Despite the great possibilities of modern neural network architectures concerning the problems of object detection and recognition, the output of such models is the local (pixel) coordinates of objects bounding boxes in the image and their predicted classes. However, in several practical tasks, it is necessary to obtain more complete information about the object from the image. In particular, for robotic apple picking, it is necessary to clearly understand where and how much to move the grabber. To determine the real position of the apple relative to the source of image registration, it is proposed to use the Intel Real Sense depth camera and aggregate information from its depth and brightness channels. The apples detection is carried out using the YOLOv3 architecture; then, based on the distance to the object and its localization in the image, the relative distances are calculated for all coordinates. In this case, to determine the coordinates of apples, a transition to a symmetric coordinate system takes place by means of simple linear transformations. Estimating the position in a symmetric coordinate system allows estimating not only the magnitude of the shift but also the location of the object relative to the camera. The proposed approach makes it possible to obtain position estimates with high accuracy. The approximate root mean square error is 7–12 mm, depending on the range and axis. As for precision and recall metrics, the first is 100% and the second is 90%.

To predict the spread of the new coronavirus infection COVID-19, the critical values of spread indicators have been determined for deciding on the introduction of restrictive measures using the city of Moscow as an example. A model was developed using classical methods of mathematical modeling based on exponential regression, the accuracy of the forecast was estimated, and the shortcomings of mathematical methods for predicting the spread of infection for more than two weeks. As a solution to the problem of the accuracy of long-term forecasts for more than two weeks, two models based on machine learning methods are proposed: a recurrent neural network with two layers of long short-term memory (LSTM) blocks and a 1-D convolutional neural network with a description of the choice of an optimization algorithm. The forecast accuracy of ML models was evaluated in comparison with the exponential regression model and one another using the example of data on the number of COVID-19 cases in the city of Moscow.

The global technological transformation of public administration and of both national and international fi nancial systems is unfolding amid a transition toward a multipolar world order. And at the same time the research focus of many Russian scholars is aimed at identifying effective technological solutions for enhancing the competitiveness of the national economics. Of particular scientific and applied interest is the study of potential applications of mathematical methods and optimization algorithms, blockchain technologies, secure communication schemes in the circulation of digital fi nancial assets, data-processing methods using artificial intelligence, and in challenges of developing a national digital infrastructure for the financial market, as well as improving the software-analytical infrastructure of national situation centers and the provision of decision-makers with the necessary instruments for forecasting development of situations under current or user-defined conditions. The relevance of the present study is determined by the strategic priorities outlined in the Russian Federation Presidential Decrees dated February 28, 2024 № 145; May 2, 2024 № 309; and June 18, 2024 № 529, and aligns with the Unifi ed Plan for Achieving National Development Goals Until 2036. The purpose of this study is to provide an analytical review of: strategic projections for the global market of digital financial products produced by major international consulting and fi nancial groups; materials from regulatory market and profile authorities on the digital transformation of the financial sector; developments and models proposed by leading Russian and international researchers in the fi elds of complex socio-economic systems modeling and high-performance data processing, including using artificial intelligence technologies; international experience in modeling decentralized physical infrastructure networks; compilation of prior works by authors in the fi eld of secure data processing; and new approaches to quantitative data assessment. Methodologically, the study is based on the principles of a system approach to analyzing the technological transformation of public administration in general, and the fi nancial sector in particular. These principles make it possible to consider data analytics tools developed by researchers as an essential component of achieving technological leadership and sovereignty.

The digital public infrastructure (DPI) sustainability is critical for public administration, and high platform and technological dependence on foreign digital service providers requires rapid overcoming in order to achieve national goals of technological leadership and digital transformation of the economy. This paper continues the study of technological challenges and opportunities for using the achievements of Russian scientists to support critical and end-to-end technologies of digital public infrastructure, including the digital infrastructure of the fi nancial market. The obtained results complement the theoretical foundations and develop a computer-mathematical apparatus for modeling and studying socio-economic processes, creating the basis for the technological transformation of the Russian economy. The relevance of this study is determined by its compliance with the priority areas of scientific and technological development, support for the achievement of national goals, critical information security technologies, and end-to-end neural network technologies. The purpose of this research is an analytical review of promising methods, approaches, and technologies for the development of the digital infrastructure of the financial market in conjunction with the national goals of the digital transformation of the state. The analysis includes materials from market regulators, relevant ministries and departments; works of leading scientists in the fields of intelligent transport and telecommunications systems, and the security of data acquisition, storage, transmission, and processing; individual previous works by the authors with applications in digital public infrastructure, including fi nancial ones, are summarized. The research methodology utilizes principles of a systems approach to the scientific and technical information analysis, and the authors adhere to the principles of independence and objectivity in their expert assessments. The theoretical basis is provided by research results in the fields of mathematical methods of financial analysis and artificial intelligence technologies, blockchain and secure communications, as well as methods of high-performance and secure data processing. The work utilizes methods of empirical, logical, comparative, and statistical analysis, allowing for the research to be carried out at a high scientific level.