Search

This paper explores an approach to analyzing the quality of meat raw materials using convolutional neural networks. The study focuses on the development and application of a comprehensive system that integrates deep learning capabilities with evolutionary algorithms to enhance the accuracy and efficiency of estimating parameters such as the hydrogen index of raw meat. Genetic algorithms are employed to optimize hyperparameters, which significantly improve model performance. The paper presents the results of comparisons between genetically optimized networks and non-optimized ones. Special attention is given to the analysis of classification accuracy. The authors conclude by discussing the strengths and weaknesses of genetic algorithms for neural network optimization, based on previous research and metrics obtained from neural networks. more...

The paper sets the task of calculating the parameters of deformation of the heart muscle according to echocardiogram data under interference conditions, for example, in the study of children. Indicators of deformation (strain value) of the heart muscle were used by us to determine the presence and severity of dysfunction of the chambers of the heart in atrial septal defect – a congenital heart defect characterized by the presence of communication between the right and left atria. The problem was solved by analyzing the video stream obtained from the installation of echocardiography using a set of deep learning neural network architectures designed for image segmentation. The study was conducted for the U-net architecture. As a result of processing the video stream, it was possible to solve the problem of segmentation of the walls of the heart muscle and binding of key points in the condition of interference in the removal of an echocardiogram on child patients unable to remain motionless during the study. The obtained indicators provide the cardiologist with important information for determining the dysfunction of the chambers of the heart (especially the right atrium, the most compromised chamber of the heart in the studied cases) with a defect of the atrial septum. more...

The article examines the influence of the regional economy on the state of the environment of the Bryansk region, examines the development of the economic potential of the region, and examines the results of the influence of industrial production directions on the state of environmental safety of the state of atmospheric air, water resources and soil cover. Research on the state of environmental safety was carried out using economic and statistical methods; a conclusion was made on the state of natural resources in the Bryansk region more...

Approaches to the process of vehicle research are described, research methods are presented, their advantages and disadvantages, and the important role of mathematical research is noted. The points of differences between operator control and automatic control systems are considered. A mathematical model of the operator’s actions in driving a vehicle is described, which reflects the psychophysical properties of the operator, the presence of absolute and differential thresholds of sensitivity. The model takes into account the delay in the operator’s response and the discreteness of information perception. The model can be used for modeling all software management tasks. Moreover, when forming the control action of the operator - in the mathematical model, the characteristic features of the operator’s activity that differ from an automatic control system are considered, and when forming the control action of the operator - in the mathematical model, some conditions were applied, thanks to which, it is possible to calculate the necessary deviation of the controls, such as the steering wheel and, accordingly, the wheels of the vehicle, knowing the required nature of changes in the parameters of the traffic’s vehicle. more...

Celluloses isolated by the nitric-acid process from domestic unconventional feedstocks such as Miscanthus, oat hulls, and intermediate flax straw were used herein to produce cellulose nitrates (CNs) with a high solubility. For the synthesis of CNs, a commercial technique was employed that involves nitration of cellulose with mixed acid containing 14 wt.% water followed by high-temperature treatment of the nitration product in acidic, alkaline, and neutral environments. The obtained CNs are similar in physicochemical attributes: 12.04–12.26% mass fraction of nitrogen, 10–14 mPa·s viscosity, and 98% solubility in alcohol– ester mixture. FTIR spectra of CNs had absorption bands (2559–2557, 1646–1631, 1277–1271, 825–812, 747–744, 683–680 cm-1) typical of nitro group vibrations. 13C NMR spectra showed chemical shifts representative of 6-mononitrocellulose, 2,6-dinitrocellulose, 3,6-dinitrocellulose, and 2,3,6-trinitrocellulose. DSC revealed that the resultant CNs were highly chemically pure with an exothermic peak at 209–212°С. The CNs obtained from the said unconventional feedstocks were compared with a commercial, highviscosity, lacquer-grade Colloxylin derived from cotton cellulose, as well as with other commercial Colloxylins, to show that the experimental CNs meet the requirements for comercial grades. Thus, the CNs obtained from the unconventional feedstocks are promising candidates as the component of composite explosives. more...

The detonation performance of melt-cast plastic-bonded explosives (PBXs) based on high melting explosive octogen (HMX) was studied in the paper. It has been found that the detonation velocity strongly depends from the dispersion distribution of HMX particles: it changes from 7800 to 8700 m/s. We explain this by the possibility of detonation propagation in PBX through different mechanisms, including detonation front propagation along a percolating cluster formed by filler particles. Thus, varying the particle size distribution can bring about one detonation mechanism or another and hence control the energy release dynamics of melt-cast PBXs to attain high efficiency in practice. Experimental results confirm the assumptions. more...