The article is devoted to the study of algorithms and protocols for congestion control in Transmission Control Protocol/Internet Protocol networks. In modern data transmission networks, the Transmission Control Protocol is of key importance, providing reliable communication between devices. Among its components a special place is occupied by the algorithm of congestion control, which determines the efficiency of data transmission. This paper considers the problem of congestion control, which is one of the fundamental and complex problems in the study of computer networks. The main objective of the study is to evaluate the effectiveness of congestion control methods using the developed mathematical model. The object of the study is congestion in Transmission Control Protocol networks, and the subject is congestion control protocols. Computer modelling techniques are used to conduct the study. The study shows the significant impact of congestion control protocols on network performance as well as different approaches to congestion control depending on network characteristics. The results obtained include comparative analysis of protocols, selection of modelling techniques and tools, development of simulation model, simulation experiments and evaluation of congestion control protocols. Evaluating the effectiveness of congestion control protocols using a mathematical model allows us to anticipate and analyze network behavior in different scenarios and optimize protocol parameters to achieve the best performance and stability of data transmission. In conclusion, we draw conclusions on the work.

The article is devoted to the study of algorithms and protocols for congestion control in Transmission Control Protocol/Internet Protocol networks. In modern data transmission networks, the Transmission Control Protocol is of key importance, providing reliable communication between devices. Among its components a special place is occupied by the algorithm of congestion control, which determines the efficiency of data transmission. This paper considers the problem of congestion control, which is one of the fundamental and complex problems in the study of computer networks. The main objective of the study is to evaluate the effectiveness of congestion control methods using the developed mathematical model. The object of the study is congestion in Transmission Control Protocol networks, and the subject is congestion control protocols. Computer modelling techniques are used to conduct the study. The study shows the significant impact of congestion control protocols on network performance as well as different approaches to congestion control depending on network characteristics. The results obtained include comparative analysis of protocols, selection of modelling techniques and tools, development of simulation model, simulation experiments and evaluation of congestion control protocols. Evaluating the effectiveness of congestion control protocols using a mathematical model allows us to anticipate and analyze network behavior in different scenarios and optimize protocol parameters to achieve the best performance and stability of data transmission. In conclusion, we draw conclusions on the work.

The article delves into the contemporary challenges facing the digital industry's evolution, particularly within the realm of Internet of Things (IoT) technology application. The authors pinpoint three pivotal hurdles that IoT endeavors to tackle: expediting notification processes, streamlining daily tasks, and enhancing industrial optimization. Moreover, the paper underscores the significance of adept channel utilization and traffic analysis for the fruitful implementation of IoT. Notably, emphasis is placed on protocol and transmission method selection, alongside the imperative for traffic modeling to discern optimal solutions. The focal point of the study revolves around the traffic transmitted by IoT devices, with a keen focus on formulating models to gauge its efficacy. The paper's objective is to scrutinize the methods, models, and algorithms pertinent to assessing traffic efficiency within IoT networks. To accomplish this aim, the authors outline three primary tasks: delving into IoT technologies, exploring their application domains, and mathematically modeling traffic flow within IoT networks. Methodologically, the research draws upon systems and network systems theory, complemented by algorithmic modeling techniques. The resultant findings encompass a comprehensive analysis of IoT technologies, delineation of their application spheres, and the development of mathematical models elucidating traffic flow within IoT networks.

This article discusses the problem of data synchronization methods using microservice architecture. Microservices is a popular and widespread software architecture today. The article investigates three main ways of interaction of microservices. They are event-based communication, interaction through direct HTTP requests and messaging, and also highlights and analyzes their advantages and disadvantages. The main purpose of the article is to analyze and make offer of the optimal option for solving the problem of synchronizing interacting microservices in real time. The optimal solution involves using the Apache Kafka message broker. It publishes data streams and subscriptions to them, as well as stores and processes them. Mathematical modeling of the proposed data synchronization method was described by constructing its state macine, as well as a system of canonical equations.

The study presented in this article delves into mathematical models pertaining to algorithmic and process synchronization functions within operating systems tailored for embedded reconfigurable computing systems. Furthermore, the article explores the hardware implementation of these algorithms and process synchronization functions. The discussion encompasses an examination of the key merits and drawbacks associated with existing models, along with considerations for potential updates. Included are diagrams illustrating a hardware-implemented reconfigurable system and its operational processes. The practical application of the obtained results is situated within computing systems, emphasizing the significance of productivity and efficiency enhancement. In the conclusion are presented the inferences based on the main results of the research.

The author of the article presents the main methods of implementing message transmission between processes in modern reconfigurable systems. The objective of this scholarly paper is to examine and explore approaches to the administration of interacting processes. In the article are also displayed the exchange between parallel processes in reconfigurable multiprocessor systems, the drawbacks of software implementations of this mechanism. The characteristics, obtained on functional models and made in the VHDL language, show the high performance of the subsystem of message queues transmitted within the reconfigurable computing system and when accessing the shared memory of the system. There is proposed a type of hardware accelerator that performs the functions of process synchronization. The results of modeling are presented. In addition, in this article are considered some of the methods of interprocess communication using the example of named pipes and shared memory. There is an examination of the issues regarding the study of software tools for measuring the performance of interprocess communication channels. The methods of interprocess communication considered in the article have different performance, that was measured using the 1mbench software package. The primary outcomes of the conducted tests are visually represented in the diagrams. Towards the conclusion of the research article, a comparative analysis between channels and shared memory is presented, focusing on two key parameters: bandwidth and latency. In conclusion, there are drawn the main conclusions and provided an outline of the objectives for the further research on this topic.

The article presents a study and analysis of known solutions and implementations of DNS servers, as well as the development of DNS server software, for which modern programming tools and technologies are used. In the process of development, the requirements for performance, scalability, security and reliability of DNS server are taken into account. The development of an efficient DNS server is an urgent task in today's digital economy. This paper aims to develop an efficient and reliable DNS server that will meet the requirements of the infrastructure of the digital economy. The results obtained can be used by organizations and enterprises to ensure stable and efficient operation of their network infrastructure. Also, the results of this work can be used to improve the quality of user experience in the field of Internet services, as DNS servers play an important role in ensuring the availability of web resources. The results are verified in real world conditions by testing the developed DNS server. Experiments are conducted to evaluate the performance and reliability of DNS server under different loads and usage conditions. The main results of this research are given in conclusion.

The article is devoted to the development of software for building a behavioral assessment of a person based on the analysis of tones of texts from social networks. This software is aimed at collecting, storing and processing data of users of the social network “VKontakte”. The paper deals with natural language processing using deep machine learning techniques. In the paper, we need to analyze the tone of the text. One of our goals is to solve the problem of analyzing posts in social networks. The intonation analysis of the text allows us to understand what intonation coloring a particular post in social networks has - positive or negative. Based on the results of the work, we have proposed a working prototype of a web application for building a behavioral assessment of a person based on the analysis of tones of texts from social networks. The results of the research will be useful to organizations when hiring employees, when it is possible to get data on a particular person from a social network and preview them. Based on the conducted research with trained models, the most accurately trained model with the highest accuracy equal to 75.10

Despite all the benefits that social networks have brought to the world, they also serve as a favorable environment for the growth of electronic crime. This article explores issues related to the detection of cyberbullying in texts posted by social media users using machine learning. It is noted that the social network VKontakte will be used as the social platform for gathering information in the research. The proposed approach consists of three main stages: pre-processing, feature extraction, and the classification stage. Feature extraction is performed using TF-IDF. Additionally, sentiment analysis is employed alongside TF -IDF to extract the polarity of sentences and add them as features to the feature list. The study utilizes five machine learning classifiers: Support Vector Machine, k-Nearest Neighbors, Logistic Regression, Long Short-Term Memory (LSTM). The article concludes with an assessment of the classifier's accuracy and relevant conclusions are drawn.

Statistical data provided by the FSBI “NMITSPN named after V.P. Serbsky” of the Ministry of Health of Russia indicate that depression, as a psychoemotional state, is the main cause of concern around the world, which in most cases leads to suicide, if not detected, and to a threat to others. Studies show that depression tends to have an impact on writing style and appropriate language use. The main purpose of the proposed study is to study user messages on the VKontakte social network and identify attributes that may indicate depressive symptoms of users. The article uses machine learning approaches (logistic regression, random forest, support vector machine, XGBoost) and natural language processing methods (removal of stop words, character deletion, tokenization, lemmatization) to prepare data and evaluate their effectiveness. The work demonstrated that the ability to search for depressed users with an accuracy of 77% using the XGBoost classifier. This method is combined with other linguistic functions (N-gram + TF-IDF) and LDA to achieve higher accuracy. In conclusion, the main conclusions of the study are formulated.

Purpose of research. The main idea of the article is to develop a digital device created on domestic components and designed to record measurement information with the function of recording on a memory card and transferring it to a personal computer using a USB-interface. The article also considers the tasks to be solved.Methods. Having analyzed possible alternative variants of development of the registering computer system, the authors offer a variant of its realization on the microcontroller, in the software of which it is necessary to provide the following functions: realization of information exchange via RS-485 interface; realization of exchange via USB 2.0 interface for transfer of the accumulated registered information to the computer; realization of recording, reading and erasing of the registered information on the flash-drive; realization of the counter of its own time with uninterrupted work at the time of the registration of the information on the microcontroller.Results. This paper develops a digital device designed for digital registration with the function of recording measurement information on an SDHC memory card. The operation of the device consists in providing registration of information with saving it in the form of files on a memory card of SDHC format. Access to the registered information is made from a computer via USB 2.0 interface in the memory device mode by means of a software driver realized in the microcontroller 1986BE92T of the Milandr company. Initialization of the device is carried out with the help of a computer, through the driver implementing hardware bridge USB-UART on the standard USB 2.0.Conclusion. The obtained results satisfy the set goal and objectives. A textual description of the microcontroller firmware in C language is developed. In addition, the paper develops application software designed to obtain measurement results and send control commands to the microcontroller. The field of application of the proposed device is specialized computing systems designed for digital recording of information.

В статье рассматривается метод корректировки релевантности при составлении списка рекомендаций, учитывающий необходимость синхронизации доступа к критическому ресурсу при асинхронной работе

В данной статье мы будем рассматривать нейронные сети, которые представляют собой модели, созданные для имитации работы человеческого мозга. Нейронные сети используются в различных областях, таких как распознавание образов, обработка естественного языка, рекомендательные системы, медицинская диагностика и многое другое. Они могут быть использованы для решения различных задач, таких как классификация, регрессия, генерация текста и изображений. При этом существуют различные типы нейронных сетей, включая перцептроны, рекуррентные нейронные сети, свѐрточные нейронные сети и многослойные перцептроны

В статье рассматриваются методы оптимизации алгоритмов машинного обучения, такие как стохастический, адаптивный градиентные спуски, RMSprop, Нестеровский ускоренный градиентный спуск. Так же представлены преимущества и недостатки методов оптимизации в сравнении со стандартным градиентным спуском.

Purpose of research. The main idea is to build a mathematical testing model that integrates different aspects of an embedded reconfigurable computing system and its interactions. This model provides an efficient representation of test scenarios and allows to analyse the dynamics of the reconfigurable computing system during testing. The paper also discusses methods for generating test sequences based on the properties of a finite state machine. Methods. The authors propose to represent the autotest as a finite state Mile machine, where states serve to store information about the current state of an embedded reconfigurable computing system. The input signal is the interaction with the system and the output signal is the system's response to the input signal. This approach allows to formalize the testing process and simplify the analysis of possible problems. Results. This paper discusses the application of automata theory in the context of automated testing of embedded reconfigurable computing systems. Automata theory provides effective methods and tools for analysis and simulation of discrete dynamic systems, which makes it suitable for automated testing tasks. Conclusion. The results show that the use of automata theory can significantly improve the quality and efficiency of automated testing of embedded reconfigurable computing systems. This approach provides a deeper analysis of the system and allows to detect and prevent potential problems that may arise during its operation.

В данной статье будут рассмотрены различные подходы к виртуализации и центрам обработки данных, а также преимущества и недостатки каждого из них. Будут рассмотрены такие темы, как виртуализация на уровне операционной системы, гипервизоры, контейнеризация и другие технологии. Также будут рассмотрены различные аспекты управления центрами обработки данных, такие как масштабирование, мониторинг и безопасность. Наконец, мы рассмотрим некоторые из наиболее популярных продуктов и решений, которые используются для виртуализации и управления центрами обработки данных.

The article discusses the possibility of using the AnyLogic simulation system in the study of models of embedded reconfigurable computing systems based on queuing theory. The most effective method of analyzing queuing systems (QS) is simulation modeling. The article substantiates the choice of the development environment, provides an overview of AnyLogic tools for the development of QS models. AnyLogic implements a special library that allows you to create QS models from ready-made blocks. Within the framework of the article, simulation modeling is used to create models in order to study the characteristics and assess the quality of service of reconfigurable computing systems, which allow analyzing their basic properties and identifying patterns inherent in the processes of priority processing of incoming tasks in various service disciplines, load and structural parameters. Studies of the influence of priorities on task processing, analysis of a system with different laws of distribution of intervals between tasks, analysis of systems with heterogeneous load have been carried out. With the help of AnyLogic, models have been developed that allow to study QS with various combinations of input parameters. As a result of the simulation, the characteristics are calculated: the load of the reconfigurable computing system (RCS) processor, the probability of losing tasks, the average and maximum waiting time and stay of tasks in the RCS and the average, current and maximum queue length, confidence intervals for loading, waiting time, stay time. The results obtained during the study will be useful to developers of embedded systems (for example, RCS).

The article examines the analysis of the depressive state of social network users. It is noted that the VKontakte social network will be used as a social platform for collecting information in the study. It is noted that a combination of vocabulary-based and machine learning methods is used to achieve the highest accuracy. Two methods based on vocabulary are considered: the dictionary-based method and the corpus method. The stages of analysis are considered: collecting data obtained using the VK_API script creation module, preprocessing data through the natural language processing pipeline (deleting raw data that does not carry a semantic role), creating a model and evaluating it. It is noted that the implementation of this task uses a high-level Python programming language with dynamic strict typing and automatic memory management, the syntax of which contains a natural language processing module (NLTK). The paper presents 4 machine learning classifiers: support vector machine (SVM), k—nearest neighbor method (KNN), random forest, logistic regression, LSTM. It is revealed that machine learning algorithms such as decision tree, support vector machine, logistic regression and LSTM demonstrate good accuracy in detecting the depressive mood of a social network user. The LSTM network showed the greatest accuracy during this experiment. In conclusion, the main conclusions on the work done are formulated.

The article is devoted to the development of a means and algorithm for balancing the load of processors of a reconfigurable computing system. A theoretical overview of the subject area of the research is given. Architectural solutions of modern analogues often do not allow scaling the system, which provides increased productivity and responsiveness. Modern solutions do not contribute to improving performance due to the use of shared memory and bus topology for switching processors, which impose additional conditions on shared memory access and synchronization of processor caches. The proposed approach will partially avoid the existing disadvantages of known solutions by using a cluster architecture to build a reconfigurable computing system, for the efficient operation of which all processors must be balanced. The issue of balancing the system load is not fully resolved, therefore, relevant. Further, the choice of the architecture of the reconfigurable computing system is justified, for which the synthesized algorithm of planning and dispatching is suitable. A description of the task planning algorithm for reconfigurable computing systems is given. The principles of interaction of processors in a reconfigurable computing system are described, taking into account the chosen architecture. The efficiency of the synthesized algorithm is analyzed using the example of test data. Using the input data, the load balancing algorithm identified various options for the distribution of tasks, one of which was marked as optimal, which is characterized by a minimum load spread of all processors of the reconfigurable computing system. At the end of the article, the main conclusions on the work are formulated.

The In this article the author substantiates a hardware approach to designing the kernel of real-time multiprocessor operating systems. The author also provides possible options for architectural solutions, and considers the formal representation of control algorithms for interacting processes operating in parallel computing systems when they access a shared resource. The theory of event-driven non-deterministic automata was used for formalization. There were obtained equations that describe the procedures for the process of entering the critical interval and remaining there, taking into account the accepted discipline of ensuring priority and mutual exclusion of incompatible events. The exit of the process from the critical section, which makes it possible to synthesize the control module was examined as well. Modeling of a device for 4 inputs of requests to a shared resource in the VHDL language was executed, the results of experimental studies were also provided.