Journal archive

The paper presents the author's approach to solving the problem of sentiment analysis of online Russian-language messages about the activities of banks. The study data are customer reviews about banks in general and their products, services and quality of service posted on the Banki.ru portal. In this paper, the problem of text sentiment analysis is considered as a binary classification task based on a set of positive and negative reviews. A vector model with a tf-idf weighting scheme was used to represent the collected and preprocessed texts. The following algorithms with the selection of optimal parameters on the grid were used for binary classification task: naive Bayesian classifier, support vector machine, logistic regression, random forest and gradient boosting. Standard statistical metrics, such as accuracy, completeness, and F-measure, were used to evaluate the quality of solving the classification problem. For the indicated metrics, the best results were obtained on the classification model developed with the use of Support Vector Machine. Thematic text modeling was also carried out using the Dirichlet latent placement method to define the most typical topics of customer messages. As a result, it was concluded that the most popular message topics are "cards" and "quality of service". The obtained results can be used in the activities of banks to automate its reputation monitoring in the media and when routing client requests to solve various problems. When solving problems, the features of the Python programming language were actively used, namely, libraries for web scraping, machine learning, and natural language processing.

Research and development (R&D) ensure stable functioning and forms the innovative potential of most companies in the production sector. Ineffective R&D management leads to the fact that many initiated projects go beyond planned deadlines and budgets, and much of the intermediate R&D results are not completed. The complexity of R&D management is associated with high information uncertainty regarding the performance of R&D and the productivity of employees. The paper considers a multi-model method of decision support for R&D management in companies. To reduce information uncertainty in solving various management problems it is proposed to use an ontological model of intellectual capital of the company, simulation models of R&D processes and individual stages, fuzzy logic models to obtain integral assessments of management decisions. The method provides a basis for making decisions on the possibility and expediency of using previously obtained R&D results (scientific and technological reserve); on the feasibility of the proposed project based on the assessment of its feasibility; on the project organization (volume-calendar planning); on the allocation of resources to tasks; on the incentives for performers; on the planning of activities for additional training and organization of information support. The paper provides a general description of the method, as well as an example of its use to support decision-making on the feasibility of an R&D project based on its assessment. Two structures for organizing the R&D process in a manufacturing company are considered as alternatives. After selecting the best structure, the impact of staffing quality on the integral feasibility assessment is evaluated.

This paper considers the actual problem of graphical information converting back into raw data format that was used to represent it. This is due to the great scientifi achievements contained in editions from the Soviet period, as well as the intention global publishers from "unfriendly" countries to close access for Russian and Belarusian organisations to scientific publications and technical information databases. As a result, Russian scientists can only have graphical materials in formats similar to PDF documents. This paper considers a fairly simple way of solving this problem when digitising graphs in printed or electronic publications with low resolution and a large picture scale, which does not allow to detail its separate fragments. The procedure for pre-processing the original image in bitmap format is described. In order to improve the numerical data resulting accuracy from the subsequent digitising, a number of features are recommended, which are available in the well-known and most common graphical editors. These functions include changing the color mode of the image, color inversion, sharpening and contrast, linear scaling (vertical and horizontal scaling), and graph line spline approximation. The above operations are accessible to users with the minimum familiarity of graphical editors Microsoft Power Point and Adobe Photoshop. As an developed procedure use example, the results of FRB 160317 signal digitising (a so-called Fast Radio Burst), are presented. The digitising of its graphical image has provided more accurate additional information on signal characteristics not given by publication authors. A visual evaluation of the digitised FRB 160317 signal accuracy by matching it with the original graphical image is presented, which showed a satisfactory match to the original. The numerical data array obtained by digitising the raw graphical material using a pre-processing procedure is becomes available for further analysis. The described way can be used by university teachers both at the initial stages of students teaching to work with images and carry out data analysis, and when preparing teaching materials when organising the educational process using distance learning technologies. The results are applicable at the starting stages of scientifi research in the initial data set formation for dependency analysis in various subject areas, where there are no initial samples refl the results of observation.

The article deals with the problem of packing objects of arbitrary geometry. Modern methods of designing irregular packing schemes use a mathematical model based on phi-functions and a hodograph vector function of dense placement. These methods make it possible to obtain exact solutions, but they are time-consuming and very sensitive to the dimension of the problem being solved and the degree of detail of the geometry of vector objects. The use of a discrete representation of placed objects in the form of orthogonal polyhedra can signifi increase the speed of construction a packing, which makes the problem of adequately transforming the shape of placed objects (vector models in the two-dimensional case and polygonal models in the three- dimensional case) relevant. The aim of the study is to systematize methods that provide the formation of orthogonal polyhedra of various dimensions for describing objects and containers of arbitrary geometry. Methods for creating orthogonal polyhedra based on set-theoretic operations (addition, subtraction and intersection), analytical modeling using a set of functions and relational operators, as well as voxelization of fl and volumetric object models are considered. The use of set-theoretic operations is best suited for the manual creation of orthogonal polyhedra with relatively simple geometry. The method of analytical modeling is intended for the formation of voxelized objects based on geometric fi es described by a set of analytically specifi functions. The application of various relational operators to obtain orthogonal polyhedra that describe the contour, internal and external regions of analytical given objects is shown. An algorithm for creating a container in the form of an orthogonal polyhedron based on a given vector model is proposed, which makes it possible to solve problems of irregular packing of objects inside containers of arbitrary shape. All the methods presented in the article are programmatically implemented with a generalization in terms of dimension and are applicable to solving any types of cutting and packing problems.

The problems of high-level synthesis of very large integrated circuits (VLSI) are considered. The review of the subject area shows that the use of the imperative model and corresponding programming languages does not provide efficient parallelization of algorithms and the possibility of efficient parallelization of programs. This leads to the impossibility of providing the required technical characteristics. This is due to the specifics of VLSI, which is essentially a scheme of parallel processing of information flows. An original VLSI synthesis method is presented. The method based on the functional-streaming paradigm of parallel computing. This method allows ensuring architectural independence and maximum coverage of implementation options. The route map of VLSI functional-flow method is outlined. The problem of estimating the requested hardware resources and clock frequency, necessary for solving, is formulated. This problem must be solved at the early stages of design. A method for estimating resources in the process of functional-flow synthesis is proposed. The method is based on the use of an additional meta-layer (HDL-graph). Taking into account the polymorphism of the solution of the resource estimation problem, it is proposed to use machine learning technologies in the new method. It is shown that the application of the indicated method in the synthesis process makes it possible to provide the most accurate assessment of resources. This is possible, because the HDL graph is a data flow graph typed and structured in accordance with the functional-flow model of parallel computing. Machine learning allows to most effectively obtain a solution to the problem of optimal selection of the required resources. The classes of resources for which an assessment is required are highlighted. Selected parameters for building a resource assessment model. The software implementation and comparison of the proposed resource estimation method based on linear regression models, neural networks and gradient boosting with known approaches is performed. It is shown that when using the technology of functional-flow synthesis when applying the proposed method for estimating the required resources and performance, an increase in the accuracy of the estimate at the high-level stage.

In this article, the construction and analysis of machine learning models were performed for short-term forecasting in the cryptocurrency market on the example of bitcoin – one of the most popular cryptocurrencies in the world. The initial data for the study leads to the conclusion that over the long period of its existence, bitcoin has shown a high degree of volatility, especially evident in comparison with traditional financial instruments. The article substantiates that this market is influenced by a multitude of factors. No one can say for sure what makes up the value of a particular cryptocurrency, as it involves a range of reasons, which cannot be fully taken into account. To overcome this problem, we have considered the principle of recurrent neural network. It is described why networks with memory are better at making predictions on the time series than conventional autoregressive model and standard forward propagation networks. The initial data processing algorithm and transformation methods are defined. The sample was reduced in order to increase the speed of the network, by reducing the number of recalculations of weights. The algorithm of the family of recurrent neural networks was built and trained to test the hypothesis about their better adaptivity due to short-term and long-term memory. The model is evaluated on the test data representing the bitcoin exchange rate for 2021–2022, since this period is characterized by high volatility. It is concluded that it is reasonable to use a similar type of models for short-term forecasting of cryptocurrency rates.

A significant increase in the number of transcatheter aortic valve replacements entails the development of auxiliary systems that solve the problem of intra- or preoperative assistance to such interventions. The main concept of such systems is the concept of computerized automatic anatomical recognition of the main landmarks that are key to the procedure. In the case of transcatheter prosthetics – elements of the aortic root and delivery system. This work is aimed at demonstrating the potential of using machine learning methods, the modern architecture of the ResNet V2 convolutional neural network, for the task of intraoperative real-time tracking of the main anatomical landmarks during transcatheter aortic valve replacement. The basis for training the chosen architecture of the neural network was the clinical graphical data of 5 patients who received transcatheter aortic valve replacement using commercial CoreValve systems (Medtronic Inc., USA). The intraoperative aortographs obtained during such an intervention with visualization of the main anatomical landmarks: elements of the fibrous ring of the aortic valve, sinotubular articulation and elements of the delivery system, became the output data for the work of the selected neural network. The total number of images was 2000, which were randomly distributed into two subsamples: 1400 images for training; 600 – for validation. It is shown that the used architecture of the neural network is capable of performing detection with an accuracy of 95-96% in terms of the metrics of the classification and localization components, however, to a large extent does not meet the performance requirements (processing speed): the processing time for one aortography frame was 0.097 sec. The results obtained determine the further direction of development of automatic anatomical recognition of the main landmarks in transcatheter aortic valve replacement from the standpoint of creating an assisting system – reducing the time of analysis of each frame due to the optimization methods described in the literature.

The work presents analysis of possible application of self-generating neural networks, which can independently generate a topological map of neuron connections while modelling biological neurogenesis, in multi-threaded information communication systems. A basic optical neural network cell is designed on the basis of the applied layered composition performing data processing. A map of neuron connections represents not an ordered structure providing a regular graph for exchange of information between neurons, but a set of cognitive reserve represented as an unconnected set of neuromorphic cells. Modelling of neuron death (apoptosis) and creation of dendrite-axon connections makes it possible to implement a stepwise neural network growth algorithm. Despite challenges in implementing this process, creating a growing network in an optical neural network framework solves the problem of initial forming of the neural network architecture, which greatly simplifies the learning process. Neural network cells used with the network growth algorithm resulted in neural network structures that use internal self-sustaining rhythmic activity to process information. This activity is a result of spontaneously formed closed neural circuits with common neurons among neuronal cells. Such organisation of recirculation memory leads to solutions with reference to such intra-network activity. As a result, response of the network is determined not only by stimuli, but also by the internal state of the network and its rhythmic activity. Network functioning is affected by internal rhythms, which depend on the information passing through the neuron clusters, which results in formation of a specific rhythmic memory. This can be used for tasks that require solutions to be worked out based on certain parameters, but they shall be unreproducible when the network is repeatedly stimulated by the same influences. Such tasks include ensuring information transmission security when using some set of carriers. The task of determining a number of frequencies and their frequency plan depends on external factors. To exclude possible repeating generation of the same carrier allocation, it is necessary to use networks of the configuration under consideration that can influence generation of solutions through the gathered experience.

The objective of the study is the development of 3D variable-length link model with electric drives to be used in designing of next-generation comfortable exoskeletons. The developed link model has two inertial absolutely rigid sections on its ends and a variable- length section, considered weightless, in between. The mechanical part of the variable-length link model has been implemented in the universal computer math "Wolfram Mathematcia 11.3" environment by building the system of Lagrange – Maxwell differential equations. The electro-mechanical link model with electric drives has been implemented in the MatLab Simulink environment. The implemented model includes the following units: the trajectory synthesis unit per each degree of freedom, the unit for controlling torques calculation based on differential equations of motion, the unit for selecting electric motors with gears, the unit for calculating electric current per each motor and implementing the control system. The electric motors, reducers, rack and pinion gears implementing the specified and programmed link motion have been selected. The inertial and geometrical variable-length link parameters corresponding to the human tibia in the period of the single-support step phase have been selected. The drives implementing the link rotation are situated in the bottom link point in the combination of two orthogonal cylindrical hinges. One of these hinges is fixed to the supporting surface, the other one is fixed to the link end. This hinge combination simulates human ankle joint in the single-support step phase. The drive controlling the link length change is situated at the end of the bottom absolutely rigid weighty link section. The programmed trajectories for generalized coordinates are specified based on the simulation requirements of the anthropomorphic tibia motion. As a result, the electro-mechanical model of a variable- length link with parameters corresponding to the average man’s tibia has been developed. The drives and gears that allow implementing the motion close to anthropomorphic one have been selected. The implementation of this motion based on the developed software in the computer math "Wolfram Mathematica 11.3" environment and in the MatLab Simulink system has been demonstrated. The numerical calculations are presented.

The problem of building an information infrastructure resistant to computer attacks is relevant for organizing the work of any enterprise. Therefore, the ability to assess the existing or developing information infrastructure is very important. In this regard, the article deals with the problem of categorizing objects of critical information infrastructure in the context of the need to assess their relationship. The current legislative acts, which are the information base for determining the objects of critical information infrastructure and determining their purpose, structure and composition, are considered, as well as the criteria for the significance of objects are determined. The article also defines the links between critical information infrastructure objects, their resistance to computer attacks, as well as possible damage due to disruption of their functioning or the performance of a critical process. The article provides a description of the criteria that are subject to assessment and a methodology for assessing the stability of critical information infrastructure objects to computer attacks and assessing possible damage due to disruption of the functioning or performance of critical processes by objects of critical information infrastructure. An augmented solution is proposed for assessing the stability of the functioning of critical information infrastructure objects with various options for their connection. The possibility of assessing the cumulative damage due to disruption of the functioning of interconnected objects of critical information infrastructure is considered.