Skip to main content

2020 | Buch

Convergent Cognitive Information Technologies

Third International Conference, Convergent 2018, Moscow, Russia, November 29 – December 2, 2018, Revised Selected Papers

insite
SUCHEN

Über dieses Buch

This book constitutes the refereed proceedings of the Third International Conference on Convergent Cognitive Information Technologies, Convergent 2018, held in Moscow, Russia, in December 2018.
The 26 revised full papers and 9 short papers were carefully reviewed and selected from 147 submissions. The papers of this volume are organized in topical sections on theoretical questions of computer science, computational mathematics, computer science and cognitive information technologies; cognitive information technologies in control systems; big data and applications; the Internet of Things (IoT): standards, communication and information technologies, network applications; smart cities: standards, cognitive-information technologies and their applications.- cognitive information technologies in the digital economics.- digital transformation of transport.

Inhaltsverzeichnis

Frontmatter

Theoretical Questions of Computer Science, Computational Mathematics, Computer Science and Cognitive Information Technologies

Frontmatter
Modeling of Financial Asset Prices with Hyperbolic-Sine Stochastic Model

We propose an analytically tractable local volatility model for asset price dynamics leading to volatility smile/skew and fatter-tailed probability distribution. The proposed local volatility model is based on stochastic process of hyperbolic-sine type. We derive the transition probability density function for hyperbolic-sine model and justify that this function has delta function terminal condition at initial time. We compare the probability density functions in Black-Scholes and hyperbolic-sine models to demonstrate that the probability distribution in hyperbolic sine model has some features of fat-tailed distributions. Risk neutral valuation technique is applied to find explicit valuation formula for European call option price in hyperbolic-sine model. In hyperbolic-sine model European call option is more valuable than an identical option in Black-Scholes model for ATM options. We verify that in hyperbolic-sine model Breeden-Litzenberger formula (relation between European call option price and probability density function) holds true. We also examine that Dupire formula correctly recovers volatility function from European call option price in hyperbolic-sine model.

Sergey Shorokhov, Maxim Fomin
On Mathematical Visualization in Education

This article treats the use of modern information technologies in the classroom educational process. It emphasizes the need to combine symbolic and visual mathematics, describes the problems associated with this issue, provides a review of the existing systems and a list of the requirements a modern mathematical visualization system must meet. The article is conceived as a manifesto for the use of mathematical visualization in education. The article then goes on to describe the developments of the authors’ research group. The functionality of visualmath.ru website is described. This resource contains an ample collection of visual and text modules for teachers to create presentations based largely on visual materials. The most important part of the article is the description of fast and powerful JavaScript visulatization libraries developed specifically for the project: Skeleton and Grafar. The former is designed to display two-dimensional graphs, while the latter visualizes three-dimensional objects with transparency and illumination effects. Both libraries are capable of processing large element sets in near-real time. In conclusion, selected examples of visualizations created using the libraries use are provided, including the ones used in courses on mathematical analysis and analytical geometry.

Alexey Karpov, Vladimir Klepov, Alexey Nikitin
Cognitive Computing Cybersecurity: Social Network Analysis

The structure and basic principles of technology for increasing the probability of identifying subjects of information processes of open Internet resources based on ontology methods are considered. Based on this ontology the knowledge base intended for creation of the program systems supporting ensuring information security has been realized. The first step in building the domain theory is a formal description of the domain ontology, i.e. the meaning of all used terms specific to the given subject area. Cognitive ontology’s of subject areas are a tool necessary to achieve high pertinence of information retrieval and are needed to describe key concepts of a given subject area. The developed ontological knowledge base has been used when developing the software complex intended for identification of the user of social networks when ensuring information security, monitoring and preventing threats. This article is next in a series of articles by the authors in which they continue to monitor and analyze the current state and new tendencies in the field of information security and safety of information.

Alimbubi Aktayeva, Rozamgul Niyazova, Gulshat Muradilova, Yerkhan Makatov, Ulzhan Kusainova
Application of the Multi-layer Method and Method of Continuing at the Best Parameter to the Solving of a Stiff Equation

By using the example of one rigid boundary value problem for a second order differential equation on a sphere, we compare our two approaches for giving construction of approximate solutions. The first approach consists of using the method of prolongation of the solution by the best parameter. This approach allows us to substantially decrease the number of steps and increase stability of the calculation process with comparison to standard methods. The second approach is linked with the building of an approximated multi-layer solution to the problem and is based on the use of analytical recurrent rations. We build those recurrent ratios based on classic numerical methods, applied to an interval of variable length. In the result, an approximated solution in the form of a table of numbers is substituted with an approximated solution is the form of a function, which is easier to use for adaptation, building graphs and other purposes. Problems related to stiffness of material can be solved by using solution of singularly perturbed differential equations with applying standard methods for the numerical solution of ordinary differential equations, however it can lead to significant difficulties. The first difficulty is the loss of stability of the computational process, when small errors in individual steps lead to an uncontrolled increase in the error of computations as a whole. Another difficulty directly connected with the first one is the need to greatly reduce the integration step, which leads to a strong slowdown of the computational process. In this work, it is shown, that both of our approaches successfully cope with indicated difficulties.

Elena Budkina, Evgenii Kuznetsov, Dmitry Tarkhov, Anastasia Gomzina, Semyon Maltsev
Forecasting News Events Using the Theory of Self-similarity by Analysing the Spectra of Information Processes Derived from the Vector Representation of Text Documents

This paper presents a new methodology developed by the authors to forecast news events based on representing texts as vectors, subtracting information process spectrums from the vectors, and analysing these with the help of self-similarity theory. Spectrum extraction is performed using text processing by applying mathematical linguistics approaches (text markups, normalisation, commenting); the vectors obtained are then clustered according to theme groups and the time of the news appearance. By applying the Hurst self-similarity method to analyse information news process spectrums, their self-similarity features are analysed. The information processes are then classified into two different classes: self-similar and not self-similar. It is proven that if the self-similarity feature is present in the processes investigated, the Hurst self-similarity method (R/S analysis) and almost-periodic functions will enable us to discover the almost periods of repeatability of events, and this will further allow us to forecast their behaviour over time and predict new events.

Dmitry Zhukov, Tatiana Khvatova, Konstantin Otradnov
Organization of Information System for Semantic Search Based on Associative Vector Space

Text arrays, created by the online community, contain specific cognitive capabilities. Analyses cover the following: mass media materials, social networks, forums, blogs, political materials, biographies and diaries, scientific publications, belles-letters and other. As practice shows, standard search systems are not always able to find the required data out of this huge volume of the data file. A difficult task for the automated computer text processing is the semantic analysis, which is interpretation of meaning of the text, its content and semantics. Performance of this task requires knowledge of meaning of words and sentences; the way to describe these values formally, and to carry out operations with them, even their storage in computer memory, cause difficulties. That is why in automated text processing computer is not able to search texts of a certain subject, without explicitly specified keywords or phrases, as well as to find texts with the similar meaning, which is quite difficult for the search procedure. Modern information retrieval systems (IRS) are mainly based on key words. The major features for this approach are frequency of word occurrence in document collection, its uniqueness, morphological and syntactic properties. The problem is that the full-text information retrieval systems initially do not imply any semantic connection between the documents and the information they contain, and do not take into account the context and many other issues of importance for semantic interpretation, which makes full-text information retrieval systems unsuitable solution for contextual search. Semantic information retrieval systems should settle the issue of full-text IRS and assist the computer in formal description of semantic meaning of the documents and the data about it. This paper examines possible organization of semantic information-retrieval system based on associations, and uses associative vector spaces as the basic semantic structures.

Valery Sachkov, Dmitry Zhukov, Yury Korablin, Vyacheslav Raev, Dmitry Akimov
Algorithm for Solving Ordinary Differential Equations Using Neural Network Technologies

The paper considers the neural network approach for solving the Cauchy problem for ordinary differential equations of the first order based on the representation of the function as a superposition of elementary functions, the algorithm of solving the problem is proposed. The application of the neural network approach allows obtaining the desired solution in the form of a functional dependence that satisfies smoothness conditions. On the basis of a two-layer perceptron, a model of a neural network solution of the problem and a numerical algorithm realizing the search for a solution are built. We developed a program and algorithmic solution of the Cauchy problem. We analyzed the accuracy of the results and its interrelation with the parameters of the neural networks used. The equivalence of the work of the neural network algorithm and the third-order numerical Runge-Kutta algorithm is shown. In addition, the problem of retraining the neural network algorithm for solving the Cauchy problem for first order ordinary differential equations is posed.

Irina Bolodurina, Denis Parfenov, Lubov Zabrodina
An Equivalence Relation on the Class of Regular Languages

This paper introduces a special binary relation on the set of regular languages, which possesses all three properties of equivalence relation. That is, this relation separates the whole class of regular languages into non-intersecting classes. In addition, it allows us to consider only one representative of each class in the description of the regular languages class, the so-called “simplified” language. Such simplified language corresponds to a “simplified” automaton. This equivalence relation makes it possible to limit the number of considered regular languages to a finite number of finite automata with a priori fixed number of states. In addition, this equivalence relation preserves the relation $$\#$$ considered in our previous papers, and therefore allows us to use the previous theory. For example, on the basis of obtained results, we can apply various algorithms of equivalent transformations of nondeterministic finite automata to simplified them.

Boris Melnikov, Vasily Dolgov, Elena Melnikova
A Semiotic Model Mapping and Reduction Properties

In this paper, we investigate semiotic models used in the computer industry, by means of linguistic approach, considering a computer modeling notation as an artificial modeling language, which, compared to a natural language of human communication, sacrifices its beauty and imagery for the sake of accuracy and unambiguity. The research is carried out in the context of Frege’s triangle, its vertexes represent three sets of different nature: material objects, ideal concepts, and signs. We suggest separating relations inter elements of one set, and a mapping describing the correspondence between the elements of different sets. Three sides of Frege’s triangle can be interpreted as mappings: conceptualization - assigns an object to a concept, semantic - link a concept to a sign, representation - connects a sign of a model to an object of a subject area. An analysis of mappings inter three sets of different nature allows making a judgment on model quality. In the case of computer modeling notations all mappings should be morphisms that carry the relations between the elements of one set to the relations between the elements of the other. Finally, we make a proposition that syntax and semantics of a computer modeling notation can be formalized by use of Bunge-Wand-Weber upper-level ontology.

Igor Fiodorov, Aleksandr Sotnikov

Cognitive Information Technologies in Control Systems

Frontmatter
Spectral MIMO H∞-Optimization Problem

This paper is devoted to the problem of spectral H∞-optimal control synthesis for LTI plants. This problem is significant in situations when spectral features of the external disturbance are not completely given. H∞-optimization problem has been paid very serious attention for the past decades and it can be solved with the help of well-known numerical methods, based on Riccati equations or linear matrix equations (LMI), but these approaches are not absolutely universal, because there are irregular situations, such as problems with no noisy measurement signal. Implementation of the spectral methods, based on parameterization of the set of transfer functions of the closed-loop system and polynomial factorization makes possible to avoid mentioned difficulties, but most of the research in this area are devoted to the plants with scalar control signal that significantly restricts its area of implementation. The approach, proposed in this paper, makes possible to overcome these difficulties. Some theoretical aspects, including matrix Nevanlinna-Pick rational function interpolation, are discussed and computational scheme for the optimal control design is formulated. Applicability and effectiveness are illustrated by the numerical example with implementation of MATLAB package.

Evgeny Veremey, Yaroslav Knyazkin
Path Planning of Mobile Robot Based on an Improved Ant Colony Algorithm

The ant colony algorithm (ACO) is an intelligent optimization algorithm inspired by the behavior of ants searching for food in the nature. As a general stochastic optimization algorithm, the ant colony algorithm has been successfully applied to TSP, mobile robot path planning and other combinatorial optimization problems, and achieved good results. But because the probability of the algorithm is a typical algorithm, the parameters set in the algorithm is usually determined by experimental method, leading to the optimization of the performance closely related to people’s experience, it is difficult to optimize the algorithm performance. Moreover, the traditional ant colony algorithm has many shortcomings, such as long convergence time and easiness to fall into the local optimal solution. In order to overcome these shortcomings, in this paper, a large number of experimental data are analyzed to obtain the main appropriate parameters of the ant colony algorithm, such as the number $$ M $$ of ants, the number $$ K $$ of iterations, the influence factor $$ \alpha $$ and $$ \beta $$, and a new pheromone updating method that is related to the sine function is proposed in this paper, the simulation results show that the improved algorithm can accelerate the speed by 60%, and the global optimal solution can be found more easily than the original ant colony algorithm.

Chong Pan, Hongbo Wang, Jinxin Li, Maxim Korovkin
Algorithm for Customers Loss Minimization with Possible Supply Chain Disruption

Continuous development of companies in various sectors of the economy has led to an expansion of the processes they implement. With the increase in the number of logistic processes of the company, there is a need for their optimization, with a subsequent reduction in the costs of their provision. Logistic costs can reach up to forty-five percent of the company’s general administrative expenses. As of today, there are many approaches to setting and solving the problem for optimization of logistics systems. In this paper, the authors suggest a set of different strategies for selecting suppliers in the market, taking into account a number of constraints, in particular, the supplier’s required reliability, as well as the goods pricing strategy, provided that such goods are competitive. The main objective of the research is to solve the problem of the optimal choice of the quantity of goods in the order with supplier losses minimization. The goal is achieved by choosing the optimal or the so-called economical order size, at which the supplier’s losses will be minimal. To determine the optimal order size, a modified Harris-Wilson formula for the economic order quantity is used. Two types of the problem are considered: a model in the absence of supply disruption and a model with probable supply disruptions. Scenarios of a customer’s behavior are suggested for possible supply disruptions, such as the supplier equipment failure or transportation problems. Using the proposed algorithm, the customer can develop a relevant stock forming strategy.

Elena Lezhnina, Yulia Balykina, Timur Lepikhin
Regulation of the Crowd Dynamic Objects Flight Through the Narrow Tunnel

Mathematical models of dynamic processes described by systems of differential-difference equations of delay type with a linearly increasing aftereffect are considered. Such a class of systems has been investigated significantly worse than the class of systems with limited aftereffect. However, in recent times many new applications have appeared in the controlled dynamic processes described by such systems. This paper is devoted to the study of the asymptotic stability of the zero solution of homogeneous differential-difference systems with several concentrated linearly increasing delays. The theoretical basis of the study is the approach of B.S. Razumikhin, which made it possible to obtain coefficient sufficient conditions for asymptotic stability. Further analysis of the asymptotic stability of nonlinear systems with unlimitedly increasing delay can be based on an adaptation of the Lyapunov-Krasovsky approach. As an application, we consider a dynamic model of the span of a large family of UAVs over a limited tunnel, which is described by a system of differential-difference equations with concentrated constant and linearly increasing delays. The approach used in the work can be applied to the analysis of stability, including systems with distributed delay.

Alexey Zhabko, Olga Chizhova, Oleg Tikhomirov
Financial Risk Assessment in the SiU8 Futures Trading Using Neural Network Based on the SAR-Method

The theoretical basis for the SAR-model applied for calculating the financial risk of time series of exchange instruments has been considered. The article describes the AI neural network for assessing financial risk in the course of exchange trading in a SiU8 US dollar futures contract on the Moscow Exchange by the MoExSAR method in order to minimize the risk. There has been suggested and proven a hypothesis that the Kohonen map neural network enables forecasting the extent of loss in the course of exchange trading in a SiU8 US dollar futures contract on the Moscow Exchange by the MoExSAR method, as well as predicting the financial instrument price, which is of practical importance for successful trading.The relevance is due to the fact that in the conditions of increasing volatility in the USD futures contract price, the risk of financial losses and its value increase, with the artificial intelligence systems applied being of great importance to forecast financial risk using the SAR model.Assessing the extent of loss on financial risk using the neural network forecast of the financial instrument price has practical significance in the conditions of market uncertainty. The neural network that allows predicting both the SiU8 futures contract price and financial risk losses in the trading process has been successfully developed.

Nikolay Lomakin
Some Questions of Trajectory Control of Quadrotor Motion

The paper presents an approach to provide the motion of a quadrotor along a given trajectory under the influence of step perturbations. The proposed approach is based on the use of a speed regulator, introduced in the works of Veremey E.I. as one of the elements of a special multi-purpose structure controller. Due to its structure, the speed controller gives for the closed-loop system the property of astatism for regulated variables, which means that the error between the actual motion and the desired trajectory converges to zero in the presence of step disturbances. In this work the controller that provides a quadrotor motion along a given trajectory, is based on four linear simplified mathematical models. Each of such simplified models describes the motion for one of the regulated variables and is used to design control law for each specific scalar regulated variable, that gives the astatism property for this variable. As a result the controller is formed to regulate the position in space and the yaw angle of quadrotor. In the end the paper presents graphs of transients of changes in position and orientation in the space under the action of the proposed control to illustrate its effectiveness; simulation is carried out in MATLAB-Simulink environment for a particular quadrotor model.

Natalia Zhabko, Timur Lepikhin, Maxim Korovkin
Dynamics Characteristics Optimization for the UAV Ensemble of Motions

The tasks of multicopters control are considered as an area for application of modern theoretical approaches to the control system design. The paper considers the multicopter control system, which includes a subsystem of equilibrium stabilization and an executive subsystem. The executive system is responsible for changing the position of the apparatus in space according to the commands of the operator. The program list of control commands and a wide range of perturbations affecting the multicopter are forming a whole ensemble of movements of the UAV. The equations of the control system expand the vector of states of the multicopter. The coefficients in the control regulator are adjusted to provide the desired dynamics characteristics of the ensemble of movements. The novelty of this approach is that the problem of simultaneous optimization of the executive and stabilizing subsystems has been presented. Ensemble of program and perturbed motions of the multicopter is described by guarantee upper estimations. The results of practical calculations for a particular UAV are presented. The simulation demonstrates the ensemble dynamics before and after optimization. Transient diagrams show an optimized response to the operator’s control commands. The analytical part of the work was carried out for a multicopter with an arbitrary even number of screws more than three.

Sergey Zavadskiy, Timur Lepikhin
Application the Evolutional Modeling to the Problem of Searching the Optimal Sensors Location of Fire-Fighting System

The aim of the study is to develop an evolutionary algorithm for the optimal sensors’ location in multi-sensory systems for early detection of fires in rooms. The legislative acts regulating the sphere of fire safety in Russia are given. It is indicated that there is no justification for choosing the location of fire detectors. An evolutionary algorithm for the optimal placement of sensors controlling such fire factors as temperature, concentration of carbon dioxide and visibility, depending on the density of the smoke. The article describes the process of developing an evolutionary algorithm and its application to the problem of finding the optimal location. Methods of evolutionary modeling, such as genetic methods, genetic programming, methods of particle swarm optimization and methods of “colony of ants”, and their basic applications are described. The main operators of the genetic algorithm, such as reproduction, crossing and mutation, and their modifications are considered. We propose our own modification method for applying it for the current task. In the supercomputer center of the Peter the Great Polytechnic University, we model fires of several types of materials: rags, gasoline, oil, diesel fuel, electric cables. The simulation results were used as data to verify the algorithm. The results of testing the algorithm on model data are presented. It shows the gain in response time of the fire extinguishing system to the occurrence of fire when the sensors are located, calculated by the genetic algorithm, in comparison with the usual uniform arrangement.

Galina Malykhina, Alena Guseva
Adaptive System Monitoring of the Technical Condition Technological Objects Based on Wireless Sensor Networks

An analysis was made of existing control systems and telemetry. There are requirements for modern geographically distributed telemetry systems. Simulation of an adaptive system for monitoring the technical condition of technological objects based on wireless sensor networks is considered as a decomposition of particular problems of forming, processing and transmitting measurement information using the methods of the theory of random processes, queuing theory and methods of the theory of signal transmission. We described a method for reducing the redundancy of measurement information in the monitoring systems of the technical condition of technological objects due to its operation in emergency and pre-emergency alarm modes, as well as taking into account external factors. It has been determined that the priority of service requests coming from sensors is characterized by the growth dynamics of the monitored parameter to the established tolerance, which is confirmed by the application service model. It is shown that the system for monitoring the technical condition of technological objects can be made in the form of application service systems, which are a queuing system that registers the flow of accident signals - applications and determine their priorities. Based on the analysis of the use of wireless sensor networks, the possibility of their integration into a simulated system for monitoring the technical condition of geographically distributed control objects is shown. It is shown that for an ordered polling of the elements of the sensor network, a polling system with dynamically changing parameters can be used. A group polling method is described in various polling modes with a fixed number of sensors registering an alarm signal, which makes it possible to significantly increase the efficiency of testing, taking into account possible errors in the transmission of measurement information.

Aleksey Vinogradenko, Pavel Budko, Vladimir Fedorenko
Disaster Tolerance of On-Board Control Systems for Ground Robots

Modern ground robotic systems can be operated in harsh conditions, as well as in combat conditions, which can provoke numerous equipment failures, both natural and intentional, as a result of which the question of ensuring the disaster tolerance of the control system of the robotic complex is raised. An essential, but not resolved issue of creating control systems of robotic systems is equipping with computer equipment that is developed on the basis of domestic microprocessors and domestic software. This article proposes methods and algorithms that are the basis for the creation of disaster-tolerant control systems for ground robots based on domestic computers and software. The authors have developed algorithms for increasing the reliability of onboard control systems to catastrophic faults and numerical results of increased reliability of these systems using the developed methods were obtained. The use of domestic computers and certified software “Elbrus” allows us to talk about the prospects of solving problems of import substitution in the field of robotics. The authors believe that the following provisions and results are new in this work: the definition of the onboard computer system disaster tolerance is introduced, algorithms are developed to ensure the disaster-tolerance of the onboard computer system using the computers and software series “Elbrus”.

Nikita Bocharov, Vasiliy Vorobushkov, Nikolay Paramonov, Oleg Slavin
Application of the Asymptotic Observers for the Stabilization of the Time-Delay Linear Equations

Stabilization of the time-delay linear systems by using the static feedback is possible only for the limited value of the time delay in the control channel. In case of the exceeding such limit the further stabilization is impossible. However, the delay limit could be increased by using the number of asymptotic observers of the special kind. The basic idea lies in the equivalence of any realization of the system with certain transfer function which leads to the possibility of distribution of the delay by the several observers. Each observer has lesser delay value so overall limit is decreased. Theoretically, if there are enough observers it is possible to stabilize the system with arbitrary big delay. Moreover, such approach can improve dynamical characteristics in cases where delay value is small enough for the system to be stabilizable. The paper describes the structure and the synthesis method for such observers. The results of the experiments with the computer model are given for the demonstration of the derived regulator’s efficiency.

Ruslan Sevostyanov, Liliya Shayakhmetova
Multi-purpose Control of a Moving Object Using Computer Vision Algorithms

The article is devoted to the design of control systems for moving objects using computer vision algorithms. The relevance of this research area is associated with the increasing use of autonomous vehicles for solving practically important tasks without human intervention. However, many of these tasks are impossible or inefficient to solve without using of visual information.The problem of visual positioning of a moving object equipped with an onboard video camera is considered. The purpose of the control is to provide the desired position of some observed object in the image plane of the camera. A mathematical model of the joint dynamics of a moving object and a set of observed points in the image plane is derived. Such joint dynamics are taken into account in control design because the camera, mounted on board, has restrictions on freedom of movement in space and on the speed of these movements.A multi-purpose approach to the synthesis of the control law is proposed, allowing to ensure the fulfillment of a set of requirements for the quality of processes in a closed-loop system in various regimes. The choice of adjustable elements of a multi-purpose structure is discussed. The application of the approach is illustrated by an example of control of a wheeled robot. The results of simulation performed in MATLAB/Simulink environment are presented.

Margarita V. Sotnikova
Stabilization of the Underactuated Robot on the Visual Trajectory

The article considers the problem of moving and stabilizing underactuated wheeled robot on the visual curve in the motion plane. The curve is detected by the video camera mounted on the robot. The task is solved with the help of the approach named visual servoing which uses the visual information in the feedback. The aim of the visual serving is to minimize the difference between desired and the actual position of the set of the points on the image. The main feature of the proposed solution is considering a number of requirements to the robot’s dynamic including the reaction on the presence of the external disturbances. Thereby the regulators of special kind called multipurpose structure are used which makes possible to decompose the basic set of requirements into smaller independent tasks. Additional complication is the underactuated nature of the considered robot. Efficiency of the derived regulator is shown through the experiments with computer model.

Ruslan Sevostyanov
Simplified Rotor Angular Velocity Estimation for a Permanent Magnets Synchronous Motor by Current and Voltage Measurements

This paper is devoted to the rotor angular velocity estimation of the permanent-magnet synchronous motor (PMSM). It is an actual problem, for example, in sensorless control. We consider a classical, two-phase model in the stator frame of the unsaturated, non-salient PMSM in the state-space representation. All parameters of the model except the stator windings resistance and rotor inertia are assumed to be known. On the first step, we find the relation between measured signals and angular velocity and excluding the unknown parameters of the motor. This relation is simplified using properties of the measured signals and represented as the first-order regression model, where the unknown parameter is the angular velocity. On the next step, we propose the estimation scheme, which is based on the gradient descent method. The efficiency is illustrated through a set of numerical simulations.

Anastasiia O. Vediakova, Alexey A. Vedyakov

Big Data and Applications

Frontmatter
On Data Analysis of Software Repositories

This article discusses the analysis of software repositories using data analysis methods. A review is made of methods for analyzing programs based on information retrieved from the program code stored in code repositories. A review is made of methods for analyzing programs based on information retrieved from the program code stored in repositories. The article reviews the works that apply methods of classification, clustering and depth learning in software development. For example, for classifying and predicting errors, changing the properties of code in the process of its evolution, detecting design flaws and debts, assist for code refactoring. The main ultimate goal for all models is, of course, an automation of programming. In practice, we are talking about more simple tasks. This includes, for example, information retrieval (program code), error prediction, clone detection, link analysis, evolution analysis, etc. Firstly, we discuss recurrent neural networks and their deployment for the analysis of software repositories. In the simplest case, recurrent networks model a programming language as a sequence of characters. Also, the paper covers clustering and topic modeling.

Dmitry Namiot, Vladimir Romanov
Development of BI-Platforms for Cybersecurity Predictive Analytics

The distribution of analytical information systems, the so-called BI platforms (BI – business intelligence) in leading state and commercial companies, allows the top-managers and analysts to work in real time with large information volumes (Big Data). However, the issue of choosing tools for secure access to these new sources of corporate data becomes relevant. The trend of recent years is the integration of business security software products, and the transition from specialized analytical solutions to multipurpose BI platforms. The article considers approaches to providing security in information systems of banks and electronic commerce using multipurpose BI-platforms. The analysis of key problems in arrangement of the Big Data was performed and the problems of implementation, operation and maintenance of BI systems were identified. The analysis of the advantages of the systems of the class Advanced Analytics (Big Data, NoSQL-storages, processing of streaming data on-line) over traditional BI-systems (ETL + SQL + reports) is made. The system features of the BI-platform of security are considered: typical agents and formats of data loading agents, possible types and model of data, the structure of the computing cluster and the gateway. An algorithm for detecting security incidents is given. It has been proven that in order to reduce the dependence level on foreign technologies, the public sector should completely switch to work with Russian software and hardware platform developers. In turn, the commercial segment should also facilitate the transition to Russian developments and more actively use them in their activities.

Sergey Petrenko, Krystina Makoveichuk
Improving the Target Quality Chat-Bots on the Basis of Linguistic Metametric Text

The paper discusses the methods and technologies used for chat bots, taking into account the specifics of Internet communications, for conscious dialogue with a given goal. The methods of formalizing the creation of pages of virtual personalities are discussed in detail. Information presentations of speech behavior meta-metrics for the implementation of a chat bot efficiency model based on the analysis of short messages are considered.As sources of attributive sense formation, not values in the generally accepted understanding, but individually-specific categorical scales, serve as an instrument for identifying, classifying and evaluating the subject’s significant characteristics of objects and phenomena of virtual reality. The goal of creation of models by the subject (agent) is formalized, which consists in obtaining a forecast, that is, a new information object (message or algorithm of actions).The phenomenological correspondence with the results of the research of SP was established by S.P. Rastorguev in the part of the model for transforming the virtual world. A technological solution is proposed on the basis of the search model of the associative context in the semantic kernel.

Dmitry Zhukov, Yury Korablin, Vyacheslav Raev, Dmitry Akimov
New Methods of the Cybersecurity Knowledge Management Analytics

The article discusses the possibilities of using Master Data Management (MDM) technology to solve the problem of developing a corporate (institutional) state system segment to detect, prevent and eliminate the cyber - attack consequences (hereinafter - SOPKA). Typical objectives of semantic cyber security MDM is identified in article. The semantic cyber security MDM means a data management system that operates rules of the object behavior and interaction in cyberspace to solve the SOPKA problems in order to prevent the protected critical infrastructure transition to catastrophic states. Cyber security ontology (meta-ontology) as the knowledge presentation way about qualitative characteristics and quantitative patterns of information confrontation is proposed. Shown, that by combining cyber security data from various external and internal information sources and corresponding rules to detect, prevent, and eliminate the cyber-attacks consequences into a single semantic domain model, it is possible to build the required intellectual (and, in the future, cognitive) information space, then to develop the appropriate artificial cognitive agents and the corresponding intelligent “semantic cyber security MDM” software and hardware complex to support SOPKA operations as a whole. The basic development principles of the “semantic cyber security MDM” software and hardware complex are formulated. The possible architecture of the “Warning-2016” software and hardware complex that is intended for early cyber-attack warning on corporate and institutional information resources of the Russian Federation is shown. It is based on SAP HANA, and the required semantic MDM is implemented on the basis of SAP NetWeaver Master Data Management (SAP NW MDM).

Sergey Petrenko, Krystina Makoveichuk, Alexander Olifirov

The Internet of Things (IoT): Standards, Communication and Information Technologies, Network Applications

Frontmatter
On a New Approach to Neighbor Discovery as Data Sharing Tool

In this paper, we propose and discuss a new approach to data sharing among mobile subscribers. Our idea is to use the neighbor discovery phase in wireless networks. It simulates a peer-to-peer network that will work without any telecommunication infrastructure. A single mobile phone (smartphone) will be sufficient both for creating a node of such telecommunication network and for publishing (distributing) information. What is important here, the usage of the standard neighbor discovery mechanism does not assume the preloading some mobile applications. Our idea is to share user-defined information during the basic neighbor discovery phase. In this case, the parties involved in the process should be able to read the shared data directly from the process of discovering for neighboring nodes. Our proposal is the further development of ideas related to context-aware systems based on network proximity principles.

Dmitry Namiot, Manfred Sneps-Sneppe

Smart Cities: Standards, Cognitive-Information Technologies and Their Applications

Frontmatter
Research of Urban Residents Involvement in Environmental Processes Using a Mobile Environmental Application

Recently there are works devoted to the possibility of using mobile applications for monitoring the environment and helping citizens in certain situations related to the environmental condition. The use of these applications by urban residents will allow them to be involved in environmental processes and, consequently, increase the environmental and social responsibility of citizens. The aim of the work is to study the increase of citizens’ involvement in environmental processes using a mobile environmental application that displays information on air pollution in the city districts. To assess the current behavior of respondents in environmental situations, as well as behavioral changes when using mobile applications, a questionnaire consisting of 5 sections has been developed. An experiment was conducted with the participation of a group of respondents. The results of the analysis have showed the influence of factors and indicators on the results of answering questions. 5 clusters are distinguished in which the behavior of respondents differ. Accordingly, for each cluster a level of social responsibility of respondents can be assessed. It is shown that all respondents can be divided into 3 groups: the group of respondents No. 1 for whom using of the mobile application is not able to involve them in environmental processes, the group of respondents No. 2 for whom using of the mobile application can strongly involve them in environmental processes, the group of respondents No. 3, for which the use of mobile applications can involve them in environmental processes, but not to a great extent.

Alexander Varnavsky
Using Augmented Reality Technology to Improve the Quality of Transport Services

The problem of marking the area of the preferred route by means of mobile technology of augmented reality for public transport routes is considered. The analysis of modern theoretical and applied solutions of using the technology of augmented reality in mobile applications is carried out. The task is to reduce the time interval for the search for the route of public transport and the decision to choose a vehicle for an ignorant urban resident, in the conditions of a limited time resource. A theoretical method for marking the routes of public transport on the basis of the transport utility function is proposed. An algorithm is developed for marking the routes of public transport. The software implementation of the algorithm in mobile execution is performed in the Unity and Vuforia environment, using the Yandex API. The problem of finding information on the routes of passenger transport and the problem of improving the perception of transport information through its visual display on a mobile device are solved. A comparison is made between the speed of the developed technology and the existing solutions by the time criterion. Recommendations on the further use of the developed approaches are discussed.

Dmitriy Skorokhodov, Yaroslav Seliverstov, Svyatoslav Seliverstov, Ilya Burov, Eugenia Vydrina, Nikolay Podoprigora, Natalia Shatalova, Victoria Chigur, Anastasia Cheremisina

Cognitive Information Technologies in the Digital Economics

Frontmatter
About the Digital Economy Software

The article discusses software tasks that should be resolved to implement the Digital Economy of the Russian Federation Program. The DE program identifies nine major digital technologies crucially depending on highly developed software. The article notes that information infrastructure is a crucial element of the Digital Economy. But is such an infrastructure created in Russia? The important point here is the advanced development of telecommunication networks of the new generation, providing any user anywhere universal broadband access to an unlimited range of services. Without the advanced development of these networks, the ubiquity of IT and the global Internet is impossible, since the Internet is the sum of technologies working on top of a telecommunication network.The article proceeds to the question of choosing the architecture of information systems. This term refers to the architecture of an enterprise, a sector of a national economy, a ministry, or even an entire country. Software in all cases can be the same (similar), and in order to save we should choose a single architecture. The article discusses the Zachman model, DoDAF architecture, Lifecycle Modeling Language and criticizing of these models. The main problem is the complexity of the proposed solutions. Further in work questions of programming of systems of the Internet of Things are considered. Here we are talking about the development and adoption of a standard architecture that will allow us to re-use the developed software.

Manfred Sneps-Sneppe, Dmitry Namiot, Vladimir Sukhomlin, Elena Zubareva

Digital Transformation of Transport

Frontmatter
Big Data Processing of Commodity Flows in the Transport and Economic Balance of the Russian Federation

Planning and forecasting transportation using econometric and mathematical tools based on the spatial input-output tables and knowledge of transportation effects is an important task for improving transport and regional economics. The spatial input-output tables of Russia further called the transport and economic balance of the Russian Federation aggregate the actual and forecast volumes of freight traffic between the regions of the country by rail, road, inland water and maritime transport by types of commodities. The actual information on freight traffic covering the period from 2007 to 2017 bases on statistics for industrial production, domestic and external trade, construction, agriculture, energy, as well as transport statistics and takes into account the relationship between production and consumption, import and export of goods. The features of the Russian statistical accounting specify the order of Big-data processing while calculating the balance.The transport and economic balance of the Russian Federation provides the forecast of interregional trade flows, transportation infrastructure loading, changes in transport network capacity, transportation costs and time. The forecast of cargo load and interregional freight flows covers the period up to 2030. The forecast model uses Russian economy growth scenarios of the Ministry of Economic Development of Russia, as well as regional economic development scenarios including changes in the technological and transport connectivity of main cargo generating industries.

Oleg Evseev, Vasily Murashov, Alexander Zaboev, Anton Zemtsov, Victor Buslov, Alexander Shubin, Alexander Schirov, Anton Shubin, Anton Urazov, Elena Anikina
Mobile Technologies in Intelligent Transportation Systems

An analysis is made of the use of cellular communication as part of intelligent transportation systems to collect information on traffic flows and population mobility. The model of the monitoring system of urban population social activity is created. The reliability of the model is demonstrated with the City Navigator mobile application. The application is developed in the Xcode 9 environment in Swift3 language, and the data analysis system - in Python 3.X. The application serves as the information source for preferential routing, enables to assess the quality of the urban system facilities and take into account the infrastructure, transport, needs, locations, photo-registration and users GPS tracks. User’s GPS tracks are tied to the classifiers of the Unified System of Classification and Codification of Technical and Economic and Social Information (USCCTESI) and the International Classification of Diseases of the Tenth View (ICD-10). The practical guidelines for the further use of mobile applications as part of intelligent transportation systems are indicated.

Igor Malygin, Yaroslav Seliverstov, Svyatoslav Seliverstov, Mikhail Silnikov, Roza Muksimova, Gleb Gergel, Victoria Chigur, Shakib Fahmi
Digital Railway and How to Move from GSM-R to LTE-R and 5G

The paper is devoted to telecommunication services for digital railways. We discuss a transition from GSM-R to LTE-R and 5G technologies. As a practical use case, we target urban railways development in Moscow, Russia. According to the European Commission, digital railways development should create so-called connected railways by providing reliable connectivity for safe, efficient and attractive railways, enhancing customer experience. It should provide added value for customers, increased capacity by enhanced reliability, efficiency, and performance of railways. In this connection, we discuss the critical elements of 5G deployment and the practical steps to move from the current telecommunication services to 5G. As historical examples, we are considering the largest projects of the transformation of the telecommunications infrastructure. As basic examples for GSM-R transition and switch to digital railways, we discuss Moscow Central Ring and Moscow Central Diameters. The paper highlights several tasks for telecom providers in Russia. In particularly, it is the development of the GSM-R network architecture taking into account existing networks, including interaction with an intelligent network, as well as the need to upgrade existing networks.

Manfred Sneps-Sneppe, Dmitry Namiot

Applied Optimization Problems

Frontmatter
Basic Concepts of the Elective Course on the Hard Computing Problems

We consider the material of the elective course for the young students, and briefly describe both so-called hard problems and some methods necessary to develop programs for their implementation on the computer. For this, we are considering several real problems of discrete optimization. For each of them we consider both “greedy” algorithms and more complex approaches. The latter are, first of all, are considered in the description of concepts, understandable to “advanced” young students and necessary for the subsequent program implementation of the branches and bounds method and some associated heuristic algorithms. According to the authors, all this “within reasonable limits” is available for “advanced” young students of 14–15 years.Thus, we present our view on the consideration of difficult problems and possible approaches to their algorithmization – at a level “somewhat higher than the popular science”, but “somewhat less than scientific”. And for this, the paper formulates the starting concepts which allows one of such “complications” to be carried out within the next half-year.

Boris Melnikov, Elena Melnikova, Svetlana Pivneva
Backmatter
Metadaten
Titel
Convergent Cognitive Information Technologies
herausgegeben von
Vladimir Sukhomlin
Elena Zubareva
Copyright-Jahr
2020
Electronic ISBN
978-3-030-37436-5
Print ISBN
978-3-030-37435-8
DOI
https://doi.org/10.1007/978-3-030-37436-5