DOI: 10.7256/2306-4196.2013.2.8307

Abstract: The work is devoted to the basic principles underlying the design of complex technique of semantic models of knowledge bases of intelligent information systems. The knowledge base is one of the key components of intelligent systems for various purposes. In developing the knowledge base is essential to ensure not only the ability to store knowledge and navigate through it, but also the opportunity to work on the creation and modification of knowledge distributed team of developers. The paper proposes a technology for component design of a knowledge base, based on unified semantic networks with the basic set-theoretic interpretation. This technology is a set of models, tools and methods for the design of knowledge bases. Semantic model of intellectual system knowledge base is a formal interpretation of the semantic space, which is known for intelligent system at the current time. This model is part of the technology component design knowledge base of intelligent systems based on semantic networks.

DOI: 10.7256/2306-4196.2014.5.13300

Abstract: The article reviews a unified logic-semantic model of an interpreter for basic programming languages oriented on the processing of sc-models of knowledge database. The mentioned above model is based on a multi-agent approach. The article is dedicated to a basic language of programming a technology of designing OSTIS intelligent systems, and more specifically, to a model of interpreter underlying this technology based on a multi-agent approach to designing knowledge processing machines. Basic concepts of this article such as sc-agent, abstract sc-agent and so on are reviewed in this article and on the web-site of this technology. The programming language discussed is basic for OSTIS intelligent systems developing technology. The article describes both sc-agents of abstract scp-machine and sc-language of their interaction. The author discusses principles of interpretation of software written on a basic programming language oriented on processing of sc-models of knowledge database. The developed model is based on a multi-agent approach that allows to effectively use the abilities of asynchronous and parallel programming and makes designed model open, that is, there is the possibility of adding new agents into it.

DOI: 10.7256/2306-4196.2015.1.13402

Abstract: In article the methodology of the qualitative analysis for decrease in marriage of castings is considered. The methodology place in a complex molding quality improvement means is given. The automated stages of defects identification methodology, identifications of the reasons their emergence and ways of elimination are described in detail. The algorithm of methodology of the qualitative analysis of defect of casting is presented. The article shows examples of process of identification of defect with use of visual and logical schemes. The stages of the search of the reasons and ways of elimination of defects of castings on the example of a light gas sink are shown. The place of the automated systems of the analysis of defects of casting within a complex of systems of improvement of quality of molding is considered. The automated atlas of foundry defects which is carrying out a role of help system at a choice of a way of elimination of defects is reviewed separately. The functionality of the atlas and structure of its database is described.

DOI: 10.7256/2306-4196.2015.2.15002

Abstract: The object of study in the article are computer intelligent information management decision support system, using such basic principles on the implementation of information technology management as the principles of adaptive, integrated, network management and real-time control, that can supply leadership and staff with easy to use and powerful by internal content means of solving the basic problems of organization management. The article describes the different management information systems such as CRM (Customer Relationship Management), ERP (Enterprise Resource Planning), systems of information support of analytical activities BI (Business Intelligence), as well as various types of real-time analytical information processing technologies - OLAP (Online Analytical Processing) systems. The article uses a comparative analysis of various data storages with a set of tools to retrieve data from ERP and other systems and ways of further analysis of the collected data. Using the systems of information support of analytical activities data resources of any organization can be converted into pure information and can be used as a basis for making effective management decisions. BI systems are considered as decisions on the basis of OLAP business analysis systems and DSS (Decision Support Systems), an integrated set of tools for processing  information and data (obtained by other corporate information systems and different methods of processing these data) is used for strategic analysis of the company.

DOI: 10.7256/2306-4196.2015.5.16368

Abstract: The subject of the research are methods and algorithms aimed at practical solution of problems of pattern recognition in the weakly formalized fields of knowledge, such as medical field, technical field, geological reconnaissance diagnostics, forecasting and construction of expert systems. The solutions of such problems entered into use a large number of incorrect (heuristic) algorithms. The authors focus on such aspects as the need for the development of the theory of corrective operations, the necessity for the synthesis of correct algorithms minimum complexity, solving the stability issues by using mathematical methods. Special attention is paid to the construction of the algorithm, correct on the whole set of recognizable objects, based on existing algorithms and decision rules drawn up for the studied area. The logical approach may be a technology of constructing a theory of the synthesis of the correct recognition algorithms based on existing family of algorithms. The article shows that these methods allow creating algorithms that implement certain expert conclusion, despite the lack of adequate mathematical models of the relationships between image and its properties, incomplete and contradictory of data. The main conclusion of the research is in a logical analysis of a given subject area, in terms of variables valued logic. The authors propose approaches to the design of procedures for recognition of precedents on the basis of incorrect set of algorithms and constructed logical decision rules. The main contribution of the authors in the study of the topic is the proposed algorithm, expanding the area of the solutions obtained and correct on the whole set of recognizable objects. The novelty of the study is the use of variables valued logic that improves the correctness of encoded information and increase the expressiveness of the conclusions.

DOI: 10.7256/2306-4196.2015.6.16744

Abstract: The subject of the study is the problem of automation of genetic similarity and genetic distance calculation and building phylogenetic trees. The object of the research is the sequence of drives (alleles) in the arms of polytene chromosomes. The author considers in detail the chromosomal characteristics of species with seven chromosome arms by the example of chironomid mosquito (genus Chironomus). This article presents a Chironomus 1.0 software solution with a simple, intuitive user interface allowing to easily calculate the distance and genetic similarity between populations. The software is developed using C# and implements Nei method to calculate the genetic similarity and genetic distance. The special contribution made by the author in the study of the theme is in significant simplification of genetic studies relating to the calculation of genetic similarity and genetic distance using Nei method. The novelty of the research is in creation of a software product that allows to easily calculate the genetic similarity and distance for all types of populations with seven chromosome arms.

DOI: 10.7256/2306-4196.2016.2.17904

Abstract: Diabetes is a chronic disease, in the pathogenesis of which is a lack of insulin in the human body causing a metabolic disorder and pathological changes in various organs and tissues, often leading to a high risk of heart attack and kidney failure. The author makes an attempt to create a system for early diagnosis of diabetes patients using the device of artificial neural networks. The article presents a model of neural network based on multilayer perceptron trained by back-propagation algorithm. For the design of the neural network the author used Neural Network Toolbox из MATLAB 8.6 (R2015b) which is a powerful and flexible tool for working with neural networks. The results of training and performance tests of the neural network designed show its successful application for the task and the ability to find patterns and complex relationships between the different characteristics of the object. The sensitivity of the developed neural network model is 89.5%, specificity of 87.2%. Once the network is trained it becomes a reliable and inexpensive diagnostic tool.

DOI: 10.7256/2306-4196.2016.3.18010

Abstract: Diabetus melitus is a metabolic disorder caused by an absolute deficiency of insulin secretion and characterized by the inability of the body to maintain an adequate blood glucose level. Optimal doses and types of artificial insulin depend on many factors. In this paper the author proposes a neural network model of blood glucose prediction allowing to predict impending critical condition of patients suffering from diabetes. Implementation of the prediction system combined with an insulin pump creates a range of opportunitities for constructing a system of automatic blood glucose level control. The simulation was performed by using The Neural Network Toolbox of the Matlab 2015b environment due to a wide range of opportunities offered by the system, convenience of developing compex applications, advanced imaging study results. The results of the training process and verification of the proposed prediction model performance show that artificial neural networks of direct distribution can help to sustain a satisfactory blood glucose level at all stages of prediction. The average quadratic prediction error did not exceed 3 in the process of the research.  

DOI: 10.7256/2306-4196.2016.5.18987

Abstract: The subject of the study is to assess the risks in mining of hydrocarbon deposits. The authors suggests a model of an expert system automated assessment of mining risks. The expert system includes a database containing information on the status of the development of a number of deposits of Tomsk region, detailed classification of risk arising during the mining planning process and exploitation of hydrocarbon fields, and the factors causing the risks. Interconnections of risk factors and patterns of their origin established on the basis of expert estimations. To evaluate the development of the risks proposed to use a comprehensive risk characterization. The rating is based on fuzzy logic. Integrated risk profile allows developing an optimal strategy taking into account the current state of the field mining. Expert system of integrated assessment of mining risks brings together experts from different fields of knowledge and provides a general picture including comprehensive assessment of risks, probabilities and risk profiles helpful to managers and other personnel.

DOI: 10.7256/2306-4196.2013.6.10168

Abstract: The article examines functioning of the software agent during the process of internet competitions and the possibility of fraud associated with this process along with the ways to control the participants and ensuring the compliance of the rules of the competition. The author suggests the software-agent for remote participation in the competition and controlling its carrying out by integrating the agent with operation system for tracking the computer hardware configuration, running programs, input/output devices and interactions with the internet. The agent provides the use of asymmetric cryptographic standards of encoding for secure data transferring, monitoring and remote control of the participants. The agent takes into account the specifics of the internet competitions such as different time zones of the participants, differences in the hardware and software configuration, low bandwidth channel for communication with the server throughout the competition. The results may be used for different kinds of internet competitions with remote participation.

DOI: 10.7256/2306-4196.2015.6.17625

Abstract: The highest requirements on reliability and fire safety are applied to electrical equipment in the oil and gas industry, since its failure can lead to an emergency situation, followed by considerable economic and environmental damage. The paper raises a question of providing the reliability of the electric machine unit using spectral analysis of the higher harmonic components of current and voltage. The authors review main classification criteria for diagnostic systems, define its place in general software classification and analyze industrial software diagnostic equipment, represented on the Russian market. The study was conducted with the use of the description and comparison of methods, the theoretical foundations of electrical engineering, electrical engineering, electronics, design and programming. The authors formulated the basic requirements applicable to the software tool for motor diagnostics. The results are planned to be used in software development of a tool for the electric machine unit using spectral analysis of the higher harmonic components of current and voltage, which can be applicable to the oil and gas industry enterprises for the detection of defects and lowering repair costs.

DOI: 10.7256/2306-4196.2013.5.9774

Abstract: The article describes a multilevel model of knowledge representation for the evaluation of document flow state in organization. The authors propose network models for knowledge representation, the use of which enables the qualitative evaluation of the various current quantitative and qualitative indicators. The authors state that effective analysis of the document flows includes not only the assessment of the quantitative characteristics bur also requires a combination of the performance workflow and business processes indicators into one multilayered model. The authors give an overview of the comparative characteristics of neural and semantic networks and conclude that semantic network is the best choice for the analysis of document flow. The article reviews the process of analysis and evaluation of the present state of document flow based on the semantic networks on the example of “Iva-Trans” L.t.d. In conclusion the authors point out that the semantic network of forecasting is build of semantic statements, which in their turn are represented by semantic constructs with nodes as sub-graphs of the semantic network of concepts.

Abstract: Project management systems are widely used at present. They are designed to support and control of the project life cycle. The project is a temporary effort of labor-time event, which corresponds to the following features• defined start and end dates; • defined a list of costs and quality conditions; • the existence of unique activities, including risks; • availability of certain boundaries that must be followed. For the project it is vital to control all phases of its development. The approach proposed in this paper aims to solve the problems of control during all phases of project development through the integration of project management system with a system of management which need to be automated. It should be noted that the approach is not universal in the sense that its use is limited to a narrow range of tasks. These tasks include: the task of managing the joint development of documentation, the task of organizing a mass event (i.e. a conference), the task of developing a knowledge base and a number of others.

DOI: 10.7256/2306-4196.2013.3.8737

Abstract: The paper proposes the use of the intelligent hybrid meta-agent for solving a problem of intellectualization management and information systems in rail transport. In order to ensure the safety and risk management for harmful natural and man-made situation in rail transport the authors propose to use intelligent software for management and informational support. The article reviews general structure of intelligent environment as hybrid cognitive agent consisting of four main parts. The main obstacles to the creation of intelligent monitoring systems are: lack of finance support, absence of knowledge base on pre-threshold facilities, nonexistence of specialized software and hardware. Modern sensor networks combined in multi-agent system where each individual sensor is a single agent, with its local knowledge base possess the necessary characteristics. Multi-agent system formed by multiple interacting intelligent agents can be used to solve these problems that are difficult or impossible to solve with a single agent. The article shows variants of construction of logical models of interaction between the sensors using the apparatus of multi-valued logic and bilattices.

Abstract: The base of knowledge is a key component of intellectual reference system. The development of this component is labor-intensive and time-consuming process, and therefore an important aspect of the design knowledge base is the organization of collective design. Based on the collective aspect of the design of a complex technique of intelligent information systems, the design of the semantic knowledge base model is detailed structuring of the knowledge base, i.e. asked to consider the structure of the knowledge base as a hierarchical system of interrelated subject areas of the knowledge base. In reviewing the process of designing the knowledge base model athor selected areas of work that can be distinguished in the creation of the model. Semantic knowledge base is a hierarchical structure of the system described by its subject areas, built over a given area of the main subject. The paper shows the complex technique of builing an intelligent information systems, based on the mass of the semantic technologies of designing computer systems at various levels OSTIS intelligence. The results in the work being tested in an open project OSTIS.

DOI: 10.7256/2306-4196.2013.4.9593

Abstract: The article deals with the problem of making a decision about the components of the physical security system for the potentially dangerous objects. The authors determines the stage of the task requiring expert information - conceptual design, including the analysis of the vulnerability of the object, the development of practical recommendations for the creation of a physical security system, selecting the variant and the composition of engineering-security equipment. The article presents different methods for solving the task, highlights the problem of the evaluation criteria for the level of protection of the object by chosen engineering and technical facilities, which consist of the uncertainty and imprecision of the expert data evaluation during the analysis of object security. The aim of the article is to set up models and methods for evaluation of object protection. The given method is based on the representation of the protected object in form of a graph. The article reviews general properties of the object’s graph. The author introduces the definition of the measure of structural protection. This measure allows to evaluate effectiveness of the security placed in the way of the offender during his aim of access the object and moving throughout the place with intent to commit unlawful acts. The author evaluates the possibility that the offender will get to one of the critical elements of the object without being detected by the technical means of security and being delayed by the physical barriers. The measure of the protection shows the possibility of detection and delay of the offender on the most vulnerable path to a critical element. The author reviews the Dijkstra's algorithm appliance to the task of defining the less protected on the graph and modifies it to compute the measure of structural protection.  The article describes ways of processing of expert information in the form of fuzzy numbers, offers the method of optimal placement of control points at the object via standard genetic algorithm. The article gives an example of calculation of the measure of structural protection by the described program.

DOI: 10.7256/2306-4196.2013.1.8305

Abstract: This paper describes a method of making technical decisions using the theory of multi-agent systems. The structure of decision-making system, and describes the possible variations of its constituent components. Multi-agent systems are the result of the intersection theory of systems with distributed artificial intelligence systems. In co-operative multi-agent systems, the decision is made as a result of joint work, and competing - individual agents' actions. At the corporate structures of multi-agent systems have the property of self-organization. The problem of making decision is the task of selecting the best option out of many under conditions of uncertainty. The functions of the agent's behavior is divided into three parts: the first lays designer agent, the second is calculated as a result of the agent on development activities, and the third - formed as a result of learning agent with experience. Job agent in a partially observable, stochastic, sequential, dynamic, continuous and multi-agent environment is considered to be the most difficult.

DOI: 10.7256/2306-4196.2015.1.13722

Abstract: The article describes an approach in management of diagnostic solutions inference in a medical diagnosis expert system. The study reviews the features of the software implementation of presented models and algorithms. The author proposes a combination of the reverse and direct inference for diagnostic solutions. At reverse deduction requesting new information from the patient requires generation of additional questions on the leading symptom. At the same time, the direct inference allows calculation of the output integral estimates of detection of possible diseases at the onset of symptoms. To output decisions under uncertainty the Mamdani fuzzy model is applied. The author proposes a RETE-network for generating a diagnostic solution in a reasonable time. The described mechanism of inference a diagnostic solutions has the following advantages: it allows the direction of reasoning on the most promising ways of obtaining a diagnosis  and determines the correct order questions on leading symptoms; it allows the diagnosis under uncertainty in information on symptoms and does not stop though the diagnostic decision may not be accurate; it allows to set a preliminary diagnosis in real time and makes a conclusion in a reasonable time after the symptoms have been entered.

Abstract: The user interface is the only way the user interacts with the system software. Therefore, it should be fairly simple, intuitive and easy to learn. Designed by modern products user interfaces for the most part are fairly complex system. The main problem in these interfaces is that it is difficult to work with them for a user with a low level of skills. This in turn reduces the number of customers and reduces the operating efficiency. Designing user interfaces of intelligent system is more difficult for a number of reasons, which makes the development of technologies for their design more relevant. The article describes the principles and techniques that helps to design user interfaces for intelligent systems that can be easily integrated and are based on existing components. On the basis of the proposed technology user interfaces of some application systems were already designed. That makes it possible for authors to make conclustions about the performance of the proposed approach.

DOI: 10.7256/2306-4196.2014.1.11316

Abstract: The article reviews the problem of theoretical justification of principles and concepts of computer-aided design for cognitive object, shows the distribution of educational courses. The author shows the integration of computer-aided design methods of realizing algorithmic synthesis represented by object technology of intelligent information processing. The proposed method of creating an educational resource opens the original direction for training in CAD. The main purpose of the use of intelligent tutoring technology in CAD is reviewed. The main feature of constructing an intelligent CAD system for designing an information object is the need to synchronize the process of automatic processing of project information and process of inference. The proposed formal representations allows to logically structure the properties of the design decisions, determine the semantic transformation rules based on causal relations domain to eliminate uncertainty on the basis of the known methods presented in this paper used to implement the teaching of intelligent technologies.  Presented intelligent CAD technology is designed to empower and distributed educational applications. Currently, e-learning systems have demonstrated the benefits of using them.

Abstract: Due to the rapid development and spread of computer systems in various spheres of human activity is to reduce the actual cost of training new and adapting already active users of new versions of systems. To the greatest extent this applies to the field of information and information systems. It is caused by a wide variety of applications, ranging from bying tickets online to complex customer support systems. The variety of such systems and the principles of interaction with them, used in practice, hinders their free use. Promising in this case is the use of a natural language familiar to the user for a dialogue with computer systems. Using the familiar to the user natural language for dialogue with computer systems is implemented by means of natural language and speech in user interface, which has a number of advantages: minimal user training to work with the system (depends on the specific implementation of the system and its operating capacity), simplicity and high speed setting arbitrary requests to the system and the high level of the domain model (is like one of the benefits, as well as a prerequisite for the successful implementation of such systems).

DOI: 10.25136/2644-5522.2018.3.26556

Abstract: The purpose of the work is the development of a machine-readable dictionary (ontology) for describing the scope and features of implementing software systems that use elements of crowd computing (information processing systems that include operations performed by people interacting with them via the Internet). Ontology will allow us to apply elements of semantic search to work with scientific and technical information in this relatively new but actively developing field of research, which, ultimately, should help to improve the level of organization of research in it. The ontology is constructed by the "top-down" method on the basis of analysis of the existing conceptualizations in the field of human-machine calculations described in the most frequently cited survey publications indexed in the bibliographic database Scopus. As a result, the ontology CROSS-ODF is formed, which allows describing four main characteristics of applications using the elements of crowd calculations: 1) the features of the problem for which the application was created; 2) the characteristics of the tasks formed by the system to the participants; 3) the contribution properties of the participants; 4) specific mechanisms for attracting participants and processing results. The generated ontology is written in the language OWL 2 and is published in the public domain. The developed ontology can be used in research support systems to simplify the search for crawl computing systems that have certain characteristics and experimental results of using such systems.

DOI: 10.25136/2644-5522.2021.1.35862

Abstract: This article explores the walking robots that are used or assist in nondeterministic environment, such as rescue operations. This required carrying out in-depth analysis of the existing models to acquire relevant information on the robots with walking mechanisms in accordance with several criteria: parameters, weight, degrees of freedom, speed of movement, input energy, runtime, maximum load, advantages and disadvantages of the reviewed models. Using the methods of comparative and critical analysis, the author analyzed the available materials for the past 5 years, which allowed accomplishing the set tasks. The results consist in compiling a summary table for largely generalized groups of walking robots and three tables for the models under review, which summarize their advantages and weaknesses. Such data would broaden the knowledge of the researchers dealing with the walking robots, analyze both national and foreign studies on the topic, apply this experience in further work, focus on solution of the problems, and emphasize the uniqueness and relevance of their developments. This article determines the peculiarities of utilization of walking robots specifically in rescue operations; however, the scope of their applicability can be broader. The author also describes the nontraditional locomotors of walking robots, which are widely known in media, video hosting, and other tools of receiving information.

DOI: 10.25136/2644-5522.2017.3.18438

Abstract: The object of study in this article involves logical algorithms for recognition and diagnostics, which are designed for functioning in weakly formalized areas of knowledge. Directional search trees and logical neural networks can be classified as such algorithms. The proposed implementation of a logical algorithm for searching for objects within a given domain, which are correspondent to a set of properties, is based upon the application of logical functions, which are formed with  variable-valued predicates. The representation of the training sample in the form of variable-valued logic function allows not only to eliminate redundancy in the description of objects, but also to construct all possible classes of objects by all attributes, and also, using the constructed functions, to reveal hidden regularities in the subject domain.The basis for constructing variable-valued logical functions is a set of production rules, each of which contains both a set of properties and an object defined by them. Integration and optimization of rules are performed using logical operations. The scientific novelty of this study is due to the following.  The author proposes knowledge extraction from the initial databases containing information on the properties of the analyzed objects using variable-valued predicates. Then a method is proposed for obtaining all possible classes of structures of telecommunication networks, which makes it possible to reveal additional properties and to make an intelligent choice of the desired topology.

DOI: 10.25136/2644-5522.2017.6.24747

Abstract: The user interface is an integral part of the software. To make its use easier for the user when working with the current task, it must be constantly optimized and simplified.This article is devoted to the development of adaptive user interfaces. The purpose of which is to facilitate the interaction of the operator with the system. Knowledge of the user, the context of the situation and the capabilities of the device allow such systems to adapt to the needs of each individual in order to make the interaction more simple, convenient, individual for each user. Data on the different characteristics of the user are vital to achieving the main objectives of such systems. To find a suitable solution, methods of system analysis, synthesis and abstraction were applied. As a result of the introduction of an additional meta-level, a new algorithm for constructing adaptive interfaces was synthesized during the operation of the data. In order to gather knowledge, several formal models were developed, which are necessary for organizing and comprehending the collected information. This article analyzes several solutions presented in the literature about user modeling, context and knowledge taking into account different approaches. In the article, their advantages and disadvantages are determined, and at last a proprietary ontological model is proposed that circumvents the described limitations.

DOI: 10.25136/2644-5522.2017.3.18659

Abstract: An overview concerns topical issues and the current situation regarding cognitive bioinspiral optimization algorithms research. Optimization problems form the majority among the many problems, which are faced by the researchers in the theoretical sphere as well as in the sphere of practical application. For some such problems the solution requires a full search for options. However, the dimensions of these problems are such that the implementation of the search for options is almost impossible  due to  the extremely high time costs. An alternative approach to solving these problems involves the application of methods based on the methodology of cognitive bioinspiral algorithms. When the computer systems became sufficiently fast and inexpensive, the bioengineered algorithms formed an important tool for finding solutions close to optimal solutions for the problems,which were previously been considered insoluble. The methodological and theoretical basis of the survey was found in the provisions of the theory of artificial intelligence and bioinspired computing, decision theory and optimization methods. The review includes a list of world scientific schools and scientists who have made a significant contribution to the development of cognitive bioinspiral algorithms, and also a brief description of the classification, terminology and libraries of bioengineered algorithms. A classical result is presented in the theory of cognitive bioinspiral algorithms - the CPT theorem and the NFL-theorem. The authors provide analysis of regularities, basic elements and structure of cognitive bioinspired calculations, they analyze the issues concerning  representation (coding) of solutions, basic cycle of bioinspired algorithms, extension of cognitive capabilities of operators of bioinspiral algorithms, and drift analysis as a promicing direction in  the sphere of  time of cognitive bioinspiral algorithms analysis.

DOI: 10.25136/2644-5522.2019.4.29809

Abstract: The subject of research is the architecture of artificial intelligent systems, developed as part of a hybrid approach to artificial intelligence. The article offers the author’s vision of the process of constructing artificial intelligent agents based on a hybrid approach using organismic principles. An artificial intelligent agent with a hybrid scheme is a “cybernetic machine” operating in a certain environment and functionally interacting with it. Of interest is the way the agent interacts and makes decisions, in which information from the environment passes through many sensors, and then it is cleaned up and sensory integrated with further translation into a symbolic form for decision making based on symbolic logic and the operation of a universal output machine. As the main research methodology, a systems engineering approach to the analysis and construction of technical systems was adopted, as well as a functional approach as an additional research method. The novelty of the study is in the use of a hybrid paradigm for constructing artificial intelligent systems in conjunction with systems and functional approaches in the design of technical systems, which made it possible to generalize the available data on the interaction of intelligent agents with the environment and identify interesting patterns for use in the development of artificial intelligence systems. The main conclusion of the study is the possibility of using a hybrid paradigm to obtain artificial intellectual agents that have important advantages of the upward and downward artificial intelligence paradigm - the ability to learn and behave appropriately in an unknown environment and the ability to explain the reasons for their decisions, respectively. This important finding will advance research into explainable artificial intelligence.

DOI: 10.25136/2644-5522.2017.6.24746

Abstract: The object of the research is the subject area, which is a precedent relationship between objects and their characteristics used in solving image recognition problems.Intellectual analysis of data is one of the necessary stages in the solution of poorly formalized problems; therefore, in many cases the accuracy of the solution of the task depends on the method of building knowledge bases, analyzing them and minimizing them. The development of common formal methods for revealing logical patterns in any given subject area seems to be a very pressing problem, as it provides the opportunity to form optimal knowledge bases, which greatly simplifies the solution and improves its quality. In this paper, the author use the apparatus for differentiating Boolean functions to analyze and minimize knowledge bases, which are the directions of modern discrete mathematics and find their application in problems of dynamic analysis and synthesis of discrete digital structures. The main results of the study are a constructed logical function that analyzes the relationship between objects and characteristics that characterize them, which is an opportunity to reveal all the laws of a given subject area; as well as the method of minimizing knowledge bases obtained on the basis of logical data analysis, revealing a minimal set of decision rules, sufficient for solving the task.

DOI: 10.7256/2306-4196.2017.2.21794

Abstract:  The object of study involves fuzzy logical multi-criterion methods and algorithms within the support systems for the decision making. The immediate object of study involves support systems for decision making in the sphere of dependability of technical equipment systems in the situation of fuzzy information input. The purpose of the study is to provide methodological basis for the development of applied fuzzy systems for the traditional priority studies for the multiple objects in the multi-dimensional set of quantity and quality markers based upon the linguistic statements by the experts. The article provides for the methodology of development for the support system for the decision-making  in the conditions of non-precise information with the use of fuzzy theory of sets and fuzzy methods for the hierarchy analysis. The author provides detailed analysis for several aspects of the topic in question, such as application of decision-making methods for multi-criteria alternative analysis, such as the fuzzy inference and the hierarchy analysis method for fuzzy proximities. The author offers the method for ranging alternatives based upon the multi-dimensional sets of facts and criteria in the situation of fuzzy data input. The methodology of studies is based upon the formation of a model for the decision-making support system, method formalization for processing fuzzy data, algorithm development and providing for the simulation experiment for various values of managing parameters within a model. The provided methodology was implemented based upon an example of the support system for the decision-making  for the expert procedure for the evaluation of general dependability of chemical technological systems.  Implementation of fuzzy logic procedures when managing a complex of dependability markers is based upon the results of expert evaluation of four separate industrial objects within a single complicated technical system of oil and gas chemical production based upon five dependability criteria. Taking an example of the hierarchical structure for dependability of oil and gas equipment, the author offers a model and an algorithm for the evaluation for deriving weights with the use of a fuzzy pairwise comparison matrix based upon the judgment matrix. The experimental calculation results show that the fuzzy pairwise comparison method  is efficient with greater degrees of priority fuzziness 50 to 75 percent. Efficiency of the judgment matrix depends upon the evaluation closeness or incoming linguistic values, however, it is completely dependent upon the correct formalization of data input via formation of the membership functions as well as on the formation of fuzzy rule bases. Fuzzy logical algorithms for decision making support in the sphere of managing the complex of dependability markers for the oil and gas equipment form a non-formalized part of the complex management and support systems for ensuring industrial equipment dependability. Such sub-systems allow for the preliminary evaluation of the general situation in the sphere of equipment dependability based upon the expert information.

DOI: 10.25136/2644-5522.2019.1.19343

Abstract: One of the most important factors for the timely provision of medical care is to quickly and accurately obtain information about the state of health of the patient. Electrocardiography (ECG) is a non-invasive process of interpreting the electrical activity of the heart, allowing to evaluate the speed and regularity of heart contractions. This data is used to determine the damage and pathologies of the heart. Automatic ECG analysis is a challenging theoretical and practical task. The goal of the work is to use neural networks to detect the characteristic ECG signals that determine heart rhythm abnormalities and identify the corresponding heart disease. In the design, the Neural Network Toolbox of MATLAB 8.6 (R2015b) was used to simulate an artificial neural network apparatus. The effectiveness of the developed neural network model for ECG analysis was investigated using the MIT-BIH database. The accuracy of detection and extraction of the components of the ECG signal shows that the developed neural network model can be used to detect heart disease in patients. The sensitivity of the model was 71%, the specificity of 89%.

DOI: 10.7256/2306-4196.2017.1.20759

Abstract: The object of the present article is information processes in asynchronous discrete event systems. Examples of such systems include organizational-economical, production and computer-based systems. The subject of the research is the methodology of formalization and analysis of asynchronous discrete event systems based on integration of artificial intellect and behavioral discrete event modeling methods. As an example of a relevant topical area the authors of the present article view a section of flexible automated manufacturing systems (FMS - Flexible Manufacturing Systems). The methodological basis of the research involves the logic of predicates of the first and second order, formal description of abstract machines, artificial intellect models and Petri conceptual nets offered for the first time. The novelty of the research is caused by the fact that as a result of their research and based on their conceptual and behavioral model of an asynchronous discrete event system, the authors define formalized directly realizable specifications, for example, typical for further realization of the wireless network system running the flexible production process. Part II of the article shows that semantic networks with events, role and causal relationships between objects (scenario networks) can in a fairly full degree represent not only declarative, but also procedural knowledge of the subject area. In order to construct a behavioral discrete-event model authors develop a transition from a semantic network with events describing a section of flexible automated manufacturing systems to Petri nets and further to a network of abstract machines described by logical-algebraic expressions.  To preserve the informative nature of the model the authors suggest variety of Petri nets, as well as a new class of Petri nets - the conceptual Petri nets. The article proposes formalized executable specifications that take into account the roles of all objects participating in the implementation of events and management from the wireless network. The use of the network language of abstract machines simplifies the further implementation of the intellectual behavioral model of the system based on programming languages such as C, C ++, C #, etc. The authors suggest a principle of constructing a logical-algebraic operational (executable) model designed to build a distributed network application for a wireless network that manages robotic production on its basis.

DOI: 10.25136/2644-5522.2018.2.25804

Abstract: The aim of the article is to offer methods and applied technologies allowing to reduce the time of adapting knowledge bases and expert systems to one another. In his research Ryaskov gives an evaluation of the current connectivity architecture of expert systems and knowledge bases and analyzes drawbacks thereof, the main drawback being the need to rewrite the layer of conjunction of expert system and knowledge base whenever the data exchange protocol is changed. The author also sets a goal to reduce the connectivity between expert system and knowledge base. The architecture that is based on the weak connectivity architecture is extensively used in other fields. The research methods used by the author include the software engineering methods, descriptive logic, knowledge engineering and numerical methods. The service layer is exected based on the requirements set forth for client-service apps. As a result of his research, Ryaskov offers to use the mediation layer (service layer) and proves the novelty and efficiency of this approach. The author carries out an analysis of technologies allowing to abstract from data format provided by the knowledge base. The author decides that it is useful to apply the GraphQl technology for data exchange and the mediation layer should be used as a server (in terms of the client-server architecture). The author describes practical implementation of that decision for the expert system of the environmental load in Volgograd. Implementation of the service layer allowed to ease up the mutual adaptation of expert systems and knowledge bases and to reduce the component connectivity. As a prospect, the author offers to embed an access management component and general public service component into the servicelayer, for example, to provide data to the population about the environmental load. 

DOI: 10.7256/2306-4196.2016.6.20740

Abstract: The object of the present article is information processes in asynchronous discrete event systems. Examples of such systems include organization-economical, production and computer-based systems. The subject of the research is the methodology of formalization and analysis of asynchronous discrete event systems based on integration of artificial intellect and behavioral discrete event modeling methods. As an example of a relevant topical area the authors of the present article view a section of flexible automated manufacturing systems (FMS - Flexible Manufacturing Systems). The methodological basis of the research involves the logic of predicates of the first and second order, formal description of abstract machines, artificial intellect models and Petri conceptual nets offered for the first time. The novelty of the research is caused by the fact that as a result of their research and based on their conceptual and behavioral model of an asynchronous discrete event system, the authors define formalized directly realizable specifications, for example, typical for further realization of the wireless network system running the flexible production process. The first part of the article demonstrates that semantic networks with events, role and causal connections between objects (scenario networks) may sufficiently present logical, structural and procedural paradigm of intelligent systems including the system of situational management. The authors have also formalized the process of building scenario models based on conceptual graphs which allows to use the aforesaid models as part of expert simulation models of the situation management system. They demonstrate that a conceptual presentation of scenarios allows a natural transfer towards building the knowledge bases based on the relational approach which improves the performance function that makes changes to the conceptual model and knowledge base (for example, when the topical area is changed). Demands for the knowledge base built on the basis of the conceptual graph may be formalized in the language of abstract machine networks which simplifies further design of a human-computer interface of the intelligence system based on famous languages like C++, C#, SQL, Visual Prolog, etc.

DOI: 10.7256/2306-4196.2017.1.21723

Abstract: The object of the study is the process of computer-aided design of artificial lighting systems. The study was made on the possibility of improving its effectiveness through the application of the concepts of methods outlined in the article: automation the selection of operating modes of lighting devices with controlled emission spectrum, methods for optimizing the placement of lighting devices in particular by using specialized robotic complexes. In the paper the authors reviews problems the solution of which is caused by the development of technical progress in the field of lighting engineering and automation systems. The appearance of LED lamps with the possibility of automated control of lighting parameters as well as the availability of modern automation and robotics poses new challenges for design professionals and at the same time opens up new opportunities to reduce the amount of manual labor in the design process. In the course of the study, the existing solutions in the field of automated design of internal artificial lighting systems were analyzed. The system solution aimed at facilitating and increasing the efficiency of the processes of construction design is suggested. The result of the study is in conceptual description of three new methods aimed at improving the efficiency of CAD in construction. As the first method, the concept of automation of the procedure for preparing project solutions is presented. This concept is applied in terms of the choice of modes of operation of smart lighting systems, depending on the criteria for the specificity of the work in the room, the physiological impact and the specified indicators of the energy efficiency of the lighting system. The second method is the optimization of the procedure for automated placement of lighting devices in the development of appropriate design solutions. The third method is the concept of automatic survey of premises and the transfer of data to CAD to generate the initial data for the relevant design decisions. In the final part of the article, the method of combining these solutions within the framework of the system approach is considered and the assumption is made about the urgency of a more detailed elaboration of these solutions.

DOI: 10.7256/2306-4196.2016.6.21271

Abstract: The subject of the present research article is the development and practical implementation of the intelligent decision support system that distributes tasks related to maintenance of the personal data processors register. The object of the research is the task of a rational choice of task performers in the system of electronic flow of documents run by the territorial body of the Federal Supervision Agency for Information Technologies and Communications. The authors examine tasks of defending the rights of personal data owners, scheme for processing and distributing these tasks of keeping the registry of personal data processors, analyze the problem of manual distribution of tasks and set a goal to automate an efficient distribution of tasks between performers. To achieve the research target, the authors offer their own fuzzy-production model that has been developed especially for these purposes. This model allows to rationally distribute tasks of different difficulty levels based on the expert evaluation of competence, working capacity and work load of performers. The authors also give a description of the decision support system and algorithm for using it in the process of tasks distribution. The scientific novelty of the authors' approach to achieving the aforesaid goal is caused by the fact that they offer an automated distribution of tasks between performers based on developing and practically implementing the fuzzy-production model. They also provide original fuzzy-production rules to formalize expert knowledge concerning a rational selection of tasks performers taking into account their competence, working capacity and current work load. Analysis of the adequacy of this fuzzy-production model as well as efficient solution of the set goals based on the developed system has proved that it is possible to considerably decrease the intellectual load of an expert in the process of tasks distribution as well as increase the speed of the decision making process by 80.3 percent. 

DOI: 10.25136/2644-5522.2018.6.27399

Abstract: On the basis of a new methodology for assessing the current state of innovative development of the region, a decision-making information support system (DSS) has been developed when developing an innovative development strategy for a region. The generalized structure of the decision support system, the description and purpose of its main modules are given. Approbation of the work of the DSS on the example of the Republic of Bashkortostan was carried out. The received recommendations are necessary for the state authorities of the constituent entity of the Russian Federation to form an effective plan of measures, taking into account the current state and the existing opportunities for innovative development of the region. The study is based on general scientific methods of knowledge.(analysis, synthesis, comparison), the presentation of tabular and graphical interpretation of empirical-factual information. The theoretical and practical significance of the study is due to the relevance of the studied problems of assessment, forecasting and planning of innovative development of territories when developing regional development strategies. The practical result of the research is the approbation and implementation of the proposed approaches in the development of an information decision-making support system necessary for obtaining recommendations on the formation of an effective action plan for an innovative development strategy for a region that takes into account the current state and available capabilities of the territory.

DOI: 10.7256/2306-4196.2017.1.21934

Abstract: The article is devoted to the task of the automated UML class diagram refactoring, which is important for the development of tools for transforming UML models in the framework of the MDA approach. The authors formulate the problem of the automated UML class diagram refactoring, introduce the abstract UML Map data structure storing hash maps of the UML class diagram elements. This data structure allows analyzing and transforming UML class diagrams in a convenient way. The paper presents algorithms of UML class diagram analysis in order to apply Strategy and Interface Insertion transformations. Computational experiment demonstrated that the computational complexity of these algorithms is O(n). The proposed algorithms became a part of the UML Refactoring Tool, which allows user to import UML class diagrams from XMI format, to analyze and transform it (calculate metrics, receive transformation recommendations) and to export it back to the XMI format.

DOI: 10.25136/2644-5522.2018.6.28081

Abstract: The subject of this research is to evaluate the effectiveness of the approximation of objects with discrete output based on fuzzy knowledge bases. The object of the research is the neuro-fuzzy model, which allows, based on the training of a fuzzy neural network, to form a system of fuzzy-production rules (a fuzzy knowledge base) for assessing the state of objects. The author examines in detail the type of fuzzy-production rules proposed by him, the algorithm of logical inference on the rules, describes the developed model of a fuzzy neural network. Particular attention is paid to the need to assess the approximating ability of the model in order to determine the feasibility and effectiveness of its practical use. This assessment was made by analyzing the following model characteristics:- convergence of the developed learning algorithm for fuzzy neural network;- satisfaction of its work with the principles of fuzzy approximation;- consistency of the logic inference algorithm on the rules of the model to the well-known algorithm for approximating objects with discrete output based on a fuzzy knowledge base. The estimation of the approximating ability of the neuro-fuzzy model was made, based on the results of which it was concluded that this model is an effective approximator of objects with a discrete output. In addition, in order to test the model, an assessment was made of the classifying ability of the fuzzy rules being formed. The accuracy of classification based on fuzzy rules turned out to be no lower than the accuracy of other known classification methods. The practical value of the application of such rules is the ability to build decision support systems for assessing the state of objects in various subject areas.

DOI: 10.7256/2306-4196.2015.5.16592

Abstract: The subject of the study is the need for decision-making in the semi structured dynamic situations, when the parameters, the laws and regularities of the situation are described qualitatively. Those are unique situations, in which the dynamics of the parameters of the situation is combined with the difficulty of predicting changes in its structure. Object of research are cognitive maps or computer systems for modeling cognitive maps. The author considers in detail such aspects of the topics as the complexity of the decision making when the information is insufficient and inaccurate, methods of optimization for cognitive maps used in forecasting. Special attention is paid to the optimization of data dimension algorithm and optimization of the cognitive maps structure. To optimize the dimensions of the data the author uses cluster analysis methods, optimization of the structure of cognitive maps is performed by automatic changing of the weights of the impact of concepts to other machine learning methods. The main conclusion of the study is the decrease in subjectivism of the cognitive map in predicting system. Authors' contributions to the study of the subject is a representation of the cognitive map as a single-layer neural network and the application of methods of neural networks training, proposed by Rosenblatt. The novelty of the study is in the new structure of cognitive maps.

DOI: 10.7256/2306-4196.2016.5.19885

Abstract: The object of research is the model of artificial immune system. Subject of the research is providing a method of constructing a fuzzy decoder. The authors proposed to use fuzzy membership function as the decoders. This functions describes the relevance of a controlled parameter to a critical situation. Using such an approach based on fuzzy decoders allows to move from binary quantitative classification to fuzzy qualitative estimates. The article present an example o f construction of a decoder for fuzzy term “semiperimeter length of L, describing a fragment of the designed product, should be no more than 0.7 nm”. On the basis of the function CON(μ1(L)), describing fuzzy matching condition “very close to 0.7 nm” the authors build a function μ5(L), describing fuzzy matching condition “a little less than 0.7 nm”. Fuzzy decoder for conformity assessment interval is based on the given interval membership function. The authors give a graph of a μ7 decoder  function semiperimeter on the length L, describing the belonging to “semiperimeter desired length from 0.55 to 0.7 nm” condition. By analogy with the conditions “very close to 0.7 nm” and “slightly close to 0.7 nm” it is possible to determine a membership functions “very in range from 0.55 to 0.7 nm” and “slightly in range from 0.55 to 0.7 nm”. The research method is based on the construction of fuzzy decoders describing the undesirable state of the computational process. Fuzziness is described by the membership function. The novelty of the research is in getting fuzzy decoders receptive to fuzzy commands. Using the corresponding fuzzy membership function μ decoder it is possible adjust the process of estimating the degree of closeness of the controlled parameter to a critical situation. Applying CON and DIL functions to the decoder functions allows to change their susceptibility on test data from 20-30% up to 200% -300%.