DESTRUCTIVE INFORMATIONAL AND PSYCHOLOGICAL INFLUENCE IN SOCIAL NETWORKS
V.P. Okhapkin, E.P. Okhapkina, A.O. Iskhakova, A.Y. Iskhakov
The article discusses the problem of the destructive information influence in social networks revealing. It is noted that the tasks that are associated with the rapid detection of destructive information influence are prerequisites for the development and improvement of methods and means for identifying such influences in social networks. To understand the social dynamics of social networks groups we consider: the communication model proposed by Theodore Newcomb, Kurt Levin’s “planar map”, and Fritz Haider’s theory of cognitive balance. UN documents on the counteraction of the use of the Internet for the extremist purposes and radicalization were analyzed. The role of the cognitive approach to the analysis of social network messages and the main scenarios implemented by influence actors in texts aimed at different audiences are considered. The study presents a systematic approach to the task of designing a multi-agent platform. Special attention is paid to the block of pattern analysis of user’s messages in social networks both from the position of mathematical modeling and social dynamics. The article describes the architecture and methods of the multi-agent system for the destructive information and humanitarian impact detection. The system consists of the administration interface, subsystems for the multi-agent system administration and agents management, clustering agents, network messages analysis and dispersion analysis. The description of the main blocks of agents and subsystems is given.
Keywords:multi-agent technologies, cluster analysis, information security, aggression, radicalization, machine learning, personality, information and psychological impact destructive informational impact, socio-cyberphysical system.
COMPARISON OF THE ACCURACY OF EXPERIMENTAL DATA APPROXIMATION USING THE LEAST RELATIVE SQUARES METHOD WITH THE LEAST SQUARES METHOD
A.B. Golovanchikov, M.K Doan, A.B. Petrukhin, N.A. Merentsov
The results of comparing the accuracy of approximation of experimental or tabular data obtained using the standard method of least squares (LSM) and the proposed method of least relative squares (LRSM), for example, a given table dependence of the viscosity of a water-glycerine solution on the mass concentration of glycerol. The advantage of the latter is shown as the sum and average values of the local relative deviation of calculated data of viscosity of the desired solution obtained by LRSM, with similar data obtained by standard LSM and maximum values of these relative deviations. So, calculated using LSM average relative deviations of theoretical viscosity of an aqueous solution of glycerin from the specified table, in absolute value equal to 12.9%; LRSM of 5.8%, i.e., below 2 times. Accordingly the largest relative deviations in the LSM are 17.9%, and LRSM – 10.6 %, that is, reduced by 68%. It is proposed to determine the conditional values of parallel experiments based on the experimental data of the main experiment. To do this, the calculation of conditional numerical values of the i-th parallel experience is determined by the method of piecewise linear approximation of i-1 and i+1 numerical values of the main experience or table data. A correlation analysis is performed to determine the correlation coefficients, reproducibility, adequacy, and significance of the coefficients of the resulting regression equation.
Keywords:linearization, approximation, absolute and relative deviations, LSM and LRSM, correlation coefficient, reproducibility, adequacy, significance.
SITUATIONAL MODEL OF DECISION-MAKING SYSTEM BASED ON ENVIRONMENTAL MONITORING DATA IN THE CONDITIONS OF URBAN DEVELOPMENT
I.G. Ivanova, A.D. Danilov, K.Y. Gusev
The paper presents a model of a decision-making system based on environmental monitoring. Air pollution in modern cities is a very urgent problem that is solved at various levels of management. The largest source of pollution is the road network. However, managing traffic flows within urban areas is an impossible or difficult task because of the existing infrastructure of the city. Therefore, we propose a system that, based on the results of training in existing cities, will form recommendations for the development of urban areas, taking into account the level of air pollution. The paper proposes a fuzzy system for supporting decision-making in the conditions of urban development. The article shows the formation of a knowledge base based on retrospective data to improve the accuracy of forecasting, as well as from the simulation environment for increasing the speed of sensing. Ranked recommendations for reduction of pollution of atmospheric air under conditions of development of urban areas. In the fuzzy situational model, a method is proposed for selecting the closest, equal situation from the knowledge base, taking into account the maximum value of the degree of belonging. The developed models can be used as a means of improving the quality of management and decision-making in the conditions of urban development.
Keywords:decision-making, environmental monitoring, fuzzy systems.
ALGORITHMIZATION OF MULTI-AGENT LEARNING WITH REINFORCEMENT IN THE GAME-THEORETIC PROBLEMS OF FINDING OPTIMAL STRATEGIES
UDC 004.8, 519.83
E.S. Sokolova, K.A. Razinkin
The relevance of the topic of the article is due to the growing interest in multi-agent simulation of dynamic systems of various physical and social nature. Currently, the concept of an intelligent agent as a simulation model of the behavior of the active element in complex situations and strategies for interaction with other active elements and the environment to achieve the goal is coming to the fore. In the general concept of an intelligent agent and agent technologies for simulating the interaction of dynamic objects in the direction of achieving a goal, a method of structural-parametric modeling of intelligent agents and multi-agent systems with algorithms for identifying and predicting the state of agents, as well as software for multi-agent simulation models of production, social and marketing systems. In this regard, the relevance of the topic is determined by the need to increase the effectiveness of multi-agent training with reinforcement in the game-theoretic problems of finding optimal strategies. The article describes multi-agent learning algorithms with reinforcement in game-theoretic problems, such as minimax-Q, when minimizing possible losses from those that cannot be prevented by an agent when events develop according to his worst-case scenario and WoLF-PHC (Win or Learn Fast – Policy Hill Climbing), which implements a policy of quick gain or quick training. In this case, the WoLF-PHC algorithm, which is a modification of the PHC algorithm. The algorithm has different learning speeds when winning an agent and a pro-game. Agent training rates vary to maintain algorithm convergence. The main idea of this algorithm is to learn quickly, losing, and slowly, winning. The advantages and disadvantages of these approaches, the principles of their modernization and the possibility of implementing these approaches in simulation environments are shown.
Keywords: multi-agent learning, reinforcement learning, stochastic games, equilibrium strategies.
USING THE METHODS AND ALGORITHMS FOR DATA ANALYSIS AND MACHINE LEARNING IN UEBA/DSS TO SUPPORT MANAGEMENT DECISION-MAKING
P.A. Savenkov, P.S. Tregubov
The aim of this study is to develop mathematical and software for detecting abnormal user behavior based on an analysis of their behavioral biometric characteristics to create new ways to provide analytical data to the analyzing service with a description of why the identified actions are considered abnormal. The subject of the study is the machine learning methods used in UBA / UEBA (User Behavioral Analytics / User and Entity Behavioral Analytics), DLP (Data Leak Prevention), SIEM (Security information and event management) systems. Object of study – UBA / UEBA, DLP, SIEM systems. This article provides an overview of the applicability of machine learning methods in intelligent UEBA / DSS systems. One of the significant problems in intelligent UEBA / DSS systems is obtaining useful information from a large amount of unstructured, inconsistent data. The methods and algorithms of intelligent data processing and machine learning used in UEBA / DSS systems make it possible to solve data analysis problems of various kinds. The application of machine learning methods in the implementation of a mobile UEBA / DSS system is proposed. This will allow to achieve high quality data analysis and find complex dependencies in them. During the study, a list of the most significant factors submitted to the input of the analyzing methods was formed. The application of machine learning methods in UEBA / DSS systems will allow you to make informed management decisions and reduce the time to obtain useful information.
Keywords: big Data, data science, software, machine learning information system, UEBA, DSS.
TYPOLOGY OF RELATIONSHIPS BETWEEN CONSTRUCTION PROJECT PARTICIPANTS IN THE INTERESTS OF RESOLVING CONFLICTS OF INTEREST BETWEEN THEM
S.I. Sigarev, V A. Chertov
A typology of relationships between participants in construction projects is given, aimed at resolving conflicts of interest between them. It differs from the known typologies of “common sense” in two ways. First, it is based on taking into account the formal factors of functional, resource and managerial nature that take place in the process of implementing projects of this type. Secondly, it reflects the main features of modern construction projects, namely: their pronounced economic orientation; the presence of resource, social, environmental, historical, cultural, and other restrictions; the structural complexity of the organization of a team of performers with conflicting relationships between them; a wide range of used construction, communication, fire, environmental, and other technologies. As a result of the study, a scheme is presented that identifies 16 types of possible relationships between participants in construction projects grouped by functional, managerial and resource characteristics. This typology can serve as a starting point for solving the problem of rational organization of construction work in the context of a conflict of interests and has the applied value that opens the way to the construction of mathematical models and computer software for decision support in the search for compromises between conflicting participants in construction projects.
Keywords: construction, project, conflict of interest, relationships, typology, functions, resource, management.
MODELING OF THE ULTRAFILTRATION PROCESS ON ROLL MEMBRANES IN A CENTRIFUGAL FIELD
A.B. Golovanchikov, M.C. Doan , N.A. Merentsov
The process of ultrafiltration on roll-type membranes installed in the rotor of a filter centrifuge of a special design that provides atmospheric pressure in the zone of filtrate formation behind the membrane and centrifugal pressure in the zone of retant filtration to the membrane is considered. Equations are obtained for calculating the performance of filtrate and permeate and the concentration of solute molecules in them. An example of calculation is given in comparison with the installation of a single layer of sheet membrane on the side wall of a perforated rotor. The results of numerical calculations of the main parameters of the process of ultrafiltration of an aqueous acylase solution using the developed algorithm at the rotor rotation speed ω = 100 rad/s, the rotor radius Rn = 0,25 m and the membrane width b = 0,5 m show that the area of the roll membrane increases 12 times, and the degree of concentration of the solution almost 6 times, while the permeate consumption increases almost 10 times compared to the sheet membrane laid in a single layer on the wall of the perforated rotor. However, the cleaning of permeate in a rotor with a roll membrane is reduced by almost 12.5 times, since the average concentration in permeate increases from 1·10-5 % to 2,6·10-5 %.
Keywords: ultrafiltration, roll-type membrane, centrifugal field, performance, retant, permeate, concentration.
A SET OF PROGRAMS FOR SOLVING PROBLEMS OF MODELING, OPTIMIZATION AND ASSESSMENT OF STABILITY OF COMPLEX SECURITY OF OBJECTS OF CRITICAL APPLICATION
UDC 004.02; 004.942; 378.1
A description of a set of programs for modeling, optimizing and evaluating the stability of integrated security processes in UIS institutions is given. The complex in the interactive mode of communication with the user allows you to: develop and display in the form of visual diagrams a model of complex security of objects of critical application; evaluate the inconsistency of local security aspects; choose the appropriate method of optimization depending on the degree of inconsistency of local security aspects and threats from malicious users; to optimize the processes of ensuring complex safety of critical application objects in regular, critical and threatening situations by the criterion of minimum deviation from the requirements; to give an integral rapid assessment of the level of safety, using models of additive, multiplicative and dichotomous convolution, as well as convolution based on the theory of non-clear sets; to carry out expert evaluation of local safety indicators at the preliminary stage of optimization; evaluate the sustainability of management decisions taking into account the management style adopted at this facility and the nature of relationships between subordinates. The complex is built on the basis of interactive ideology and differs from the existing disparate software products of similar purpose in that it is implemented as an information and calculation system of dialect type with a single interface and a common database. The complex is implemented in an integrated TURBO PASCAL environment using VISUAL BAISIC, DELPHI, and C++ procedures and functions that are focused on creating applications running Windows 10. It can find practical application as a decision support tool for managing the safety of critical application ergatic systems.
Keywords: critical application object, safety, complex of programs, management decision, stability.
APPROACH TO MATHEMATICAL MODELING OF THE DISTRIBUTION OF THE ACADEMIC LOAD OF THE TEACHING STAFF OF THE DEPARTMENT BASED ON SET THEORY
UDC 004.02; 004.942; 378.1
T.I. Kasatkina, E.V. Bolgova, L.V. Rossikhina, R.V. Kuzmenko
The purpose of the research is to develop an approach to modeling the distribution of educational load, taking into account the features and specifics of each Department and the requirements of the educational organization. The model built on the basis of this approach can be used as an auxiliary tool when compiling the load for each of the departments. The distinctive features of the proposed approach to modeling are such features as the ability to adapt the subject area, which provides the search and implementation of the optimal ratio of discipline-employee of the Department from among the teaching staff; compliance of the report structure with the requirements of the reporting documentation instructions on labor rationing of teaching staff or similar documents of departmental educational organizations; the possibility of using the model for any number of employees staff of the Department and any number of types (number of subjects) and types (classes lecture-type class-type seminars, practical classes, etc.) teaching load of the Department, as well as the possibility of changes outside the classroom and extracurricular load PPP. As research methods and criteria for optimal load distribution, we used the weight coefficients of teaching staff, depending on the type and type of educational work and the matrix of personal weight coefficients of employees. The possibility of using set theory methods in load modeling was also shown. Based on the results of the research, an approach to the representation of the academic load of the Department in the form of sets of sets is proposed. It is shown that the load distribution problem can be reduced to solving an unbalanced modeling problem. A lot of “teaching load of the Department” consisting of many “types of Cathedral work,” many “types of academic work” and many “workers of the faculty of the Department.” The structure of the set of ” types of educational work “is represented as a combination of a subset of” classroom contact work “and a subset of”extracurricular work”. A relational scheme of relations in the load distribution model and its structural units, which are sets, is proposed. The direct and feedback relationships between structural units are shown. A set of weighting factors for the level of professional competence of an employee has been developed and a method for calculating its elements has been developed. At the same time, the method of determining the level of competence of the employee of the teaching staff of the Department by type of work is clearly demonstrated in the form of diagrams. A model for implementing the optimal distribution of academic load between the teaching staff of the Department is proposed based on a comparison of the levels of competence of teaching staff in each discipline from the set of “types of Cathedral work”. As a result of research and development, an approach to the distribution of educational load was proposed, which makes it possible to present the educational load of the Department in the form of sets of sets, and allows to distribute the educational load taking into account the features and specifics of each Department of an educational organization. Calculations of employee competence levels were performed, the results of which are presented in the form of diagrams. As a result, it is concluded that the proposed approach to distribution will allow higher education organizations to significantly reduce the burden on the teaching and administrative staff of the organization, and thus make it possible to increase the time resources for making managerial decisions and performing teaching duties.
Keywords: mathematical model, educational organization, load distribution, discipline, educational load, set, report, department.
STREAM DATA CLASSIFICATION BASED ON BAYESIAN CRITERIA
L.S. Lomakina, A.N. Subbotin
The paper describes the issue of stream data classification. Stream data is described as a set of objects arriving from different sources at random moments of time. It might be a stream of data containing ocean coastal area sensors measure information and describing the parameters of the ecosystem condition, as well, it might be a stream of texts acquired from incoming emails attachments, etc. The Internet contains vast volumes of unstructured information. The lack of organization makes data inconvenient and resource-intensive to work with. Addressing to such an issue considered to be a relevant problem. Classification provides an opportunity to make it easier to work with unstructured information. The paper describes the algorithm for stream data classification based on Bayesian criteria. Text stream data model is proposed. This model allows applying natural language text classification algorithms to stream data. Naive Bayes classifier modification using tf-idf measure for evaluating the proximity of a classified document to a particular class that allows improving the classification quality is proposed. The classifier has been trained using the machine Fund of the Russian language. Software allowing text data stream extraction from the Internet and its classification using the proposed algorithm in real-time scale is proposed.
Keywords: classification, data stream, naive Bayesian classifier, Bayesian criteria.