Increasing image contrast is very important for the visual analysis of X-ray images. To improve the contrast of medical images, various contrast enhancement methods are used, such as histogram equalization and histogram modifications, gamma correction, etc. The paper explores adaptive methods for enhancing the contrast of digital X-ray images. Research was carried out on 1000 images from the open Kaggle database. Combinations of sequential application of several methods for enhancing image contrast were evaluated. Experiments using gamma image correction allowed us to select ranges of input and output parameters of the brightness conversion function. To obtain a better result, before performing gamma correction, it is proposed to use the method of equalizing the histogram of an X-ray image. Possibilities of adaptive image histogram equalization are explored. The performed experiments allow us to propose an improved version of increasing the contrast of X-ray images. Combining the adaptive histogram equalization algorithm with contrast clipping has a visually noticeable effect of improving the contrast of X-ray images. Contrast improvement is supported by objective NIQE and BRISQUE quantifications that do not require reference images. A feature of this work is the use of objective non-reference assessments to determine the quality of images. The performed experiments indicate that the NIQE score correlates better with the visual assessment of image contrast changes. As a result of the experiments, recommendations were proposed for choosing the parameters of the gamma correction and adaptive histogram equalization methods, which make it possible to enhance the contrast without the intensification of noise in the image

This article is devoted to the research and development of methods for classifying pathologies on digital chest radiographs using two different machine learning approaches: the eXtreme gradient boosting (XGBoost) algorithm and the deep convolutional neural network residual network (ResNet50). The goal of the study is to develop effective and accurate methods for automatically classifying various pathologies detected on chest X-rays. The study collected an extensive dataset of digital chest radiographs, including a variety of clinical cases and different classes of pathology. Developed and trained machine learning models based on the XGBoost algorithm and the ResNet50 convolutional neural network using pre-processed images. The performance and accuracy of both models were assessed on test data using quality metrics and a comparative analysis of the results was carried out. The expected results of the article are high accuracy and reliability of methods for classifying pathologies on chest radiographs, as well as an understanding of their effectiveness in the context of clinical practice. These results may have significant implications for improving the diagnosis and care of patients with chest diseases, as well as promoting the development of automated decision support systems in radiology.

Classification of urban area is important for urban planning, infrastructure management and detection of illegal constructions. However, automatic object recognition in urban environments is difficult due to textural similarity of materials, varying lighting conditions and partial overlap of buildings with vegetation. The identification of buildings partially hidden by green spaces is particularly challenging because their boundaries merge with the surrounding environment, which reduces the accuracy of traditional classification methods. In this study, a stepwise approach to object classification in aerial images is proposed to improve the recognition of buildings partially hidden by vegetation. The analysis was performed in two stages using three-channel high-resolution aerial images acquired from an unmanned aerial vehicle. In the first stage, classification was performed based on Haralick features computed from a co-occurrence matrix of gradations, which allowed the extraction of statistical texture features. However, this was insufficient for accuracy, so in the second stage, a Gabor filter was additionally applied to provide analysis of local texture features, taking into account the frequency and orientation of image elements. The final classification was performed using Random Forest algorithm, which allowed to divide objects into three categories: "buildings", "vegetation" and "buildings partially hidden by vegetation". The classes "buildings" and "vegetation" were considered as auxiliary, providing quality control of the classification and allowing us to focus on improving the recognition of objects partially occluded by vegetation. Experimental results confirmed that the proposed method is effective for recognizing buildings partially hidden by vegetation. The inclusion of the Gabor filter improved the classification accuracy of this class from 0.84 to 0.90, the completeness from 0.74 to 0.86, and the F1-estimation from 0.79 to 0.88. The 11% improvement in completeness is particularly important because it indicates a reduction in the number of missed buildings. In comparison, the classification accuracy of fully visible buildings increased from 0.84 to 0.91 and that of vegetation from 0.88 to 0.95. Thus, the proposed method, which combines global and local texture features, demonstrated high performance to improve the identification accuracy of complex objects whose boundaries merge with the surrounding vegetation.

Risk stratification of impaired glycemic control remains a major challenge in biomedical data analysis due to heterogeneous metabolic, behavioral, and therapeutic factors observed in large-scale populations. This study proposes a calibrated and interpretable decision–support framework, termed Calibrated Multi-Task Stacking Ensemble (CMSE), for joint modeling of clinically related glycemic outcomes. The framework integrates demographic variables, lipid profiles, renal and inflammatory biomarkers, dietary and smoking indicators, and therapy-related features within a unified predictive architecture. Robust modeling is ensured through leakage-aware preprocessing, quantile-based Winsorization, out-of-fold stacking, and isotonic calibration of probabilistic outputs. The physiological coherence between short-term and long-term glycemic markers is investigated using an explicit intertask coupling mechanism based on the estimated average glucose (eAG) ratio. Model interpretability is supported using SHAP analysis, mutual information, distance correlation, and feature importance metrics. In the primary medication-free screening configuration, the framework is evaluated on the NHANES 2017–March 2020 dataset, achieving ROC-AUC of 0.865 for diabetes classification and R² values of 0.385 and 0.366 for plasma glucose and HbA1c prediction, respectively. These results indicate that CMSE provides a reliable and explainable approach for calibrated glycemic risk assessment and clinical decision support.

Real-time human movement analysis has become an essential component of modern computer vision applications, including sports performance assessment, rehabilitation monitoring, intelligent surveillance, and human–computer interaction. Although deep learning–based pose estimation methods provide accurate human body landmark detection, executing person detection on every video frame introduces considerable computational overhead, limiting their applicability on resource-constrained CPU-based systems. This paper proposes an efficient YOLO–ROI framework for real-time human movement analysis that combines scheduled YOLO person detection, region-of-interest (ROI) generation, MediaPipe Pose estimation, and lightweight landmark smoothing. Instead of performing object detection on every frame, the proposed framework periodically executes the YOLO detector while reusing the most recently detected ROI between detection cycles. Consequently, MediaPipe Pose continuously estimates body landmarks within the ROI, significantly reducing redundant object detection operations and improving computational efficiency. The proposed framework was evaluated using a self-collected dataset consisting of 200 videos recorded from 10 participants performing five physical exercises under controlled indoor conditions. Computational performance was analyzed under different ROI sizes, detection intervals, and MediaPipe Pose complexity levels using CPU-based execution. Experimental results demonstrate that the proposed optimization strategy achieves a maximum processing speed of 61.32 FPS with an average processing latency of 16.31 ms, enabling stable real-time operation without GPU acceleration. The obtained results further show that scheduled YOLO detection, ROI reuse, and lightweight landmark smoothing effectively reduce computational workload while preserving continuous pose estimation throughout video processing. The proposed framework provides a simple, computationally efficient, and easily deployable solution for real-time human movement analysis and can be readily integrated into sports analytics, rehabilitation systems, intelligent surveillance applications, and edge-based computer vision platforms.

This study presents NORIA, an availability-aware multitask learning framework for clinical prediction from incomplete electronic health records (EHRs). We analyzed a public dataset of 77,724 patients and 107 numerical features. To prevent temporal leakage, predictors were grouped by availability, and training-only feature selection identified three baseline and two first-year variables. NORIA jointly predicts baseline and updated glycemic control, an HbA1c change index, and 21 medication labels using shared representations, masked training, and stage-specific prediction updates. Comparators included classical machine learning, gradient boosting, deep tabular models, and multitask architectures (MMoE and PLE). On the internal test set, NORIA achieved AUROCs of 0.8554 and 0.8888 for baseline and updated glycemic control, respectively, and medication macro-AP of 0.1854 versus 0.1879 for CatBoost. The predefined medication improvement criterion was not met. With 20% of baseline features artificially masked, updated-control AUROC declined by 0.0271 for NORIA, versus 0.0510 for CatBoost and 0.0542 for FT-Transformer. Ablation analyses indicated that masked training provided the clearest robustness benefit. NORIA thus demonstrated competitive accuracy and robustness in selected simulated missing-data scenarios, without establishing overall superiority.