Vol 21, No 4 (2023)

This article demonstrates results for a queuing system formed by right-shifting an Erlang distribution and a second-order hyperexponential distribution. As is known, the first distribution provides a coefficient of variation less than one, and the second one – more than one. From the general queuing theory, it is known that the average delay of requests in the queue in the QS G/G/1 is related to the coefficients of variation of arrival intervals and service times by a quadratic dependence, and the system we are considering belongs precisely to this type. An operational shift in the distribution laws leads to a multiple reduction in delay compared to a conventional system, and this value depends on the value of the shift parameter. To construct a mathematical model of the delay, the method of spectral solution of the Lindley integral equation for the system under consideration was applied. For the practical application of the obtained results, the standard method of oprobability theory moments is used. The obtained results of numerical and analytical modeling in Mathcad clearly confirm the adequacy of the proposed mathematical delay model.

Modern high-end cars have many electronic control units for driving assistance that combine huge amounts of data about the functioning of car components. A significant part of these vehicles use a controller area network for communication between electronic units. Controller area network is a simple and reliable network protocol that due to its simplicity lacks any security mechanisms for data transmission. The problem of controller area network vulnerability is worsening as constantly growing amounts of data between cars, road infrastructure and the Internet. The traffic of attacks on controller area networks can be treated as abnormal that allows using anomaly detection methods for their recognition. In this work we propose the recurrent long short-term memory encoder-decoder neural network for controller area network attacks detection.

This article considers queue formation in the M/D/1 system with statistical characteristics of the first two orders that areclose to real, as the purpose of telecommunication traffic modeling. The input stream to the system is considered to be a group stream with constant parameters of the package and distance between arrivals, influenced by gamma distribution. These parameters are determined by a neural network trained to determine parameters of such input streams according to statistical characteristics of the queue at various loads of device. The results obtained demonstrate a good ap-proximation with the use of gamma-ray fluxes. Parameters are evaluated with the use of the neural network. The practical usefulness of the considered approach and the prospects of using neural net-works for practical tasks in solving which queue theory is used are provided.

Light beams with orbital angular momentum have unique properties that make them valuable for research and practical applications. From revolutionizing communication technologies to enabling advanced microscopy and quantum computing possibilities, these beams continue to drive innovation and open up new frontiers in optics and photonics. In this paper, the dependence of the radiation flux density of an optical vortex beam on the geometry of the emitting structure is investigated. A micro-ring resonator with periodic structures is used as an optical vortex beam emitter structure. In our study, optimizing the width of the ring waveguide leads to an increase in the radiation flux power up to 30% for the resonant wavelength of 1563 nm. To analyze how the whispering gallery modes are distributed in the cross section of the annular waveguide, we increased the annular waveguide width from 400 nm to 500 nm. This proposed approach can be applied to radiating micro-ring resonators in various applications.

The article is aimed to provide reception algorithm as a whole with element-by-element decision making. It belongs to the group of decision, making algorithms with feedback. It is used to demodulate discrete signals that have passed through a memory channel. The study presents an example of signal processing of a binary phase modulator. This example shows processing features that are not obvious for considering of the mathematical formula that describes demodulation algorithm. Another algorithm was developed for a quadrature phase modulator as well. The noise immunity for additive gaussian noise was estimated by the numerical simulations. The same research was carried out using an equalizer filter that suppresses channel memory effect. Simulation results were used as the base for the graphs of the error probability versus signal-to-noise ratio.

Data mining is recognized as highly sought-after service. Many universities are involved in training specialists in this field. However, consumer demands are increasing, resulting in higher requirements for the mathematical models used in this regard. Clients need to be sure in the quality level of the recommendations they get. One method to achieve this is provided with the use of Explainable Artificial Intelligence (XAI) technology. The current situation worldwide poses limitations on the use of foreign software, and domestic analytical systems available to universities may not have XAI module among their functions. The solution is to develop such system independently. The authors developed a software product that enables training of three types of mathematical models, each capable of generating an explanation in textual format for its forecasts. A series of experiments was conducted in order to confirm functionality of all elements of the created product, as well as its potential to be used training processes in higher education system.

Interaction between man and machine is the future of technology. Different mechanisms and mediums are used for this interaction such as voice, signals, pictures, videos, text etc. Text is one of the most popular mediums of interaction and has gained popularity over past decades. It is used for making predictions of stock market, analysis of people’s opinion, identification of group of people with similar interests etc. In this research, the focus is to identify and analyze the intent of the written text and used it to prepare an appropriate machine response to text. There are several systems available that uses semi-automatic mechanisms for interaction with humans such as the online customer care services for banks and the telecommunication industry. Different models and algorithms are used for this semi-automatic interaction. This study works on the design of a fully automated system for extracting the intents from the text, prepare an appropriate response and use the intent to do the prediction of the text. The results of the research are detailed in the methodology and experiment sections of the paper.

This article delves into the exciting possibilities that arise when technology is applied to the field of medicine. It explores how automation can streamline various processes, leading to more efficient and accurate healthcare. One focus area is the potential for replacing direct interaction between doc-tors and patients with automated systems. By utilizing advanced neural networks, diagnostic and treatment processes can become automated, leading to faster and more precise outcomes. For example, AI-powered systems can analyze medical images and detect abnormalities with incredible accuracy, aiding doctors in making diagnoses. Additionally, virtual assistants and chatbots can provide personalized healthcare advice, reducing the need for in-person consultations for minor concerns. These advancements not only enhance efficiency but also have potential to improve access to healthcare, especially in remote areas. Embracing technology in medicine opens up a lot of possibilities for better patient care and overall healthcare outcomes.

The article presents the results of the analysis of the general quality indicators of the mobile radiotelephone services. The source of data for such analysis was the results of tests organized by Roskomnadzor in the period from 2022 to 2023 on the networks of four major mobile operators (Beeline, Megafon, MTS and Tele2) in the five largest cities of the Volga Federal District with a population of more than a million inhabitants. The main quality indicators have been selected: voice transmission, data transmission and SMS transmission, for which a comparative analysis is performed based on a rating methodology. The positions of the control objects (the city center of the region and the operators of the PRS) are distributed in accordance with the value of the same type of indicators for each control parameter with the determination of the best and worst objects. A cumulative final rating has been compiled for each city where inspections were carried out and for each operator.

The article is devoted to issues related to the modeling of the business process of forming wages for manufacturing enterprise workers in the context of digital transformation. The importance of modeling the business process of paying workers is shown, on which the efficiency of the production process largely depends, and, accordingly, the efficiency of the enterprise as a whole. A model for the formation of workers' wages has been developed, including information, technological and organizational aspects. An objective assessment of the work of workers leads to increased motivation, high-performance and high-quality work. The application of a balanced scorecard system is shown, which makes it possible to move from strategy to operational planning, taking into account the mutual influence of four modules – financial, production, consumer and innovation. Together, these modules have a significant impact on improving the efficiency of the entire enterprise. However, without digital transformation, it is impossible to consider the innovative activity of an enterprise. In addition, it is only in the conditions of digital information that it is possible to abandon the poorly documented distribution of shift-daily tasks to workers and promptly monitor their implementation. The development of a methodology for paying workers leads to the fact that having operational results of production activities, it is possible to objectively evaluate the work of workers, monitor their activities and determine the amount of encouragement not only once a month, but also daily. The implementation of this technique allows you to activate workers to perform shift-daily tasks within the time limits set by the plan and in the prescribed range, increase production discipline, encourage economical use of material, energy and other resources. In addition, production information is promptly displayed in the management system, which allows managers to have an up-to-date picture of the production plan implementation.