Abstract: The subject of the study is the concept of "power of attorney" of artificial intelligence controlling robotic means of varying degrees of autonomy. The relevance of the choice of the subject of research as the principles of the use of robotic systems for various purposes, including in a group, and the object of research, which are algorithmic problems arising in the implementation of group action algorithms, is determined by the existing contradiction between the need for joint use of robotic systems, primarily autonomous, and the complexity of the software implementation of this requirement. The implementation of robotics generates certain technological problems related to the efficiency and safety of algorithmic support of autonomous and controlled robotic systems. The manifestation of such problems may be application errors that reduce the effectiveness of joint actions. In robotics, the main potential reason for the appearance of such a situation is the insufficient effectiveness of existing group application control algorithms, determined by the low level of problem study. The article formulates a list of typical situations that determine the use of autonomous and controlled robots in a group with a leader. On the basis of the proposed classification, possible algorithms for controlling movement in the group are analyzed: both calculations for target maneuvering and for ensuring mutual security. The main situations concerning the types of maneuver are formulated and the mathematical apparatus for their calculations is described. Based on the overview analysis of typical algorithms for controlling movement in space, the formulation of the scientific problem of solving the problem of developing group algorithms and mathematical methods is synthesized.

Keywords: mathematical security, safety behavior management, morality of robotic systems, ethics of robotic systems, safe behavior, control of behavior algorithms, trustworthy artificial intelligence, control software, artificial intelligence, robotic system

Abstract: The article reflects the use of neural network technologies to determine the facts of falsification of the contents of video sequences. In the modern world, new technologies have become an integral part of the multimedia environment, but their proliferation has also created a new threat – the possibility of misuse to falsify the contents of video sequences. This leads to serious problems, such as the spread of fake news and misinformation of society. The scientific article examines this problem and determines the need to use neural networks to solve it. In comparison with other existing models and approaches, neural networks have high efficiency and accuracy in detecting video data falsification due to their ability to extract complex features and learn from large amounts of source data, which is especially important when reducing the resolution of the analyzed video sequence. Within the framework of this work, a mathematical model for identifying the falsification of audio and video sequences in video recordings is presented, as well as a model based on a three-dimensional convolutional neural network to determine the fact of falsification of a video sequence by analyzing the contents of individual frames. Within the framework of this work, it was proposed to consider the problem of identifying falsifications in video recordings as a joint solution to two problems: identification of falsification of audio and video sequences, and the resulting problem itself was transformed into a classical classification problem. Any video recording can be assigned to one of the four groups described in the work. Only the videos belonging to the first group are considered authentic, and all the others are fabricated. To increase the flexibility of the model, probabilistic classifiers have been added, which allows to take into account the degree of confidence in the predictions. The peculiarity of the resulting solution is the ability to adjust the threshold values, which allows to adapt the model to different levels of rigor depending on the task. The architecture of a three-dimensional convolutional neural network, including a preprocessing layer and a neural network layer, is proposed to determine fabricated photoreceads. The resulting model has a sufficient degree of accuracy in determining falsified video sequences, taking into account a significant decrease in frame resolution. Testing of the model on a training dataset showed the proportion of correct detection of video sequence falsification above 70%, which is noticeably better than guessing. Despite the sufficient accuracy, the model can be refined to more significantly increase the proportion of correct predictions.

Keywords: batch normalization, anomaly detection, data preprocessing, audio falsification, deepfake detection, deepfakes, video falsification, convolutional neural networks, neural networks, machine learning

Abstract: The paper considers the problem of automated recognition of single emergencies in chemical and oil refining industries. Modern chemical and technological production facilities are maintained and managed by a small number of personnel, which increases the burden on each operator. To reduce the number of operator errors, their training is regularly conducted on simulators equipped with a set of both standard situations (routine start-up, shutdown, normal process management, switching from one mode to another) and emergency scenarios (column depressurization, pump failure, failure of the power supply system). Nevertheless, it is impossible to foresee all possible failures during operator training, and even a trained operator may not notice the first signs of an accident, and therefore it is necessary to create a decision support system that helps the operator to recognize failures of technological equipment in a timely manner. To recognize failures, it is proposed to use a neural network trained on an array of simulated accident data. An industrial simulator based on the RTsim platform was used to simulate typical accidents. The novelty of the research lies in the use of artificial intelligence methods to diagnose the property of the technological process according to the SCADA system and the use of data for training a neural network not from a real object (which will always be insufficient), but from a model that exactly corresponds to a specific technological site. The number of simulated scenarios used to train a neural network can be quite large, which reduces the proportion of erroneous system responses. The developed system confidently copes with the recognition of individual equipment failures. The results obtained can be used to help process operators and to improve emergency protection systems. The analysis of the time required by the system to recognize an emergency situation can be used to design new production facilities, modify the control and management system.

Keywords: industrial safety, decision-support system, simulation modeling, Digital Twin, RTsim, computer trainer, artificial intelligence, accident, failure, oil refining

Abstract: The object of the research is artificial neural networks (ANN) with convolutional architecture for image classification. The subject of the research is the study and development of algorithms for constructing ensembles of convolutional neural networks (SNS) in conditions of limited training sample. The aim of the study is to develop an algorithm for the formation of an effective model based on an ensemble of convolutional SNS using methods of averaging the results of each model, capable of avoiding overfitting in the process of improving the accuracy of the forecast and trained on a small amount of data, less than 10 thousand examples. As a basic network, an effective SNA architecture was developed as part of the ensemble, which showed good results as a single model. The article also examines methods for combining the results of ensemble models and provides recommendations for the formation of the SNA architecture.  The research methods used are the theory of neural networks, the theory of machine learning, artificial intelligence, methods of algorithmization and programming of machine learning models, a comparative analysis of models based on different algorithms using classical ensembling with simple averaging and combining the results of basic algorithms in conditions of limited sampling, taking into account weighted average. The field of application of the obtained algorithm and model is medical diagnostics in medical institutions, sanatoriums during primary diagnostic admission, using the example of a research task, the model is trained to classify dermatological diseases according to input photographs. The novelty of the study lies in the development of an effective algorithm and image classification model based on an ensemble of convolutional NS that exceed the prediction accuracy of basic classifiers, the process of retraining an ensemble of classifiers with deep architecture on a small sample volume is investigated, from which conclusions are drawn on the design of an optimal network architecture and the choice of methods for combining the results of several basic classifiers. As a result of the research, an algorithm has been developed for the formation of an ensemble of SNS based on an effective basic architecture and weighted average averaging of the results of each model for the classification task of image recognition in conditions of limited sampling.

Keywords: pre-treatment, methods of neural network ensembling, medical diagnostics, the task of classification, ensembles of neural networks, weighted average, methods of averaging the results, convolutional architecture, artificial neural networks, balanced voting

Abstract: The subject of the research is the development of a software package for intelligent forecasting of the execution of government contracts using machine learning methods and analysis of unstructured information. The object of the study is the process of control and decision-making in the field of public procurement, including the selection of contractors, the execution of contracts and the assessment of the timing and cost of their implementation. Special attention in the study is paid to the development and application of interpreted machine learning methods to solve the problems of assessing the risks of choosing an unscrupulous contractor, the risks of non-fulfillment of the contract on time and forecasting the likely timing and cost of contract implementation. The authors consider in detail such aspects as a unique set of data that was collected from various information systems. They have also developed automated data collection and update systems that can be installed on customers' servers. The methods of machine learning, analysis of unstructured information and interpreted methods were used in the work. Interpreted machine learning models were built to assess the risk of choosing an unscrupulous contractor, assess the risk of non-fulfillment of the contract on time, as well as assess the likely timing and cost of contract implementation. A unique set of data was collected in the work, including more than 83 thousand data on more than 190 features from various systems, such as the Unified Information System (UIS) Public Procurement Register, the Register of Unscrupulous Suppliers (RNP) EIS and SPARK Information System. Automated data collection and updating systems have been developed that can be deployed on customer servers. In the course of the study, software packages were developed for intelligent forecasting of the execution of government contracts, which provide an opportunity to conduct a more accurate risk analysis using unstructured information analysis methods, machine learning models and interpreted methods. This makes it possible to increase the effectiveness of monitoring the implementation of government contracts and reduce the likelihood of corruption and violations. The study demonstrates the importance and applicability of machine learning methods and models in the field of public contracts and provides new opportunities for improving control and decision-making processes in the field of public procurement.

Keywords: ensemble methods, interpreted artificial intelligence, regression analysis, risk assessment, forecasting, the method of support vectors, data visualization, intelligent systems, machine learning, government contracts

Abstract: The subject of the research is a logical approach to data analysis and the development of software tools capable of identifying hidden patterns, even with a limited amount of data. The input data consists of indicators of the diagnosis of patients, their diagnoses and the experience of doctors obtained in the course of medical practice. The research method is the development of software tools based on systems of multivalued predicate logic for the analysis of patient data. This approach considers the source data as a set of general rules, among which it is possible to distinguish those rules that are sufficient to explain all the observed data. These rules, in turn, are generative for the area under consideration and help to better understand the nature of the objects under study. The novelty of the study lies in the use of multivalued logic to analyze a limited amount of medical data of patients in order to determine the most likely diagnosis with a given accuracy. The proposed approach makes it possible to detect hidden patterns in the symptoms and results of patient examinations, classify them and identify unique signs of various forms of gastritis. Unlike neural networks, logical analysis is transparent and does not require training on large amounts of data. The conclusions of the study show the possibility of such an approach for diagnosis with a lack of information, as well as the offer of alternatives if the required accuracy of diagnosis is not achieved.

Keywords: properties, training, product rules, classifier, hidden patterns, analysis, data, multivalued logic, communications, diagnostics

Abstract: The subject of this study is to identify a set of common structural properties inherent in recurrent neural networks and stochastic automata, the feature of which is purposeful behavior in dynamic environments. At the same time, the necessary commonality of properties is revealed both in the process of their functioning and in the process of their training (tuning). The author considers in detail such topics as: formalization of purposeful behavior, consideration of the design of automata, as well as a comparative analysis of the considered designs of automata. From the revealed commonality of functioning and the established one-to-one correspondence of neurons of a fully connected recurrent neural network and states of a probabilistic automaton with a variable structure, it follows that the structure of a tuned stochastic automaton can be considered as a reference for a set of connections of a recurrent neural network. This leads, even at the setup stage, to the removal of redundant states (neurons) and connections between them, based on the parameters of the corresponding automaton. The methodology of the conducted research is the construction of a one-to-one correspondence between the neurons of a fully connected recurrent neural network and the internal states of an automaton with a variable structure and the probabilities of transitions between them that are relevant after the tuning process. With a one-to-one correspondence, the probabilities of transitions of the automaton correspond to the weights of connections between neurons of the optimal configuration. The main conclusions of the study: 1. Comparing the structures of recurrent neural networks and automata with a variable structure allows one to take advantage of an automaton with a variable structure to solve the problem of appropriate behavior in dynamic environments and build a recurrent neural network based on it; 2. The correspondence of the internal structure of a recurrent neural network and an automaton with a variable structure allows already at the training stage to release the trained recurrent neural network from redundant neurons and redundant connections in its structure; 3. Due to the fact that an automaton with a variable structure approaches the optimal automaton with linear tactics for these conditions with nonlinear values of the learning rate, this allows a logical analysis of the structure of the final recurrent neural network.

Keywords: markov chain, probability matrix, linear tactics, appropriate behavior, management task, context, time sequence, neuron, machine, recurrent neural network

Abstract: Veterinary medicine is an area where modern technology can have a significant impact. The application of expert systems in this field has not yet been fully explored. Expert systems can process large amounts of data, including symptoms, disease history and other parameters to provide accurate and rapid diagnoses. This is especially valuable in situations where rapid intervention can save an animal's life. These systems can serve as a supportive tool for veterinarians, especially in complex or rare disease cases. They can provide recommendations based on the latest research and clinical practices. In agriculture, expert systems can analyze data on the health of the entire herd and identify possible problems or trends, helping farmers and veterinarians to take timely action. This article focuses on the development of a veterinary expert system that reflects current animal health needs. The authors perform a detailed analysis of existing veterinary systems, highlighting key functionalities needed by veterinary and agricultural professionals. One unique aspect of the paper is the use of symptom-complexity weighting and probability calculations of diagnosable diseases, which can make a significant contribution to the accuracy and efficiency of animal disease diagnosis. The paper can serve as a useful resource for veterinary specialists as well as software developers involved in the creation of intelligent systems in medical and agricultural applications.

Keywords: artificial intelligence, relational databases, knowledge base, veterinary software, veterinary diagnostic systems, diagnosis, expert module, expert system, software systems, computational methods

Abstract: The subject of the study is the architecture of the RSS feed aggregation system. The author considers in detail such aspects of the topic as choosing the right data aggregation strategy, an approach to scaling a distributed system, designing and implementing the main modules of the system, such as an aggregation strategy definition module, a content aggregation module, a data processing module, a search module. Particular attention in this study is given to a detailed description of the libraries and frameworks chosen for the implementation of the system under consideration, as well as databases. The main part of the system under consideration is implemented in the C# programming language (.Net Core) and is cross-platform. The study describes the interaction with the main data stores used in the development of the aggregation system, which are PostgreSQL and Elasticsearch. The main conclusion of the study is that before developing an aggregation system, it is necessary to analyze the publication activity of data sources, on the basis of which it is possible to form an acceptable strategy for updating the search index, saving a significant amount of resources. computing power. Content aggregation systems, such as the one considered in this study, should be distributed, built on the basis of event-driven and microservice architectures. This approach will make the system resistant to high loads and failures, as well as easily expandable. The author's special contribution to the study of the topic is a detailed description of the high-level architecture of the RSS aggregator, designed to process 50,000 channels.

Keywords: content categorization, cross-platform, fault tolerance, scalability, competing consumers pattern, microservice architecture, RabbitMQ, Elasticsearch, RSS aggregation, expert system

Abstract: The Internet has emerged as a powerful infrastructure for worldwide communication and human interaction. Some unethical use of this technology spam, phishing, trolls, cyberbullying, viruses caused problems in the development of mechanisms that guarantee affordable and safe opportunities for its use. Currently, many studies are being conducted to detect spam and phishing. The detection of telephone fraud has become critically important, as it entails huge losses. Machine learning and natural language processing algorithms are used to analyze a huge amount of text data. Fraudsters are identified using text mining and can be implemented by analyzing the terms of a word or phrase. One of the difficult tasks is to divide this huge unstructured data into clusters. There are several thematic modeling models for these purposes. This article presents the application of these models, in particular LDA, LSI and NMF. A data set has been formed. A preliminary analysis of the data was carried out and signs were constructed for models in the task of recognizing the subject of the text. The approaches of keyword extraction in the tasks of text topic recognition are considered. The key concepts of these approaches are given. The disadvantages of these models are shown, and directions for improving text processing algorithms are proposed. The evaluation of the quality of the models was carried out. Improved models thanks to the selection of hyperparameters and changing the data preprocessing function.

Keywords: phishing, phone fraud, thematic modeling, NMF, LSI, LDA, text analysis, natural language processing, information security, machine learning

Abstract: The subject of this research is the development of the architecture of an expert system for distributed content aggregation system, the main purpose of which is the categorization of aggregated data. The author examines the advantages and disadvantages of expert systems, a toolset for the development of expert systems, classification of expert systems, as well as application of expert systems for categorization of data. Special attention is given to the description of the architecture of the proposed expert system, which consists of a spam filter, a component for determination of the main category for each type of the processed content, and components for the determination of subcategories, one of which is based on the domain rules, and the other uses the methods of machine learning methods and complements the first one. The conclusion is made that an expert system can be effectively applied for the solution of the problems of categorization of data in the content aggregation systems. The author establishes that hybrid solutions, which combine an approach based on the use of knowledge base and rules with the implementation of neural networks allow reducing the cost of the expert system. The novelty of this research lies in the proposed architecture of the system, which is easily extensible and adaptable to workloads by scaling existing modules or adding new ones.

Keywords: Support Vector Machine, Knowledge acquisition, Content categorization, Neural network, Content aggregation, Fuzzy fingerprints algorithm, Expert system, TF-IDF, CLIPS, Spam identification

Abstract: This article describes the author's proposal of cognitive architecture for the development of artificial intelligence agent of the general level (“strong" artificial intelligence”). The new principles for the development of such architecture are offered: hybrid approach in artificial intelligence and psychophysiological foundations. The scheme of architecture of the proposed solution, as well as the descriptions of possible areas of implementation are given. Strong artificial intelligence represents a technical solution that can solve arbitrary cognitive tasks accessible to humans (human level intelligence), and even beyond the capabilities of human intelligence (artificial superintelligence). The areas of application of strong artificial intelligence are limitless – from solving the current problems faced by humans to completely new tasks that are yet inaccessible to human civilization or expect for their groundbreaker. This study would be interested to the scholars, engineers and researchers dealing with artificial intelligence, as well as to the readers who want to keep in step with modern technologies. The novelty consists in the original approach towards building a cognitive architecture that has absorbed the results of previous research in the area of artificial intelligence. The relevance of this work is based on the indisputable fact that currently, the research in the area of weak artificial intelligence begin to slow down due to the inability to solve general problems, and the majority of national strategies of the advanced countries in the area of artificial intelligence declare the need for the development of new artificial intelligence technologies, including the artificial intelligence of general level.

Keywords: bionic approach, hybrid artificial intelligence, artificial intelligent agent, cognitive architecture, strong artificial intelligence, artificial intelligence, machine learning, multisensory integration, goal-setting, explainability

Abstract: The authors propose to combine logical inference with the apparatus of fuzzy sets. When each solution is associated with a set of possible outcomes with known conditional probabilities, the solution is chosen based on digital information under conditions of uncertainty. Therefore, the main purpose of using fuzzy logic in expert systems is to create computing devices (or software complexes) capable of simulating human thinking and explaining decision-making methods The purpose of the work is to describe in detail a reproducible standard method of constructing rules for the output of an expert system for various economic subject areas, using a universal knowledge base scheme To make decisions in a fuzzy system, it is proposed to use the process of identifying the structure of a rule - determining the structural characteristics of a fuzzy system, such as the number of fuzzy rules, the number of linguistic terms into which incoming variables are divided. This identification is carried out using fuzzy cluster analysis, which is carried out using fuzzy decision trees. The authors present a block diagram of the inference methodology based on fuzzy logic. The method of constructing rules and the algorithm of fuzzy inference presented in the article can be used in various spheres of the economy. The novelty of the work lies in the automation and integration of the system for determining fuzzy inference rules with the stage of collecting input data in the subject area

Keywords: Machine learning, Data processing, DSS, Accessory function, Knowledge base, Fuzzy logic, Fuzzy sets, Decision trees, Withdrawal rules, Expert system

Abstract: The article describes an algorithm for generating control actions on various engineering systems of an intelligent building, individually or in combination, within the framework of intelligent control of the parameters of the internal environment of such a building. The intelligence of the algorithm is due to the possibility of its autonomous operation and adaptability in relation to the parameters of the internal environment in relation to which the monitoring and control is carried out. The article provides a brief description of the algorithm, as well as a mathematical model for the selection and application of control actions. As a research method, a set-theoretic approach to modeling management processes was adopted, as well as BPMN notation for representing algorithms. The novelty of the issue under consideration is due to the use of a functional approach for the development of an intelligent algorithm, as well as the use of methods of distributed computing and computing on terminal devices within the framework of the hybrid paradigm of artificial intelligence. The relevance of the presented model is based on the need to translate the life cycle management processes of buildings and structures into the Industry 4.0 paradigm in order to increase their degree of intelligence. The article will be of interest to scientists and engineers working in the field of automation of technological and production processes. The present work is theoretical.

Keywords: distributed computing, functional approach, adaptability, autonomy, control system, management, intellectualization, automation, edge computing, intelligent building

Abstract: The subject of the research paper is the question of wages at the enterprises of Russia, as well as an object considered the remuneration system and the problem of their choice. In this regard the authors offer a model of a decision support system that will allow users to obtain the likely results of the introduction of a particular wage system in the enterprise, without actual testing. The principle of the model of this system is based on simulation modeling, which allows you to obtain and evaluate statistics using regression analysis and make an adequate managerial decision. In the framework of the article, the fundamental method is simulation. Using it, it is possible to build an adequate model and reflect options for the results of the enterprise. The article reveals in a new way the issue of choosing wage systems and combines economic and mathematical approaches;For the first time, the algorithms of simulation modeling are described in the question of the choice of wage systems in enterprises;A model of a decision support system in the field of remuneration is obtained, which is scientifically justified and easy to understand, as a result of information processing in which the user receives data on the consequences of introducing one or another standard remuneration system at his enterprise;A feature of the model is its scalability. In the sense that other salary systems can be added to, appraised in the general system model, in addition to pre-laid.

Keywords: piecework system, time system, Monte Carlo method, algorithms, wage systems, simulation modeling, decision support system, time bonus, modeling, data base

Abstract: The subject of the research is the development of a model and algorithm for cross-selling to bank borrowers.The object of the research is the information system for managing the lending process.The system developed by the authors implements an algorithm for selecting the next question to check from the existing set and introducing a stop parameter stopping the client's survey due to the achievement of a probability value indicating a high customer need to purchase a certain cross-product. By implementing this algorithm in the system, a bank employee can sell the cross-product that is most appropriate for a given client to the client by asking the client a limited number of questions in a short period of time.The algorithm proposed by the authors is universal. Each of the steps described is decomposed into several mechanisms that fulfill a specific goal. The previously selected mechanisms, based on statistical data, can be replaced in the course of work with the most relevant and effective ones. In the developed model of cross-product selection, an algorithm based on using the Bayes formula for competing hypotheses will be used. The article discusses the question “Is it possible to organize the implementation of cross-sales to bank customers online so that a potential customer can learn additional individual options?”. To solve this problem, it is proposed to develop a model and algorithm for cross-selling to bank borrowers. As part of the ongoing scientific research, an expert system is being developed that, when contacting a client at a commercial Bank, to determine a specific banking product or service, determine the client’s potential need for an additional product (cross product) and sell the product to the client.

Keywords: management in the system, individual characteristic, Bayes formula, model, algorithm, scoring, Information system, cross-sales, optimal solution, information processes

Abstract: The subject of the research of the article is the actual task of analyzing the state of the documentation support of the management of the organization. In the conditions of modern society, this task becomes particularly acute, since the effectiveness of managing the organization as a whole depends on the proper organization of the DOE system. At the moment there is no uniform methodology for solving this problem, and the existing approaches are subjective. To solve this problem, an automated information system has been developed that allows solving the following tasks: 1) building a knowledge base that captures empirical patterns between the emergence of individual indicators of the state and their probabilistic characteristics; 2) the adaptation of the system to the peculiarities of the current situation and the requirements of the employee performing the analysis; 3) identification of violations in the work with documents and implementation of business processes; 4) identification of indicators of the state of pre-school management and the efficiency of business processes, which may later take on unsatisfactory significance; 5) the provision of recommendations for the elimination of violations. The study used the methods of knowledge engineering, mathematical modeling, graph theory, probability theory, object-oriented programming. As a result of the research, a prototype of an automated information system for analyzing the state of pre-school educational institutions is described in detail, the main functional capabilities of its program modules are described. The procedure of interaction with the system of knowledge engineer and end user is considered. The correctness of the functioning of the AIS prototype is confirmed by successful test tests on the example of the activities of a commercial organization transporting goods both domestically and abroad.

Keywords: theorem Bahasa, knowledge engineering, software modules, components of AIS, automated information system, analysis of DOU, active focus, prior probability, engineer knowledge, final user

Abstract: The subject of the study is adaptive testing with multiple choice questions. This type of testing allows you to implement a machine assessment of the level of knowledge of the participants is simple and accessible, eliminating errors of evaluating the results. However, the adaptive testing model includes a parameter describing the probability of guessing answers to test tasks, which depends on many factors: the difficulty of the task, the level of knowledge of the learner, the presence of a fine for trying to guess, and the degree to which the participant’s answers with a higher level of knowledge influence the opinions of other participants. in the conditions of individual and group testing. The need to explicitly set this parameter complicates the model and introduces uncertainty in the test results. The introduction of a fuzzy cognitive map, which determines the degree of "pure" and "partial" guessing in response to test tasks, reduces the complexity of the testing model as a result of excluding the explicit probabilistic parameter. Unlike the well-known definitions of a cognitive map, the proposed interpretation is based on models of individual and group adaptive testing with multiple choice. The results of computational experiments in real testing confirmed the effectiveness of the introduction of the map. It was found that fuzzy estimates of the responses of participants with a lower level of knowledge to more complex tasks are more consistent than estimates that require explicit assignment of the probability of "pure" guessing. The method of reducing the complexity of a testing model based on a fuzzy cognitive map can be used both in educational software systems and in intelligent systems and decision support systems that provide for testing with multiple choice.

Keywords: Bloom's taxonomy, interval-valued fuzzy set, cognitive modelling, knowledge assessment, pure guessing, partial guessing, collaborative learning, adaptive testing, cognitive map, logistic model

Abstract: The author considered in detail the main classes of modern models of information impact assessment. The subject of research is economic-mathematical methods, which include elements of approaches and results, the theory of fuzzy sets, the theory of probability, the theory of decision making and operations research and the theory of Markov chains, in the context of application to modeling the influence of information on economic processes. The purpose of the study is to analyze in detail the existing domestic and foreign models of information influence. The methodology and methodological apparatus of the research is represented by the developments and theoretical concepts presented in the works of domestic and foreign authors in the field of economic and mathematical modeling, probability theory and mathematical statistics. The novelty of the research lies in the fact that, based on the analysis of existing models of information impact, it was possible to develop approaches to the construction of mathematical models of the influence of information effects on economic processes. Also highlighted areas for further work to improve the existing models of information influence in order to further more effective assessment of information impacts on economic processes.

Keywords: targeted informational impact, Markov chains, SOCIAL NETWORK, simulation models, information management, optimization models, information impact, decision theory in economics, models of information influence, modeling

Abstract: The object of study of this work is a measure of semantic connectivity of texts, the subject of study is an algorithm for calculating the measure of semantic connectivity of texts. The article focuses on the method for determining the hybrid measure of the semantic connectivity of two concepts. This method underlies the algorithm for computing the similarity of two texts. Wiki projects (Wikipedia and Wiktionary) are used as sources of knowledge. Sharing them allows covering a much larger number of words as compared to using one of the wiki projects. The method uses the well-known Wikisim measure. This measure is simple, but has good performance. In the classic Wikisim method, only Wikipedia is used, so it is adapted for Wiktionary. The methodology of the work is based on modeling the process of extracting high-quality knowledge from Wiki projects - the individual work of independent volunteers. The novelty of the research lies in combining the two sources of knowledge of Wikipedia and Wiktionary and creating on their basis a new hybrid measure of semantic relatedness of concepts. The main conclusion of the work is that the combination of formal (Wiktionary) and informal (Wikipedia) sources of knowledge can lead to a better assessment of semantic connectivity between text units. The described method can be applied in economics, sociology and politics to clarify people's opinions on issues of interest.

Keywords: text, Wiktionary, Wikipedia, WikiProject, knowledge source, relatedness hybrid, semantic relatedness, word, concept, frequency response

Abstract: The subject of the study is the process of developing software for automated control systems. Object of research - methodologies for organizing software development. Automation of management is a universally recognized promising direction of increasing the efficiency of the application of complex technical systems. First of all, automation, organized by the principle of decision support systems. The basis of the effectiveness of any automated system is its software. First of all, this applies to application software. The development of such programs entails certain difficulties, primarily organizational ones. Generalized analysis has shown that in the world practice there is a rather wide range of methods for organizing the development of programs. These methods can be divided into two large groups with respect to the algorithms used for "hard" and "flexible" ones. Each of the approaches is effective for certain conditions of work. The article analyzes the factors influencing the effectiveness of applying a particular methodology, synthesizes suggestions on the appropriateness of using different methodologies in different conditions of the development process. The analysis showed that for the development of automated decision support systems, the use of "flexible" approaches is most effective. In the article features of Scrum technology are considered, as a typical implementation of "flexible" methodologies. Conclusions about the expediency of its application in the development of application software for automated decision support systems are formulated

Keywords: development process organization, DMSS, software development technologies, software, automated systems, decision support, control automation, flexible technologies, Agile technology, Scrum development method

Abstract: The paper shows the solution of the problem of constructing an ontological model for the choice of software development tools. The classes of the constructed ontological model form a taxonomy. Questions of representation of the developed ontological model in the form of the non-uniform oriented graph are considered. To support the ontology and solve on its basis the tasks of selecting software development tools on the constructed model, operations of adding and modifying the main ontology concepts are defined, which are the criteria for evaluating software quality. To evaluate and decide on the choice of tools based on the developed ontological model, an algorithm based on the method for estimating the similarity of objects in the intellectual space of knowledge is proposed. The novelty of the presented work is to build an ontological model of knowledge for making decisions on the choice of software development tools that allows to expand the composition of concepts and relationships between them, which provides the opportunity to describe various objects, subjects and processes of the software life cycle.

Keywords: estimation of similarity of objects, decision-making algorithm, concept, class, non-uniform oriented graph, taxonomy, ontological model, intellectual space of knowledge, evaluation criterion, life cycle

Abstract: In this article the authors offer a method for constructing logical operations to analyze and correct the results of the operation of sigma-pi neural networks designed to solve recognition problems. The aim of the research is to reveal the logical structure of implicit regularities formed as a result of training the neural network. The method proposed by the authors restores the training sample based on the values of the sigma-pi weighting coefficients of the neuron, analyzes the relationships of this structure and allows to detect implicit regularities, which contributes to the increase of the adaptive properties of the sigma-pi neuron. To solve this problem, the authors perform a logical-algebraic analysis of the subject area within the framework of which the cigma-pi of a neuron is trained, a logical decision function is constructed, its properties and applicability to the correction of the work of a neuron are investigated. It is widely known that the combined approach to the organization of the recognition algorithms increases their effectiveness. The authors argue that the combination of the neural network approach and the use of logical correctors allows, in cases of an incorrect response, to indicate the object closest to the requested attributes from the sample on which the sigma-pi neuron was trained. This significantly improves the quality of the automated solution of intellectual problems, i.e. ensuring the accuracy of achieving the right solution by using the most effective systems for analyzing the original data and developing more accurate methods for their processing.

Keywords: decision function, operations on algorithms, algorithm, predicate, logical function, neural networks, neuron, corrective operation, logical-algebraic approach, Classifier

Abstract: The object of studies involves waste collection by trucks in urban aglomerations within the "Smart City" concept. The authors provide detailed evaluation of the problems concerning the construction of waste disposal schedules, since these schedules currently do not correspond to the state of fullness of garbage  containers, and  they also do not involve optimization of the routes for specialized transport are discussed in detail. The object of research in this article concerns formation  of a multi-criteria optimal route for garbage disposal, which takes into account the fullness of trash containers, the travel time, and expert knowledge of the current road situation in the area of the route. The research method involves construction of a hybrid intelligent system that takes a decision to model a dynamic optimal route based on graph theory, modeling fuzzy expert knowledge that takes into account the road situation. Scientific novelty is due to the development of a hybrid approach to managing the removal of domestic waste in large megacities, which uses several technologies for optimizing the timetable. These technologies include mobile technologies that link the system hardware and software components into a single whole, take into account the current state of the road network, and expertise to evaluate the schedule. Route options are calculated using an optimization algorithm for constructing several options of the shortest route. The article presents one optimization criterion for choosing a route for servicing container sites - the time necessary to maintain sites with household waste. It is obvious that the dynamic nature of the chosen mathematical model of the entire system allows the addition of other optimization criteria. These criteria for the schedule formation  may involve fuel consumption rate, material resources, the requirement of equal load level of all trucks. The advantages of the said system involve the simultaneous consideration of the situation with the filling of containers for waste, the road situation for the routes, as well as the expert rules.

Keywords: hybrid control system, smart city, schedule, gabbage collection, expert system, optimization criteria, mobile technologies, Mamdani method, fuzzy rules, dynamic network

Abstract:  Selection of appropriate web services is an important step in the development of service-oriented architecture (SOA) for an information system. When selecting a web service, the quality of service criteria (QoS) are used regularly. These criteria characterize the non-functional properties of web service candidate. However, the functional characteristics of the service that are difficult to quantify, and the factors of the effectiveness of the lifecycle management of composite architectures are also important. The article discusses the comprehensive approach to  evaluation and selection of web services in SOA development on the basis of factors related to non-functional and functional requirements and taking into account the economic efficiency evaluation of implementation and use of service-oriented applications. The choice of service is performed via fuzzy models for integrated assessment of the web service quality. The developed model and algorithm of web service quality evaluation and its software implementation will allow to realize decision support procedures for substantiation and choice of an appropriate structure of SOA-based information system in the situation of incomplete information.

Keywords: QoS, functional requirements, integrated evaluation of quality, non-functional requirements, economic efficiency evaluation, fuzzy model, decision-making support, web services, SOA, Service-oriented architecture

Abstract: The article focuses on the theoretical basis of the development and dash board application in the system of quantitative and qualitative control of staff in enterprises. The author examines in detail the example of a decision support system in the form of a "holistic" system based on the evaluation of the complexity of work using integrated assessment methods combined with an assessment of the qualifications of specialists in order to determine the effective fund of working time of each of them based on the assumption of productivity growth as a result of continuing education. The paper demonstrates a compromise solution in accordance with the "management grid". The solution is aimed at cooperation in solving the problem of optimizing the quantitative and qualitative composition of specialists that ensure the performance of works related to the development and implementation of projects of the enterprise. The novelty of the application of integrated assessment methods for the purpose of assessing the complexity of work is undeniable, because previously this approach was never used for these purposes. The dash board, built on the basis of self-normalization, the methods of complex assessment of the complexity of work and the agreement of opinions, allows to model possible solutions, to justify in the forecast period the optimal qualitative and quantitative composition. The dash board build by the authors is one of the important tools for increasing the efficiency of the activities of specialists and the enterprise as a whole. Previously a comparison of the qualifications of employees reflected in the change in the effective fund of working hours with the complexity of the work performed was not used, since only the assessment of the ability of specialists to perform certain jobs was made, whereas this material indicates the fact of productivity growth as a result of growing qualifications.

Keywords: qualitative composition of staff, optimization of the number, dash board, coordination of forecasting opinions, comprehensive evaluation, decision support, management grid, conflict of interest, modeling, efficiency

Abstract: The author reviews widely used in artificial intelligence systems AND-OR trees with specified parameters in the terminal arcs or vertices. The parameters are defined recursively on the decision trees with the use of continuous convolution functions monotone in each argument. The author solves a problem of enumerating convolution functions satisfying the system of restrictions on the parameters. Earlier a linear complexity and memory algorithm for the case of a single additive index was presented. But even for two parameters there is no polynomial-time algorithm for solving the problem. The author suggests two “branch and bound”  algorithms . The first algorithm implements a consistent selection of subtrees for allowable solutions using restrictions on separate parameters. The second algorithm can effectively cut off the unacceptable subtrees. The basis of the both algorithms is the concept of the minimum AND-OR tree subsest on monotonic restriction. The first algorithm is more applicable in the presence of a large number of solutions of the system of inequalities because it allows to choose the solutions as sets of AND-OR tree subtrees. The second algorithm is applicable in a case where the system of inequalities has a small number of solutions.

Keywords: system of constraints, system of inequalities, decision tree, AND-OR tree, AND-OR graph, enumeration, algorithm, artificial intelligence systems, monotonic function, complexity of algorithm

Abstract: The subject of the study is to evaluate the effectiveness of assigning tasks in the automated systems of electronic document management on the basis of fuzzy methods of rational choice of alternatives. The object of the research is the problem of a rational choice of employee for the task based on qualifications, performance, workload as well as difficulty of the assignment. The paper focuses on three job assignment strategies:  based on the method of maximin convolution, additive convolutions and fuzzy-production model. Particular attention is paid to the software developed on the basis of the proposed methods. The authors present an example of its operation, as well as the results of studies evaluating the effectiveness of allocation tasks for the performers. As the methods of research authors used methods of fuzzy rational choice of alternatives: maximin convolution, additive convolutions and fuzzy-production model. These methods are used to assign tasks the automated systems of electronic document management. The main conclusions of the study are: -          method based on fuzzy logic inference has shown the best results, most closely consistent with the intuitive representation of an expert on rational choice assignments performers; -          maximin convolution method is a pessimistic approach, that does not take into account the good side of the alternatives; -          method of additive convolution is an optimistic approach in which low scores on the criteria have the same weight as compared to the high marks that affected its low accuracy. A special contribution to the authors of the study is in developing an effective fuzzy-productions tasks assignment model as well as the implementation of the software system for performing the necessary calculations to evaluate its effectiveness. This determines the scientific novelty and practical value of the study.

Keywords: additive convolution method, maximin convolution method, software package, fuzzy-production model, decisionmaking, tasks distribution, electronic flow of documents, rational choice of alternatives, fuzzy inference, personal data operator

Abstract: The subject of study is computer technology for research automation by the construction of graphical cognitive model. Cognitive modeling helps better understanding of the problem situation on the basis of a qualitative analysis of the system. Cognitive modeling has been used in the development of management decisions in economic, sociological and environmental and other semi-structured systems. The essence of the cognitive approach is to develop effective management strategy, based not so much on intuition, but mostly on the orderly and verified knowledge of the complex system. Population surveys or polls of expert groups can be used as the source of such knowledge. The developed method of constructing cognitive model involves building a model in two stages. At the first stage a rough model based on identifying the most common opinions of large groups of the population is built. At the second stage, the model is improved by involving small groups of qualified experts. This stage allows to determine quantitative assessment of the links cognitive model. The authors developed a set of tools to automate the work of researchers in the development of cognitive models. The advantage of the developed computer technology is that it allows the user to focus on the researched topic, without spending time on routine calculations. The study proves that the developed software tool has the following features: efficiency, reliability, flexibility, processability, availability.

Keywords: cognitive models, questionnaire, computer technology, automation, multivariate analysis, data processing, algorithm, data model, socio-economic problems, peer reviews

Abstract: The research question is the semantic relatedness of terms. The target of research is measure the semantic relatedness of terms. The authors consider such aspects as the rationale for the choice of the theme of background knowledge, the construction of a graph of links and measurement of relatedness between concepts. In earlier studies the authors of semantic proximity is calculated based on the statistical characteristics using different contextual analysis methods, such as latent semantic analysis. This work is the first experience with the reference methods for determining a semantic relatedness. Therefore, the focus placed on ease of calculation steps. Evaluation semantic similarity is based on the WLM method and proximity measure for separate types of references of M. I. Varlamov, A.V. Korshunov. In contrast to the well-known measures of semantic proximity, based on the use of Wikipedia proposed in the measure uses a simple links Wikipedia articles such as "See. Also" and "Links". This approach allows us to raise the performance of the algorithm and is designed for use in applications requiring high accuracy of the result is not, and better performance of the algorithm. These tasks include establishing a correspondence between the competencies and educational standard annotations disciplines of the curriculum or the task of analyzing the students' answers to the open questions in the form. The developed measure is cheap, reasonably accurate and accessible.

Keywords: link, structure of article of Wikipedia, the database of Wikipedia, background knowledge, semantic similarity of concepts, concept, link graph, distance between concepts, count indexing, link-based Measure

Abstract: Achieving the objective conditions of functioning institutions, socio-economic systems it is inextricably linked to improving the efficiency of the work of individual artists. The most important role is occupied by the complex questions of assessment activities, the rational choice of metrics. In other words, any evaluation system must implement a certain paradigm of the process approach - effective management is possible only if quality measurements. Initially, any rating system should provide some degree of freedom, which allows you to quickly adapt to changing operating conditions.The article examines the creation of rating systems based on the principle of an open (agreed) management . Architecture of the system variable, focused on the use of agile software development , in which the major subsystems interact with each other through interfaces . The basic idea is to use a two-stage approval procedures and metrics objects activity in each period of the system. On the one hand, this approach allows you to refine and specify the metric used on the new range planning based on previous experience. On the other hand, in the control loop feedback appears to the actual perpetrators of that form applications centered, tailored to their needs, wishes and preferences. The system evolves with each new stage of its activity, new elements are introduced and the conditions that allow to actualize the past experience, the new range planning. Thus, the artists performed directly involved in the formation of corrective actions.The purpose of using open controls in the rating systems is to create the architecture of changing the system , where the main participants are motivated to make changes. The changes are necessary because the human, social and economic groups are on the move and constantly evolving.

Keywords: management teams, multi-level system, evaluation, open management principle, the agreed principle of management, the working efficiency, rating system, multiagent organizational systems, active systems, organizational systems

Abstract: The subject of research is the development of intelligent information and measuring systems for ergometric testing the flight personnel of maneuverable aircraft. The authors reviews the technical and ergonomic requirements for the modernization of an isometric exerciser for leg muscles and abdominals used in ground training of flight crews to the conditions of the flight and maneuvers and for the medical-flight examination. The above requirements are implemented in the hardware-software complex for ergometric testing which is a special information-measuring system essential for the safety of maneuvering flight. The following methods were used in the study: methods of systems analysis, software engineering, designing software and hardware for medical purposes, the theory of reliability, aviation cybernetics. The main conclusion of the study is in formulating a set of reasonable engineering solutions for creating an intelligent information and measuring system for ergometric tests of flight personnel of maneuverable aircraft. The proposed solutions were formulated considering the needs of the practice of aviation medicine  and combine the latest achievements in the field of medical equipment, aviation medicine and software engineering, and, as shown by experimental testing, meet the needs of the practice.

Keywords: automation of medical examinations, flight safety, hardware and software system, ergatic system, aviation ergonomics, intelligent medical systems, maneuverable flight, medical-flight examination, software engineering, information-measuring system

Abstract: One of the problems hampering the development of the active use of renewable energy is to determine the optimal placement of wind and solar power plants on the earth's surface. The paper presents a model for predicting the level of solar energy in the region allowing choosing the most effective location for solar power location. The forecast of the level of solar energy is given using an artificial neural network of direct distribution educated on the basis of meteorological stations data using the back-propagation algorithm. Designing a neural network was carried out with the Neural Network Toolbox package of MATLAB 8.6 (R2015b). Comparison of results of forecasting solar energy performed by artificial neural network level with the current values shows a good correlation. This confirms the possibility of using artificial neural networks for modeling and forecasting in regions where there are no data on the level of solar energy, but some other data of meteorological stations is present.

Keywords: alternative power engineering, prediction, error back propagation, multilayer perceptron, modeling, artificial neural network, solar energy, feedforward network, supervised learning, resource map

Abstract: The subject of the article is the current state, problematic issues and promising field of research of bio heuristics for solving optimization problems. Bio heuristics are mathematical transformations of the input stream to the output data based on simulation mechanisms of evolution, natural analogies, on a statistical approach to the study of situations and iterative approximation to the desired solution. Currently, bio heuristics have become an important tool for finding close to optimal solutions of problems which earlier were considered unsolvable. The methodological and theoretical bases of the scoping study are optimization techniques and decision making support methods, artificial intelligence, evolutionary computation theory. The article analyzes the fundamental results obtained in the field of bio-heuristic optimization algorithms: Holland theorem and TAD-theorem. The article establishes patterns and structure of bio heuristics, especially coding solutions, basic cycle of bio heuristics algorithms. The study reviews a promising direction in the analysis time of the biological cognitive heuristics - drift analysis.

Keywords: evolution operator, evolutionary computation, optimization, metaheuristics, cognitive bioinspired algorithm, NFL-theorem, drift analysis, fitness function, programming, modeling

Abstract: The article is devoted to methods of obtaining the necessary information for the functioning of the situational centers of various levels. The subject of research is the algorithm for obtain the relevant data and knowledge on the Internet. Under relevant data and knowledge the authors mean the information required to solve a problem or task. The object of the study the “IntellST” software, an information-analytical system for obtaining relevant data and knowledge on the Internet. Investigations take into account peculiarities of the Internet as the source of a huge volume of unstructured information. As the methods for the studying the authors used system analysis, information theory, algorithm theory, algebra, logic, set theory, comparative analysis, data mining techniques and methods of software development and database. The article presents general algorithm for finding data and knowledge on the Internet for the purposes of information support of situational centers. The authors present a universal functional diagram of a decision support system with the data and knowledge from the Internet. The paper shows the results of evaluation of the effectiveness of software “IntellST”. The authors concluded that it is possible to use “IntellST” to obtain information on the issue in the framework of the situational centers.

Keywords: making decisions, knowledge, data, DSS, IntellST, information, Internet, Situation Centre, problem, estimation of efficiency

Abstract: The authors study urgent problem of analysis and evaluation of workflow in an organization. The work proved the need for complex analysis of records management system in any organization. The authors formulate the basic objectives of the study and suggest using of an Automated Information System to analyze the workflow, which will allow gaining knowledge of the current situation in the field, analyze the state of workflow in terms of performance indicators based on documents as well as based on processes, taking into account correlation of indicators of records management system and parameters of efficiency of business processes and activities of the organization. The system proposed will help identifying errors in the documents and forming recommendations to address the shortcomings recorded. The study used methods of mathematical modeling, graph theory, probability theory, object-oriented programming. The authors developed a multi-level model of representation of knowledge about the state of workflow and business processes of the organization, identified the main components of automated information system and described its role in the operation of the system, considered in detail the algorithm of the user interaction with the automated information system. Use of the developed the system will allow to optimize state of the workflow, improve the efficiency of business processes and the functioning of the organization as a whole.

Keywords: workflow analysis, automated information system, model of knowledge representation, semantic network, structure of the AIS, database, knowledge base, logical inference subsystem, Bayesian method, operation algorithm

Abstract: The aim of the research is to solve the problem of choosing the application of geographic information system, optimal in performance for use in the interest of the study of maritime and coastal zones. Some software products presented on the market of geographic information systems can be used as alternatives. The assessment quality indicators are individual ratings of basic features implementation: building contour relief; calculation of the flooded area; construction of three-dimensional models; create custom layers; the creation of custom objects. The presented solution is based on a modified fuzzy analytic hierarchy process method. Methods use in the research: qualimetry complex systems, analysis of hierarchically organized structures, fuzzy logic, geoinformatics, matrix calculus, computational mathematics. The main conclusions of the study is that the use of a modified fuzzy hierarchy analysis method allowed to find a solution to the problem of choosing an alternative embodiment, a hierarchically organized system meets the quality criterion with given functions of mutual preferences of criteria and alternatives, obtained on the basis of expert opinion aggregation domain.

Keywords: preference among criteria, geographic information systemi, analytic hierarchy process, hierarchical convolution, fuzzy hierarchy, linguistic preference function, group selection of alternatives, preference for alternatives, geoinformatics, monitoring of water areas

Abstract: The subject of the research is the synthesis of the base of psychological and didactic tests for monitoring the level of knowledge, implemented through a system test control system of computer-aided learning systems. The functioning of such systems is based on the implementation of adaptive testing as a process of automated selection of test items (test questions) of a such level of difficulty, in which the objective accuracy of the level of student's knowledge measurement reaches a maximum. A base of control tests, combining psychological and didactic tests is an important part of such system. To carry out the research the authors used methods of pedagogical science, structural systems analysis, expert assessments, database design for automation systems. As a result of the research the authors developed and successfully tried out the synthesis technology for base of tests in computer-aided learning, allowing implementing adaptive management of education process by providing training influences appropriate for individual psychological characteristics of each student and providing a level of training of students with automated control of their level of motivation and commitment.

Keywords: standardized test scores, adaptive testing, automated control of knowledge, computer aided learning, educational informatics, base of tests, didactic tests, psychological tests, system of tests, management training

Abstract: An important step in the early stages of the life cycle of hearing protectors is an ergonomic expertise. For its implementation a software complex was developed. It provide interactive input of values of operational, technical and economic characteristics of all samples of used individually hearing protectors (ear muffs, helmets, earplugs, protection against air acoustic vibrations and etc.), obtained using objective (direct measurements) and subjective (survey respondents) methods for further calculation of the integral index - the coefficient of ergonomics as a weighted convolution of indicators. Methods of the research: a systematic analysis, expert information processing, ergonomics, programming, software engineering, ergonomic qualimetry, computer science, cybernetics. By using the developed programs author provided standardization of the procedures of ergonomic examination of personal protective equipment from aircraft noise, creating and filling a database of economic expertise (with both primary information and integrated assessments) and most importantly timely detection and elimination of design flaws that reduce the usability of developed remedies, which, as a result, improved the comfort of their usage by aviation specialists. Software solutions are created using the ActionScript (Flash) and have the certificates of state registration.

Keywords: computer-aided system, expert system, acoustic efficiency, noise protection, software package, ergonomic expertise, life safety, weighted sum of indices, ergonomic qualimetry, software

Abstract: The article reviews a procedure of solving the uncertainty in identifying the similarities and duplications between the results of intellectual activity, due to the presence of semantic and pragmatic ambiguity in natural language form of results description. The aim of the study is to provide identification of duplicate results of intellectual activity in an automated mode, in which experts only manage its settings by determining the composition of the classifiers used in the construction of relations of similarity, simplification of inter-agency coordination based on the results of intellectual activity and integrity of the database, as well as increasing the reliability and efficiency of the procedure identifying duplicate the results of intellectual activity by combining the frequency-semantic methods and formalized expert knowledge. The research methodology is based on a system analysis, pattern recognition, synthesis databases and knowledge bases, the automatic processing of natural language texts. The authors developed an approach for building knowledge bases classes for information representations of the results of intellectual activity that would classify its different types and systematize knowledge about the classes of intellectual property through the use of the author's method of automated classification and identification of duplications of intellectual property.

Keywords: pragmatic ambiguity, semantic ambiguity, classification of scientific results, expert information, research coordination, database, natural language, results of intellectual activity, description of the scientific results, avoiding duplication of information

Abstract: in this paper a complex model based on the theory of fuzzy sets is proposed for the automatic analysis of the results of self- evaluation of quality of management system of the structural unit of the university. The model consists of 11 modules, each module is a fuzzyproduction subsystem. The article shows a graphical representation of the membership functions of the input linguistic variables, a fragment of the base of fuzzy productions rules consisting of 125 rules, a sample of surface of fuzzy inference and a demo of the proposed model. The authors use fuzzy inference algorithm, suggested by E. Mamdani, implemented in FuzzyTECH software environment. The novelty of the presented complex fuzzy-production model is in the use of the theory of fuzzy sets, which have not yet been applied in analysis of the results of self-evaluation of quality of management system of the structural unit of the university. Testing of the model on situational examples proved its adequacy in simulated situations.

Keywords: quality management system, self-evaluation, efficiency evaluation, fuzzy set, fuzzy-production model, linguistic variable, term-set, universal set, fuzzy productions rule, surface of fuzzy inference

Abstract: Medical diagnostics is one of the most difficult tasks of practical health care. Currently, there is a need for appliance of information and communication technologies in medicine, especially in solving the task of creating diagnostic telemedicine systems. This is the cheapest and easiest way to organize telemedical diagnosis at any distance. A user-patient sends medical information to the system via telecommunication channels. The system prepares the diagnostic conclusion based on a set of symptoms received in real time and outputs the solutions to a patient. If the patient does not accept the decision, he may request the system solution from expert physicians. In that case the system organizes the dialogue with physicians in delayed mode. Then the system automatically generates and sends questionnaires to doctors of the assumed specialty. Then doctors form the diagnostic answers to the questions and send them by email. Thus, the telemedicine expert system for differential diagnosis is to perform a medical diagnosis in a reasonable time after the patient enters detected symptoms. Also, the system should allow the patient to communicate with physicians through the use of web technologies that allow patients to receive medical diagnosis outside the clinic. The authors suggest that architecture for this system should be based on the principles of creating web applications and describe the basic levels of web-based systems. The article presents a scheme of a database with a description of the tables for creating the system. This work is useful for software implementation of the medical expert system of differential diagnosis.

Keywords: medicine, diagnosis, expert system, internet, web-application, IIS webserver, ASP.NET web-forms, CMS DotNetNuke, DBMS MS-SQL Server, business logics

Abstract: the article is devoted to development of algorithms and methodical provisions for obtaining relevant data and knowledge on the Internet. Under the relevant data and knowledge the authors mean the information needed to solve a problem or task. The article examines issues related to semantic data compression, providing semantic coherence of the text, defining semantic similarity of texts or phrases, as well as with automatic search of brief and accurate answers to questions. Research takes into account peculiarities of the Internet as a source of huge amounts of unstructured information. The study uses a systematic approach, theory of algorithms, algebra of logic, set theory and comparative analysis. The article presents a general algorithm for the problem-oriented auto-reviewing. The authors raise the questions of finding the semantic relationships between sentences. The article describes techniques of generating an integrated review and identifying the semantic similarity of the two texts. The authors developed an algorithm of finding the answers to question and show the results of building the information-analytical system of obtaining relevant data and knowledge on the Internet.

Keywords: data, knowledge, Internet, search engines, problem-oriented auto-reviewing, semantic connections, pronominal anaphors, regular expressions, semantic similarity, ternary expression

Abstract: Small business is the most important sector of the modern market economy, the efficiency of which is largely determined by the state of the economy as a whole. The main features of the small business lie in the way of management and decision-making methods. Modern information technology is a tool by which the effectiveness of management can be significantly improved. The subject of this study is to determine the features of the use of information technology on the basis of the analysis of the specificity of economic activity and the management of this category of subjects of the market economy. The work is based on general scientific methods of analysis and synthesis both published in the literature fragmentary information on the subject and the results of own experience of the author, reflecting his scientific interests. The author does not know any domestic publications on the subject despite its scientific and practical importance. In this regard, the article has a scientific novelty in attempts to carry out a systematic analysis of the specific use of information technology in small business. The presence of such specificity requires its consideration while building the new management technologies and developing commercial software products for small businesses.

Keywords: small business, information technology, management functions, industry specifics, infrastructure, resource limitations, integrated solutions, cloud services, susceptibility of technology, business information richness

Abstract: In this paper the author concretizes the principles of modeling border activities and considers the sequence of development of methods and models for border security and their classification. The basic approach (the set of methods and techniques) to development of the concept of automation is in consistent decomposition of the domain based on the classification of measures. The elements of the domain are combined into a single system by identifying flow through processes, by the use of cycles of border activity and border control. The suggested classification of management methods for regime, prevention and border measures allows obtaining a complete and consistent list of border tasks to be automated. The article also reviews a methodology of automation of border activity, based on the decomposition of the process of border security. Building the automation concept for border activity involves the use of methods of systems analysis and systems engineering, ETOM methodology, the main provisions of the theory of law, criminology, theories of security, border studies and border metrics. In order to create a highly effective decision support systems in the field of border security management the author classifies the methods of border security. The article considers and substantiates the structure of regime, prevention, security, control and operational security measures. The block diagram of the processes of the first level is build and includes two parts: border security management processes and border units’ management processes.

Keywords: border activities, border security, concept, automation, automation methodology, management methods, border measures, information models, mathematical models, principles of modeling

Abstract: despite the reduction in corporate market volumes for many branches of commercial banks the center of attraction for the front-office subdivisions increasingly shifts towards retail segment. However, the huge competition in retail forces banks to move towards the unpopular measures of labor intensification and personnel optimization. Under such conditions traditional ways of decision making typical for HR do not work well. The new approaches for retrieving data for decision making must be found, new tools for objective analysis of the situation and developing optimal solutions are needed. The article is devoted to a description of a practical solution to the mentioned above problem. In other words, the subject of the study presented in this paper is HR-process in retail subsystem of a commercial bank. The research of the process of decision making in the HR-subsystem of a commercial bank was held in terms of system analysis. The author developed visual model representing processes typical for the subsystem, revealed the sources of information for decision making. Next, using the built model, based on the simulation techniques and methods of numerical optimization, the technology of automated preparation of recommendations on personnel policy for the retail subsystem of credit institutions was developed. The approach suggested in this paper is fundamentally different from its analogues by the width of coverage of available sources of information and methods of extracting knowledge from databases. Suggested approach for the first time implements simulation modeling of operational risks for retail subsystem of the commercial bank, allowing calculating a complete probability space of outcomes. Thus the higher accuracy and stability calculations is provided compared to Monte Carlo methods with comparable computational cost.

Keywords: computational complexity, simulation modeling, Petri nets, risk, decision making support, personnel management, commercial bank, class of complexity, optimization, Nelder-Mead method

Abstract: the article reviews AND-OR trees with defined cost of arcs or vertices, widely used in artificial intelligence systems. The author describes branch and bound algorithm allowing enumerating all decision trees with cost less or equaling to defined constant value. The complexity of producing another decision tree is O(N), where N is the number of vertices of the AND-OR tree. The article shows a way to use stack for information organization, reducing the memory consumption to O(N) without changing the previous complexity estimate. The article presents software realization of the described algorithm, proving the theoretical evaluation of complexity and amount of the required memory in tests. The effectiveness of search is increased by introduction of the concept of a minimal AND-OR tree cost-constraint subset, which ensures the existence of valid decision trees while descending the decision tree. The decision subtrees are not listed separately but organized in blocs of AND-OR subtress in which all options are possible.

Keywords: artificial intelligence, algorithm, enumeration, AND-OR graph, AND-OR tree, decision tree, AND-OR tree version, cost, cost constraint

Abstract: the article deals with problem of designing intelligent control system with the use of soft computing technologies on the example of a complex control object – redundant robot manipulator with seven degrees of freedom. It is well known, that effectiveness of means used to solve a particular task in the problem-oriented field depends on the level of compliance between the computational intelligence of the tools and the level of complexity of the problem being solved. Selection of an adequate and effective tools for particular problem-oriented field is challenging (or shows intuitive contradictions) for students, engineers and developers of new science-based high technologies. The article describes effective techniques and appliance of soft computing technologies. The authors discusses methods of usage of applied models of intelligent computing, reviews their combined use in tasks of intelligent control. The main advantage of implementation of integrated intelligent control systems is the possibility of obtaining a guaranteed result: achieving the management goals with maximum of control quality at the top level and at the same time with minimal consumption of the resource of “object of control – regulator” system on the lower level (performer) of hierarchical automatic control system.

Keywords: intelligent management system, automated management system, genetic algorithm, soft computing technologies, base of knowledge, fuzzy control, management exception, subject to management, control decomposition, control action

Abstract: the article is devoted to solving a problem of analysis of document flow in organization. Constant improvement of production process leads to intense modification of structure and amount of produced documentations and their flow ways and requires continuous studying of document flow. Currently there is no unified and universal technique of document flow analysis. Comprehensive analysis of the document flow is highly labor-consuming and requires considerable effort in collecting, systematization and analysis of data. Therefore the author concludes that there is a need to automate processes of gathering and analyzing data. The weakness interconnection between parameters of document flow and business processes evaluation makes it appropriate to use the techniques of knowledge engineering. The paper reviews multilevel model of knowledge representation, including semantic network of concepts, statements, business-processes and forecasts. Since all characteristics of document flow and processes are probabilistic, the authors suggest to use Bayesian method for system adaptation to the characteristics of the current situation. The proposed system allows to study current state of document flow in given period of time and provides an opportunity to forecast not only the “bottlenecks” in the document flow, but also predict indicators of organizational performance, depending on the characteristics of the state of document flow. As a result the use of AIS allows to bring both document flow analysis and functioning of the organization as a whole to a completely new level.

Keywords: document, document flow, business process, automated informational system, database, base of knowledge, knowledge representation model, semantic network, adaptation, Bayesian treatment

Abstract: principles of cognitive organization of intelligent systems are closely related with multiagent division of functions in a multicellular organism. In opinion of the authors, cognitive centers in the human brain as well as in an intelligent system should be represented by active systems that interact with each other on the basis of the principles of collective optimization of parameters critical in the first place for preserving the integrity of the system and its survival. The article reviews a concept and definitions that are related to the ability of perception of the observer and his sensitivity thresholds. To implement the proposed formalization a library of classes was developed using C++ programming language. The library describes constructions suggested in the research. The paper describes only a part of the developed multiagent recursive cognitive architecture, but the presented realization already makes it possible to study the simplest cases of agent interaction. The research is directed on creation of self-organizing multiagent emergent systems capable of emulation of the psyche functions, goal-setting and adaptive goal-directed behavior on the basis of reality semantization and making social ties.

Keywords: intelligent systems, cognitive organization, recursive cognitive architecture, library of classes, reality semantization, agent, rational thinking, semantics, formalization, recursive agent

Abstract: the main techniques for evaluate proposed variants of solutions in design and studying complex systems are simulation methods and methods of experiments scheduling. The accuracy of decision making may be increased with the use of neural network (NN) to summarize the results of simulation experiments. Predicted with such method the solutions are then tested on the simulation model. The use of genetic algorithm makes it possible to find the corresponding genetic operators that provide faster convergence for each specific task of simulation. A database of experiments allows choosing a plan of experiment according to the type of parameters of simulation model. One of the main problems that must be solved in implementation of this technique is the choice of a suitable type of a neural network that will provide high percentage of recognition and low training time. A three-layer feedforward network with a combined learning algorithm based on the use of genetic algorithm and simulated annealing algorithm was proved to be ths best neural network architecture for solving the given.

Keywords: design, research, simulation methods, experiment scheduling methods, decision making, neural network, genetic algorithm, genetic operators, a three-layer network, simulated annealing algorithm

Abstract: Programming is characterized by a variety rules, techniques, methods and means of its implementation, applied depending on qualification, experience and individual peculiarities of programmers. The authors analyze the different algorithms of source code plagiarism detection and semantic noise values calculated by those methods for different source codes. The article presents algorithm based on the combined approaches of several text and semantic algorithms, shows the form to which the source code is transferred in the majority of modern algorithms, describes classes of the modern algorithms for plagiarism detection in software source code. As a result the authors present an improved algorithm for plagiarism detection suggested for use in educational practice to detect plagiarism in students’ works. The given algorithm combines features of both text and semantic algorithms, the computational part has high parallelization, which lowers the execution time in presence of computation power.

Keywords: plagiarism, source code, program code, token, semantics, semantic algorithms, matching coefficient, coefficient of commonality, metric, combined algorithm

Abstract: The authors suggested an approach to solving a fundamental problem of artificial intelligence (AI) of formalization of the semantics of rational thinking with the use of cognitive modeling based on the concept of recursive (fractal) cognitive architecture and a hypothesis of invariant of organizational and functional structure of the process of intelligent decision based on the cognitive functions. This researches with previously suggested method of learning in a multiagent neural like systems based on the ontoneuromorphogenesis are leading to the creation of self-organizing multiagent emergent networks, capable of simulation of psyche functions, goal-setting and adaptive goal-directed behavior based on the semantization of reality and building social connections. The principles of cognitive organization of intelligent systems are tightly connected with multiagent division of functions in multicellular organisms. Cognitive centers as in human brain as well as in an artificial intelligent system should be made as active systems, interworking with each other on the basis of the collective optimization parameters, critical in the first place to maintain the integrity of the system and its survival. Formal description of the agent should take into account that agent’s behavior consists of actions, which are carried out in the agent’s habitat and require energy. It is also important to note, that the exchange of energy and information happens not only between agent and the environment, but also between inside agents (organs, neurons) of the agent of a top level of recursive cognitive architecture.

Keywords: multiagent systems, cognitive architecture, neural-like networks, intelligent systems, neural networks, agent, development, design, intelligent behavior, modeling

Abstract: the article suggests a new way to automate the search of anomalous zones in the structure of the under sleeper pad base of the railway through the search of anomalous zones with the upper track structure examination during the overall control and diagnosis of the railway based on the building a model using the GPR radarograms representation. The proposed method is based on the article devoted to the methods of search for the anomalous zones, that points out the need of finding a connection between anomalous data and describing them in a unified mathematical representation model. This method is presented as a description of the mathematical model made up of mathematical models of all anomalous axes of phase synchronism obtained by earlier studies of the ballast railway. The method can be used to automate the classification of data on the ballast railway structure, not previously investigated, and in using data about the structure of the known railway track sections.

Keywords: Software, ground penetrating radar, georadar, layer, radiogram, track, method, model, anomaly, vector.

Abstract: the article reviews a technique of designing the knowledge base oriented neural networks represented by semantic networks. The technique is based on the appliance of a unified model of a neural network. A distinctive feature of the proposed design technique for processing the knowledge bases is in usage of a component approach and the libraries of compatible components of neural networks to reduce the labor contribution during the development, decrease the requirements for the qualification of developers and solve the problem of integration of neural network specific methods with other methods of representation and processing data in the development of hybrid intellectual systems.

Keywords: Software, hybrid intelligent system, knowledge base, semantic network, model, neural network, method of design, component, library, specification.

Abstract: this article considers the methodology of semantic models designing for one of the most important classes of intellectual systems – intellectual reference system. The methodology is based on use of semantic networks for encoding the information stored in knowledge base. The method is built on two principles: the principle of evolutionary design and the principle of collective design. A distinctive feature of this approach in designing intellectual systems is that at the each step of the designing process a working prototype of the system is available, which speeds up putting the developed system in operation both for testing and end-users and significantly increases the life cycle of the product.

Keywords: Software, methodology, design, system, knowledge, semantics, artificial intelligence, model, component, subject field

Abstract: the article emphasizes the need for a new knowledge representation model for increasing the efficiency of the expert diagnostic systems in social and technical fields of study. The authors present a fuzzy-production model, which allows the rules of the field of study to be described on a set of data of different types, represented both in clear and fuzzy scales. The authors develop a methodology of grouping the parameters, describing the object of diagnostics, to construct the cascade of parameters in accordance with the stages of the diagnostic process. The cascade of production rules is build upon the base of given model and method allowing to diagnose the state of a complex object. The authors describe the algorithm of a logical conclusion on the cascade of rules. On the solution of the medical diagnosis problem the author shows the effectiveness of the proposed approach, poses the problem of the future studies.

Keywords: Software, fuzzy, model, diagnostics, knowledge, expert, system, acceptance, decision

Abstract: the authors describe the open semantic technology of designing intellectual problem solvers. Special attention is given to the method of designing solvers and operations, which composes these solvers. The technology is a multilevel system and each level is responsible for specific functions during the problem solving. The special purposes agents function at each level and each level contains a supervisor agent responsible for the agents’ work optimization. The article shows a description of the supervisor agents’ algorithms and the principles of the organization of such systems in the whole.

Keywords: Software, intellectual system, intellectual problem solver, logical conclusion, semantics, agent, supervisor, hierarchical structure, algorithm, technology