Search Results (3,617)

Satellite monitoring of agricultural crops plays a crucial role in ensuring food security and in the sustainable management of agricultural resources, particularly in regions dominated by rainfed farming, such as the Turkestan region of Kazakhstan. Many satellite monitoring tasks rely on remote identification of different types of cultivated crops. In developing the proposed method, we accounted for the temporal characteristics of crop growth and development in various climatic zones of rainfed agriculture, analyzed the dynamics of the Normalized Difference Vegetation Index (NDVI) together with ground-based data, and identified effective time periods and patterns for successful crop recognition. This study aims to develop and comparatively assess two methods for the automatic identification of cultivated crops in rainfed zones using Sentinel-2 satellite data for the years 2018 and 2022. The first method is based on detailed classification of pre-digitized field boundaries, providing high accuracy in satellite-based mapping. The second method represents a fully automated approach applied to large rainfed areas, emphasizing operational efficiency and scalability. The results obtained from both methods were validated against official national statistics, ground-based field surveys, and farm-level data. The findings indicate that the field-boundary-based method delivers significantly higher accuracy (average accuracy of 91.1%). While the automated rainfed-zone approach demonstrates lower accuracy (78%), it still produces acceptable results for large-scale monitoring, confirming its suitability for rapid assessment of sown areas. This research highlights the trade-off between the accuracy achieved through detailed field boundary digitization and the efficiency provided by an automated, scalable approach, offering valuable tools for agricultural production management. Full article

This study presents a methodology to automatically assess visibility distance on secondary roads using mobile LiDAR systems. The method evaluates both braking and overtaking visibility distances based on the 3D geometry of the road, applying a dynamic analysis through a series of parametrised quadrangular pyramids that simulate the driver’s field of view. Road segments are classified into three risk levels, low, medium, and high, according to the feasibility of stopping or overtaking safely. The methodology was validated on three secondary roads in Spain, achieving an average accuracy of 92.7% when compared to existing road signage. These results demonstrate the method’s potential to improve road safety through continuous, data-driven visibility monitoring. Its application supports advanced driver assistance systems and offers road authorities a reliable tool for proactive risk assessment and road infrastructure planning. Full article

Background/Objectives: Thyroid cancer encompasses distinct histological subtypes with varying biological behavior and treatment implications. Accurate preoperative subtype differentiation remains challenging. Although ultrasound (US) is widely used for thyroid nodule evaluation, qualitative assessment alone is often insufficient to distinguish between papillary (PTC), follicular (FTC), and medullary thyroid carcinoma (MTC). Methods: A retrospective analysis was performed on patients with histologically confirmed PTC, FTC, or MTC. A total of 224 standardized B-mode ultrasound images were analyzed. A set of fully quantitative features was extracted, including morphological characteristics (aspect ratio and perimeter-to-area ratio), internal echotexture (echogenicity and local entropy), boundary sharpness (gradient measures and KL divergence), and structural components (calcifications and cystic areas). Feature extraction was conducted using semi-automatic algorithms implemented in MATLAB. Statistical differences were assessed using the Kruskal–Wallis and Dunn–Šidák tests. A Random Forest classifier was trained and evaluated to determine the discriminatory performance of individual and combined features. Results: Significant differences (p < 0.05) were found among subtypes for key features such as perimeter-to-area ratio, normalized echogenicity, and calcification pattern. The full-feature Random Forest model achieved an overall classification accuracy of 89.3%, with F1-scores of 93.4% for PTC, 85.7% for MTC, and 69.1% for FTC. A reduced model using the top 10 features yielded an even higher accuracy of 91.8%, confirming the robustness and clinical relevance of the selected parameters. Conclusions: Subtype classification of thyroid cancer was effectively performed using quantitative ultrasound features and machine learning. The results suggest that biologically interpretable image-derived metrics may assist in preoperative decision-making and potentially reduce the reliance on invasive diagnostic procedures. Full article

Background/Objectives: Human epidermal growth factor 2 (HER2) scoring is critical for modern breast cancer therapies, especially with emerging indications of antibody–drug conjugates for HER2-low tumors. However, inter-observer agreement remains limited in borderline cases. Automatic artificial intelligence-based scoring has the potential to improve diagnostic consistency and scalability. This study aimed to develop two transformer-based models for HER2 scoring of breast cancer whole-slide images (WSIs) and compare their performance. Methods: We adapted a large-scale foundation model (Virchow) and a lightweight model (TinyViT). Both were trained using patch-level annotations and integrated into a WSI scoring pipeline. Performance was evaluated on a clinical test set (n = 66), including clinical decision tasks and inference efficiency. Results: Both models achieved substantial agreement with pathologist reports (linear weighted kappa: 0.860 for Virchow, 0.825 for TinyViT). Virchow showed slightly higher WSI-level accuracy than TinyViT, whereas TinyViT reduced inference times by 60%. In three binary clinical tasks, both models demonstrated a diagnostic performance comparable to pathologists, particularly in identifying HER2-low tumors for antibody–drug conjugate (ADC) therapy. A continuous scoring framework demonstrated a strong correlation between the two models (Pearson’s r = 0.995) and aligned with human assessments. Conclusions: Both transformer-based artificial intelligence models achieved human-level accuracy for automated HER2 scoring with interpretable outputs. While the foundation model offers marginally higher accuracy, the lightweight model provides practical advantages for clinical deployment. In addition, continuous scoring may provide a more granular HER2 quantification, especially in borderline cases. This could support a new interpretive paradigm for HER2 assessment aligned with the evolving indications of ADC. Full article

Benthic habitats are highly complex and diverse ecosystems that are increasingly threatened by human-induced stressors and the impacts of climate change. Therefore, accurate classification and mapping of these marine habitats are essential for effective monitoring and management. In recent years, Unmanned Aerial Vehicles (UAVs) have been increasingly used to expand the spatial coverage of surveys and to produce high-resolution imagery. These images can be processed using photogrammetry-based techniques to generate high-resolution digital elevation models (DEMs) and orthomosaics. In this study, we demonstrate that integrating descriptors extracted from pre-trained Convolutional Neural Networks (CNNs) with geomorphometric attributes derived from DEMs significantly enhances the accuracy of automatic benthic habitat classification. To assess this integration, we analyzed orthomosaics and DEMs generated from UAV imagery across three shallow reef zones along the Red Sea coast of Saudi Arabia. Furthermore, we tested various combinations of feature layers from pre-trained CNNs—including ResNet-50, VGG16, and AlexNet—together with several geomorphometric variables to evaluate classification accuracy. The results showed that features extracted from the ResNet-50 FC1000 layer, when combined with twelve geomorphometric attributes based on curvature, slope, the Topographic Ruggedness Index (TRI), and DEM-derived heights, achieved the highest overall accuracies. Moreover, training a Support Vector Machine (SVM) classifier using both pre-trained ResNet-50 features and geomorphometric variables led to an improvement in overall accuracy of up to 5%, compared to using ResNet-50 features alone. The proposed integration effectively improves the automation and accuracy of benthic habitat mapping processes. Full article

Early and accurate identification of brain tumors is essential for determining effective treatment strategies and improving patient outcomes. Artificial intelligence (AI) and deep learning (DL) techniques have shown promise in automating diagnostic tasks based on magnetic resonance imaging (MRI). This study evaluates the performance of four pre-trained deep convolutional neural network (CNN) architectures for the automatic multi-class classification of brain tumors into four categories: Glioma, Meningioma, Pituitary, and No Tumor. The proposed approach utilizes the publicly accessible Brain Tumor MRI Msoud dataset, consisting of 7023 images, with 5712 provided for training and 1311 for testing. To assess the impact of data availability, subsets containing 25%, 50%, 75%, and 100% of the training data were used. A stratified five-fold cross-validation technique was applied. The CNN architectures evaluated include DeiT3_base_patch16_224, Xception41, Inception_v4, and Swin_Tiny_Patch4_Window7_224, all fine-tuned using transfer learning. The training pipeline incorporated advanced preprocessing and image data augmentation techniques to enhance robustness and mitigate overfitting. Among the models tested, Swin_Tiny_Patch4_Window7_224 achieved the highest classification Accuracy of 99.24% on the test set using 75% of the training data. This model demonstrated superior generalization across all tumor classes and effectively addressed class imbalance issues. Furthermore, we deployed and benchmarked the best-performing DL model on embedded AI platforms (Jetson AGX Xavier and Orin Nano), demonstrating their capability for real-time inference and highlighting their feasibility for edge-based clinical deployment. The results highlight the strong potential of pre-trained deep CNN and transformer-based architectures in medical image analysis. The proposed approach provides a scalable and energy-efficient solution for automated brain tumor diagnosis, facilitating the integration of AI into clinical workflows. Full article

While Internet privacy is a subjective term that is challenging to define, describe, and quantify, assessing the level of privacy provided by data processors offering services over the Internet is essential for detecting privacy flaws and enabling continuous improvement. Moreover, assessing Internet privacy is fundamental for estimating the risk of personal data disclosure, the degree of compliance with privacy regulations, and the effectiveness of implemented protection mechanisms. Remarkably, the absence of a standardized criterion for this assessment has led to the proliferation of diverse heuristic techniques applied with different approaches. In this paper, we conduct an in-depth analysis and introduce a novel taxonomy for categorizing existing heuristic techniques to assess Internet privacy. Moreover, we scrutinize various protection mechanisms designed to enhance users’ privacy. We cover this broad topic across all domains of application and levels of automation, considering all relevant papers regardless of publication year, ultimately providing a comprehensive review of this important field of knowledge. Leveraging our proposed classification framework, we systematically organize and categorize 160 papers carefully selected from 934 candidates, elucidating existing gaps and challenges while foreseeing future research directions. Overall, our findings reveal that most studies predominantly rely on information measurement methods for assessing Internet privacy. Although most heuristic techniques are based on automatic mechanisms, they are applied with a clear focus on the traditional use of Internet services through a web browser, demanding more research efforts for other domains. The development of new technologies that incorporate privacy-by-default and include telemetry modules in their architectures will be essential for assessing and enhancing users’ privacy when delivering services over the future Internet. Full article

Retrieval-Augmented Generation (RAG) offers a promising strategy to harness large language models (LLMs) for delivering up-to-date, accurate clinical guidance while reducing physicians’ cognitive burden, yet its effectiveness hinges on query clarity and structure. We propose an adaptive Self-Query Retrieval (SQR) framework that integrates three refinement modules—PICOT (Population, Intervention, Comparison, Outcome, Time), SPICE (Setting, Population, Intervention, Comparison, Evaluation), and Iterative Query Refinement (IQR)—to automatically restructure and iteratively enhance clinical questions until they meet predefined retrieval-quality thresholds. Implemented on Gemini-1.0 Pro, we benchmarked SQR using thirty postoperative rhinoplasty queries, evaluating responses for accuracy and relevance on a three-point Likert scale and for retrieval quality via precision, recall, and F1 score; statistical significance was assessed by one-way ANOVA with Tukey post-hoc testing. The full SQR pipeline achieved 87% accuracy (Likert 2.4 ± 0.7) and 100% relevance (Likert 3.0 ± 0.0), significantly outperforming a non-refined RAG baseline (50% accuracy, 80% relevance; p < 0.01 and p = 0.03). Precision, recall, and F1 rose from 0.17, 0.39 and 0.24 to 0.53, 1.00, and 0.70, respectively, while PICOT-only and SPICE-only variants yielded intermediate improvements. These findings demonstrate that automated structuring and iterative enhancement of queries via SQR substantially elevate LLM-based clinical decision support, and its model-agnostic architecture enables rapid adaptation across specialties, data sources, and LLM platforms. Full article

Digital transformation (DT) has become a strategic priority for public administrations, particularly due to the need to deliver more efficient and citizen-centered services and respond to societal expectations, ESG (Environmental, Social, and Governance) criteria, and the United Nations Sustainable Development Goals (UN SDGs). In this context, the main objective of this study is to propose an innovative methodology to automatically evaluate the level of digital transformation (DT) in public sector organizations. The proposed approach combines traditional assessment methods with Artificial Intelligence (AI) techniques. The methodology follows a dual approach: on the one hand, surveys are conducted using specialized staff from various public entities; on the other, AI-based models (including neural networks and transformer architectures) are used to estimate the DT level of the organizations automatically. Our approach has been applied to a real-world case study involving local public administrations in the Valencian Community (Spain) and shown effective performance in assessing DT. While the proposed methodology has been validated in a specific local context, its modular structure and dual-source data foundation support its international scalability, acknowledging that administrative, regulatory, and DT maturity factors may condition its broader applicability. The experiments carried out in this work include (i) the creation of a domain-specific corpus derived from the surveys and websites of several organizations, used to train the proposed models; (ii) the use and comparison of diverse AI methods; and (iii) the validation of our approach using real data. Based on the deficiencies identified, the study concludes that the integration of technologies such as the Internet of Things (IoT), sensor networks, and AI-based analytics can significantly support resilient, agile urban environments and the transition towards more effective and sustainable Smart City models. Full article

Background: Left atrial strain, particularly reservoir strain, has emerged as a sensitive marker of left atrial function and an early indicator of diastolic dysfunction and cardiovascular risk. However, automated left atrial strain analysis is not universally available, particularly in resource-limited settings. In this study, we propose a manual method for calculating biplane left atrial reservoir strain and validate its agreement with automated software in patients with atrial fibrillation and in sinus rhythm. Methods: Echocardiography examinations from 30 patients with atrial fibrillation and 30 patients in sinus rhythm were analyzed. Left atrial reservoir strain was calculated using both an automatic speckle tracking imaging-based algorithm and a manual point-by-point method based on atrial wall delineation. Agreement between methods was assessed using Pearson correlation, Bland–Altman analysis, and intraclass correlation coefficient. Results: Strong correlation and excellent agreement were observed between the two methods in both groups. Pearson correlation coefficients were r = 0.95 (p < 0.0001) in the atrial fibrillation group and r = 0.94 (p < 0.0001) in the sinus rhythm group. Bland–Altman analysis showed narrow limits of agreement, particularly in the atrial fibrillation group. The intraclass correlation coefficient was 0.95 in atrial fibrillation and 0.92 in sinus rhythm, indicating excellent reliability. The standard error of measurement and minimal detectable change were low in both groups. Conclusions: Manual measurement of left atrial reservoir strain is feasible, reproducible, and demonstrates excellent agreement with automated software. It may serve as a reliable alternative in clinical scenarios where automated tools are unavailable. Full article

The proximity of urban green spaces to residential areas has become a central principle in contemporary urban planning, with cities worldwide adopting “15-minute city” concepts that prioritize walking-distance access to parks. This study examined whether proximity to different types of parks influences park visitation, physical activity, and mental well-being in Bangkok, Thailand, where the government recently launched a 15-minute parks policy initiative to improve the proximity of urban residents to green spaces. Using a cross-sectional survey of 615 residents across Bangkok’s 50 districts, we measured proximity to six park types using GIS network analysis and assessed health outcomes through validated instruments (Global Physical Activity Questionnaire, GPAQ for physical activity GPAQ for physical activity, and WHO-5 for well-being). Our findings revealed that only proximity to community parks (5–20 ha) was significantly associated with park visitation, sufficient physical activity, and good well-being. Proximity to smaller parks, including the new 15-minute parks, pocket parks, and neighborhood parks, showed no significant associations with any health outcomes, despite being within walking distance. These results suggest a critical size threshold below which parks cannot generate health and well-being benefits in Bangkok’s environment. The findings challenge the argument commonly used in proximity-based green space policies that assume closer parks automatically improve park visitation and public health benefits, indicating that cities facing similar constraints should balance between providing small park networks and securing larger, functional parks to support meaningful recreational use or health improvements. Full article

In the context of Industry 4.0 and intelligent manufacturing, the scale and complexity of complex equipment systems are continuously increasing, making effective high-precision modeling, simulation, and prediction in the engineering field significant challenges. Digital twin technology, by establishing real-time connections between virtual models and physical systems, provides strong support for the real-time monitoring, optimization, and prediction of complex systems. However, traditional digital twin models face significant limitations when synchronizing with high-dimensional nonlinear and non-stationary dynamical systems due to the latter’s dynamic characteristics. To address this issue, we propose a multi-layer deep Koopman operator-based (MDK) credibility-based self-evolution algorithm for equipment digital twins. By constructing multiple time-scale embedding layers and combining deep neural networks for observability function learning, the algorithm effectively captures the dynamic features of complex nonlinear systems at different time scales, enabling their global dynamic modeling and precise analysis. Furthermore, to enhance the model’s adaptability, a trustworthiness-based evolution-triggering mechanism and an adaptive model fine-tuning algorithm are designed. When the digital twin model’s trustworthiness assessment indicates a decline in prediction accuracy, the evolution mechanism is automatically triggered to optimize and update the model with the fine-tuning algorithm to maintain its stability and robustness during dynamic evolution. The experimental results demonstrate that the proposed method achieves significant improvements in prediction accuracy within unmanned aerial vehicle (UAV) systems, showcasing its broad application potential in intelligent manufacturing and complex equipment systems. Full article

In printed circuit board (PCB) assembly, the volume of dispensed glue is closely related to the PCB’s durability, production costs, and the overall product reliability. Currently, quality inspection is performed manually by operators, inheriting the limitations of human-performed procedures. To address this, we propose an automatic optical inspection framework that utilizes convolutional neural networks (CNNs) and post-hoc explainable methods. Our methodology handles glue quality inspection as a three-fold procedure. Initially, a detection system based on CenterNet MobileNetV2 is developed to localize PCBs, thus, offering a flexible lightweight tool for targeting and cropping regions of interest. Consequently, a CNN is proposed to classify PCB images into three classes based on the placed glue volume achieving 92.2% accuracy. This classification step ensures that varying glue volumes are accurately assessed, addressing potential quality issues that appear early in the production process. Finally, the Deep SHAP and Grad-CAM methods are applied to the CNN classifier to produce explanations of the decision making and further increase the interpretability of the proposed approach, targeting human-centered artificial intelligence. These post-hoc explainable methods provide visual explanations of the model’s decision-making process, offering insights into which features and regions contribute to each classification decision. The proposed method is validated with real industrial data, demonstrating its practical applicability and robustness. The evaluation procedure indicates that the proposed framework offers increased accuracy, low latency, and high-quality visual explanations, thereby strengthening quality assurance in PCB manufacturing. Full article

Microseismic monitoring has become a critical technology for hydraulic fracturing in unconventional oil and gas reservoirs, owing to its high temporal and spatial resolution. It plays a pivotal role in tracking fracture propagation and evaluating stimulation effectiveness. However, the automatic picking of first-arrival times and accurate source localization remain challenging under complex noise conditions, which constrain the reliability of fracture parameter inversion and reservoir assessment. To address these limitations, we propose a hybrid approach that combines optimized variational mode decomposition (OVMD), wavelet thresholding denoising (WTD), and an adaptive fractal box-counting dimension algorithm for enhanced first-arrival picking and source localization. Specifically, OVMD is first employed to adaptively decompose seismic signals and isolate noise-dominated components. Subsequently, WTD is applied in the multi-scale frequency domain to suppress residual noise. An adaptive fractal dimension strategy is then utilized to detect change points and accurately determine the first-arrival time. These results are used as inputs to a particle swarm optimization (PSO) algorithm for source localization. Both numerical simulations and laboratory experiments demonstrate that the proposed method exhibits high robustness and localization accuracy under severe noise conditions. It significantly outperforms conventional approaches such as short-time Fourier transform (STFT) and continuous wavelet transform (CWT). The proposed framework offers reliable technical support for dynamic fracture monitoring, detailed reservoir characterization, and risk mitigation in the development of unconventional reservoirs. Full article

Background/Objectives: Intraoperative frozen biopsies are essential during surgery for Hirschsprung’s disease (HD). However, this method has several limitations with the need for a faster and real-time diagnostic alternative. For this, consistent histoanatomical and morphometric differences between aganglionic and ganglionic bowel must be established. The primary objective was to compare dimensions of bowel wall layers between aganglionic and ganglionic segments histopathologically in resected rectosigmoid specimens from children with HD. Secondary objectives were to design a diagnostic algorithm to distinguish aganglionosis from ganglionosis and assess whether full bowel wall thickness correlates with patient weight and age. Methods: Each histoanatomic bowel wall layer—mucosa, submucosa, and muscularis propria’s layers—was delineated manually on histopathological images. Mean thicknesses were calculated automatically using an in-house image analysis software. Paired parametric tests compared measurements in aganglionic and ganglionic segments. Results: Resected specimens from 30 children with HD were included. Compared to aganglionic bowel, ganglionic bowel showed a thicker muscularis interna (mean 0.666 mm versus 0.461 mm, CI −0.257–(−0.153), p < 0.001), and a higher muscularis interna/muscularis externa ratio (2.047 mm versus 1.287 mm, CI −0.954–(−0.565), p < 0.001). An algorithm based on these features achieved 100% accuracy in distinguishing aganglionosis from ganglionosis. No significant difference in full bowel wall thickness was found between aganglionic and ganglionic segments, nor any correlation with patient weight or age. Conclusions: Histoanatomic layer thickness differs between aganglionic and ganglionic bowel, forming the basis of a diagnostic algorithm. Full bowel wall thickness was independent of patient weight and age. Full article