Software & Systems

Articles of journal № 1 at 2023 year.

Order result by: Public date | Title | Authors |

11. Automated solution of the problem of detecting industrial objects on a orthomosaic using a neural network [№1 за 2023 год]
Authors: Nazarov T.R. , Mamedova N.A.
Visitors: 2406
The task of object detection is common for any image type; only the detection quality indicators and the process technological support of differ. The basis for this study was the materials of aerial photography of industrial facilities. Office processing of aerial photography images by overlapping the original photographs to obtain orthophotomaps of the captured area is a complex and costly process, its automation is fragmen-tary. This article contains a solution for automating the stage of constructing the industrial object contours as a part of the process of their detection on an orthophotomap. As an approach that provided automation, the authors used modeling of a trained convolutional neural network with a one-stage pass through the SSD al-gorithm and based on the backpropagation method. The result was the development of a software package capable of identifying and classifying several objects on an orthomosaic. For optimal work with the software package, there are described types and methods of storing generated data, as well as the implementation of the process of a transition from an image coordinate system to a spa-tial coordinate system using orthomosaic mapping files. The practical significance of the results is in the fact that all steps in the development of the software package are described: there is the given rationale for choosing technologies and algorithms, there are identi-fied and formulated requirements for the software package; there is a described process of training a neural network and the project structure. This allows not only reproducing the proposed solution of the automation problem, but also scaling it considering the input parameters for detecting industrial objects on orthomosaics.

12. Vectorization of the three-dimensional immersed boundary method for improving the efficiency of calculations on Intel microprocessors [№1 за 2023 год]
Authors: Rybakov, A.A., Meshcheryakov A.O.
Visitors: 1539
The work is devoted to increasing the efficiency of modern computational applications on high-performance computing systems. The authors consider program code vectorization as a tool for increasing efficiency. Vectorization helps combining scalar operations of the same type into vector analogs, significantly increas-ing performance. Modern Intel microprocessors were chosen as the target platform, for which a unique set of vector instructions AVX-512 is supported. The paper considers an approach to vectorization of a gas dynamic solver using the immersed boundary method and the Steger-Warming upwind scheme in 3D case. This solver has a complex programming con-text that cannot be vectorized automatically. The paper considers the implementation of the solver, as well as approaches to organizing the code and bringing it to a form suitable for automatic vectorization by the icc compiler. To ensure automatic application of vectorization to the solver code, three basic equivalent transfor-mations were applied. First, the calculations, which are the same for all iterations including matrix opera-tions, were localized and brought to the stage of preparing calculations. Second, the main functions of the solver were organized as flat loops, and the data structures were presented as sets of arrays. Third, splitting by condition optimization was applied to loop nests, which can be used to reduce the degree of control branching inside the loop body. These transformations allow the compiler to automatically apply code vec-torization. As a result of the work performed, the solver was accelerated by a factor of 3 due to vectorization when performing calculations on double-precision real numbers.

13. Developing a software tool for constructing a social graph of a social network user in the task of analyzing its security from multi-pass social engineering attacks [№1 за 2023 год]
Authors: Khlobystova, A.O. , Abramov, M.V. , Sazanov, V.A.
Visitors: 2432
The study is based on the problem of lacking visualization tools showing the intensity of interaction between users of the VK online social network, namely the display of metrics that allow evaluating and ranking the intensity of interaction both between a user and his friends, and between friends with each other. The aim of this paper is to improve the accessibility and timeliness of users’ interaction intensity analysis by automating social graph visualization. It is assumed that the numerical coefficients of the social graph arcs will be compared with an assessment of user interaction intensity based on data extracted from publicly available sources of the VK social network. To achieve this goal, the authors considered the following issues: optimization of aggregating necessary data on observed interaction of friends in the VK social network, software implementation of functions for building a social graph, visualization of users' interaction intensity with the possibility of choosing metrics of interest, creation of convenient interface and embedding the developed toolkit into a web-application. The subject of the research is the data of interaction between VK users and the ways of their visualiza-tion. The research methods are based on optimizing sending queries to VK API, as well as developing func-tions and settings to build a social graph. The theoretical significance of the proposed solution is in the development of approaches to analyze the proliferation of multistep social engineering attacks and to validate models for estimating user interaction in-tensity. The result has significant practical relevance consisting in automating the process of assessing the in-tensity of employee interaction, thereby laying the foundation for taking effective measures to mitigate the risks of successful social engineering attacks. The novelty of the research is in the proposed improvement of visualization of VK users' social graph construction by adding new metrics to assess the intensity of users' in-teraction.

14. A simulation model of distributed object radar tracking [№1 за 2023 год]
Authors: D.V. Khrestinin, Pozdnyakov A.A.
Visitors: 1688
The subject of research is radar tracking of distributed objects like groups of small drones. The peculiarity of these objects is in their complex composition and an unusual for most classic aircrafts movement character. The research method is simulation modeling. It allows evaluating the effectiveness of radar tracking algorithms and classification in selected terms. The article presents the process organization of simulation modeling of integrated radar system functioning in the de-tection, measurement, tracking and classification modes. It also presents the description of analytical models and their inter-action, as well as simulation results, which are received using traditional experiment processing methods. The methods take into account a required number of tests to provide probability values in confidence interval no more than 0,01 of the ob-tained value with a confidence probability no more than 0.8. The authors evaluated performance of the most popular tracking and classification algorithms. Tracking algorithms include α-β-γ algorithm, Kalman filter, Unscented Kalman filter, partial filter. Classification algorithms include optimal Bayes algorithm, parting algorithm, Viterbi algorithm, Savrasov algorithm. The model, unlike the known ones, takes into account the influence of all reflections and re-reflections of the probing signal from the sophisticated object elements. According to the simulation results, the authors make a conclusion that among the tracking algorithms, the most effi-cient are algorithms based on the partial filter and Unscented Kalman filter; among the classification algorithms, the most ef-ficient is Savrasov algorithm. However, based on the requirements for a radar performance, none of the considered algo-rithms provides the required quality under the described conditions. This indicates the need to improve the scientific and methodological apparatus of radar trajectory processing.

15. Integrated development of software and hardware components of the frequency converter filter for operating in power-limited ship networks [№1 за 2023 год]
Authors: Chernyi, S.G., Sobolev A.S.
Visitors: 1873
Complex energy systems use a large number of different consumers with a non-linear load. Most of them are complex technical and expensive devices. Due to the non-linearity of the load of these consumers, elec-tromagnetic interference occurs in the network, which negatively affects the correct operation of such equipment. Due to the impact of electromagnetic interference on the operation of complex technical equip-ment operating in large power systems, a decrease in the quality of signals and power, as well as a noticeable decrease in the service life of devices affected by interference, can occur. In frequency converters, due to electromagnetic interference in low-current control signals of power elements, there is a possibility of a short circuit, which will lead to a complete failure of the device. To reduce the effect of electromagnetic interfer-ence on devices, passive or active filtering is often used. This article discusses the development and design of an experimental sample of an active filter to use in low-current circuits of frequency converters, as well as the development of an algorithm for the operation of an active filter control system. The research method is to review existing solutions in order to understand how the algorithms are implemented on other devices. The control system, the algorithm was developed for, is implemented on the debugging platform STM32F411E-DISCO. Such solution will make it possible to meet all the emerging needs that arise during the implementation of the active filter device. The creation of the operation algorithm for this filter was carried out in the MATLAB software package. Due to this solution, it becomes possible to create an operation algorithm without additional difficulties asso-ciated with the further translation of the algorithm into C++ code loaded into the microcontroller.

16. Cognitive regulators: soft computing technologies and the information-thermodynamic law of intelligent control self-organization [№1 за 2023 год]
Authors: Shevchenko A.A., Shevchenko A.V., Zrelova D.P., Ulyanov, S.V.
Visitors: 2388
The paper considers a methodology for designing intelligent cognitive control systems for complex dynamic systems. There are brief descriptions of informational and thermodynamic approaches that unite dynamic stability, controllability and robustness criteria under a homogeneous condition. The authors indicate the problems of training and adaptation of a fuzzy controller, which are relevant in modern control theory. Many existing solutions use artificial neural network models based on the backprop-agation algorithm (BP), the Cohen multilayer structure, etc. Unfortunately, such algorithms do not guarantee the required level of reliability and control accuracy in complex unforeseen situations. These schemes work successfully if the control task is performed in the absence of underdetermined stochastic noise in the envi-ronment, in sensors, in the control loop, etc. The paper proposes one of the solutions to the problem of developing a cognitive control system, which proposes a constructive solution to the problems of designing knowledge bases and intelligent robust cogni-tive control in a given problem-oriented application. There is a comparison of various types of regulators, in-cluding an intelligent regulator based on emotional brain training. The paper describes the advantages of de-signing robust knowledge bases based on the software-algorithmic complex Soft Computing Optimizer based on fuzzy logic. The paper also considers one of the key tasks of modern robotics that is the development of technologies for cognitive mechanical interaction, which makes it possible to implement intelligent control functions through the redistribution of knowledge and control at the program level. A practical example shows the ef-fectiveness of the proposed hybrid cognitive control system, which increases the accuracy and reliability of recognizing mental commands.

◄ ← Preview | 1 | 2