Search

The paper proposes an approach based on the use of mathematical methods for modeling the behavior of the designed web application and user behavior. This approach allows an evaluation of the usability of this application. The paper discusses the models of user interfaces (UI), which are used to assess the convenience of site navigation. The possibility of using two classes of UI models is shown – structural-logical (ontological) and probabilistic. Models of the first class are used to assess the degree of comprehensibility of the proposed UI navigation on the search web resource in the accepted terms. For this, mathematically defined measures of similarity between the elements of the UI and their relationships and the elements of a hypothetical (but plausible) model of the user’s perception of the search area in a given subject area are used. In particular, the paper substantiates the possibility of using Jaccard and Levenshtein lexicographic distance metrics as such measures of similarity. Probabilistic models are based on Markov chains. With the help of these models, in the presence of reliable statistical data collected during the trial operation of a web application or its prototype, it is proposed to estimate the average number of user steps required to solve a specific problem of finding information about a subject area object. The paper provides some recommendations on the use of similarity measures to improve the usability of the UI of web applications. In addition, data on the technique for estimating the probabilities of transitions of Markov chains and semantic connections are presented. To clarify the features of the UI analysis models proposed in the article, the website of the RTU MIREA Admission Committee (https://priem.mirea.ru) is provided with a fairly simple organization that provides a search for information about admission and training at the University. The application of the approach described in the paper, along with traditional methods of testing the usability of UI, will increase the overall level of usability of applications, and thereby reduce the cost of identifying and correcting related errors.

Implementation of the task of creating a digital platform for a full-featured system of information and analytical support for public administration at the federal, regional and municipal levels, requires a lot of resources and serious expertise.In this regard, the subject of the study was the experience and trends in the construction and operation of digital platforms for state and public administration. The aim of the paper was to summarize the international practice of creating, operating and developing digital public administration platforms. As part of the study, the authors carry out a systematic, content and comparative analysis of various sources: regulatory documents, scientific papers, analytical materials of a number of international organizations, etc.The article presents the results of a study of world experience in the application of various tools to support e-government and support digital governance platforms. The authors describe global trends in the use of information and communication technologies to support public administration. The paper presents a list of general principles for the operation of digital platforms, gives the results of the analysis on the compliance with these principles of the state digital platform of the European Union, highlights its distinctive properties.The article forms proposals and development directions, based on the results and available studies on the development and promotion of digital management platforms, that can help accelerate the spread of digital transformation of public administration in the Russian Federation. The results of the study can be applied to identify the potential of the existing platform, its strengths and weaknesses, including in the context of the possibilities of developing the process of digital transformation of governance, as well as effectively moving towards the formation of the digital platform of public administration in the Russian Federation.

The paper deals with a problem of the obfuscated JavaScript code detection and classification based on Abstract Syntax Trees (AST) coloring. Colors of the AST vertexes and edges are assigned with regard to the types of the AST vertexes specified by the program lexical and syntax structure and the programming language standard. Research involved a few stages. First of the all, a non-obfuscated JavaScript programs dataset was collected by the public repositories evaluation. Secondly, obfuscated samples were created using eight open-source obfuscators. Classifier models were built using an algorithm of gradient boosting on the decision trees (GBDT). We built two types of the classifiers. The first one is the model that classifies the program according to the type of the obfuscator used, i.e. based on what obfuscator created the sample. The second one tries to detect samples obfuscated by the obfuscator whose samples are not observed during training. The quality of the obtained models is on par with the known published results. The feature engineering method proposed in the paper does not require a preliminary analysis of the obfuscators and obfuscating transformations. In the final part of the paper we analyze a quality of models estimated, discussing the certain statistical properties of the obfuscated and non-obfuscated samples obtained and corresponding colored ASTs. Analysis of generated samples of obfuscated programs has shown that the method proposed in the paper has some limitations. In particular, it is difficult to recognize minifiers or other obfuscating programs, which change the lexical structure to a greater extent and the syntax to a lesser extent. To improve the quality of detection of this kind of obscuring transformations, one can built combined classifiers using both the method based on the AST coloring and the additional information about lexemes and punctuation, for example, entropy of identifiers and strings, proportion of characters in upper and lower case, usage frequency of certain characters etc.

This paper suggests an approach to the semantic image analysis for application in computer vision systems. The aim of the work is to develop a method for automatically construction of a semantic model, that formalizes the spatial relationships between objects in the image and research thereof. A distinctive feature of this model is the detection of salient objects, due to which the construction algorithm analyzes significantly less relations between objects, which can greatly reduce the image processing time and the amount of resources spent for processing. Attention is paid to the selection of a neural network algorithm for object detection in an image, as a preliminary stage of model construction. Experiments were conducted on test datasets provided by Visual Genome database, developed by researchers from Stanford University to evaluate object detection algorithms, image captioning models, and other relevant image analysis tasks. When assessing the performance of the model, the accuracy of spatial relations recognition was evaluated. Further, the experiments on resulting model interpretation were conducted, namely image annotation, i.e. generating a textual description of the image content. The experimental results were compared with similar results obtained by means of the algorithm based on neural networks algorithm on the same dataset by other researchers, as well as by the author of this paper earlier. Up to 60 % improvement in image captioning quality (according to the METEOR metric) compared with neural network methods has been shown. In addition, the use of this model allows partial cleansing and normalization of data for training neural network architectures, which are widely used in image analysis among others. The prospects of using this technique in situational monitoring are considered. The disadvantages of this approach are some simplifications in the construction of the model, which will be taken into account in the further development of the model.

Introduction. The paper considers improving the management quality of an educational organization through automating the personalized data collection, storage and ranking. The authors have developed a module of the university corporate system, an ePortfolio of students, which implements a multicriteria optimization method for calculating the students’ rating on the basis of the collected and stored data. The study object is multicriteria ranking methods. The subject of the study is the automated calculation of student’s rating within the electronic portfolio. The study objective is to develop tools for collecting, storing and processing data on individual achievements of students and the implementation of the mathematical method of multicriteria optimization for ranking students on the basis of the portfolio data. Practical implications include development of a tool for an effective management of the educational process.Materials and Methods. A prototype module of the university corporate system “ePortfolio” on the platform of 1C: Enterprise 8.3 is presented. To rank students, a special case of the alternative ranking method is implemented in the block of the data analysis module – pairwise comparison in order of their relative importance. At that, a unified scale of relations was used.Research Results. The authors described the scheme of the information system (IS) operation “ePortfolio”, presented a process interaction pattern for the portfolio formation, as well as a diagram of business processes under calculating an individual rating. A fragment of the sample is shown on which the performance of the multicriteria optimization block has been tested. The criteria of the calculations are described, as well as the rule of screening alternatives for solving for the optimum.Discussion and Conclusion. The paper presents the results of the IS block operation on ranking a list of students. The calculation results coincide with the practical data.

International audience; The paper deals with the problem of identification of linearly varying frequency of sinusoidal signal with unknown amplitude and phase. Identification task for linearly varying frequency occurs, for example, during telescope operation control and it is of practical interest. Existing synthesis methods for identification algorithms of linearly varying frequency of sinusoidal signal use unlimited functions of time that is not attractive from a technical point of view, since the measurement noise multiplied by an unlimited function tends to give extremely poor estimates of the tunable parameter. This paper proposes a new approach for identification of linearly varying frequency comprising iterative filtering of measured sinusoidal signal (with the use of linear first order stable components), which in turn gives the possibility to obtain a simple linear regression model with one unknown constant parameter. We present computer simulation results, illustrating the performance of the proposed identification algorithm. Computer modeling was performed both in the presence and absence of the measurement noise. Also, comparative analysis of the proposed approach with the previously obtained methods was carried out within the framework of computer simulation. It was shown that the presented solution provides a significant improvement in the accuracy of an unknown frequency identification in the noise presence.; Рассмотрена задача идентификации линейно меняющейся частоты синусоидального сигнала, имеющего неизвестные амплитуду и фазу, возникающая, например, при управлении телескопом. Традиционно методы синтеза алгоритмов идентификации линейно меняющейся частоты синусоидального сигнала используют неограниченные функции времени, что вызывает технические проблемы, поскольку в этом случае наличие шумов при измерении может существенно исказить настраиваемый параметр. Предложен подход к идентификации линейно меняющейся частоты, предусматривающий итеративную фильтрацию (с использованием линейных устойчивых звеньев первого порядка) измеряемого синусоидального сигнала, которая позволяет получить простую линейную регрессионную модель с одним неизвестным постоянным параметром. Приведены результаты компьютерного моделирования, иллюстрирующие работоспособность представленного алгоритма идентификации. Компьютерное моделирование выполнено как при наличии шумов в измерениях, так и в их отсутствие. Путем компьютерного моделирования проведен сравнительный анализ предлагаемого подхода с полученными ранее методами, и показано, что представленное решение обеспечивает существенное повышение точности идентификации неизвестной частоты при наличии шумов

In this paper, we suggest to use hybrid approach to time series forecasting problem. In first part of paper, we create a literature review of time series forecasting methods based on hybrid neural networks and neuro-fuzzy approaches. Hybrid neural networks especially effective for specific types of applications such as forecasting or classification problem, in contrast to traditional monolithic neural networks. These classes of problems include problems with different characteristics in different modules. The main part of paper create a detailed overview of hybrid networks benefits, its architectures and performance under traditional neural networks. Hybrid neural networks models for time series forecasting are discussed in the paper. Experiments with modular neural networks are given.

The paper presents an analytical review of the application of biometric recognition systems in relation to facial image identification technologies. The classification of biometric systems is presented. The trends of technological progress in the field of biometrics and facial recognition capabilities are considered. It is determined that in 2020 there is a trend of transition from the use of biometric recognition technologies in traditional state security systems to the sphere of commercial and user applications. The process of «linking» encryption keys and passwords with the biometric parameters of the data subject is described. It is proposed that a biometric feature and a biometrics parameter mean a certain value that has a physical meaning that characterizes the subject itself. The possibility of using circular neighborhood and bilinear interpolation of pixel intensity values in biometrics is also presented. This will make it possible to build a local binary template. In order to solve the problem of identification of persons, it is advisable to investigate the essence of biometric systems in the technologies of identification of persons, their types, identifying the shortcomings of each of them, on the basis of which to present the directions of elimination and search for the most reliable technologies. The essence of the use of biometric systems in the technologies of identification of persons is, for example, that the user can provide the bank or other counterparty with evidence that it is he who wants to use the services on his accounts. At the same time, the demand has increased for contactless biometric solutions. These technologies are implemented in order to conduct additional biometric verification of users. This allows to minimize possible fraud or violation of the internal rules of the service, for example, the transfer of accounts of some registered users to others.

This paper is devoted to construction of reference walking trajectories for developing pedestrian navigation algorithms for smartphones. Such trajectories can be used both for verification of classical algorithms of navigation or for application of machine learning technics. Reconstruction of closed trajectories based on data from foot-mounted inertial measurement units (IMU) is investigated. The advantages of the approach are the use of inexpensive sensors and the simplicity of the presented method. We propose algorithms for reconstruction of smooth 2D pedestrian trajectories based on measurements from a single IMU as well as on combined measurements from two IMU’s. Introduced algorithms are based on application of modified Kalman filter with an assumption of IMU having zero velocity when foot contacts the ground. In case of two measurement units, it is additionally assumed that the positions of the sensors cannot differ significantly from each other. The algorithms were tested on trajectories lasting from 1 to 10 minutes, passing indoors on horizontal surfaces. Obtained results were compared with high precision trajectories acquired with GNSS RTK receivers. Additionally, the process of inter-device time synchronization is investigated and detailed description of the experiments and used equipment is given. The dataset used for verification of proposed algorithms is freely available at: http://gartseev.ru/projects/rtj2021.

The paper addresses the problem of assessing the quality of fingerprint images using spatial analysis methods. The author proposes using the previously developed mathematical model to describe the set of magnitudes of the image gradient. The model is based on the two-parameter Weibull distribution. The author proposes two approaches to assess the quality of fingerprints. The first approach is implemented by the so-called “Full reference method”, which compares the Weibull distribution parameters’ values of statistical estimates. The results of identifying sweat pores using this method are presented. The second approach is called the “No-Reference method” and is used to assess fingerprints’ quality when analyzing and identifying the information content of their individual sections. It is proposed to use an image blur map as a quality characteristic and a statistical estimate of the Weibull distribution shape parameter as a measure of the blur. The shape parameter is estimated at each image point by the combination of magnitudes of the image gradient in the vicinity of the point; in this, the previously developed blur mapping technique is applied. The specific examples illustrate effectiveness of the proposed approaches.

Introduction. Signals constructed on the basis of ensembles of code sequences are widely used in digital communication systems. During development of such systems, the most attention is paid to analysis, synthesis and implementation of periodic signal ensembles. Theoretic methods for synthesis of periodic signal ensembles are developed and are in use. Considerably fewer results are received regarding construction of aperiodic signal ensembles with given properties. Theoretical methods for synthesis of such ensembles are practically nonexistent.Aim. To construct aperiodic Gold code ensembles with the best ratios of code length to ensemble volume among the most known binary codes.Materials and methods. Methods of directed search and discrete choice of the best ensemble based on unconditional preference criteria are used.Results. Full and truncated aperiodic Gold code ensembles with given length and ensemble volume were constructed. Parameters and shape of auto- and mutual correlation functions were shown for a number of constructed ensembles. Comparison of the paper results with known results for periodic Gold code ensembles has been conducted regarding growth of minimax correlation function values depending on code length and ensemble volume.Conclusion. The developed algorithms, unlike the known ones, make it possible to form both complete ensembles and ensembles taking into account the limitation of their volume. In addition, the algorithms can be extended to the tasks of forming ensembles from other families, for example, assembled from code sequences belonging to different families.

Objectives. This article presents an application for the processing of scanned images of sales receipts for subsequent extraction of text information using the Tesseract OCR Engine. Such an application is useful for maintaining a family budget or for accounting in small companies. The main problem of receipt recognition is the low quality of ink and printing paper, which results in creasing and tears, as well as the rapid fading of printed characters.Methods. The study is based on a number of algorithms based on mathematical morphology methods for opening, closing and morphological gradient operations, as well as image conversion, which can significantly improve the final recognition of characters by Tesseract.Results. In order to solve this problem, a special image normalisation algorithm is proposed, which includes locating a receipt on an image, processing the received image section, removing image capture and carrier defects, as well as point processing for restoring missing characters. The developed application supports increased recognition accuracy of text information when using Tesseract OCR.Conclusion. The developed system recognises characters with fairly high accuracy, demonstrates a result that is better than that obtained when using the unmodified Tesseract method, but which is still inferior to the recognition accuracy of ABBY FineReader. Methods are also been proposed aimed at improving the developed algorithm.

A review of robotic systems is presented. The paper analyzes applied hardware and software solutions and summarizes the most common block diagrams of control systems. The analysis of approaches to control systems scaling, the use of intelligent control, achieving fault tolerance, reducing the weight and size of control system elements belonging to various classes of robotic systems is carried out. The goal of the review is finding common approaches used in various areas of robotics to build on their basis a uniform methodology for designing scalable intelligent control systems for robots with a given level of fault tolerance on a unified component base. This part is dedicated to industrial robotics. The following conclusions are made: scaling in industrial robotics is achieved through the use of the modular control systems and unification of main components; multiple industrial robot interaction is organized using centralized global planning or the use of previously simulated control programs, eliminating possible collisions in working area; intellectual technologies in industrial robotics are used primarily at the strategic level of the control system which is usually non-real time, and in some cases even implemented as a remote cloud service; from the point of view of ensuring fault tolerance, the industrial robots developers are primarily focused on the early prediction of faults and the planned decommissioning of the robots, and are not on highly-avaliability in case of failures; industrial robotics does not impose serious requirements on the dimensions and weight of the control devices.

In this paper the term of «intelligent data analysis» is discussed, the cloud computing concept is described. The system developed and deployed on the computer cluster by ECM department of BSUIR is shown as an example of the intelligent data analysis by means of cloud computing. Some results of research with the help of this system are given.

In the last 10 years there has been a revolu on in the fi eld of computer image analysis and pa ern recogni on. Modern algorithms of computer vision equaled and even in some problems surpassed human capabili es. This jerk is largely due to the emergence and development of the technology of deep convolu onal neural networks.Recent developments in the fi eld of image processing and machine learning open up the prospect of crea ng systems based on ar fi cial neural convolu onal networks, superior to humans in problems of image classifi ca on, in par cular, in solving problems of analysis of various medical images. Among the most promising applica ons: automated recogni on and classifi ca on of skin diseases, detec on of pathologies on X-ray, CT, MRI, ultrasound imaging. In the proposed project, we will focusour a en on on the diagnosis of human skin diseases.At the moment, melanoma is one of the most dangerous types of malignant tumors of the skin with a lot of deaths due to rapid metastasis, which is difficult to treat. The development of computer vision technology has allowed the development of technical vision systems that allow detec on and classifi ca on of skin diseases with a quality that is comparable and in some cases exceeds the values a ained by man.In this paper, the authors propose an algorithm for the primary diagnosis of skin melanoma based on deep neural networks, achieving an accuracy of 91% for melanoma in dermatoscopic images. At the moment, the algorithm is implemented programma cally and is used in the test version of the online system for detec ng and classifying skin diseases, available at skincheckup.online.Thanks to this development, the prospect of a signifi cantincrease in the propor on of people subjected to preven ve examina on for the presence of skin diseases opens up. Along with this, an addi onal source of informa on for specialized professionals can also play a role in seng the right diagnosis.

Study purpose.Existing approaches to forecasting dynamics of financial markets, as a rule, reduce to econometric calculations or technical analysis techniques, which in turn is a consequence of preferences among specialists, engaged in theoretical research and professional market participants, respectively. The main study purpose is developing a predictive economic-mathematical model that allows combining both approaches. In other words, this model should be estimated using traditional methods of econometrics and, at the same time, take into account the impact on the pricing process of the effect of clustering participants on behavioral patterns, as the basis of technical analysis. In addition, it is necessary that the created economic-mathematical model should take into account the phenomenon of existing historical trading levels and control the influence they exert on price dynamics, when it falls into local areas of these levels. Such analysis of price behavior patterns in certain areas of historical repeating levels is a popular approach among professional market participants. Besides, an important criterion of developing model’s potential applicability by a wide range of the interested specialists is its general functional form’s simplicity and, in particular, its components.Materials and methods. In the study, the market of the pound sterling exchange rate against the US dollar (GBP/USD) for the whole period of 2017 was chosen as the considered financial series, in order to forecast it. The presented economic-mathematical model was estimated by classical Kalman filter with an embedded neural network. The choice of these assessment tools can be explained by their wide capabilities in dealing with non-stationary, noisy financial market time series. In addition, applying Kalman filter is a popular technique for estimation local-level models, which principle was implemented in the newly model, proposed in article.Results. Using chosen approach of simultaneous applying Kalman filter and artificial neural network, there were obtained statistically significant estimations of all model’s coefficients. The subsequent model application on GBP/USD series from the test dataset allowed demonstrating its high predictive ability comparing with added random walk model, in particular judging by percentage of correct forecast directions. All received results have confirmed that constructed model allows effectively taking into account structural features of considered market and building good forecasts of future price dynamics.Conclusion. The study was focused on developing and improving apparatus of forecasting financial market prices dynamics. In turn, economic-mathematical model presented in that paper can be used both by specialists, carrying out theoretical studies of pricing process in financial markets, and by professional market participants, forecasting the direction of future price movements. High percentage of correct forecast directions makes it possible to use proposed model independently or as a confirmatory tool.

The paper presents a comparative overview of decentralized data storages of various types. It is shown that although they have a number of common properties that are typical of all peer-to-peer (P2P) networks, the problems to be solved and, accordingly, the technologies used to build different types of storages differ significantly., 19 pages, 1 figures, 87 references; in Russian

In this paper, we consider methods for hyperspectral image processing, required in systems of image formation, storage, and transmission and aimed at solving problems of data compression and protection. A modification of the digital image compression method based on a hierarchical grid interpolation is proposed. Methods of active (on the basis of digital watermarking) and passive (on the basis of artificial image distortion detection) data protection against unauthorized dissemination are developed and investigated.