Vol 30, No 3 (2024)

One of the main problems in ensuring the unmanned aerial systems (UAS) safety and control performance indicators is the operational analysis organization of heterogeneous data coming from on-board sensors and the formation of adequate recommendations and decisions on their basis of flight missions implementation. In recent years, there have been many research papers devoted to solving this problem using artificial intelligence (AI) methods. The article discusses AI methods for using in tasks related to UAS. We have described the sources of information to generate the data necessary for the application of AI methods. We have classified typical tasks of computer vision and navigation systems for solving using AI methods. We have analyzed the generally accepted classification of AI methods within the scope of the research subject. At the same time, special attention is paid to the features of AI methods that allow solving many well-known problems of recognition, approximation, optimization for UAS target and navigation tasks realization and effective operator support. In particular, we have considered neural networks, decision trees, support vector machines, k-nearest neighbors, genetic, ant colony algorithms, artificial immune systems. Currently, the hardware allows integrating complex algorithms based on these methods on board and widely using them in flight missions. The results of the study conducted as part of the review are illustrated by examples from the scientific publications.

Currently, there is an active use of distributed registry technology in various sectors of the economy by providing transparency, improving tracking of actions within processes, and ensuring trust in open systems. There is a need to evaluate the performance of distributed registries based on measurable indicators. The article presents an overview of distributed registries performance indicators, methods to improve the efficiency and evaluation of distributed registries.

The construction of integrated energy systems (IES) based on traditional energy systems that operate separately ensures higher efficiency and reliability of energy supply to consumers. IES are complex objects for design. The digital twin is a tool that allows one to integrate all the tools necessary for design in a single information space. Software tools that implement the digital twin of IES and are developed for their design require high flexibility in organizing calculations, which is due to the need to simulate a variety of equipment and involve a wide set of methods and mathematical models. Automating the construction of the computing subsystem is an effective solution to overcome the above difficulties. The article proposes a methodological approach to automating the construction of the computing subsystem of the digital twin of the IES. In accordance with the proposed approach, automated construction is performed on the basis of a software platform using modern metaprogramming tools. When building, the concept of Model-Driven Engineering is implemented and knowledge formalized in the form of ontologies is used.

The article outlines the components of the proposed methodological approach to automating the construction of the computing subsystem of the digital twin of the IES, which include the following:

1. principles of software platform development;
2. software platform architecture;
3. technique for automated construction of the digital twin computing subsystem;
4. principles for ensuring the universality of software components.

The digital twin obtained as a result of the practical application of the proposed methodological approach makes it possible to carry out computer and mathematical modeling of the IES in the virtual space, exploring various configurations of its construction. The implementation of modeling within the framework of the digital twin of IES makes it possible to implement flexible and efficient approaches to solving the problems of designing IES and to obtain design recommendations that can be implemented when building real IES.

Improving algorithms for automatic recognition of electrocardiograms requires increasing of training dataset, which is not always possible due to the rarity of certain cardiac diseases or ethical issues. It is possible to improve the algorithms for generating synthetic electrocardiograms using mechanistic models and generative-descriptive neural networks (GANs). At the same time, when evaluating the effectiveness of the proposed solutions, various authors offer different quality assessment metrics from subjective expert assessment to the squared mean error. We compare two approaches to generating synthetic electrocardiograms: pseudo-ECG generation using a one-dimensional cardiomyocyte model and GAN based on long-term short­term memory in terms of machine learning metrics: accuracy, recall, f1-score. We solve the problem of binary classification with bagging method, class 0 — normal sinus rhythm, class 1 — atrial fibrillation. We found that classifier trained on synthetic ECGs generated using GAN is slightly more effective compared to pseudo-ECGs generated using mechanistic models ones. At the same time, it turned out that GANs are not stable enough. The generation of synthetic electrocardiograms using both mechanistic models and GAN can be used to enrich the training set in case of recognition of rare cardiac diseases.