Category Archives: Issue # 3(26)

INFORMATION RECEIVING IN ONLINE TRAINING PROCESS MANAGEMENT BASED ON COMPLEX OPEN ENDED ASSIGNMENTS SCORING

UDC 005.9
DOI:10.26102/2310-6018/2019.26.3.030

V.A. Latypova


Information gathering stage is one of the most important stages in management. The efficiency of management depends on received information. Information gathering methods depend on an object of management specificity. Testing results are the main information in training process management in training systems. Collected statistics of the testing results is the base for decision-making. A problem occurs when a training course contains tasks, implementation results of which cannot be checked by means of tests. Such tasks are complex open ended assignments. Different methods are used for scoring such tasks in learning management systems and massive open online course platforms. The methods are addressed in the paper. Method classes such as: methods implemented by standard tools of training systems (student self assessment, peer assessment, tutor or external expert manual assessment), methods implemented by extending the functional possibilities of training systems (situational assignment), methods implemented by external programs (special methods for specific domain) are described. Applicability of methods for information gathering in online training process management is identified. Reliable and complete information can be received only by using situational assignment and special methods for specific domain.

Keywords: online learning, information gathering, training process management, complex open ended assignment, scoring technique, situational assignment.

Full text:
Latypova_3_19_2.pdf

CONSTRUCTION OF DECISION RULES USING THE ARTMAP NEURAL NETWORK

UDC 004.032.26
DOI:10.26102/2310-6018/2019.26.3.029

I.L. Kashirina, K.A. Fedutinov


This article discusses the ARTMAP neural network architecture, compatible with a symbolic representation based on IF-THEN rules. In particular, the knowledge gained during the training of the ARTMAP network can be transformed into a compact set of decision rules for classifying the source data, which can be analyzed by domain experts, by analogy with interpreted machine learning methods, such as decision trees or linear regression. Similarly, knowledge in the a priori area presented in the form of IF-THEN rules can be transformed into the ARTMAP neural network architecture. The presence of a preliminary set of rules used in the initialization of the network increases the accuracy of classification and the effectiveness of training. The original set of rules can be supplemented using the learning algorithm ARTMAP. Each rule formed in the process of learning a network has a confidence factor that can be interpreted as its importance or usefulness. The architecture, training algorithms and functioning of the ARTMAP network for the extraction of rules are described in terms of the previously proposed generalized model of networks of the ART family proposed by the authors.

Keywords: neural network, machine learning, adaptive resonance theory, ARTMAP, rule extraction.

Full text:
KashirinaFedutinov_3_19_1.pdf

EVALUATION OF EFFICIENCY OF MANAGEMENT DECISIONS ON SEGMENTATION OF THE MARKET OF SALES OF PRODUCTS PRODUCED BY ENTERPRISES OF THE CRIMINAL EXECUTIVE SYSTEM

UDC 519.6
DOI:10.26102/2310-6018/2019.26.3.027

O.E. Shugay


The article discusses current issues and problems of developing systems for evaluating the effectiveness of managerial decisions on market segmentation at the enterprise level; the classification of mutual influences of market segments is made in order to identify the groups that have the greatest impact on the efficiency of the production and economic activity of the enterprise. The study of these issues showed that it is from the decisions taken at the planning stage that the network can ensure a stable increase in the company’s production indicators. A comprehensive assessment of management decisions made in the field of segmentation of the sales market is an urgent task for every enterprise striving for prosperity. However, as analysis shows, this problem has not yet received a proper solution. In the process of considering the above problem, a mathematical model was described and an algorithm was developed that provides an assessment of the effectiveness of management decisions on market segmentation at the enterprise level. This approach allows you to quantify the effectiveness of management decisions on segmenting the sales market of products manufactured by commercial enterprises, according to the following criterion: a management decision on market segmentation will be effective if the current sales volumes of products in the selected market segments are not less than the specified values. The developed five-stage algorithm is aimed at widespread use by commercial enterprises in the conditions of market competition.

Keywords: efficiency, criterion, mutual influence, model, algorithm

Full text:
Shugay_3_19_1.pdf

CHARACTERIZATION OF GEOGRAPHICALLY RELATED ORGANIZATIONAL SYSTEMS AND APPROACH TO INTELLECTUALIZATION OF THEIR MANAGEMENT

UDC 681.3
DOI:10.26102/2310-6018/2019.26.3.026

V.V. Goriachko, E. M. Lvovich


The article introduces a description of one of the classes of complex systems – geographically related organizational systems, widespread in the social and economic spheres. The characterization of the systems under study is given through classification features according to their belonging to territorial and industry clusters, according to the method of spatiotemporal information generation for effectiveness evaluation. A variety of combinations of these features leads to the three main tasks of geographically related organizational systems management: management of resource, productive and resource-productive interaction of objects of the main and related systems.It is represented that the mechanisms of the generation of spatio-temporal information play a special role in the intellectualization of decision-making in the listed managerial tasks. Such mechanisms are monitoring and rating. The first mechanism allows obtaining estimates of indicators characterizing the functioning of the main system objects and the results of interaction with objects of related systems in a set period of time. The second mechanism is aimed at aggregating the monitored indicators into an integrated assessment, based on which the position number of the main system object in the rating list is determined. The main fields of intellectualization of management of organizational systems class under the study, which are determined by the optimization condition of potential efficiency and require the development of problem-oriented methods for analyzing GIS-oriented spatio-temporal information and algorithms of decision-making intellectual support are substantiated.

Keywords: organizational system, management, interaction, efficiency, intellectualization, spatio-temporal information.

Full text:
GoryachkoLvovichEM_3_19_1.pdf

MANAGERIAL DECISION MAKING TO IMPROVE RESOURCE EFFICIENCY OF A NON-PROFIT ORGANIZATION BASED ON EXPERT AND VERIFICATION EVALUATION

UDC 681.3
DOI:10.26102/2310-6018/2019.26.3.025

G.P. Sapozhnikov


The article considers the models and procedures of intellectual support of managerial decision making based on optimization and expert assessment. The main attention is paid to the long-term planning of the resource efficiency increase of a non-profit organization. The development of these theories for specific managerial problems is proposed. Non-profit, non-governmental organizations, organizations of the third sector serve as synonyms for NGOs. The issues of development and functioning of non-profit organizations, their socio-economic potential, mechanisms to increase the efficiency of their activities, tools to ensure partnerships with the government, are studied by economists, sociologists, and management specialists in social and economic systems. The so-called theories of the third sector that currently exist are aimed at analyzing NGOs as a management system, and economic mechanisms that affect the functioning of social movements and organizations with the use of regression and neural network models based on monitoring and rating information. The allocation of additional costs for the implementation of measures to improve resource efficiency is proposed to be carried out using a multi-step process of optimal decision making. As a result, we have many alternative solutions. To select a rational option, an expert assessment procedure has been developed with the involvement of a group of experts and the building of an inverse rank sequence and matrix of individual weighting coefficients. The final managerial decision choice is made by the logical conditions sequentially checking and obtaining a group compromise assessment.

Keywords: resource efficiency, multivariance, management, multi-step optimization, group expert assessment, ranking.

Full text:
Sapozhnikov_3_19_1.pdf

METHOD OF DIFFERENTIAL DIAGNOSTICS OF THE NOSOLOGICAL FORM OF VIRAL HEPATITIS WITH THE APPLICATION OF NEURAL NETWORK OF CASCADE CORRELATION

UDC 004.891.3
DOI:10.26102/2310-6018/2019.26.3.028

A.N. Astafev


An important aspect of determining the nosological form of hepatitis is the combination of input data at the beginning of the study. The use of neural networks in medicine, which have the ability to search for hidden dependencies by learning from the experience of doctors, makes it easier to work in the role of advisor. However, the question of selecting the most effective topology for a specific task remains open. This paper substantiates the need to use neural network algorithms to solve the problem of determining the nosological form of hepatitis. The analysis and selection of input factors characterizing the clinical condition of the patient, and output factors characterizing the specific nosological form of hepatitis, neural network. The algorithm, its use is described, and a cascade neural network is compared with others in the context of the problem under consideration. At the end, a description is made of the established system for determining the nosological form of hepatitis using a cascade correlation neural network, and also describes the clinical efficacy.

Keywords: neural network, viral hepatitis, nosological form of hepatitis, neural network of cascade correlation, classification.

Full text:
Astafev_3_19_1.pdf

MATHEMATICAL MODELING OF THE TASK OF DETERMINING A SET OF CONTROL EVENTS USING A FUZZY METHOD OF ANALYSIS OF HIERARCHIES AND A METHOD BASED ON MEASURING LATENT VARIABLES

UDC 519.876.2
DOI:10.26102/2310-6018/2019.26.3.024

N.E. Krasova, N.A. Aleynikova


The article discusses the mathematical modeling of the problem of multi-criteria selection of control measures for the ongoing monitoring of performance using two methods: a method of fuzzy analysis of hierarchies and a method based on measuring latent variables (the Rush method). Both methods are expert methods. The advantage of using a fuzzy hierarchy analysis method is to describe the relative attribute values using fuzzy numbers instead of exact ones. Due to this, the expert gets the opportunity not only to assess the degree of preference of one object over another, but also to express his doubts, experience, intuition in this assessment. The main disadvantage of this approach is the complexity and complexity of the calculations. The advantages of the Rush method are in the simplicity of calculations, in the transition from the subjective assessments of experts to the objective ones, which possess the property of linearity. Within the framework of the constructed hierarchical model aimed at increasing the efficiency of the learning process, weights of different types of control measures are determined by these methods. In the future, the weights obtained can be used as parameters in the models for the formation of a set of control measures based on minimizing the difficulty of their implementation and maximizing their usefulness.

Keywords: expert estimation methods, pairwise comparison matrix, fuzzy analysis of hierarchies, latent variables, Rush method.

Full text:
KrasovaAleynikova_3_19_1.pdf

STUDY OF ARTIFICIAL INTELLIGENCE METHODS FOR CONSTRUCTING A CLASSIFICATION MODEL OF SUCCESSFUL TRANSACTION IMPLEMENTATION IN THE SS7 NETWORK

UDC 004.8
DOI:10.26102/2310-6018/2019.26.3.023

A.V. Roslyakov, S.V. Palmov, E.V. Glushak


Telecommunications have a decisive influence on the development of human society. The type of communication can be improved in various ways. Artificial intelligence allows to contribute to the solution of the abovementioned problem. However, there is the problem of choosing the method that is most suitable for solving a specific task in a particular subject area. This is due to the large number of existing artificial intelligence tools, as well as a significant variety of situations that require consideration of certain restrictions and nuances when analyzing them. The authors of the paper conduct an experiment that aimed to simplify the solution of the stated problem when it is necessary to build a classification model that determines the success of a SS7 network transaction implementation in the provision of voice and SMS services in a mobile communication network using transferred mobile subscriber numbers. The capabilities of the five methods are analyzed: decision tree, support vector machines, random forest, neural network and naive Bayes classifier. The classification models generated by the abovementioned methods test for compliance with two requirements: the reliable predictions generation and the results stability. Models quality evaluated by three metrics: F-measure, specificity and standard deviation. The experiment used real depersonalized statistics obtained in the network of a large mobile operator. After carrying out the relevant calculations and comparisons, it was found that the decision tree method usage seems to be the most preferable, since it forms the highest quality classification models.

Keywords: artificial intelligence, telecommunications, F-measure, decision tree, classification model, SS7.

Full text:
RoslyakovSoavtori_3_19_1.pdf

SUPPORTING DECISION MAKING TO IMPROVE PSYCHO-PHYSICAL READINESS FOR PROFESSIONAL ACTIVITY ON BASIS OF INTELLECTUAL TECHNOLOGIES

UDC 004.82
DOI:10.26102/2310-6018/2019.26.3.022

M.B. Guzairov, N.I. Yusupova, O.N. Smetanina, T.V. Naumova, E.Y. Sazonova, A.I. Agadullina


The article presents the analysis results of current state of Data Mining problem and knowledge formalization to support decision-making. The importance of professionally important qualities (PIQ), which significantly affect the labor efficiency of any specialist, is given. Authors of this article focus on models and methods of intellectual decision support in the development of PIQ. A large amount of knowledge about relationships of PIQ, psycho-physical state of a person and effect of exercise on a person has accumulated to date. The source of such knowledge may be textbooks, monographs, expert knowledge. It is noted that taking into account the preparation of students in groups by identifying students with similar characteristics will make it possible to formulate recommendations for groups and conduct joint physical training. A formal statement of the problem of decision-making support in the development of PIQ is given for the effective performance of professional activities, which consists in formalizing expert knowledge (tests for assessing PIQ, exercises for developing PIQ) and implicit knowledge obtained using Data Mining test results for assessing PIQ. In this article authors don’t consider questions of knowledge extraction, but they study questions of knowledge formalization and use for making decisions in decision support systems the technology of expert systems

Keywords: technology of expert systems, decision support, Data Mining, professional qualities, knowledge formalization.

Full text:
GuzairovSoavtori_3_19_1.pdf

DISPERSION OF THE NUMBER OF FAILURES IN MODELS OF PROCESSES OF RESTORATION OF TECHNICAL AND INFORMATION SYSTEMS. OPTIMIZATION PROBLEMS

UDC 519.873, 004.056
DOI:10.26102/2310-6018/2019.26.3.021

I.I. Vainshtein, V.I. Vainshtein


In this work, for several models of recovery processes, dispersion formulas for the number of failures are obtained, depending both on the recovery functions of the considered model of the recovery process and on the recovery functions (average number of failures) of other models. Considering the formulas for the average and variance of the number of failures, the problem statements are given on the organization of the recovery process in which the minimum variance is achieved with a given limit on the average number of failures, or so that there is the smallest average number of failures with a given dispersion limit. The formulation tasks resemble Markowitz’s well-known task of forming a portfolio of securities, where the average makes sense of income, risk variance. The solution of the formulated problems is obtained for a simple recovery process with an exponential distribution of operating time, and for this case the Chebyshev inequality and the formula for the coefficient of variation are written. The developed mathematical apparatus is intended for use in the formulation and solution of various optimization problems of information and computer security, as well as in the operation of technical and information systems, software and hardware-software information protection when failures, threats of attacks, and security threats of a random nature occur.

Keywords: distribution function, recovery process, recovery function, failure rate dispersion, coefficient of variation

Full text:
VainshteinVainshtein_3_19_1.pdf