Knowledge Engineering Methods Research Articles

Development of computer-based methodology for remote advanced training of medical doctors

Aim. To formulate the methodology for developing the interactive virtual computer simulations with a rating assessment of trainees’ decisions and the capability of remote access.Material and Methods. The methods of knowledge engineering were used to extract and formalize expert knowledge about the structure, significance, and relevance of clinical diagnostic information. The materials for creating virtual computer simulations were based on texts from the archival medical records, laboratory data, and multimedia results of instrumental methods of study. A three-tier network architecture was applied to provide the capabilities of remote access. It was organizationally represented by three components: a client layer, a business logic layer, and a data layer. Data transfer was provided by the Web protocols while microservices represented the infrastructure.Results. The information was formalized and structured after expert analysis and identification of significant diagnostic and prognostic data. The process included defining the domain model, identifying the aggregates and connections between them, and designing software and user interfaces. Possible solutions for trainees are now presented in the form of interactive reference lists. The artifacts of the user’s work are saved in the storage represented by the module for working with the server file system and the object-relational database management system. Each task module contains static and interactive blocks of information. The purpose of static blocks is to provide trainees with the necessary information for making clinical and diagnostic decisions. The interactive blocks allow selecting one or more solutions from the list. The content and sequence of further information presentation are determined by the trainees’ answers to the questions of an interactive block. Trainees’ decision-making competencies are evaluated using the rating system. The final personal rating is calculated as a multiplication of all coefficients related to the trainees’ decisions. This approach integrates a rating system with the trajectory chosen by the trainee for task completion.Conclusions. The distance learning technologies, developed for clinical disciplines in this study, are quite new and innovative. The repository of virtual computer simulations is under development to improve the methodological support of remote clinical training.

Design of knowledge-based systems for automated deployment of building management services

Despite its high potential, the building's sector lags behind in reducing its energy demand. Tremendous savings can be achieved by deploying building management services during operation, however, the manual deployment of these services needs to be undertaken by experts and it is a tedious, time and cost consuming task. It requires detailed expert knowledge to match the diverse requirements of services with the present constellation of envelope, equipment and automation system in a target building. To enable the widespread deployment of these services, this knowledge-intensive task needs to be automated. Knowledge-based methods solve this task, however, their widespread adoption is hampered and solutions proposed in the past do not stick to basic principles of state of the art knowledge engineering methods. To fill this gap we present a novel methodological approach for the design of knowledge-based systems for the automated deployment of building management services. The approach covers the essential steps and best practices: (1) representation of terminological knowledge of a building and its systems based on well-established knowledge engineering methods; (2) representation and capturing of assertional knowledge on a real building portfolio based on open standards; and (3) use of the acquired knowledge for the automated deployment of building management services to increase the energy efficiency of buildings during operation. We validate the methodological approach by deploying it in a real-world large-scale European pilot on a diverse portfolio of buildings and a novel set of building management services. In addition, a novel ontology, which reuses and extends existing ontologies is presented.

Criteria for a systematic approach in the digitalization of horticulture of agricultural enterprise

The analysis of the relevance of the State land policy in the Russian Federation (RF) is given. The perspective of its implementation is shown taking into account the technological policy for land management of “work sites” on an ecological-landscape basis. A way is proposed to optimize the horticultural system in agricultural enterprises using knowledge engineering methods and sustainable development methodology. The purpose of the study is to identify the modern tasks of horticulture in agricultural enterprises, the formation of environmentally friendly industrial landscapes for them, ensuring the effective management of the production of fruit and berry products. In the work, methods of different scientific fields were used that substantiate the knowledge base “garden landscape” of an agricultural enterprise. These include geobotany, phytocenology, biogeocenology, ecology landscape, landscape ecology, environmental engineering and knowledge engineering. These areas are not yet used in the methodology of horticulture and seem to us extremely necessary in accordance with the requirements of modern legislative and regulatory acts of the Russian Federation imposed on the greening and digitalization of fruit and berry production and land use. They were chosen by us not so much for improving the “gardening system” as for engineering and management of environmentally friendly production. To create a knowledge base on the “garden landscape” of an agricultural enterprise, the importance of the ontology of primary bio-, phyto-, eco- and geosystems is substantiated, a system of “transitionstranslations” between them is proposed to prepare the digitalization of horticulture. The development of accounting methods for different types of landscape territorial structures for agro ecological assessment of lands on the catchments of the hydrographic network, agro ecological requirements of crops (varieties) to environmental factors, identification of garden able “primary agro ecologically homogeneous land plots” for the horticultural system, the need for their selection as work sites is recommended . It is proposed to carry out digitalization of horticulture on a new scientific platform, Nature-Industrial Systems (NIS), taking into account the knowledge of the garden landscape and the methodology of a systematic approach to solving the problems of sustainable development, perfection and optimization of the basic technology registers, certification of applied developments, energy control.

Additive and hybrid technologies for products manufacturing using powders of metals, their alloys and ceramics

Purpose: The paper is a comprehensive review of the literature on additive and hybrid technologies for products manufacturing using powders of metals, their alloys and ceramics. Design/methodology/approach: Extensive literature studies on conventional powder engineering technologies have been carried out. By using knowledge engineering methods, development perspectives of individual technologies were indicated. Findings: The additive and hybrid technologies for products manufacturing using powders of metals, their alloys and ceramics as the advanced digital production (ADP) technologies are located in the two-quarters of the dendrological matrix of technologies "wide-stretching oak" and "rooted dwarf mountain pine" respectively. It proves their highest possible potential and attractiveness, as well as their fully exploited attractiveness or substantial development opportunities in this respect. Originality/value: According to augmented holistic Industry 4.0 model, many materials processing technologies and among them additive and hybrid technologies for products manufacturing using powders of metals, their alloys and ceramics are becoming very important among product manufacturing technologies. They are an essential part not only of powder engineering but also of the manufacturing development according to the concept of Industry 4.0.

Manufacturing technologies thick-layer coatings on various substrates and manufacturing gradient materials using powders of metals, their alloys and ceramics

Purpose: The paper is a comprehensive review of the literature on manufacturing technologies thick-layer coatings on various substrates and manufacturing gradient materials using powders of metals, their alloys and ceramics. Design/methodology/approach: Extensive literature studies on manufacturing technologies thick-layer coatings on various substrates and manufacturing gradient materials using powders of metals, their alloys and ceramics have been carried out. The paper is illustrated with examples of various structure images obtained as part of research of engineering materials made by authors with powders. By using knowledge engineering methods, development perspectives of individual technologies were indicated. Findings: The manufacturing technologies thick-layer coatings on various substrates and manufacturing gradient materials using powders of metals, their alloys and ceramics as the advanced digital production (ADP) technologies are proves the highest possible potential and relatively good attractiveness, as well as their fully exploited attractiveness or substantial development opportunities in this respect. Originality/value: According to augmented holistic Industry 4.0 model, many materials processing technologies and among them manufacturing technologies thick-layer coatings on various substrates and manufacturing gradient materials using powders of metals, their alloys and ceramics are becoming very important among product manufacturing technologies. They are an essential part of powder engineering.

Overview of conventional technologies using the powders of metals, their alloys and ceramics in Industry 4.0 stage

Purpose: Among the technologies that play a crucial role in the current stage of development of Industry 4.0 conventional powder engineering technologies are of great importance. Based on a comprehensive literature review, conventional technologies using the powders of metals, their alloys and ceramics are described. Development perspectives of the most widespread among them were indicated. Design/methodology/approach: Extensive literature studies on conventional powder engineering technologies have been carried out. By using knowledge engineering methods, development perspectives of individual technologies were indicated. Findings: In addition to the presentation of conventional sintering technological methods, sintering mechanisms in solid-state and liquid phase sintering which accounts for 90% of the commercial value of sintered products are presented. Originality/value: According to augmented holistic Industry 4.0 model, many materials processing technologies and among them conventional powder engineering technologies play a key role in current industry development. For this reason, these technologies have been characterized in detail on the basis of available literature sources.

Визуальное представление знаний о клинических проявлениях лизосомальных болезней накопления

The article discusses the representation of information on lysosomal storage diseases to support the process of diagnostic decisions in childhood. This hereditary pathology refers to rare (orphan) diseases that are difficult to recognize and without timely appropriate therapy has a negative effect on the quality and expectancy of life. The article analyzes information sources for 16 nosological units from this group. Using the methods of knowledge engineering, information about the identified clinical manifestations is represented in the form of visual portraits (mind map) for diagnostics diseases and improvement qualification of pediatricians.

Поддержка принятия решений при управлении программными проектами на основе нечѐткой онтологии

The article deals with knowledge management in software projects and decision-making support of its participants. The novelty of research is justified by the need to reduce the degree of uncertainty in decision-making and is confirmed by statistics indicating a sufficiently large number of unsuccessful projects. It is proposed to organize decision-making support based on the cases analysis of previously occurring problem situations. Also, it is proposed to use knowledge engineering methods, in particular, ontological analysis of the subject area. A formation of a fuzzy ontology method is developed for decision-making support in the software development. The novelty of the mathematical model lies in the combination of various inference mechanisms when making decisions on the basis of the entire complex of knowledge about the subject area. Increasing amount of information does not allow using simple searches for quick retrieval of the necessary information. Therefore, an algorithm is proposed for generating a search query that takes into account fuzzy properties, fuzzy taxonomic and associative relations between classes of objects in ontology. The effectiveness of the proposed solutions is confirmed by an experiment on the prototype of an intelligent decision-making support system.

Концепция поддержки лазерного аддитивного производства на основе онтологического подхода

A general concept of software and information support for laser-based additive manufacturing of metal parts from powder compositions is proposed. It is based on an ontological two-level approach to the formation of knowledge about the processes of laser additive manufacturing. Under this approach, the ontology is clearly separated from the knowledge base. So subject-matter specialists can create and develop knowledge in the representation that they understand. The conceptual architecture of the decision support software for laser-based additive manufacturing processes is presented. Its information and software components are described. Information components are ontologies, databases of laserbased additive manufacturing system components, databases of materials for additive manufacturing, knowledge base and case database. The knowledge base contains formalized information on the settings of laser-based additive manufacturing modes that ensure compliance of the obtained metal parts with the requirements of the current industry-specific guidelines (regulatory documents for this type of parts). The case database contains a structured description of the protocols for using laser technological equipment for additive manufacturing of metal parts from powder compositions. Software components are editors for creating and maintaining data and knowledge bases (controlled by the corresponding ontologies), decision support system based on both, knowledge and cases, and tool for cases structuring. There are also external tools for mathematical modelling of directed energy deposition physicochemical processes. When making decisions a hybrid approach that combines knowledge engineering methods and case-based search by analogy is proposed. The specialty of the approach is the continuous knowledge base update due to its improvement by experts and due to its verification in the process of accumulating cases.

Extended Advanced Method of Clustering Big data to achieve high dimensionality

Clustering is one of the relevant knowledge engineering methods of data analysis. The clustering method will automatically directly affect the result dataset. The proposed work aims at developing an Extended Advanced Method of Clustering (EAMC) to address numerous types of issues associated to large and high dimensional dataset. The proposed Extended Advance Method of clustering will repetitively avoid computational time between each data cluster object contained by the cluster that saves execution time in term. For each iteration EAMC needs a data structure to store data that can be utilized for the next iteration. We have gained outcomes from the proposed method, which demonstrates that there is an improvement in effectiveness and pace of clustering and precision generation, which will decrease the convolution of computing over the old algorithms like SOM, HAC, and K-means. This paper includes EAMC and the investigational outcomes done using academic datasets.

Comparing machine learning to knowledge engineering for student behavior modeling: a case study in gaming the system

ABSTRACTLearning analytics research has used both knowledge engineering and machine learning methods to model student behaviors within the context of digital learning environments. In this paper, we compare these two approaches, as well as a hybrid approach combining the two types of methods. We illustrate the strengths of each approach in the context of a case study in building models able to detect when students “game the system”, a behavior in which learners abuse the environment’s support functionalities in order to succeed by guessing or copying answers. We compare the predictive performance, interpretability and generalizability of models created using each approach, doing so across multiple intelligent tutoring systems. In our case study, we show that the machine-learned model required less resources to develop, but was less interpretable and general. In contrast, the knowledge engineering approach resulted in the most interpretable and general model. Combining both approaches in a hybrid model allowed us to create a model that performed best across the three dimensions, but requiring increased resources to develop.

ONTOLOGICAL ENGINEERING FOR THE DEVELOPMENT OF THE INTELLIGENT SYSTEM FOR THREATS ANALYSIS AND RISK ASSESSMENT OF CYBERSECURITY IN ENERGY FACILITIES

The article describes the main results of applying ontological engineering in the development of the intelligent system for threats analysis and risk assessment of cybersecurity violations in energy facilities. The ontological knowledge space for the problem area of risk assessment has been built, comprising identification, analysis and evaluation of the risk of cybersecurity incidents that can cause extreme situations in the energy sector. The paper highlights the intellectual system architecture being developed and tasks for which the ontological engineering was carried out. The ontological knowledge space is represented as combining ontology subsystems, the development of which is carried out for each block of the intelligent system. The authors provide ontologies that reflect the basic concepts of cybersecurity, including current threats in the energy sector, risk classification and components of the emergency situation scenario in the energy sector. The produced ontologies allowed to integrate the concepts of the main research areas, including energy security, cybersecurity, scenario planning, and risk management. We used methods of system analysis, methodological foundations for building intelligent information systems in energy research, methods for supporting decision-making, methods of knowledge engineering, methods of semantic modeling, including ontological engineering. The novelty of the work is in the structuring of expert knowledge and the construction of the ontological knowledge space, which is used to develop an intelligent system for analyzing threats and assessing the risks to the cybersecurity of energy facilities.

A knowledge engineering framework for intelligent targeting of online video advertisements

One of the newest and most promising media employed by digital marketing is the distribution of advertising video spots through social media and popular websites. This paper addresses the problem of optimising the effectiveness of such video ads by using intelligent technologies which improve the matching between ads and targeted audience. Multidimensional data analysis methods are applied to discover relations among video ad characteristics, audience characteristics and the resulting effectiveness of the ads, thus extracting knowledge on how certain design features, such as music, scenario and humour may affect aspects of the ad effectiveness. The analysis findings are introduced in a knowledge-based tool so that an inference engine can automatically match selected ads to target audiences for which high prospects of success are predicted. The paper presents the analysis and knowledge engineering methods, as well as results of a small-scale application.

A knowledge engineering framework for intelligent targeting of online video advertisements

One of the newest and most promising media employed by digital marketing is the distribution of advertising video spots through social media and popular websites. This paper addresses the problem of optimising the effectiveness of such video ads by using intelligent technologies which improve the matching between ads and targeted audience. Multidimensional data analysis methods are applied to discover relations among video ad characteristics, audience characteristics and the resulting effectiveness of the ads, thus extracting knowledge on how certain design features, such as music, scenario and humour may affect aspects of the ad effectiveness. The analysis findings are introduced in a knowledge-based tool so that an inference engine can automatically match selected ads to target audiences for which high prospects of success are predicted. The paper presents the analysis and knowledge engineering methods, as well as results of a small-scale application.

Integrating Content Expertise and Methodological Expertise in Team‐Based Settings to Address Complex Societal Issues—A Systems Perspective on Challenges

Systems‐based approaches to societal problem‐solving entail a capacity to synthesise our knowledge and skills such that we can resolve shared problems. However, the increasing range of knowledge specialisms, scientific and engineering methods, and skill profiles at the population‐level challenges solidarity. It is also difficult to identify unifying goals and establish sustainable educational infrastructures that support transdisciplinary teamwork. Drawing upon the collective intelligence of a multidisciplinary group, this paper highlights challenges to integrating content expertise and methodological expertise in team‐based efforts to address complex social issues. Challenges identified include the following: stakeholder participation, heterogeneity and conflict, supporting effective group dynamics, defining goals, planning and resourcing, resistance and fears amongst group members, and the absence of effective teamwork methodologies. A systems model developed by the group helped to clarify interdependencies between challenges. We conclude by highlighting the need to develop societal infrastructures supporting our capacity for teamwork into the future. © 2018 John Wiley & Sons, Ltd.

Computerized and distance learning systems (the case of medical diagnostics)

The purpose of this paper is to analyze the current state and the possibility of developing computer systems of various types in education (the case of medicine). Particular emphasis is on the use of case studies that combine linguistic and multimedia components and on intellectual technologies to implement the learning process, individually controlled at different stages. The considered methods of knowledge engineering in the construction of intelligent systems form the skills of individual and teamwork. A separate aspect is the methods and means of distance learning with the use of telemedical and internet technologies in teaching and continuous professional development. Ontologies are used as a means of cognitive visual representation of knowledge. They find application in the presentation of medical knowledge that characterize pathological processes. Intellectual maps and concept maps are used as the primary analysis of logical relationships of characteristics. Role games contribute to the development of knowledge extraction for expert systems. This allows all members of the group to simulate the roles of a knowledge engineer and an expert. In addition, the teacher corrects, if necessary, this process and indicates in conclusion on the mistakes made and the unused possibilities for optimizing the dialogue between the student-cognitive scientist and the student-expert. Based on case-method it is proposed to implement examples and questions from clinical practice, including video fragments. This allows you to monitor the correctness of the actions of students during inspections and manipulations. The expert system and remote methods of work are used for the analysis of microscopic drugs under the supervision of the teacher. Building an intellectual learning system that includes cases is the basis for acquiring the skills of differential diagnosis in the process of examining a virtual patient. Telemedical technologies, using different video cameras, suggest remote teaching of not only theoretical, but also clinical subjects with examination of patients, including testing of students and video examinations. As a result of the research, the author proposed schemes of computerized and intellectualized technology for teaching medical subjects of various types (morphological, clinical, and cybernetic). This contributes to the increase of knowledge, taking into account the individual abilities of students on personal programs, forms skills to extract and analyze the information received. Videoconferencing allows you to improve your skills remotely at the place of work in the process of contact with lecturers and teachers. Specially developed approaches presuppose remote examination and diagnostics under the supervision of the teacher. In addition, demonstration of patients with various pathologies during telelectures. These approaches offer opportunities for individual mastering of knowledge based on modern methods of electronic education and intellectual technologies. Personalization of the approach to learning allows you to repeat the insufficiently mastered sections of the material. Distance learning methods will allow setting and solving tasks of continuous improvement of professional skill of medical workers on a fundamentally new level. In principle, the use of many of these approaches is possible in other areas of education.

Text mining tools for extracting information about microbial biodiversity in food

Information on food microbial diversity is scattered across millions of scientific papers. Researchers need tools to assist their bibliographic search in such large collections. Text mining and knowledge engineering methods are useful to automatically and efficiently find relevant information in Life Science. This work describes how the Alvis text mining platform has been applied to a large collection of PubMed abstracts of scientific papers in the food microbiology domain. The information targeted by our work is microorganisms, their habitats and phenotypes. Two knowledge resources, the NCBI taxonomy and the OntoBiotope ontology were used to detect this information in texts. The result of the text mining process was indexed and is presented through the AlvisIR Food on-line semantic search engine. In this paper, we also show through two illustrative examples the great potential of this new tool to assist in studies on ecological diversity and the origin of microbial presence in food.

DeepPhe: A Natural Language Processing System for Extracting Cancer Phenotypes from Clinical Records.

Precise phenotype information is needed to understand the effects of genetic and epigenetic changes on tumor behavior and responsiveness. Extraction and representation of cancer phenotypes is currently mostly performed manually, making it difficult to correlate phenotypic data to genomic data. In addition, genomic data are being produced at an increasingly faster pace, exacerbating the problem. The DeepPhe software enables automated extraction of detailed phenotype information from electronic medical records of cancer patients. The system implements advanced Natural Language Processing and knowledge engineering methods within a flexible modular architecture, and was evaluated using a manually annotated dataset of the University of Pittsburgh Medical Center breast cancer patients. The resulting platform provides critical and missing computational methods for computational phenotyping. Working in tandem with advanced analysis of high-throughput sequencing, these approaches will further accelerate the transition to precision cancer treatment. Cancer Res; 77(21); e115-8. ©2017 AACR.

Analysis of existing solutions for preventing invasion in information and telecommunication networks

The article presents an overview of the current state of cybernetic space in the context of the growth of cybercrime (large-scale cyber attacks, which have received wide publicity in Ukraine and the world). A comparative analysis of the main existing software solutions for the prevention of intrusions into information and telecommunications networks, based on public licenses. The characteristics of the main methods for detecting attacks (intrusions) are given. There is identified its main shortcomings: lack of adaptability, persistence and verification, high level of erroneous attacks, those misses of cyber attacks, weak opportunities to identify new attacks, lack of ability to determine the attack in its initial stages, practical lack of identification of the attacker and the purpose of the attack, in real time, a significant load of the system and a weak interpretation of the current situation. Prospective ways of their elimination based on the use of hybrid intelligent intrusion prevention systems based on the methods of knowledge engineering, the mathematical apparatus of fuzzy sets theory and fuzzy inference, as well as methods and technologies for data mining are proposed. Obtained results can be considered as a basis for the implementation of new mechanisms for identifying cybernetic attacks and their application during the implementation of intrusion detection systems of the next generation in order to respond to previously unknown types of cybernetic attacks. This will increase the efficiency and validity of the decisions taken by the security administrator of information and telecommunication systems and networks in real time during the detection and prevention of cybernetic attacks.

Creating the Knowledge-structured Texts in Agriculture Companies: A Cost Modeling Approach

Agriculture is one of the most regulated sectors. Council regulations, national legal acts, subsidies, nature protection, market regulations and many other directives induce the necessity to work with a lot of text documents and to manage the knowledge in them. Thus, it is worth considering the creation of specifically designed internal documents to represent knowledge explicitly in so-called knowledge-structured However, it is a costly process to create the knowledge texts. The objective of this paper is to create a model that is capable of showing what time point the successive costs of the two types of text are equal at. Linking the methods of knowledge engineering and management is carried out with the help of an integrating element, i.e. general systems theory, through system dynamics. Despite an initial investment in the knowledge texts, the results show their potential for lowering the costs in the middle- and long-term horizons.