Search

The purpose of this work is to develop an IT diagnostic system for Parkinson's disease (PD) with remote access based on the Internet of Things (IoT) network.Methods. The authors have developed a method for complex recognition of Parkinson's disease using machine learning, based on markers of voice analysis and changes in patient movements on known datasets. In the architecture of the Internet of Things network, a smartphone is the point of initial data collection and preprocessing, including extracting features from an audio recording of the patient's voice and his motor activity. Data is transmitted via a local Flask server, which acts as a channel for sending functional data to the Open Semantic Technology for Intelligent Systems (OSTIS) server. The OSTIS server processes the data received from the local Flask server and uses a neural network prediction agent to recognize BP. This agent downloads features and makes predictions based on a trained neural network, linking these predictions with knowledge in the OSTIS system, and stores them in a database.The result of the study is the architecture and algorithms of the IoT network. The workflow of the entire system includes data collection and preprocessing by the Internet of Things device, subsequent data transfer to the local Flask server, further forwarding to the OSTIS server, processing of the neural network model by a neural network predictor agent and, ultimately, linking the processed results to the knowledge graph and storing them in the system.The BP remote IT diagnostics system provides real-time processing of patient data, recognition of disease signs on the Internet of Things, support for advanced analysis and decision-making for further treatment.

The animal models used in biomedical research cover virtually every human disease. RatDEGdb, a knowledge base of the differentially expressed genes (DEGs) of the rat as a model object in biomedical research is a collection of published data on gene expression in rat strains simulating arterial hypertension, age-related diseases, psychopathological conditions and other human afflictions. The current release contains information on 25,101 DEGs representing 14,320 unique rat genes that change transcription levels in 21 tissues of 10 genetic rat strains used as models of 11 human diseases based on 45 original scientific papers. RatDEGdb is novel in that, unlike any other biomedical database, it offers the manually curated annotations of DEGs in model rats with the use of independent clinical data on equal changes in the expression of homologous genes revealed in people with pathologies. The rat DEGs put in RatDEGdb were annotated with equal changes in the expression of their human homologs in affected people. In its current release, RatDEGdb contains 94,873 such annotations for 321 human genes in 836 diseases based on 959 original scientific papers found in the current PubMed. RatDEGdb may be interesting first of all to human geneticists, molecular biologists, clinical physicians, genetic advisors as well as experts in biopharmaceutics, bioinformatics and personalized genomics. RatDEGdb is publicly available at https://www.sysbio.ru/RatDEGdb.

The paper proposes an approach to the individualization of user interfaces based on the integration of existing ontologies in the form of a single semantic model. The relevance of the work is due to the need to improve the efficiency and usability of user interfaces of intelligent systems. Guidelines for applying software individualization to achieve the highest possible level of usability based on ISO 9241-129:2010 and existing ontologies for implementing individualization are reviewed. A semantic model is developed to provide individualization of user interfaces of ostis-systems. The model is implemented within the framework of the Nika intelligent dialog assistant and is a reusable component, the use of which allows to reduce the cost of development of intelligent systems that require user interface individualization possibility.

The article describes an approach to implementing the ability of intelligent systems to self-learn through an intelligent framework for the development of artificial neural networks. A method of interaction between intelligent systems and a framework based on a library of reusable components is proposed, which allows to automatically design and train artificial neural networks based on a given problem specification. Based on the analysis of the activity of developers of artificial neural networks, a model of the problem solver of such a framework is described in the form of a hierarchy of actions for the development of artificial neural networks.

The information technology of a robust intelligent control system design based on quantum fuzzy inference is considered. The application of the developed design methodology is based on the quantum self-organization of imperfect knowledge bases of fuzzy controllers and leads to an increase in the robustness of intelligent control systems in unforeseen situations. The results of mathematical modeling and physical experiment are compared using the example of an autonomous robot in the form of an “cart - pole” system. Experimental confirmation of the existence of a synergetic effect of the formation of a robust self-organizing fuzzy controller from a finite number of non-robust fuzzy controllers in on line has been obtained. The resulting effect is based on the existence of hidden quantum information extracted from the classical states of the processes of time-varying gain coefficients schedule of regulators. At the same time, the amount of useful work performed by the control object (at the macro level) exceeds the amount of work spent (at the micro level) by a quantum self-organizing regulator to extract quantum information hidden in the reactions of imperfect knowledge bases without violating the second information law of thermodynamics of open quantum systems with information exchange of entangled (super-correlated) states. A concrete example of an autonomous robot is given, demonstrating the existence of a synergetic effect of quantum self-organization of imperfect knowledge bases. A generalized strategy for designing intelligent robust control systems based on quantum / soft computing technologies is described, which increase the reliability of hybrid intelligent controllers by providing the ability to self-organize. The main attention is paid to increasing the level of robustness of intelligent control systems in unpredictable control situations with demonstration by illustrative examples. A SW & HW platform and support tools for a supercomputer accelerator for modeling quantum algorithms on a classical computer are described.

A new algorithm for making autonomous decisions when controlling spacecraft carrying out descent in the atmosphere is developed, which allows to carry out stable control of the spacecraft relative to the nominal flight trajectories, which provide to reliably fulfill the targets of space missions. Analytical dependences are formed, with the help of which it is possible to obtain high-precision calculations of the parameters of the movement of a spacecraft in the atmosphere and determine corrective programs for controlling the apparatus. This makes it feasible to implement the movement of a spacecraft in the atmosphere along trajectories close to optimal, even under conditions of significant influence of disturbing factors on the dynamics of the flight of the vehicle. The authors give an estimate of the performance of the algorithm for making autonomous decisions on the example of parrying disturbing influences during the descent of a spacecraft in the atmospheres of Mars and Jupiter. It is shown that with complete qualitative agreement between the data calculated using the analytical dependences and the results of numerical integration, the computational errors do not exceed 3%. With the most unfavorable combinations of navigation errors and atmospheric density variations, the development of the corrective control programs developed in most cases ensures a qualitative coincidence of the disturbed and nominal trajectories. The developed algorithm for making autonomous decisions based on analytical dependencies can be effectively applied when a spacecraft moves in planetary atmospheres under various boundary conditions, constraints, design characteristics of the spacecraft and atmosphere models.

The design of a human personalized diet considering a variety of different factors is associated with system analysis and formalization of data and knowledge, as well as with the development of digital technologies. The paper presents the methodology of optimization and formation of personalized diets based on structural-parametric modeling. The proposed approach allows solving the following tasks: 1) to analyze the daily diet or individual meals (breakfast, lunch, afternoon snack, dinner, additional meals or snacks) with a known quantitative set of finished products in terms of energy value and chemical composition in order to reveal dietary disorders; 2) to calculate quantity of products optimal for a meal from the fixed list, thereby composing an individual reference diet with regard to the mental and physical activities, nutritive status of a consumer and economic aspects; 3) to optimize a diet depending on the task at hand by selecting a group of finished products from a complete or selected list of archival data, equally taking into account all the necessary parameters; 4) to adjust the diet taking into account dietary deviations in certain parameters of the chemical composition and energy value by additional introduction of special purpose products with the increased biological value, multivitamin and multivitamin-mineral supplements, as well as natural bioactive substances.

An approach to develop a problem solver for automatic answer verification to objective questions in intelligent tutoring systems constructed using OSTIS (Open Semantic Technology for Intelligent Systems) technology is сonsidered. The problem solver is developed based on multi-agent technology within OSTIS. The proposed problem solver automatically verifies the correctness and completeness of the user’s answer at the semantic level by starting the corresponding sc-agent sets according to the type of the questions. The objective question answer verification is one of the main purposes of the developed problem solver, it can also perform the calculation of the similarity between any two semantic graphs.

The main task of knowledge acquisition (also named knowledge extraction) from natural language texts is to extract knowledge from natural language texts into fragment of knowledge base of intelligent system. Through the induction of the related literature about knowledge acquisition at a home country and abroad, this paper analyses the strengths and weaknesses of the classical approach. After emphatically researching the rulebased knowledge extraction technology and the method of building ontology of linguistics, this article proposes a solution to the implementation of knowledge acquisition based on the OSTIS technology. The main feature of this solution is to construct a unified semantic model that is able to utilize ontologies of linguistics (mainly, syntactic and semantic aspect) and integrate various problem-solving models (e. g., rule-based models, neural network models) for solving knowledge extraction process from natural language texts.

Background. The subject of the study is information on the classification and performance characteristics of military ground equipment, which is in the public domain. The object of research is ontological models of knowledge. The purpose of the work is to develop an ontology of military ground equipment. Materials and methods. The design of the ontology was based on a system analysis using the “top to bottom” method. To develop the ontology, the free software Protégé and the ontology description language OWL were used, HermiT was used as an inference machine. Results. An ontology of military ground equipment has been developed. The classes, properties and axioms that define the logic of inferences for ontological engineering of knowledge are described. Conclusions. The presented ontology can be used to solve problems in tactical and strategic planning in military affairs, as well as for educational purposes.

The article presents a hierarchy of requirements necessary for the successful design of food products with given composition and properties considering age restrictions and various diseases. The need for generalization and systematization of scientifically based principles, specific medical and biological requirements for food products, diets for the most common nutritional diseases in the knowledge base is shown. Using the k-means cluster analysis method, 1) meat raw materials were analyzed for inclusion in functional food for gerodietetic nutrition according to the most significant descriptors (protein, methionine + cystine amino acids, tryptophan), 2) spicy herbs and spices were analyzed for inclusion in the Muhammara recipe as natural antioxidant sources according to the descriptor of antioxidant properties. Using the example of the Muhammara recipe change, all stages of a systemic approach in the development of functional foods are shown. The first stage is related to obtaining information from the knowledge base about scientifically based nutritional principles and specific biomedical requirements for the given age group. At the second stage, the clustering of raw materials of animal and vegetable origin is carried out in order to reasonably include in the recipe of food product being developed. At the third stage, a system of balance linear algebraic equations for the chemical composition of the food product being developed (mass fraction of fat, protein, water, carbohydrates, vitamins, macro- and microelements, amino acids, etc.) is formed. The fourth stage is associated with the establishment of the target function (optimization criterion), and restrictions for recipe and balance. At the fifth stage, the problem is solved using a high-level language in a modern programming environment. At the final (sixth) stage, the nutritional value of the optimal balanced recipe is analyzed considering the target function and the given restrictions. As a result, we receive a modified Muhammara recipe with optimized protein: fat ratio. Mathematical simulation was carried out using the R Studio software with open-source lpSolve and lpSolveAPI libraries.

Objectives. The creation of ontologies of subject areas is considered. The goal is to develop a mathematical model of ontology and the information system for ontological modeling. The task is to reduce the complexity of ontological modeling.Methods. As research methods, the theory of hybrid intelligence systems, the theory of sets, elements of mathematical logic, methods for developing the information systems, comparative analysis of information systems, informal analysis of information system were used.Results. Mathematical model of ontology using the concept of metaobject is developed. Ontological modelling based on this model involves specification, conceptualization and formalization. A glossary of terms is being built at the specification stage. At the conceptualization stage, objects in the subject area and their hierarchy are defined, and then connections between objects are identified. In the formalization stage, the metaobjects and the relationships between metaobjects that correspond to objects and the relationships between objects were defined. This is considered as the ontology of the subject area. During the actualization stage, the parameters of subject area objects and their values, classes, subclasses, and instances of classes were defined. Parameters, parameter values, classes, subclasses, and instances of classes are implemented in ontology as metaobjects of relative types. An information system with a unique architecture has been developed, namely a hybrid intelligence system for the automation of ontological modelling.Conclusion. The article conducts a comparative analysis of the developed information system with the systems used today for creation of ontologies. The analysis showed that the information system developed by paper author in most parameters is not inferior to considered systems and at the same time easier to use and expand. The mathematical model of ontology and the information system for ontological modeling of subject areas, developed by author, are tested in practical creation of ontology on ecology. On the basis of the conducted comparative analysis and informal analysis of practical use, it is concluded that ontological modeling with the help of the information system developed by author reduces the labor intensity and decreases the time of ontologies creation.

Some data on the knowledge base to support the development of low-thrust liquid-propellant rocket engines using computer technologies are presented. The structure of the base is proposed on the basis of characteristic features of engines, including the purpose, fuel components, physical principles of organizing the work process of the engines, etc. The presence of electronic versions of schematic diagrams, configuration and the main achieved characteristics in the database will make it possible to choose effective design solutions at the design stage of new products. In the future these solutions will lead to the required parameters and characteristics of the low-thrust rocket engines being developed. The description of the engine used in the database allows assessing the capabilities of the engineering solution used in the design, as well as tracing the development trends of a particular direction in rocket propulsion. The peculiarity of the base being created is that, in parallel with the information about low-thrust rocket engines, the data on their components and accessories is accumulating, which can also be used in new developments. Given the growing volume of the knowledge base on low-thrust rocket engines, some forms of communications are presented that make it possible to quickly find the required information, but requires certain ordering of the design data already at the initial stages.

Introduction. The article describes the approach to solving the problem of complex technical system troubleshooting based on expert knowledge modeling. Intelligent information systems are widely used to solve the problems of diagnostics of multilevel systems including combine harvesters. The formal description of the subject domain knowledge is the framework for building the knowledge base of these systems. The sequence of creating an expert system knowledge base in accordance with production rules is considered. Materials and Methods. The approach is founded on the fault function table. As the object of diagnostics, one of the subsystems of the combine harvester electric equipment “opening the hopper roof flaps” is considered. The basis for constructing a sequence of elementary checks is a system of logical equations describing both the serviceable and possible faulty states of the subsystem. Results. A structural logic model is developed. As a result of analyzing the fault function table, the sets of elementary checks are determined. Four criteria have been used to analyze the weight of these checks. The authors have determined optimal sequence of checks and have developed a decision tree, which allows finding the cause of the malfunction and is the basis for creating the knowledge base of an intelligent information system. A fragment of the knowledge base is given. Discussion and Conclusion. The proposed approach of expert knowledge modelling increases the efficiency of the unit for troubleshooting of the intelligent decision support system. It makes possible to structure the base of expertise and establishing the optimal sequence of elementary checks. This allows determining the optimal sequence of application of the knowledge base production rule that makes it possible to reduce the time of restoring the serviceability of combines.

To implement natural language user interface and an intelligent answer to questions, the knowledgebased semantic model for Chinese language processing is proposed. The article gives careful consideration to the existing methods and various knowledge bases for natural language processing. The analysis of these methods has led to the conclusion that in natural language processing, the knowledge base is the most fundamental and crucial part. The knowledge base makes it possible to ensure processing of a natural language based on initially described knowledge and to explain the processing operations. By virtue of the analysis of various methods for constructing knowledge bases about the English and Chinese languages, an ontological approach to the Chinese language processing was proposed. The Chinese language processing model has two main aspects: the design of knowledge base about the Chinese language and the development of ontology-based knowledge processing machine. The proposed approach is aimed at developing a semantic model of knowledge on the Chinese language. As a stage in the implementation of the approach, I designed the ontology of the Chinese language that can be applied for further processing of the language. This paper considers the preliminary version of the ontology and the principle of building a knowledge base about the Chinese language. There are no uniform standards and evaluation system for designing an ontology. Expansion, refinement and evaluation of the ontology require further research.

This article presents software tools designed for construction of heterogeneous models by software integration of logical models having their work methods set in the knowledge bases and engineering models created in a technical simulation environment. In order to build logical models we use our software «Software-and-mathematical model of the command-andmeasurement system’s onboard equipment». Engineering models are built in the graphical programming environment of the LabVIEW. The software functions are described for creation of graphical schemes of models, data structures and telemetry data packages design, creation of the command base and setting of the methods of the model’s elements work in the knowledge bases’ rules. We provide an example of a heterogeneous model simulating the logics of the spacecraft’s command-and-measurement system’s onboard equipment operation including the library of virtual devices for the receiving and transmitting path simulation and the knowledge base with the rules of the onboard system’s interaction during reception, transmission, execution and confirmation of commands. This example demonstrates the points of integration of logical simulators and virtual devices. The model allows to assess the parameters of the receiving and transmitting path and the influence of destabling factors on communication line’s quality, simulate generation and transformation of the signal coming from the source of information – ground segment – to the onboard equipment and simulate logical interaction of the systems if the necessary signal level is provided. Each element of the model can be transformed and processed by the subject area’s specialist depending on the specifics of the solved tasks.

This article proposes an approach for designing a general subsystem of automatic generation of questions in intelligent learning systems. The designed subsystem allows various types of questions to be automatically generated based on information from the knowledge bases and save the generated questions in the subsystem knowledge base for future use. The main part of the subsystem is the automatic generation module of questions, which allows one to generate questions of various types based on existing question generation strategies in combination with the structural characteristics of knowledge bases built using OSTIS technology. In this article, a variety of strategies for automatically generated questions are proposed, the use of which allows various types of questions to be automatically generated, such as multiple-choice questions, fill-in-the-blank questions, questions of definition interpretation and etc. The most important part of the subsystem is the knowledge base, which stores the ontology of questions, including the question instances themselves. In this article, the knowledge base is constructed based on OSTIS technical standards. The type classification of automatically generated questions was developed, as well as the subject area for storing generated questions and the corresponding ontology described in the knowledge base of the subsystem. The generated questions are stored in the subsystem knowledge base in the form of SC-code, which is the OSTIS technology standard. When testing users, these automatically generated questions are converted to the corresponding natural language form through the natural language interface. Compared with the existing approaches, the approach proposed in this article has certain advantages, and the subsystem designed using this approach can be used in various OSTISbased systems driven by OSTIS technology.

Introduction. A mathematical model of the industrial safety monitoring system in mechanical engineering is investigated. The work objective was to create a mathematical model based on expert assessments of workplace safety parameters with a calculated and experimental justification of its applicability to the “STRAZH” expert security monitoring system.Materials and Methods. The classification of expert systems for engineering enterprises is proposed. The stages of creating expert systems are considered. A methodology for assessing the consistency of experts as a basis for models of expert systems in the field of mechanical facilities safety is presented.Results. The basic safety parameters of the workplace are identified. A matrix of expert evaluation of parameters based on the opinion of leading experts in the field of engineering is created. The results of modeling the expert system “STRAZH” with the calculated and empirical support of the mathematical model validity are presented. The advantages of implementing expert systems to increase the level of personnel safety are proved.Discussion and Conclusions. The results obtained have a high degree of expert coordination and can be used in the development of expert safety monitoring systems for engineering enterprises.

В работе представлены подходы к компьютерному проектированию ракетных двигателей малой тяги с использованием разветвлённой базы знаний, позволяющей принимать основные технические решения, определяющие проектный облик двигателя, на основе разработанного алгоритма этого процесса. Рассмотрена процедура создания электронной 3D-модели ракетного двигателя малой тяги на газообразном кислородно-водородном топливе в среде графического комплекса UNIGRAPHICS. Получены 3D электронные модели основных элементов ракетного двигателя тягой 25 Н с последующей виртуальной сборкой всех компонентов, включая составляющие, заложенные в базу знаний, обеспечивающие разработку, в том числе, конструкторской документации, создание производственной среды на основе электронной модели двигателя, подготовку и собственно производство изделия.

The author offers new approaches to dealing with the strategic and operational management of the company. The model of guaranteed algorithmic impact of strategic requirements (recommendations) expressed in specific indicators on monthly budgeting process is offered in the article. The organic interaction of these control types will allow management to implement model developments systematically and consistently in the enterprise. Embedding monthly budgets in strategic management involves the creation of intellectual information system, the core of which would be the hierarchical knowledge base that provides algorithmic communication between the strategy and budget. In addition, the database of formulas must be created which are designed for monthly calculations of indicators that are defined by the strategic goal. The provided in the article technology of fuzzy hierarchical search of restrictions on a number of key fiscal indicators clearly demonstrates the process of smoothing conflicts and resolving problems encountered during the adaptation of target strategic requirements to the real possibilities of the enterprise.

The development of highly efficient technologies in genomics, transcriptomics, proteomics and metabolomics, as well as new technologies in agriculture has led to an “information explosion” in plant biology and crop production, including potato production. Only a small part of the information reaches formalized databases (for example, Uniprot, NCBI Gene, BioGRID, IntAct, etc.). One of the main sources of reliable biological data is the scientific literature. The well-known PubMed database contains more than 18 thousand abstracts of articles on potato. The effective use of knowledge presented in such a number of non-formalized documents in natural language requires the use of modern intellectual methods of analysis. However, in the literature, there is no evidence of a widespread use of intelligent methods for automatically extracting knowledge from scientific publications on cultures such as potatoes. Earlier we developed the SOLANUM TUBEROSUM knowledge base (http://www-bionet.sysbio.cytogen. ru/and/plant/). Integrated into the knowledge base information about the molecular genetic mechanisms underlying the selection of significant traits helps to accelerate the identification of candidate genes for the breeding characteristics of potatoes and the development of diagnostic markers for breeding. The article searches for new potential participants of the molecular genetic mechanisms of resistance to adverse factors in plants. Prioritizing candidate genes has shown that the PHYA, GF14, CNIH1, RCI1A, ABI5, CPK1, RGS1, NHL3, GRF8, and CYP21-4 genes are the most promising for further testing of their relationships with resistance to adverse factors. As a result of the analysis, it was shown that the molecular genetic relationships responsible for the formation of significant agricultural traits are complex and include many direct and indirect interactions. The construction of associative gene networks and their analysis using the SOLANUM TUBEROSUM knowledge base is the basis for searching for target genes for targeted mutagenesis and marker-oriented selection of potato varieties with valuable agricultural characteristics.

The article proposes the structure of decision-making support system (DMSS) for management of the production logistics of industrial enterprise, which will increase efficiency of production system (by reducing time for decision-making which are based on the information about actual stocks, planned downtime and losses), and will determine the cost of failed managerial decisions in order to eliminate the possibility of recurrence in the future. The main aspects of functioning of the proposed DMSS are illustrated on the example of the process of converter production of steel at a metallurgical plant, describing each of the units presented in the structure of the system. The author proposes a decision-making mechanism, based on close interaction between the modeling module, knowledge base, and databases, using which one can generate recommendations concerning the movement of one or another unit, which participates in the process of converter production of steel. On the basis of her own experience of developing the alike systems, the author proposes a group data processing, suggesting use of a personal interface for each category of users, which will attract the main participants in the production process to decision-making, collective formulation of new ideas. It is specified that improvement of efficiency of functioning of economic objects is possible, first of all, by means of a competent application and further perfection of information systems.

An approach to the intellectual assessment of students' knowledge within the framework of a hybrid intelligent learning environment (HILE) based on the construction and training of neural networks is considered. Structural schemes of the system for assessing knowledge in mathematics for schoolchildren of various grades are developed. The models of the pedagogical process "teacher" – "HILE module" – "student", "teacher" – "student", as well as a neural network agent model of the learning process are considered. The choice of types of neural networks and types of machine learning is substantiated, taking into account goal-setting. Neural network algorithms and training criteria for neural networks are characterized. The results obtained are aimed at creating methods that provide the processes of operational learning, control and assessment of knowledge, competencies and procedures, the level of formation of subject and professional competencies of students in the information and educational intellectual environment.

The purpose of the study is to develop an approach to improve information support for the development of the contents of higher education programs and teaching methodological materials. The system of higher education faces the challenges of supporting the development of the digital economy through training and research. Creating the appropriate content of education becomes a difficult task with the high rate of development of digital technologies and methods to use them. Now, in smart learning, the technical aspects of the organization of the educational process often overshadow aspects, related to the methodology or content of smart learning. However, the issues of the content of education become most relevant. Research in the field of knowledge management remain relevant because, the more perfect the technologies become, that notice the algorithmized work of specialists, the higher the value of creativity for society and the economy.Materials and methods of research include discourse analysis of domestic and foreign scientific sources devoted to the issues of smart education and knowledge management, the systematization of the material. Methodological basis for developing an approach to improve information support is the methods and technologies of the theory of knowledge management.The results of the research show that the need for the development of the digital economy places high demands not only for technologies, but also primarily on the competencies for their use. The logic of IT development in education indicates that there is a gradual change in the stages of informatization: from distance education technologies to e-learning and then to smart learning. Each stage of the informatization of education allows solving the problems that are important for the economy and society. There are the factors, influencing the formation of requirements for the content of educational programs: technological, economic, social and geopolitical. The following requirements of smart training for the content of educational programs are revealed: actual information and tasks in the training course; opportunities for independent cognitive, research and project activities of students; distributed information system of smart learning; integration of the educational environment with professional communities; individualization of the content of training.The conclusion. Technologies and methods of knowledge management can provide the necessary level of speed and quality of development of educational materials. The article describes the knowledge management system, which through the knowledge base, communities and co-creation tools, ensures the relevance of the developed content and fills the smart learning with the necessary content.

An innovative approach to the documentation of technological objects is presented. Recommendations and methods for the development of the intellectual passport for technological objects in PLM system, its knowledge bases, organizations, data and knowledge presentation and processing are given.

The reviewed book by Damien Nouvel, Maud Ehrmann, and Sophie Rosset Named Entities for Computational Linguistics deals with automatic processing of texts, written in a natural language, and with named entities recognition, aimed at extracting most important information in these texts. The notion of named entities here extends to the entire set of linguistic units referring to an object. The researchers minutely consider the concept of named entities, juxtaposing this category to that of proper names and comparing their definitions, and describe all the stages of creation and implementation of automatic text annotation algorithms, as well as different ways of evaluating their performance quality. Proper names, in this context, are seen as a particular instance of named entities, one of the typical sources of reference to real objects to be electronically recognized in the text. The book provides a detailed overview and analysis of previous studies in the same field, based mainly on the English language data. It presents instruments and resources required to create and implement the algorithms in question, these may include typologies, knowledge or databases, and various types of corpora. Theoretical considerations, proposed by the authors, are supported by a significant number of exemplary cases, with algorithms operation principles presented in charts. The reviewed book gives quite a comprehensive picture of modern computational linguistic studies focused on named entities recognition and indicates some problems which are unresolved as yet.

Rapid development of high-performance genomic, transcriptomic, proteomic and metabolic technologies led to an information explosion in the field of plant biology and agrobiology. To date, the number of scientific publications on only one of the most important agricultural crops of Solanum tuberosum L. (potato) has exceeded 1.5 million. Effective access to knowledge distributed over such a multitude of non-formalized natural language textual sources requires the use of special computer-assisted intelligent methods of data mining (text-mining). However, in the literature, there is no data on the application of intellectual methods of automatic knowledge extraction from publications on agricultural crops, such as potato. Previously we have developed a pilot version of the SOLANUM TUBEROSUM knowledge base. SOLANUM TUBEROSUM is a computer platform for complex intellectual processing of large data bodies, including (1) automatic analysis of scientific publications and databases for extraction of information on genetics, markers, breeding, diagnostics, protection and storage technologies for potato, (2) formalized representation of extracted information in the knowledge base, (3) user access to these data, (4) analysis and visualization of query results. The ontology of the SOLANUM TUBEROSUM knowledge base contains dictionaries of molecular genetic objects (proteins, genes, metabolites, microRNAs, biomarkers); phenotypic characteristics of potato varieties; potato diseases and pests; biotic/abiotic environmental factors; potato agrobiotechnologies. This article describes the current version of the SOLANUM TUBEROSUM knowledge base developed from an extensive analysis of scientific publications on the moleculargenetic regulation of metabolic pathways in potatoes, as well as model plant organisms (maize, rice, Arabidopsis thaliana). In total, about 9,000 full-text articles and more than 130,000 abstracts of PubMed were analyzed. With the help of automatic analysis of scientific publications, more than 59,000 facts on molecular genetic interactions and genetic regulation were identified, and the analysis of factual databases revealed more than 380,000 such interactions in the examined organisms. It turned out that about 3 % of extracted facts about molecular genetic interactions and genetic regulation were related to Solanum tuberosum L. Thus, the inclusion of information on well-studied model species during the extraction of information on the molecular-genetic regulation of metabolic processes is important. It allows prediction of orthologous genes in potato and their further identification and analysis based on homology. An associative network of genetic regulation of starch biosynthesis in potatoes, including 33 metabolites, 36 proteins, 6 metabolic pathways and 132 interactions between them, 86 of which describe catalytic reactions, and the rest – regulatory events, was reconstructed. The reconstructed network is the basis for the search for target genes for directed mutagenesis and marker-oriented selection of potato varieties with specified starch properties. The trial version of the SOLANUM TUBEROSUM knowledge base is available at http://www-bionet.sysbio.cytogen.ru/and/ plant/.

Copyright of Electronics & Control Systems is the property of National Aviation University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Based on the analysis of the peculiarities of operational and service activities of the regional administration and existing approaches, a model of the system of situational management of regional management of the State Border Guard Service of Ukraine was proposed. The novelty of the proposed approach is the application of a database of instructions - a case-law approach and a knowledge base-an athletic approach to justifying a decision on the actions of organs (divisions) in protecting the state border in situations. The process of substantiation and decision-making is provided by the support of a quantitative set of knowledge. The formalization of this process is possible when considering the sequence of actions that are carried out by the management bodies in attracting expert knowledge. The proposed model allows to form a decision bank for "typical" variants of the enemy's actions in an armed conflict, with the subsequent appeal to these solutions, which provides the opportunity to reduce the time costs of the regional governance authorities, the use of formal and declarative knowledge and allows you to combine the advantages of the quantitative elements of the justification of the decisions in the unification with knowledge of experts. By analogy, you can create elements of the knowledge base for other situations.

This paper considers the logical approach to the theoretical justification of constructing correct algorithms that extend the area of the solutions obtained on the basis of existing algorithms. The proposed method makes it possible on the basis of a given set of pattern recognition algorithms to identify additional knowledge of a given subject area and to build a minimum rule, providing additional training of these algorithms.

The aim of this paper is to present the participation and involvement of the University of Ruse in the Danube: Future Project for sustainable development of the Danube Region. A white paper on integrated sustainable development of the Danube River Basin produced by representatives of Danube Rectors’ Conference and Alps-Adriatic Conference member universities. Case study of the participation of the University of Ruse in the 3 editions of the DIANET International School, the 1st Danube:Future Workshop, and in the Management Committee of the Project. The general conclusion drawn in the paper is that the Danube:Future project has allowed the University of Ruse to be more engaged in the scientific development in the Danube Region, and has improved its visibility among other universities and stakeholders. The paper results can serve as a motivation for other researchers and universities to join the project and contribute to its growing Knowledge Base. The study will contribute to finding new paths for developing research in the Danube Region by making the environmental and cultural heritage of the DRB visible and bringing it into the context of sustainable development.

Article represents the features of modern educational environment for training specialists in the fi eld of aerospace robotics. Training requirements of modern specialists are pointed. Approaches to the description of the subject areas of onboard intelligent systems are demonstrated. Implementation variations of these approaches are shown in the architecture of an intelligent system and in the demo example of planning system.

A person has no ability to capture entirely and to estimate correctly the logical coherence and consistency of Regulations in the Text Form. It leads to mistakes in a work of an Enterprise Staff and to the impossibility of mastering of the Regulations with considerable volume. Presented Information Technology allows the Regulations Executor to receive on-line proper information of the Optimum Actions in any possible Situation, which can arise in the course of the work. Leading Experts of any Enterprise may create the full-fledged Expert System by themselves with the help of Specialized Software. Such a System will contain the knowledge in the Functional Model of Regulations (the Optimum Business Process). Stages of realization of the represented Information Technology and the peculiarities of on-line data displaying for the Regulations Executor are illustrated by the Pharmacy Customer Service Regulations.

Application suitability for one of the intelligent methods for risk management of software projects has been shown based on the review of existing algorithms for fuzzy inference in the field of applied problems. Information sources in the management of software projects are analyzed; major and minor risks are highlighted. The most critical parameters have been singled out giving the possibility to estimate the occurrence of an adverse situations (project duration, the frequency of customer’s requirements changing, work deadlines, experience of developers’ participation in such projects and others.). The method of qualitative fuzzy description based on fuzzy logic has been developed for analysis of these parameters. Evaluation of possible situations and knowledge base formation rely on a survey of experts. The main limitations of existing automated systems have been identified in relation to their applicability to risk management in the software design. Theoretical research set the stage for software system that makes it possible to automate the risk management process for software projects. The developed software system automates the process of fuzzy inference in the following stages: rule base formation of the fuzzy inference systems, fuzzification of input variables, aggregation of sub-conditions, activation and accumulation of conclusions for fuzzy production rules, variables defuzzification. The result of risk management automation process in the software design is their quantitative and qualitative assessment and expert advice for their minimization. Practical significance of the work lies in the fact that implementation of the developed automated system gives the possibility for performance improvement of software projects.

The analysis showed the existing information and telecommunications systems are not able to make enough timely and quality support decision-making on criminal analysis and require further improvement. Application of fuzzy inference model to identify offenders legislation to control, according to the formulation of the mathematical problem of identifying offenders in a non-linear estimation of the object with the set of input variables and one output variable. For example, if the living condition is poor and the availability of appropriate vehicles is high, the degree of possibility of offense is high. Each sign is formalized as the level of compliance with the implementation of crime. Obviously, the higher the score, the more can be carried out illegal activities. Output variable is the level of the degree of possibility of the offense: transportation of contraband, weapons, drugs, etc. in a particular area of the border. In the fuzzy model of risk assessment of unlawful activity, all variables are presented as linguistic, universal set is measured on a scale of personnel based on their knowledge, experience and intelligence. Construction of membership functions of terms "low", "medium", "high", used to assess linguistic variables, by using the method of statistical analysis expert information. The contradiction between a large number of input variables and the number of rules is solved by constructing a hierarchical knowledge base. The method of activation used min. Since all the rules as a logical connection to of the conditions only applies fuzzy conjunction (operation "AND"). As a method of aggregation used operations min-conjunction. For accumulation endings rules applied max-disjunction. As a method defazzyfikation the method of center of gravity. Implementation of fuzzy inference model by using the package fuzzyTech. The practical implementation of this model was carried out in a software module "Identifying offenders" which proposed to include subsystems "risk" information and telecommunication systems "Hart" of the State Border Guard Service of Ukraine. The application of the model in contrast to the existing allows: use of quality indicators, taking into account inaccurate, approximate information about the meaning of the signs, the use of knowledge professionals from operational activities - experts who served in the form of fuzzy inference rules, more qualitative assessment of object investigated in criminal analysis.

We believe that this knowledge base of training system structure is based on the subject semantic network (SSN) containing concepts of subject domain and relations between them. The SSN is represented as a direct graph, with tops corresponding to concepts, and arcs corresponding to relations. We consider a technique for trainee’s conceptual knowledge assessment using the cognitive maps of trainees (CMT), each of which formalizes his ideas of some SSN fragment and theoretically coincides with this fragment. Assessment of trainee’s achievement of this SSN fragment comes to comparison of SSN subgraph, corresponding to this fragment, with the direct graph, which is defined by the corresponding CMT.A number of important subject domains possess the property that concepts in them have the attribute called ‘role’, and roles of concepts can be linearly sorted. The direct graph SSN, corresponding to such ontology can be presented in a tiered form.The work concerns the assessment of trainee’s conceptual knowledge in the subject domains of this class. The work represents the SSN and CMT models used, describes the offered methods to create CMT, as well metrics for trainee’s achievement of the conceptual knowledge based on his CMT.The main results of work are the following: the model of the semantic network corresponding to hierarchical role ontology, and also a model of a trainee’s cognitive map of are offered, methods for creating the trainee’s cognitive maps are developed, metrics of trainee’s achievement of conceptual knowledge are suggested.

This article describes the structure of a uniform object capable of representing information about relations between separate basic semantico-syntactic structures in a natural language knowledge base. The first part of the article deals with analyzing relations in natural language and defining their common properties. Particular attention is paid to estimating usefulness of these properties in the broader context of components of knowledge base and connections between them. The second part of the article is focused on mapping the obtained properties to an artificial structure suitable for use in a relational database and determining their limitations. The resulting structure allows the basic structure of the knowledge base to be finalized, providing a complete architecture that can be implemented as a software product to test the basic capabilities of the proposed structure and to determine its limits in solving more complicated tasks.

In this article, a method was developed for antifault control of complex technical systems using a hybrid expert system. The presented hybrid expert system is based on a neural network and fuzzy logic, and also uses an automated knowledge base. Factors and criteria for the operability of technical units of complex technical systems are considered, on the basis of diagnostics and forecasting, a final conclusion is made about the operability of the system, and actions are in place to apply which can eliminate emergency or abnormal situations in the event of their detection. As an example for simulating a neural network, data from the ship's air conditioning system were taken. [ABSTRACT FROM AUTHOR]

The article considers problems of formation of systems of self-servicing of customers. These processes take place in different branches of service and are determined by development of information technologies. History of development of systems of self-servicing is rather long, but they became to develop actively during formation of social networks and spontaneous solution of social tasks. Specific feature of the process of self-servicing is the fact that its participant plays both the role of the producer and customer. The condition of formation and development of systems of self-servicing is their complete information openness and voluntariness. It is necessary to create special systems of knowledge for development of this type of service systems. Functioning of the systems of self-servicing is an important element of ensuring stability of an economic system.В статье рассматриваются проблемы формирования систем самообслуживания потребителей. Данные процессы происходят в различных отраслях сервиса и определяются развитием информационных технологий. История развития систем самообслуживания достаточно длительная, но они стали активно развиваться при формировании социальных сетей и стихийном решении общественных задач. Спецификой процесса самообслуживания является то, что его участник выступает одновременно как производитель и как потребитель. Условием формирования и развития систем самообслуживания является их полная информационная открытость и добровольность. Для развития данного вида сервисных систем необходимо создание специальных систем знаний. Функционирование систем самообслуживания является важным элементом обеспечения устойчивости хозяйственной системы.

The fundamental goal of modern information technology is to support decision making process in organizations, for both routine and highly complex problems, based on heterogeneous data sources. The main objective of the paper is to present the construction concept of knowledge base for an expert system designed to support the decision making in cardiac surgery. A knowledge‐based medical expert system is designed to support decision‐making process in cardiac surgery where knowledge from medical guidelines, risk scales, and registries is applied to reason the medical procedure in a particular case scenario.

An innovative approach to the documentation of technological objects is presented. Recommendations and methods for the development of the intellectual passport for technological objects in PLM system, its knowledge bases, organizations, data and knowledge presentation and processing are given.

The modern demands for diagnosing automobiles on all stages of the life cycle are consid-ered. A knowledge base consisting of six volumes and a system textbook consisting of 4 volumes arecreated.

The basic construction concepts of unifying two-digit and multi-valued means of processing symbolic data are considered. The present approach is based upon a single methodological and special purpose principle by applying the proposed methods of the intelligence theory for mathematical input/output data and their intermediate transformations by an appropriate AFP-structure of the third grade.