Models, systems, networks in economics, technology, nature and society

Background. In 2020, Russian regions responded differently to external shocks due to the specific industry-specific effects of the COVID-19 pandemic. The study of factors of sustainable development of regional economies continues to be the focus of research interest. The subject of this work is the substantiation of industry determinants that can significantly determine the resistance of Russian regions to the 2020 pandemic shock. Research hypothesis: based on the analysis of industry dynamics in combination with the dynamics of GRP, it is possible to determine directions for increasing the sustainability of regional socioeconomic systems. Materials and methods. General scientific methods of analysis and synthesis, comparison and generalization of information, comparative, monographic, as well as special methods of economic and statistical research (grouping, correlation and regression analysis) were used. Results. The study concluded that the shocks that took place in 2020 have a negative impact on industries related to quality of life and human capital. Conclusions. As recommendations, it is proposed to implement systemic transformational changes in the economy of Russian regions in order to change the nature of the relationship between these industries and the dynamics of GRP in the long term. Institutional influences are also advisable, which should stop negative trends in the short term.

Background. In recent years, price fluctuations have increasingly affected the socio-economic stability of the constituent entities of the Russian Federation, especially under conditions of global turbulence and sanctions pressure. The aim of the study is to iden tify mechanisms capable of mitigating inflationary pressure and stabilizing regional econo mies. Materials and methods. The study employs an integrated approach combining eco nomic analysis, historical parallels, and critical evaluation of current regulatory measures. Results. The paper analyzes the impact of inflation on key sectors of regional economies, examines historical examples (including those from the 1990s), and assesses anti-crisis tools applied at the regional level. Special attention is paid to regional specifics, such as differences in economic structure, dependency on the federal center, and the population's social sensitiv ity. Conclusions. The effectiveness of responses to crisis processes largely depends on the coherence of fiscal and social policies, regional openness to innovation, and the flexibility of administrative decision-making. The article may be of interest to anti-crisis strategy devel opers, public administration bodies, and scholars studying regional resilience mechanisms under inflationary shocks. 

Background. Sustainable development of the country's economic system is a function of the system of national interests, the implementation of which is largely deter mined by the degree of effectiveness of international economic institutions. The purpose of the study is to establish the nature of the conflict of international mechanisms for imple menting national interests and analyze the problems of functioning of modern international economic institutions that generate it. Materials and methods. To achieve this goal, general scientific and special methods were used: aggregation, abstraction, systematization of the analyzed material, grouping. The research methodology is based on the institutional-evolu tionary concept and systems approach. Results. The concept of dependence of the implemen tation of national economic interests on the degree of effectiveness of international economic institutions is presented. Conclusions. Resolving contradictions, a successful response to threats and challenges provoked for international economic institutions by the modern geo economic situation, is a necessary condition for overcoming the conflict of international mechanisms for the implementation of national economic interests, preserving national sov ereignty and ensuring sustainable development of the national economic system. 

Background. Ant Colony Algorithm is an effective method of solving assembly job shop problem. But its computational complexity makes it impractical for real-life tasks of hundreds and thousands of operations. Materials and methods. This article describes a method to significantly increase computational effectiveness of the algorithm for multimachine problem – the most important case for practical use. The proposed method uses separation of the task queue into a number of subqueues for each type of the processing machines and applying Ant Colony Optimization to each of them separately. Results. It is shown that for large-scale problems (thousands of operations) runtime decreases 10 times or more without losing the quality of solutions. Conclusions. This modification significantly increases ACO algorithm speed when applied to practical tasks of machine manufacturing plants.

Background. This study presents the development of a neural network-based binary classifier for detecting COVID-related pneumonia in chest X-ray images. Arguments are given in favor of using X-ray as an alternative to computed tomography in detecting abnormalities in the lungs, associated with COVID-19. An analysis of existing publications on automatic classification of X-ray images with signs of COVID-19 pneumonia is conducted. Materials and methods. The author's dataset consisting of 1240 chest X-ray images was used to train and test the model. The training part of the dataset was subjected to the augmentation procedure. An original fourteen-layer classifier model was proposed and trained over 20 epochs. Results. The classification quality was assessed using standard metrics. The following metric values were obtained: Sensitivity (Recall) – 95,4 %, Specificity – 97,8 %, Accuracy – 96,7 %, Precision – 96,6 %, F1-scope – 96 %. Supplementary testing on 228 images from the COVID-19 Radiography Database of the Kaggle platform demonstrated consistent performance: Sensitivity (Recall), Specificity, Accuracy – 96 %, Precision – 93 %, F1-scope – 94 %. Conclusions. The quality of classification of chest X-ray images by the developed model corresponds to the current level and is close enough to the medical one. The developed classifier can be used in clinical radiology practice as an AI-assistant for radiologists.

Background. The paper highlights the need to modify traditional statistical methods that are based on the assumption of normal distribution of quotes and do not take into account more complex dynamic characteristics of financial assets. The author proposes a new methodology that includes a binary approach to selecting assets in a portfolio, where the basis for making a decision is the feedback received from multidisciplinary forecasting methods. The purpose of the study is to improve the efficiency of investment decisions by developing a comprehensive methodology for supporting decision-making based on the transformation, combination and synthesis of statistical and spectral methods for forecasting time series. Materials and methods. The comprehensive methodology includes forecasting methods ARIMA/ARMA, ARIMA/GARCH and Fourier decomposition, modified by the author. To make decisions on this basis, a general model and its special cases was developed - modified random forest and Adaboost algorithms. Results. Validation of the models included in the methodology was carried out in comparison with the classical Markowitz model on four world indices for different periods. In the vast majority of cases, the proposed models showed a better result than the classical model. Conclusions. The integrated methodology for supporting investment decision-making is more flexible compared to existing ones due to adaptation to the nature of time series and allows for increased investment efficiency, which was shown during validation. In the future, author plans to test the methodology on the Russian market with calculation of the economic effect.

Background. Calculation and comparative analysis of heart rate variability and variability parameters is an urgent task of classification of arrhythmic and normal ECG signals. The objective is a comparative analysis of statistical indicators of heart rate variability and ECG signal variability by two methods and assessment of differences in parameters for different types of signal. Materials and methods. Two groups of signals from the open PhysioNet database were selected as initial data: those obtained from healthy people and those with arrhythmic disorders. For these signals, histograms of the probability density distribution of their amplitude characteristics and relative increments of a number of cardiointervals were constructed. The areas of mismatch of the histograms were calculated as metrics of their difference. Results. An assessment was made of the difference in the indicators of ECG signal variability and heart rate variability based on the averaged histograms of the distributions of ECG signal values for each group and the calculation of the ratio of the area of the mismatch region to the total area of the histogram, while the ratio for the first method was 48 %, and for the second – from 33 to 38 % for various indicators. Conclusions. The obtained data show the potential applicability of both methods for analyzing ECG signals for signs of arrhythmia.