The paper discusses the problem of building a unified system for a metallurgical enterprise that integrates heterogeneous information systems of various purposes, such as Computerized Information Systems (CIS), Manufacturing Execution Systems (MES), Enterprise Resource Planning (ERP), and Process Automation Systems (PAS). Data exchange with various automated systems of the enterprise is carried out by a special Data Exchange Module with Automated Systems of the Enterprise (DEMAS), which is implemented as a web service. DEMAS aims to ensure guaranteed information exchange between information systems and store information in a single data repository.

Keywords: information system, engineering process, metallurgical company, integration, web-service

This paper considers the modern classification methods of breast cancer histopathology. The main purpose of the study is to conduct an extended test of the trained model on data that fundamentally differs from the training dataset. We chose a large Russian dataset with different types of classification as the training dataset. The dataset contains images with different resolutions and magnifications. As testing data, the same dataset was used, but the resolution, color balance, brightness, and contrast of the images were changed. The classes in the dataset were unbalanced, so we applied augmentation methods (flipping and rotation). The models ResNet 152, DenseNet 121, Inception_resnet_v2 were selected for training. The transfer learning approach was used for training. The preprocessing of images consisted of normalizing the values of all image channels in the range from 0 to 1. The models had good results with standard testing methods. The resolution change slightly reduced metrics. The change in color balance, brightness, and contrast significantly reduced all metrics. The test results show that elementary normalization is not enough for high-quality training of models resistant to changes in input data.

Keywords: neural network, model, machine learning, breast cancer, cancer classification, artificial intelligence, transfer learning, histopathology

The article considers the practical part of the implementation of the task of determining the relevance of training directions, using the example of the direction "Applied Informatics", possible professions and companies for the employment of graduates by comparing the skills obtained in the framework of training and the requirements of the labor market. The results of the practical testing of the formalized model will be used as part of the module of digital tools for remote career guidance.

Keywords: service requests, vacancies, demand for training areas, career guidance, digitalization of career guidance activities, job search services

The objective of this study is to determine the patterns of development of new information technologies in the industry and formulate the main barriers to their introduction into project activities. The study of the issue was carried out on the basis of scientific publications of domestic and foreign researchers. The main theoretical methods are used: analysis, classification, analogy and synthesis. This article makes a comparative analysis of the use of modern technologies in European countries according to the "center-periphery" scheme and shows the similarities of information processes between Russia and European countries. The success of promoting innovative developments in the construction sector depends on: the presence of major players in the construction market, government support, the introduction of new educational standards, standardization of information modeling. The main obstacles are related to the compatibility of all processes in one digital space, legal and legal norms, issues of training and education.

Keywords: building information modeling, government order, BIM standardization, construction education, innovation, international experience

To achieve effective communication in the process of human-machine interaction, polymodal user interfaces are used. The article classifies typical interface elements corresponding to various communication channels in order to identify the composition of elements for the implementation of a polymodal interface that provides the ability to display the user's professional activities. Taking into account the above classification, a model of the interface structure is proposed that reflects the logic of the user's work.

Keywords: polymodal interfaces, user interface, classification of interface elements, interface model, typical interface elements, technical systems, information systems, communication channels, modality

The article discusses the methodology for organizing the use of the user interface design module by the end user on their own. One of the main stages of the methodology is the user's description of his professional activity. To implement this stage, the functional structure of the module for generating a description of the activity by the user, a description of its components (submodules) and the composition of the main algorithms are given.

Keywords: design, user interface, user activity, activity model, functional structure, user activity description generation module

The article deals with the problems of communication between the customer and the development team in the process of designing information systems. Based on the identified shortcomings of existing solutions, a conclusion is made about the need to develop a new approach and means of its implementation. The paper sets the task of developing a common model for the interaction of subjects using a single platform. The article describes the concept and modular architecture of the platform for implementing the system notation for designing architectural schemes. The modules of such a platform and its general functionality are considered.

Keywords: information system, life cycle, developer, end user, architectural scheme, basic abstraction, subject area, systems design

The article provides an overview of wearable devices that improve the quality of user recognition of objects of the surrounding world, reveals the process of developing an intelligent module for recognizing objects of urban infrastructure for "sound glasses" - a device designed for blind users. The functionality of the module under development, its architecture is characterized, the process and results of neural network training for object recognition are described, and an algorithm for identifying the color of traffic lights is given. The results of testing the developed software module are presented. The software module created in this work is an integral component of a fully functioning device "sound glasses", the use of which will allow people with visual disabilities to get information about events and the surrounding environment and navigate even in an unfamiliar environment.

Keywords: computer vision, neural network, smart glasses, sound glasses, visually impaired, YOLOv5, object recognition

This paper describes the development of a recommender system for the selection and configuration of deep neural network models. Her key area of work is evaluating the effectiveness of a neural network for a particular type of problem. The recommender system designed within the framework of the repository allows for precise search, selection and flexible configuration of neural networks depending on specific project-oriented tasks.

Keywords: recommender system, machine learning, deep learning, neural network model, expert system, neural network, repository, spatial data, geographic information system, configuration, architecture

The work is devoted to the glaciers of the North Caucasus. The factors influencing the dynamics of the glacier area are analyzed, and the principles of the organization of observations of glacier fluctuations are considered. The level of modern development of the field of remote sensing provides an excellent opportunity for a detailed and accurate study of the dynamic characteristics of the surface layer of ice on glaciers based on cartographic animations of a number of images. The work is based on data from space monitoring using the Meteor-M No. 2 apparatus.

Keywords: diversification of management, production diversification, financial and economic purposes of a diversification, technological purposes of ensuring flexibility of production

In this paper, based on Russian and foreign experience in mathematical modeling of photovoltaic installations, the authors consider the approaches to the construction of these models. The relevance of the research is confirmed by the wide spread of electric energy sources using solar energy. The scheme of photovoltaic element substitution and the dependences describing the processes occurring in it are given. The authors conclude that despite the large number of various mathematical models of photovoltaic elements, all of them can be grouped into two categories. The first category includes models that consider photovoltaic panels as a separate element, and the second category includes models where the photovoltaic panel is a component of a generating complex. Despite the difference in the analyzed approaches, the authors single out a number of parameters that characterize the operation of a photovoltaic panel and are sufficient to obtain simulation results with the required accuracy.

Keywords: photovoltaic panel, mathematical modeling, substitution scheme, distributed generation, power generation

The problem of human self-knowledge is very relevant nowadays. People are constantly looking for new methods to study their own “I”. Graphology is one of such methods. The main difficulty of graphological analysis is the lack of automation of the process, the result depends only on the knowledge of the person. In addition, at the moment there is no service capable of carrying out a competent analysis of a person's handwriting. However, there are computer vision methods that, in combination, can produce work similar to that of a graphologist. Such methods include segmentation, binarization, and integral estimation methods. To compare the characteristics of handwriting with human characteristics of character, it is necessary to use classifiers. The use of all methods makes it possible to create a service that automates graphological analysis.

Keywords: graphology, handwriting, personal characteristics, graphological analysis, slope, direction of handwriting, text

The paper proposes a method for calculating the interval values of the coefficients of the polynomials of the numerator and denominator of the transfer function. An algorithm is presented that describes the sequence of actions performed, which makes it possible to obtain interval coefficients for the study of both linear and nonlinear systems. An illustrative example is given, which shows the calculation of the interval values of transfer functions, both continuous and discrete systems based on the use of the Matlab system.

Keywords: control system uncertainties, robust stability, marine mobile objects, transfer function with interval coefficients

In this article, as a result of the analysis, it was revealed that attributive access control should be applied in heterogeneous Big Data storages. Then, an algorithm for transferring rights between different data models that are part of heterogeneous Big Data storages was formulated. The limitations imposed on this algorithm are also revealed. Thus, the task of implementing a method for managing rights in heterogeneous Big Data repositories has been completed.

Keywords: database management system, heterogeneous storages, big data, relational database models

"This article describes the application of the ontological approach to the creation of an intelligent system of recommendations in the work of military recruitment committee. A popular and perfectly proven approach to describe and represent knowledge is ontologies. Designing knowledge-based systems is impossible without a thorough systematic study of the subject area in which the problem is to be solved. The result of systems research should be represented by the formalism best adapted for further implementation. Ontology is such a formalism, and this article discusses approaches to the formal representation of ontologies as the most important mechanism of knowledge engineering. Conceptually, ontology design processes are similar to those with multi-agent systems. In this case, nodes or agents connected to each other materialize our knowledge of the problem solution. An agent is comparable to the notion of an entity in an ontology. In both cases, an ontology graph is used. The Protégé software platform was chosen as one of the most popular development tools to implement the ontology ""Military Recruitment Committee"". An important factor is the support of SWRL, which is necessary for the future development of the project. In the process of ontology design, three main branches of entities were identified: questionnaire data; medical data; psychological data. Based on the results of the logical inference, a recommendation (advice) is formed regarding further decisions (actions) on working with a conscript. The SWRL is used to create rules for checking the set of properties for each conscript, on which a verdict is made. If necessary, the system will explain its actions. As a result, a preliminary ontological graph of the investigated domain in the OWL language is made. Implemented some software modules. Conducted a logical inference on the Protégé platform based on the description in SWRL language of the rules reflecting the impact of the set of entities of the ontology on the inferred recommendations."

Keywords: ontology, knowledge management, Protégé, knowledge-based systems, advisory systems, military recruitment committee

The article describes the development of a repository of neural network models designed to solve design problems in the field of spatial data analysis. The key options for using the system to provide support for making managerial decisions in the field of sustainable development are presented. The results of designing the ontological model of the repository are presented. The storage subsystem for neural network models is implemented in the form of a metalanguage. Models are converted into representations that are compatible with modern software systems for deep machine learning. The graphical web interfaces of the repository of deep neural network models and the visualization subsystem of deep machine learning models in the form of graph diagrams, as well as interfaces for obtaining structured information about specific neural network models are given. Within the framework of the repository, there is a subsystem for delimiting access rights for administrators and users of the system. The issues of updating the repository of deep neural network models in the process of solving practice-oriented problems in the field of ensuring the conditions for sustainable development of Russian regions and developing a recommender system for selecting and configuring neural network models stored in the repository are discussed.

Keywords: repository, neural network, neural network model, deep learning, spatial data, geographic information system, interface, data exchange, object detection, application programming interfaces

In this paper, we investigated the effectiveness of an intelligent system for classifying radiographic images into three classes using transfer learning and fine-tuning methods. The convolutional neural network VGG16 structure was used to evaluate the effectiveness of predicting the presence of characteristic pathologies by the system. A catalog consisting of 4,228 chest X-ray images was used for training, verification of training and testing this neural network. A catalog was divided into three classes such as pneumonia, Covid-19 and in the absence of lung diseases. To provide modeling processes there were used deep learning libraries such as Keras and TensorFlow. In the course of the work, there were presented the results of the neural network accuracy of the classification of chest X-ray images by full-trained neural network model. We also demonstrated an increase in prediction accuracy by using transfer learning method, as well as with fine-tuning of the neural network structure. Based on the results of the work, the neural network has learned to recognize images with signs of pneumonia, Covid-19 and normal radiograph. In conclusion, the best accuracy index of 98.4 % was achieved by using the fine-tuning method for our convolutional neural network.

Keywords: chest X-ray, Covid-19, pneumonia, intelligent system, machine learning, deep learning, convolutional neural networks, transfer learning, fine-tuning of convolutional neural network

The article discusses approaches to solving natural language processing problems such as extracting key concepts or terms, as well as semantic relationships between them to build data-driven IT solutions. The subject of the work is relevant due to the constant growth of volumes of low-structured and unstructured digital text. The extracted information can be used to improve numerous processes: automatic tagging, optimization of content search, construction of word clouds and navigation sections; furthermore, to create draft versions of dictionaries, thesauri, and even bases for expert systems.

Keywords: natural language processing, term, lemma, semantical relationship, statistical processing, machine learning, word2vec

Any mobile application consists of work screens that contain various information. Every year there are more and more requirements for applications. This is due to the constant growth in the number of users of various services that require certain software components for their functioning. The use of primitive development methods, as well as outdated components, leads to an increase in the timing of design, implementation and implementation of the project. But the development of technology does not stand still, which makes it possible to solve the emerging time-consuming tasks in an easier form and much faster. And an example of this is the developed library "The Navigation Component", which allows you to create a convenient and understandable navigation scheme inside the application, and this is simply necessary when a mobile application has many working windows. The article will list the components of the library "The Navigation Component". The main attributes are shown. The principle of operation of each component is considered.

Keywords: navigation diagram of the application, The Navigation Component, application, Android

This article discusses the formation and connection of layers in the task of classifying images of traffic signs, as well as calculating weights on the corresponding layers of the neural network. The authors describe the biological structure of brain neurons, as well as their comparison with artificial neural networks. A conceptual model of an artificial neuron and a neural network with a description of structural elements is presented. The matrix structure of the weights of the neural network is given. The process of converting an RGB image of a road sign into an input layer of a neural network is described. A corresponding description is provided for each hidden layer. In addition, a description of the convolution layers and the maximum pool is given, as well as an explanation of the need to use this type of layers in a convolutional neural network. The authors also described an algorithm for the formation of a convolutional neural network for the classification of road signs. Examples of the operation of this neural network are given.

Keywords: convolutional neural networks, classification, deep learning, big data, mathematical modeling, computer science

The results of the development of a software package are presented that allow training personnel to work in a district heating system to ensure a reliable process of energy transportation in heat networks. The developed simulator described in the article is a software package that includes a SCADA system and a Termas client for modeling and simulation operation of the district heating system. The simulator consists of a thermal-hydraulic mathematical model of the operating modes of the heating network, software and information support for setting up the operating modes of the simulator and assessing the actions of the personnel by the instructor based on the results of work on the simulator. The requirements for the functionality of the simulator are presented. The Demand Analysis application was used to collect data on energy consumption and outdoor temperature. The process of operation of the simulator in the simulation and modeling mode for the heat networks of the city of Yekaterinburg is presented. The developed software simulator makes it possible to simulate an accident, train personnel in the skills of safe equipment control in complex non-stationary modes. The software package allows you to reduce energy costs.

Keywords: training simulator, software, district heating, heating networks, SCADA system, Termis platform, model, temperature, accident

The most important task of the admissions committee of any university is to advise applicants on admission to the specialties available at the university. In this article, an automated information system has been developed, which, based on the applicant's questionnaire, allows you to form recommendations when choosing a training specialty, taking into account the applicant's personal preferences. Artificial neural networks are proposed to be used as a method of choice, and the multilayer perceptron (MLP) was the model of the neural network.

Keywords: neural network, career guidance, multilayer perceptron, neural network training, methods, automated information system, training directions

A model is proposed for selecting potentially interesting events for a person, in accordance with his requests and wishes, in order to achieve the goal of increasing the effectiveness of informing the population about cultural events of the city, and, as a result, improving the cultural level of society, Describes the implementation of the model in the form of a software product, which, with the help of intelligent data selection algorithms, allows you to simplify the process of searching for both potential cultural events that are interesting for a person, and new participants for their organizers. The criteria for selecting the event of interest and the process of selecting them in accordance with the degree of importance to the user are described. Formulas for calculating the final coefficients that serve as a numerical characteristic of the optimality of the event for a particular user are given. An example of the implementation of the proposed algorithm is given.

Keywords: intellectual search, selection criteria, cultural level, selection of events, forecasting

Methods and technologies for solving the problem of patent landscape visualization based on cluster analysis of the patent array are considered and used. Algorithms for downloading patent archives, parsing patent documents, clustering patents and visualizing the patent landscape have been developed. A software for clustering patent documents based on the Latent Dirichlet allocation model and visualization of the patent landscape on clustering data using the gensim, PySpark, and sklearn libraries has been implemented. The implemented software has been tested on patents issued by the US Patent and Trademark Office. The accuracy of classification of patents by category has been achieved - 84%.

Keywords: patents, information extraction, clustering, patent landscape, innovation potential

The article highlights the distinguishing features of low-code, no-code platforms, their advantages and disadvantages, reviews existing research in the field of low-code, no-code development, discusses the main components of the platform being designed and fragments of algorithms responsible for generating program code.

Keywords: low-code, no-code, software development, laravel, platform design