Intellectual Decision Support System Research Articles

Methods and models of organization and processing of data and knowledge in an intelligent decision support system for the identification of cultural values

The problem of developing an intellectual decision support system for the identification of cultural values (on the basis of works of art), the issue of choosing and justifying methods and tools for its construction is considered. Methods of research and construction of complex objects, prospects of using similar systems based on modern artificial neural networks as a tool for developing an intelligent decision support system are considered. Considerable attention is paid to the issues of methods of automatic identification and classification of works of art, as the main elements of an intelligent decision support system. Prospects and ways of further research and use of this subject area are also defined.

Clinical decision support systems in advanced qualification: history and modern trends

The problem of physicians’ continuous professional development may be solved in different ways. The purpose of this article is to demonstrate the use of computerized clinical decision support systems for resolving the considered problem. It is shown that intelligent systems possess the ability to obtain new knowledge, in contrast to computing systems based on data processing. We have come to this conclusion by explaining the sequence of hypothesis generation and analysis, as well as by explaining the proposed solution. In addition, there are intelligent systems that are focused on dialogue with a physician directly to improve his qualifications in a specific subject area. Thus, in the field of continuous additional professional development, we can use both special educational intellectual programs and decision support systems, including explanation modules. In the future, stand-alone diagnostic and other systems will be used only in exceptional cases. The modern trend is focused on their integration into electronic medical records systems. In this case, such systems will be used in the framework of preventive examinations or treatment-and-diagnostic process.

Управление качеством наукоемких проектов на основе применения интеллектуальных систем поддержки принятия решений

Управление качеством наукоемких проектов на основе применения интеллектуальных систем поддержки принятия решений

МОДЕЛЮВАННЯ ВЗАЄМОДІЇ ДЕРЖАВНИХ ОРГАНІВ І СТРУКТУРНИХ ОДИНИЦЬ БУДІВЕЛЬНИХ КЛАСТЕРІВ

Правильна організація зв’язків структурних одиниць кластера з державними орга-нами забезпечує передумови досягнення найбільшого внеску всіх підсистем кластера в його діяль-ність. Таким чином забезпечується додатковий синергетичний ефект, урахування якого приуправлінні, в значній мірі, сприяє підвищенню конкурентоспроможності та стійкості кластера.Роль держави в процесах формування і розвитку кластерів полягає в створенні інфраструктурита органів, призначенням яких є забезпечення сприятливих умов для ефективної діяльності клас-тера. При цьому особливої актуальності набуває задача виявлення тих структурних одиниць буді-вельного кластера, державна підтримка яких, забезпечить максимальний синергетичний ефект. Вроботі запропоновано схему, згідно з якою здійснюється обґрунтування вибору структурних оди-ниць кластера, що потребують державної підтримки. Схема передбачає багатоваріантне про-гнозування ефективності діяльності різних кластерних структур и формування бази знань, яка вподальшому стане основою інтелектуальної системи підтримки прийняття рішень щодо виборуструктурних одиниць кластера

РІШЕННЯ ЗАВДАННЯ ОПТИМІЗАЦІЇ ПАРАМЕТРІВ ОБРОБКИ МЕТАЛІВ ПРИ ОПЕРАЦІЇ ТОЧІННЯ

The statement and solution with the application of the intellectual decision support system (IDSS) for optimization of metal processing parameters during the turning operation are shown. The task was posed during the development of IDSS, which allows automating the development of the technological process (TP), optimizing and managing it. The absence of such systems of intellectual support for decision-making does not allow enterprises to fully utilize the capabilities of high-tech equipment and reduces the efficiency and profitability of production due to inefficient use of machine tools, material and engineering resources of enterprises. The tasks of synthesis of the optimal technological process are solved in two stages: the first – structural optimization of the technological process (synthesis of the optimal TP structure); the second – parametric optimization of the technological process (determination of optimal operating parameters for all operations of the technological process). The task of optimizing the parameters of metal processing during the turning operation is one of the subtasks of the second stage of the synthesis of the optimal structure of the technological process of metal machining. The task is solved taking into account the level of accumulated wear on the back surface of the tool, the level of machine efficiency, depending on the operating modes and the period of economically effective tool life. The task is solved in a multi-criteria setting taking into account three objective functions: the cost of operations, the specific energy costs for operations and the operation's performance and the ten existing technical and technological limitations. The solution is obtained as a Pareto-optimal solution. During the solution, an artificial neural network and the genetic algorithm FFGA were applied. This approach allows us to solve the problems of optimization of real production. Shown: the statement of the problem and its practical solution, the structure of the developed system of intellectual support for decision-making, present’s practical results of solving the task, verified the results obtained. The technological map obtained with the help of the IDSS for processing the surface of the «Filter housing» component of the GP-21 generator drive.

Rationale for prompt access to the appendix in people with abdominal obesity.

Relevance. Currently, acute appendicitis occupies a leading position in the structure of surgical diseases that require urgent surgical intervention. A significant part of operations for acute inflammation of the appendix is ​​performed from the laparoscopic approach. But, despite the wide possibilities of modern medicine, it is often necessary to resort to traditional laparotomic access. The classic access to the appendix is ​​the access via Volkovich-Dyakonov through the Mac-Burney point or the Lanz point. In fact, in most cases, the projection of the base of the appendix does not coincide with the Lanz and Mac-Burney points. This is due to differences in the location of the appendix in the abdominal cavity, as well as with individual constitutional parameters, including the presence or absence of obesity. In addition, in women the dome of the cecum and the appendix are slightly lower than in men. Considering these aspects, as well as the inadmissibility of delaying surgical treatment, it becomes necessary to determine the access point to the appendix as clearly and quickly as possible.
 Aim is development and implementation of the surgeon’s intellectual decision support system (IDSS) in the definition of operative access to the appendix in people with abdominal obesity.
 Materials and methods: for the development of the IDSS of the surgeon, 101 SKT images were analyzed, which were used to build 3D models of the studied areas. 3D modeling allows for more accurate geometric measurements. The program “Inobitec DICOM Viewer” was used to work with images. It was decided to use the development environment “Embarcadero Delphi XE7” to implement the decision support system.
 Results: an algorithm was developed to support the surgeon's decision in determining prompt access to the appendix, and the software implementation of the IDSS of the surgeon was completed. The IDSS of the surgeon was tested and showed good results.
 Conclusion: the development of the IDSS of the surgeon is designed to speed up preoperative preparation and significantly reduce the number of medical errors in determining prompt access to the appendix, which is important in urgent surgery.

A MODIFIED CASE-BASED REASONING METHOD BASED ON THE ROUGH SET THEORY

Context. Knowledge bases are the main element of artificial intelligence systems. They are formed on the basis of two generally accepted approaches: the object-oriented approach and object-structural approach. Knowledge structuring through its ordering, classification and typing of selected classes is the main operation that is implemented in both approaches. Quite often there are situations when data or knowledge is not exact and it is impossible to perform their exact classification. These features necessitate the development of new approaches aimed at solving problems of extracting knowledge from large arrays of unordered data, structuring, presenting and analytical processing of inexact knowledge in automated construction of knowledge bases. Objective. The objective of this paper is a research of new approaches for solving problems of representation of knowledge about cases in intellectual decision support systems. Method. An approach aimed at modifying Case-Based Reasoning method on the basis of Rough Set Approach has been proposed in this paper. The proposed method forms a partition of cases to determine the degree of their belonging to the goal classes using upper and lower approximations of goal classes, considering the relative importance of classification attributes and formed equivalence classes. Results. The proposed modification of Case-Based Reasoning method allows extracting knowledge about cases from arrays of unordered data with the purpose of the case base construction, and handling the inconsistent (in cases where for the same values of attributes cases belong to different classes), and incomplete (in cases where the values of some attributes or information of the case belonging to the given class is missing or unreliable) information about cases. Conclusions. The proposed method of representation knowledge about cases, their adaptation and subsequent search in the case base formed under uncertainty and existence of inexact, rough, inconsistent initial data constitutes a theoretical basis for constructing intellectual decision support systems.

ПІДХІД ЩОДО ФОРМУВАННЯ РЕКОМЕНДАЦИЙ ДЛЯ ПРИЙНЯТТЙ ОБГРУНТОВАНИХ РІШЕНЬ ОПЕРАТОРОМ ПРИ ДИСТАНЦІЙНОМУ УПРАВЛІННІ БЕЗПІЛОТНИМ ЛІТАЛЬНИМ АПАРАТОМ

The article considers the system of remote control of UAV. The task of forming teams in remote control is logical and analytical, the development of common rules for determining the program, flight parameters under uncertainty is difficult to solve. Insufficient degree of adaptability to external conditions and the impossibility of forming control signals on board the UAV on the basis of incomplete, inaccurate initial information, despite the sufficient level of solving settlement problems, negatively affects the quality of the solution of a given task. It is proposed to increase the efficiency of solving the tasks of intelligence, target identification, correction of artillery fire, assessment of the impact of the use of the intellectual decision support system (DSS). At the heart of the functioning of intellectual DSS is the procedure of matching the current and reference image with the subsequent formation of recommendations to the operator for the management of UAV. The use of a structurally-linguistic approach is proposed, when each object in an image after coding represents a certain structure of the "linguistic" type. After reconciling the reference and current images as a result of the logical output in the production model of presentation of knowledge formed recommendations to the operator.

INTELLIGENT MEANS IN THE SYSTEM OF MANAGING A MANUFACTURING AGENT

The subject of the study is intellectual means in the system of managing an intelligent manufacturing agent; the goal is to ensure the quality of managing a flexible integrated robotic system by developing the intellectual decision support system. The following problems are solved in the work: current tendencies of developing and implementing the intelligent systems for production management are considered; the demands for developing simulation models of decision support systems for solving flexible integrated production systems are formulated; the logical model of a decision support system for an intelligent manufacturing agent is developed, this model describes the decision-making process in the form of the functioning strategy formation on the basis of the knowledge of the current state of the integrated system, the system of knowledge describing probable actions of the robotic equipment, the objectives of the production system, and adapts the strategy if the working space of the integrated system or its individual goals change; the system of knowledge of a flexible integrated system is presented as a set of standard description of probable actions for robotic equipment; the distributed workspace of integrated systems is considered and described; separate objects are identified using the means of computer vision. The research is based on the following theoretical and practical foundations: the theory of sets is used to represent general simulation models of the decision support system; the theory of predicates is used to create a logical model of decision-making; knowledge-oriented methods and the tools of Prolog programming language use used to represent the knowledge system of a flexible integrated system, the MatLab system is used to analyse the workspace of a flexible integrated system. The following results are obtained – mathematical and informational software of the system for managing an intelligent production robotic agent is developed. The possibilities of the proposed model application in the system of managing an intelligent robot are shown and the ways for improving such systems are suggested.

The emergency simulation with the help of four-layer hidden Markov model

The object of research is the process of selecting a synergistically determined pair for the elements of complex systems in the design, manufacture or repair. One of the most problematic places in the selection is the need to numerically evaluate the result of combining the elements, taking into account the explicit, additive properties of elements and hidden manifestations of the pair that are unusual for the elements alone (emergence). Lack of accounting for emergence can significantly distort the apparent picture of the processes taking place in systems, which makes many existing models of such processes inadequate. During the research, methods of extracting information from arrays known, hidden for direct observation were used. In particular, four-layer hidden Markov models with an additional hidden layer were used. The models were trained by the Baum-Welch method, adapted to work with an additional layer. As training samples used data obtained as a result of statistical processing of information available for object monitoring, expert assessments, as well as data obtained in the world's computer networks. The test of the method and model on real medical and technical objects confirms their clinical and technical effectiveness. In particular, thanks to this in the medical industry: in the medical industry, the incidence of thromboembolism of the branches of the pulmonary artery and deep veins of the thigh and lower leg are decreased by 65 %; frequency of postoperative bleeding is decreased by 43 %; by 36 % the total number of drug-related medicines aimed at correcting the blood coagulation system is decreased. In the technical field, the test results confirm the increase in the service life of rubber-metal shock absorbers by 14.5 %. This is due to the fact that the proposed method has a number of features, in particular, for the first time in its evaluation of emergence a four-layer hidden Markov model is used. The results obtained in the work make it possible to propose a general scheme of an intellectual decision support system in the selection of a synergistically determined pair of elements for complex systems of various purposes.

АНАЛИЗ МЕТОДОВ УПРАВЛЕНИЯ ДОМЕННОЙ ПЛАВКОЙ НА ОСНОВЕ ИНФОРМАЦИИ О ФОРМЕ И ПОЛОЖЕНИИ ПЛАСТИЧНОЙ ЗОНЫ

The aim of the work is to formulate recommendations on the adoption of control actions on the course of smelting in modern conditions. The ideology of the modern intellectual decision support system for blast smelting management is based on providing the optimal plastic zone in the blast furnace (DP). Blast furnace melting control methods are based on information on the shape and position of the plastic zone in the blast furnace. According to the results of research carried out by various scientists, it was shown that the plastic zone is a hollow cone, the walls of which consist of alternating horizontal coke layers with high gas permeability and low-permeable for gas layers of iron ore materials that are in a softened, semi-molten state. The work describes the factors that determine the shape and position of the plastic zone in the DP. The analysis carried out showed that the mode of loading of charge materials has the main influence on the formation of the plastic zone. It was noted that, in addition to various modeling methods, it is advisable to create a criterion for assessing the shape and position of the plastic zone, which would take into account its thickness, profile and position in the DP, to control and control the blast smelting process. Developed recommendations for making management decisions during smelting.

Development of robototechnological complex of intellectual management by bread manufacturing for technological loading territories

The object of research is a technological line for production of bakery products. One of the most problematic places in the technological process of industrial production of bakery products is the incoming quality control and preliminary preparation of ingredients, as well as the implementation of the processes of preparation of dough and kneading dough. To improve and intensify the relevant processes, it is proposed to use robotic technological complexes with an intelligent control system and built-in intensifiers. The principle of the intensifiers of the technological process is based on ultrasonic technologies of water treatment, mixing of components, intensification of physical and chemical processes of bread production, quality control of the process. For the production of bread with therapeutic and prophylactic characteristics, the controlled ultrasonic cavitation effects are studied. It has been proved that processes of ultrasonic cavitation, disintegration, coagulation of water, flour, oil, liquid yeast, hydrochloric and sugar solutions and other ingredients promote the production of medical type. Ultrasonic cavitation causes increased fluid mixing of the micro streams that form around the oscillate bubbles. Such mixing is especially useful in the technological process of producing bread for dispersion when enriched with vitamins and minerals. Systems for automated control of parameters of pre-dough-dough based on high-frequency ultrasonic vibrations are developed. It is proved that robotic technological complexes with developed sensor system allow to reduce the salt and sugar content in bread by 15–20 % without changing the taste of the product. A multi-level intelligent system of automated management of the technological process of bread production has been developed. The architecture of this system uses a robotic technology complex with: – intellectual decision support system and training blocks; – databases and knowledge; – block output information on the corporate performance monitor; – automated workplace with an interface system; – artificial neural network for recognition of emergency, abnormal and normal situations. Thus, with the help of the robotic technological complexes built into the technological process of bread production, it is possible to achieve a higher quality of bakery products.

Boundary conditions in problems of studying the stability of a plane stationary detonation wave

The research’s problems of a plane stationary detonation wave’s stability are considered. It is shown that the boundary conditions for the two-front model allow estimating the main parameters of the internal structure of gas detonation. Such a model can serve as the basis for development of mathematical support and software for an intellectual decision support system for the problems of explosion-proof and explosion protection. An attempt has been made to systematize the problem of setting boundary conditions in studies of the stability of a detonation wave in order to further create a decision support system (DSS) on problems of explosion safety and explosion protection. The following models of a plane stationary detonation wave were considered, which the stability problem is stated for: 1) the Chapman-Jouget detonation model is the simplest model where the shock-detonation front is modeled by a direct shock wave, and all chemical transformations are assumed to occur instantaneously, directly at the front; 2) a two-front (single-stage, square-wave) model based on the assumption that chemical transformations also occur instantaneously, not on the leading shock front, but in a plane (called the instantaneous combustion front), which is separated from the leading shock front by the induction zone; 3) a multistage model that approximates the continuous distribution of parameters behind the leading shock front piecewise constant function; 4) a model with a continuous distribution of parameters behind the leading shock front, which most accurately reflects the real physical processes in a stationary detonation wave. These models are fundamentally different in boundary conditions, which small pertur-bations in the region separating the regions of the initial combustible medium and detona-tion products satisfy. The advantages and disadvantages of the models described above are both assessed from the standpoint of the correctness of the physical analysis of the detonation process and from the point of view of applicability for the mathematical support of DSS on problems of explosion safety and explosion protection. It is shown that the boundary conditions for the two-front model allow to estimate the main parameters of the internal structure of the gas detonation. Such model can be as the basis for the development of mathematical support and software of DSS for problems of explosion safety and explosion protection

Case-based reasoning approach for monitoring multi-phase liquid in pipeline

A method based on collecting, integrating and subsequence analyzing data on multi-phase liquid flow condition in pipeline is suggested in the paper. The principles of constructing multi-component liquid control system with the use of ultrasonic signal as a sensing one and initial execution algorithm of ultrasonic emitters-receivers with subsequent change of roles are presented as well. CBR method used while identifying multi-phase condition is an element of processing part of the system – intellectual decision-support system.

INTELLECTUAL EVOLUTION SYSTEM OF SUPPORT OF DECISION-MAKING BASED ON NEURAL NETWORK AND IMMUNE APPROACHES

The article considers the model of the intellectual decision support system based on the neural network, the training and evolution of which are carried out using the immune approach.
 The evolution of the system is considered as the task of adapting it to the conditions for changing the external environment and the properties of the decision-making object, consisting of procedures for correcting the number of neurons in the hidden layers and the parameters of the system model using immune models for clonal selection and the immune network.

Method of Neuronet Classification of Situations in Financial Markets and Its Implementation in IDSS

Задача разработки инструментов анализа финансовых рынков, основанных на современных методах искусственного интеллекта, имитирующих работу трейдеров рынка, которым для принятия решения необходимо проанализировать большое количество разнородной информации о рынке, становится все более актуальной в настоящее время. В статье рассматривается применение нейросетевого классификатора в качестве ядра интеллектуальной системы поддержки принятия решений трейдера финансовых рынков. Обозначены основные характеристики систем типа интеллектуальная система поддержки принятия решений. Приведена методика нейросетевой классификации рыночных ситуаций, построенная с применением различных подходов к анализу финансовых рынков, таких как технический, фундаментальный анализ и эконометрическое моделирование. Основу методики составляет интегрированный анализ информации на основе нейронной сети топологии многослойный перцептрон. Представлены результаты проектирования системы, использующие алгоритм методики нейросетевой классификации рыночных ситуаций, архитектура системы, исследования работоспособности и эффективности работы интеллектуальной системы поддержки принятия решений трейдеров на финансовых рынках, основанной на описанной методике классификаций рыночных ситуаций. По результатам экспериментального исследования на нормированной по параметрам эксперимента выборке обозначена эффективность работы системы в 83 %.

Complex systems modeling with intelligent control elements

The approach to managing complex systems through the usage of fuzzy technology in combination with the system-dynamic modeling is improved. The methods of system dynamics and artificial intelligence represented the research subject. Object of study includes process operation of complex systems. For the experiment selected banking system (BS) and commercial bank (CB) as its subsystem. The mathematical models of the BS and CBs are developed; elements of intelligent control are formalized. The knowledge base in the form of production rules is designed in the paper. Functions of fuzzy variables and their parameters are selected for building fuzzy models using Mamdani and Sugeno algorithms. The control impact and the functioning of intellectual decision support system for the prediction task are studied. The efficiency of scientific research on the example of the Ukrainian BS is evaluated.

Construction of intelligent decision support system in control of gas compression process

The necessity to construct the intelligent decision support systems (IDSS) in the control of the gas compression process with inclusion in structure of the training module is substantiated. А block diagram of human-computer interaction in the system "Dispatcher - IDSS - ASC GCU - CS" is shown, and the functions of the separate blocks of the intellectual decision support system in the control of the gas compression process are defined

Local a priori Inference in Algebraic Bayesian Network: a Set of Basic Algorithms

A priori inference is a key feature in intellectual decision support systems based on imperfect probabilistic knowledge. The paper describes a set of local a priori inference algorithms in algebraic Bayesian networks.

Matrix-Vector Equations for Local Probabilistic Logic Inference in Algebraic Bayesian Network

Probabilistically uncertain knowledge patterns processing in intellectual decision support systems falls into three kinds of probabilistic-logic inference, such as reconciliation, a priori and a posteriori inference. The paper presents formulae that allow for putting the process down in terms of matrix-vector language.