The article analyzes the problem of developing artificial neural networks within the framework of creating an artificial brain. The structure and functions of the biological brain are considered. The brain performs many functions such as controlling the organism, coordinating movements, processing information, memory, thinking, attention, and regulating emotional states, and consists of billions of neurons interconnected by a multitude of connections in a biological neural network. The structure and functions of biological neural networks are discussed, and their advantages and disadvantages are described in detail compared to artificial neural networks. Biological neural networks solve various complex tasks in real-time, which are still inaccessible to artificial networks, such as simultaneous perception of information from different sources, including vision, hearing, smell, taste, and touch, recognition and analysis of signals from the environment with simultaneous decision-making in known and uncertain situations. Overall, despite all the advantages of biological neural networks, artificial intelligence continues to rapidly progress and gradually win positions over the biological brain. It is assumed that in the future, artificial neural networks will be able to approach the capabilities of the human brain and even surpass it. The comparison of human brain neural networks with artificial neural networks is carried out. Deep neural networks, their training and use in various applications are described, and their advantages and disadvantages are discussed in detail. Possible ways for further development of this direction are analyzed. The Human Brain project aimed at creating a computer model that imitates the functions of the human brain and the advanced artificial intelligence project – ChatGPT – are briefly considered. To develop an artificial brain, a new type of neural network is proposed – neural-like growing networks, the structure and functions of which are similar to natural biological networks. A simplified scheme of the structure of an artificial brain based on a neural-like growing network is presented in the paper. Figs.: 8. Refs.: 17 titles.
In the last decades, we have witnessed an exploding growth of different kinds of sophisticated distributed systemswith financial, industrial, ecological, security, military, and many other applications. Providing high integrity of such systems is becoming a key point of their development, evolution, and usage, especially in various crisis situations and under disastrous and adversarial conditions. The paper reviews a number of existing works on the integrity, security, and recovery of distributed systems. It also briefs the main aspects of the Spatial Grasp Model and Technology (SGT), reflecting some general issues of the paradigm, its Spatial Grasp Language (SGL), and networked SGL interpretation in distributed environments. SGT can dynamically establish and keep superior power over large distributed systems, including creating them from scratch.Using a graph-based representation of the distributed system topologies, with nodes having both virtual and physical properties, the paper shows full topology creation starting from all nodes in parallel and then from a single node, also copying the existing topology in similar cases. In addition, it demonstrates how to organize distributed systems in such a way so that they can self-recover in any circumstances and after any damages by supplying their nodes with universal genetic-like capabilities by which any self-repairs can be organized. Such recovery may be from missing neighboring nodes and links to the rebuilding of thedistributed topologies, which means they cannot be destroyed even in the severest conditions. These features can be particularly useful after IT network damages, environmental and industrial disasters, for crisis management, and on battlefields.The paper confirmsthe efficiency of the developed distributed control approach for providing high integrity and self-recovery of important distributed systems. Figs.: 6. Refs.: 26 titles.
Today, there is no workplace at any enterprise where employees don’t use information technologies. Automation provided by information technologies has already covered all the aspects of company’s activity: document flow, accounting, warehouse accounting, financial accounting, analytical accounting, and enterprise management. To work efficiently, employees need access to systems the use of which is required by their positions. The management and control of user accounts in corporate IT systems are serious tasks for the IT department or information security service. Since the systems are weakly integrated with each other, each of them requires a separate configuration of user accounts and corresponding access rights. The main directions in the management of access to corporate IT systemsare the identification of accounts, the management of user accounts, and compliance with the requirements of authorized access rights. The modern concept of work with corporate systems consists in the formation of a service model based on the used IT systems. From the point of view of the service model, the company provides an employee with a certain service based on the existing corporate systems. The organization of the effective management of user rights in corporate IT systems requires automation. A step forward in access management automation is the creation of self-service portals, where employees can familiarize themselves with the list of corporate services available to them and request access to them in the automated mode. The automation of the process of giving and changing user accounts in the corporate IT systems allows you to reduce the time it takes to create or change access rights, create prerequisites for controlling access rights to systems, and increase the efficiency of the IT department as a whole.Figs.: 2. Refs.: 6 titles.
Neural network models, which were initially used to model the processes of recognition of graphic images, are now widely used in the field of recognition of multi-parameter objects and in adjusting the parameters of complex systems. Such an application is effective in solving problems of information security management. With the help of neural networks, the tasks of classifying threats, choosing the parameters of protection measures, and adjusting the operating modes of information systems are successfully solved. In the scientific literature, there is a wide variety of approaches and methods for creating artificial neural networks. At the initial stage of designing information security systems, when it is necessary to determine the main parameters of the software being created, it poses a problem for the designer. Miscalculations made at this stage of the design can lead to the unsuccessful completion of the entire project. The article provides a brief comparative analysis of artificial neural networks that differ in the methods of setting (training) the network and in the form of its structure. The applicability, advantages, and disadvantages of such methods for tuning neural networks are characterized. These are the method of backpropagation of an error, genetic algorithm, iterative Widrow-Hoff algorithm with variable step, modified least squares method, and sequential learning method. The differences in the structure for networks designed to solve the problems of adjusting information processes and recognizing multi-parameter objects are shown. To regulate the processes, the structure of the neural network is studied on the example of the fuzzy neural network ANFIS. For the classification problems, the structure of a multilayer perceptron is given, in which the structure of the inner layers reflects the ontological network of the subject area under consideration. The presented results can be used to justify the type of neural network used for a specific task in the field of information security. Figs.: 4. Refs.: 10 titles.
One of the possible ways to improve the quality of operational management of counteracting emergency situations by means of situation centers is the use of appropriate decision support systems. As such a decision support system, the article examines the DSS SPOR which provides solutions to the problems of operational management of countermeasures against emergencies with the help of electronic action plans. The article describes the first part of the methodological bases of creating electronic action plans, the purpose of which is to consider the general theoretical problems of structuring the process of countering an emergency situation, independent of the specifics of a specific emergency, aimed at substantiating of the general methods of creating of electronic action plans. In order to avoid possible disagreements in the interpretation of the main concepts used in the presentation of methodological bases, their definitions are provided. The purpose and structure of the methodological bases are substantiated and the main actions that underlie the development of an electronic action plan are characterized. The requirements for an emergency situation, to meet which it is expedient to use DSS SPOR, have been determined. General methodological bases for the development of electronic action plans are outlined as well. The features of forming a set of operations that form ordered sequences that will make up an electronic action plan are described. The problem of updating the content of the initial data when adapting a typical electronic action plan is characterized and the requirements for the initial data of operations necessary for the creation of an electronic action plan are formulated. The peculiarities of the use of the obtained results in the creation of electronic action plans will be presented in the second part of the methodological bases. Figs.: 2. Refs.: 6 titles.
The paper considers the introduction and development of the risk-based approach (RBA) paradigm. It describes the capabilities of RBA methods to categorize threats by their level of danger, which allows the use of information technologies and the implementation of more efficient optimization measures. A gradual transition to the RBA paradigm from the point of view of IT development and as a way to the independent (impartial) audit of the main safety parameters has been traced. The possibilities and limitations of the existing methods are analyzed, and the trend toward the transition to adaptive security management is shown in the paper. The possibilities of reducing the costs of building models for determining the numerical values of risk due to the development of probabilistic structural and logical models by types of dangerous objects and productions are demonstrated. The significant potential of domestic developments concerning the development and implementation of a probabilistic-physical approach to the assessment of durability and reliability using probabilistic models based on DM- and DN-distribution functions in conditions of insufficient information on failures is described in the article. The work demonstrates the effectiveness of the transition to the modern methods of safety analysis based on the RBA paradigm in Ukraine's nuclear energy sector since the early 2000s. In this sector, thanks to the updating of development processes, safety planning measures, and government control, the damages resulting from emergency shutdowns have decreased by more than 10 times. At the same time, it has been noted that our country is lagging behind in implementing the RBA paradigm in other areas of production and life. To accelerate the implementation of RBA in a wide range of industries and spheres of life, the priority problems and tasks related to the development of IT, which require solutions in our country and all over the world, have been formulated. Fig.: 1. Refs.: 27 titles.
The article discusses the basic requirements for electronic commerce information systems that support business. The features of the modular design of electronic trade information systems are characterized and the advantages and disadvantages of independently developed information-but-computational resources are determined. The expediency of using distributed information systems for electronic trade tasks is justified. The concept of distributed information systems involves the use of various technologies and protocols to ensure the availability, reliability, and scalability of the system. The architecture of a distributed information system involves the creation of a system with distributed components that interact using standard interfaces and use various technologies for communications. The prospects for the use of distributed information systems are determined and the advantages of using a distributed architecture are analyzed. The article studies the stages of building the architecture of a distributed information systemand defines its main components. The architecture of distributed systems can consist of such components asdatabase servers, web servers, applications, security tools, and network equipment, and may vary depending on the specific system and its needs. The types of architectures of distributed information systems and the specifics and features of their application are determined. The article discusses microservices-oriented architecture (Microservices-Oriented Architecture, MOSA), the basic idea of which is that software is divided into small, autonomous microservices that interact with each other using APIs. The use of MOSA for electronic trade information systems allows for increasing the speed of development and implementation of additional functions and ensures scalability and resistance to failures. Fig.: 1. Refs.: 5 titles.
The article defines the main tasks and features of corporate information networks and analyzes the specifics of the corporate network implemented in a medical center. The proposed data protection system at the enterprise is developed on the basis of the Bella-La Padula modelsince the key provisions of this model are the assignment of special security levels to all participants in the protected data processing process and to the documents in which it is contained. The specified security levels are arranged using the established dominance relationship, and the access control is carried out depending on the security levels of the interacting parties, which allows the application of technical solutions of the Active Directory service. One of the elements to ensure data protection is the use of a Shadow Copy of data according to the appropriate schedule. An important component of ensuring data protection is the individual process of setting up group policies and checking replication with other servers running the Active Directory directory services of the medical center. As a result of the implementation of elements of the company's data protection system, it was possible to significantly increase the level of protection and set up a backup server, on which appropriate folders were created, to which backup copies would be made according to the schedule. This function makes it possible to save the history of changes in any file for a certain period. The proposed elements of the security system can be used to analyze the security system, control access, ensure data integrity, etc. The Active Directory directory services were implemented in the medical center, and data replication to a backup server was configured. Taking into account the specifics of the enterprise, namely the medical center, the implemented elements of the data protection system ensure the delimitation of access levels, implement protection profiles and secure the personal data of patients. Figs.: 3. Refs.: 5titles.
Controlling the sheet width using a computer on heavy plate mills (HPM) and roughing mill trains (RMT) of wide-strip hot rolling mills (WSHRM) must ensure the set width of the sheet (roll), rectangularity of the sheet (roll) in the plan characterized by the uniformity of the sheet width in the middle part along its length, as well as at the front and rear ends, and the minimal trimming of the front and rear defective ends of the sheet (so-called “tongues” and "swallowtail"). Forming the desired sheet width is carried out either in jointly working vertical and horizontal mills in a reversible mode or in a continuous non-reversible group of mills (vertically-paired – horizontal). With the leading participation of the authors, there were carried out the development of the automated process control system (APCS) and studies aimed at regulating the width in the RMT of mill 560. Mathematical models describing natural and additional expansion and the requirements for their accuracy are presented in famous scientific works. To assess the accuracy of the characteristics, experimental studies were conducted on a laboratory mill. The rolling conditions in the RMT of mill 560 were simulated during the research. The analysis of experimental data and data obtained through the calculation using various formulas provided in literary sources showed that all known models do not meet the accuracy requirements set by the APCS for the RMT of mill 560. Therefore, new mathematical models of expansion were developed. The paper presents the mathematical models for changing the width in the middle part along the length of the roll and the models for changing the width at the “head” and “tail” of the roll. A method for determining a roll gap is described, which implements the law of change of the gap of vertical rolls that eliminates deviations in the width of the roll from the initial (before rolling) value. The testing of the developed mathematical models under the conditions of the technological process in the RMT of mill 560 showed their ability to solve the problem of controlling the sheet width in real time. Figs.: 2. Refs.: 6 titles.
QUALITY, RELIABILITY, AND CERTIFICATION OFCOMPUTER TECHNIQUE AND SOFTWARE
The article is devoted to solving the problem of determining the residual resource of pipelines. Erosion and corrosion damage was selected as the main negative factor that is being investigated and affects the service life. In particular, it is the erosion-corrosion damage of the “pitting corrosion” type which is one of the most serious and widespread types of corrosion that can cause a significant shortening of the service life of technical objects and an increase in the cost of their maintenance, repair, and replacement. The residual thickness of the pipeline wall was chosen as the defining parameter. In case there are no significant failure statistics, a probabilistic-physical approach is used to assess the objective technical condition and predict the residual resource of the specified structures. The approach to durability assessment is based on a probabilistic model and uses the DM failure distribution that is specially formalized on the basis of a Markov random process of the diffusion type with a constant rate. The DM distribution most accurately aligns statistical data on failures of mechanical objects, which are pipelines for various purposes. It is very valuable that the parameters of the used model are based on a physical interpretation, which allows for estimating the parameters of the model when there are no failure statistics. The analysis is based on two key parameters: the average rate of change of the defining parameter change (the performance criterion) and the coefficient of variation of the generalized degradation process. The paper provides an example in which the residual resource of a pipeline section is determined with the help of the probabilistic-physical method. The results obtained during the calculations are compared with the results obtained by another traditional method. Refining the assessment of the residual resource of the pipeline section will allow for optimizing the operating costs by reducing the intervals between repairs. Таbl.: 1. Figs.: 3. Refs.: 7 titles.
Prediction of the pipeline system residual life can be a valuable tool for engineers and operators in developing future strategies for safe application, including planning technical assessment and inspections, as well as the formation of an effective maintenance schedule. This will minimize the risks of pipeline system failures until the expected end of its service life. However, given the large number of factors affecting the formation of defects of different nature, achieving accurate predictions becomes a challenging task. A detailed assessment and prediction of the main defect indicators in pipeline systems can help to prevent leaks and ruptures at the facility, reducing the risks of accidents and human casualties. This also significantly reduces operational risks, which helps to avoid material losses, including expenses that may be caused by large-scale pipeline replacement. This article examines the main approaches described in the commonly used regulatory standards that allowestimatingthe service life, suitability for use, and residual lifeof pipelines. In the course of the work, the following techniques have been studied: inspection, facility testing and monitoring, processing and evaluation of the obtained dataon defects, calculation of technical parameters for assessing the suitability of components for their further usage, as well as other engineering recommendations for analyzing the facility at some stages of its lifecycle. Based on the work done, it has been found that the complex use of several relatively different or, conversely, compatible regulatory documents, equipment, and software (considering the specific needs and specifications of the project)is a fairly popular practice that allows you to improve the evaluation process of the residual life and provides more reliable results when assessing the technical condition of the facility. Tabl.: 1. Refs.: 31 titles.
