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

In today's world, fire forecasting and early detection play a critical role in preventing disasters and minimizing damage to the environment and human settlements. The main goal of the study is the development and testing of machine learning algorithms for automated detection of the initial stages of fires based on the analysis of multispectral images. Within the framework of this study, the capabilities of three popular machine learning methods: extreme gradient boosting, logistic regression, and vanilla convolutional neural network (vanilla CNN), are considered in the task of processing and interpreting multispectral images to predict and detect fires. XGBoost, as a gradient-boosted decision tree algorithm, provides high processing speed and accuracy, logistic regression stands out for its simplicity and interpretability, while vanilla CNN uses the power of deep learning to analyze spatial and spectral data. The results of the study show that the integration of these methods into monitoring systems can significantly improve the efficiency of early fire detection, as well as help in predicting potential fires.

This work deals with the urgent problem in the mechanics of a deformable solid: studying factors of the stress-strain state of a single-span statically indeterminate beam with complex boundary conditions that is under conditions of complex resistance (axial compression with plane transverse bending). To solve the problem, both analytical methods (the method of forces in the form of “five” support moments, the method of initial parameters) and the numerical finite difference method with a “linear” grid with density n=8 were used. The necessary resolving equations and matrices are given to take into account changes in the rigidity parameter of the right hinged support and variations in concentrated and uniformly distributed loads, both along the axis of the beam and across it. In the final form, diagrams of deflections, bending moments and shear forces were constructed for specific values of bending rigidity and the degree of elastic compliance of the right hinge-yielding support. Reliability of the theoretical principles and applied results obtained by the authors is confirmed on the basis of the given alternative calculation methods.

This study proposes a reproducible hybrid computational model for the explainable classification of territorial vulnerability using heterogeneous tabular data. The approach integrates fuzzy logic and extreme gradient boosting in a two-stage architecture that balances interpretability and predictive performance. First, a fuzzy transformation is applied to construct interpretable risk and resilience indicators based on multi-source administrative indicators. The analytical dataset was formed by integrating 11 heterogeneous administrative sources into a single matrix of 166 territorial units and 76 features. The model was evaluated on a stratified 75/25 split of the training and test sets using the F1 score, ROC-AUC, precision, recall, and integrated quality criterion. Experimental results show that the proposed Fuzzy-XGBoost framework achieved an F1 score of 0.7333 on the test dataset, an ROC-AUC of 0.8291, and an Integrated Score of 0.768, outperforming the strongest baseline and improving recall in highly vulnerable areas. Furthermore, probabilistic threshold optimization identified an operating point at τ = 0.35, reducing the number of missed high-risk cases while maintaining acceptable specificity. The results demonstrate that fuzzy feature expansion combined with gradient boosting provides an efficient and interpretable solution for tabular risk classification and decision support problems under heterogeneity and uncertainty.

In this work there has been studied the rod system operation dependence on the action ofexternal force effects. The system presents a multi-span continuous beam with elastic yieldingsupports. To identify the stress-strain state of the object under study, a precise analytical methodof forces is used. The method of five moments is used as the resolving (canonical) equations. Thefinal results are the parameters of the stress-strain state for a five-span continuous beam withvariable compliance coefficients on 5 intermediate supports and an absolutely rigid left extremesupport, deflections, bending moments, shear forces, and support reactions.Theoretical provisionsand practical results can be used in the design of load-bearing beam structures in buildings andvarious engineering structures.

This paper presents a study of natural oscillations of a cantilever bar with five point masses with variable geometric and stiffness parameters (distances between locations of the masses, coefficients of variability of the bending stiffness of the bar sections). Using the exact method of forces based on the Mohr formula, there have been obtained expressions in general form for calculating the main unit coefficients of the secular equation, which makes it possible to perform calculations and to determine the oscillation frequency response of natural oscillations with a wide range of changes in the initial parameters of the physical and geometric state of cantilever bars. A numerical example has been given to illustrate the proposed theoretical approaches. The results have been compared with the results based on calculating a similar can tilever bar with one( reduced by masses) degree of freedom. A graphical dependence of the oscillation frequency response value on changing the value of the bending stiffness along the length of the cantilever bar gas been obtained. The theoretical provisions and applied results presented in the work will be widely used both in the practical design of bar systems and in scientific research in the field of mechanics of a deformable solid body.