiencies in insurance claims and repair workflows. Existing deep learning methods, such as CNNs, often struggle with generalization, require large annotated datasets, and lack interpretability. This study presents a robust and interpretable deep learning framework for vehicle damage classification, integrating Vision Transformers (ViTs) and ensemble detection strategies. The proposed architecture employs a RetinaNet backbone with a ViT-enhanced detection head, implemented in PyTorch using the Detectron2 object detection technique. It is pretrained on COCO weights and fine-tuned through focal loss and aggressive augmentation techniques to improve generalization under real-world damage variability. The proposed system applies the Weighted Box Fusion (WBF) ensemble strategy to refine detection outputs from multiple models, offering improved spatial precision. To ensure interpretability and transparency, we adopt numerous explainability techniques—Grad-CAM, Grad-CAM++, and SHAP—offering semantic and visual insights into model decisions. A custom vehicle damage dataset with 4500 images has been built, consisting of approximately 60% curated images collected through targeted web scraping and crawling covering various damage types (such as bumper dents, panel scratches, and frontal impacts), along with 40% COCO dataset images to support model generalization. Comparative evaluations show that Hybrid ViT-RetinaNet achieves superior performance with an F1-score of 84.6%, mAP of 87.2%, and 22 FPS inference speed. In an ablation analysis, WBF, augmentation, transfer learning, and focal loss significantly improve performance, with focal loss increasing F1 by 6.3% for underrepresented classes and COCO pretraining boosting mAP by 8.7%. Additional architectural comparisons demonstrate that our full hybrid configuration not only maintains competitive accuracy but also achieves up to 150 FPS, making it well suited for real-time use cases. Robustness tests under challenging conditions, including real-world visual disturbances (smoke, fire, motion blur, varying lighting, and occlusions) and artificial noise (Gaussian; salt-and-pepper), confirm the model’s generalization ability. This work contributes a scalable, explainable, and high-performance solution for real-world vehicle damage diagnostics. Full article

This study developed a deep learning–based water level recognition model using Closed-Circuit Television (CCTV) footage. The model focuses on real-time water level recognition in agricultural reservoirs that lack automated water level gauges, with the potential for future extension to flood forecasting applications. Video data collected over approximately two years at the Myeonggyeong Reservoir in Chungcheongbuk-do, South Korea, were utilized. A semantic segmentation approach using the U-Net model was employed to extract water surface areas, followed by the classification of water levels using Convolutional Neural Network (CNN), ResNet, and EfficientNet models. To improve learning efficiency, water level intervals were defined using both equal spacing and the Jenks natural breaks classification method. Among the models, EfficientNet achieved the highest performance with an accuracy of approximately 99%, while ResNet also demonstrated stable learning outcomes. In contrast, CNN showed faster initial convergence but lower accuracy in classifying complex intervals. This study confirms the feasibility of applying vision-based water level prediction technology to flood-prone agricultural reservoirs. Future work will focus on enhancing system performance through low-light video correction, multi-sensor integration, and model optimization using AutoML, thereby contributing to the development of an intelligent, flood-resilient water resource management system. Full article

Particulate matter, particularly PM_2.5, poses a significant threat to public health due to its ability to disperse widely and its detrimental impact on the respiratory and circulatory systems upon inhalation. Consequently, it is imperative to maintain regular monitoring and assessment of particulate matter levels to anticipate air pollution events and promptly mitigate their adverse effects. However, predicting air quality is inherently complex, given the multitude of variables that influence it. Deep learning models, renowned for their ability to capture nonlinear relationships, offer a promising approach to address this challenge, with hybrid architectures demonstrating enhanced performance. This study aims to develop and evaluate a hybrid model integrating Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for forecasting PM_2.5 levels in India, Milan, and Frankfurt. A comparative analysis with established deep learning and machine learning techniques substantiates the superior predictive capabilities of the proposed CNN-RNN model. The findings underscore its potential as an effective tool for air quality prediction, with implications for informed decision-making and proactive intervention strategies to safeguard public health. Full article