T. Avdeenko

• Doctor of Engineering Sci., Professor
• Professor (Full) at Novosibirsk State Technical University

Solving the problem of document clustering involves two fundamental stages. The first stage is preprocessing a text document and representing it as a data table suitable for subsequent application of data analysis methods. The second stage is actually the optimization clustering algorithm, which allows to achieve best dividing the document collecti...

Developers’ qualifications and their professional development are the important aspects of IT project’s success. Software developers are interested in advancing their careers and improving their skills in order to maintain their level of professional value both for organizations and for the labor market. However, the evaluation of developers' quali...

In present paper we investigate an approach to intelligent support of the software white box testing process based on evolutionary paradigm. As a part of this approach, we solve the urgent problem of generating the optimal set of test data that provides maximum statement coverage of the code when it is used in the testing process. Earlier approache...

The paper explores the application of feature selection techniques for the brain activity classifying patterns task. The study aim is to compare the machine learning algorithms results depending on the chosen feature selection technique. As an example for analysis, the task of classifying of open-eyes and closed-eyes resting states according to EEG...

The effectiveness of the correlation-based method (CFS) for feature selection based on electroencephalogram (EEG) data of the resting state for the purpose of intelligence assessment is investigated. A modification of the CFS is proposed, which makes it possible to vary the cardinality of a subset of selected features using a hyperparameter. A prac...

Modern universities developing a digital environment rely on a student-centered approach, relevant pedagogical and didactic practices taking into account learners' characteristics and adapting it to the educational process. Personalization of the educational environment should improve the quality of the educational process raising it to a new level...

The paper proposes an approach to extracting ontology concepts from the results of automatic processing the software requirements written in natural Russian-language. Relevance of developing an approach to automating the process of extraction of the ontology concepts from the requirements written in natural language is due to the necessity to maint...

The paper examines the applicability of classification algorithms to identify brain activity patterns according to EEG data using the example of determining the state of eyes. In this area of research, the following main subareas can be distinguished: search for a features’ set that can be extracted from EEG data using a minimum number of electrode...

In present paper we solve an urgent problem of generating the optimal set of test data that provides maximum statement coverage of the code when it is used in the software white box testing process. Formulation of a fitness function containing two terms, and, accordingly, two versions for implementing genetic algorithm (GA) have been proposed. The...

The decisive factor for the successful work of modern IT organizations is the professional qualities of the personnel and the system for its development. Staff training for software development organizations is of particular importance due to the fact that activities in this field make high demands on the level of qualifications of employees, their...

In the present paper, we investigate how the general intelligence quotient (IQ) and its subtests changed for students from Russian University from 1991 to 2013. This study of the effect of such factors as gender, department, and year on the IQ response is carried out using the ANOVA model. Given the unevenness of the initial sample by years and dep...

In present paper we consider ontology-driven approach applied to neurocognitive science. At the beginning, a brief overview of the works revealing the prospects and possibilities of constructing ontological models in this field of knowledge is given. Based on the conducted analysis we have concluded that the scientific community states the urgency...

In present paper we investigate an approach to intelligent support of the software white box testing process based on evolutionary paradigm. As part of this approach we solve the urgent problem of finding the optimal set of test data that provides maximum coverage of the code when it is used in the testing process. Traditionally, to solve this prob...

In the present paper, we investigate an approach to intelligent support of the software white-box testing process based on an evolutionary paradigm. As a part of this approach, we solve the urgent problem of automated generation of the optimal set of test data that provides maximum statement coverage of the code when it is used in the testing proce...

Ontology-based knowledge representation techniques are used today as well-proven tools supporting decision making. The paper proposes OWL ontology which accumulates knowledge about cognitive functions and methods for assessing cognitive functions. A brief overview of using the ontologies capabilities for representation of knowledge about cognitive...

The paper presents an approach to the agile requirements engineering based on the OWL ontologies. A brief overview of the benefits of an ontology-based approach to requirements engineering is given. Attention is focused on agile engineering requirements process. The proposed approach uses three ontologies. The first ontology is used to represent kn...

In present paper we propose an approach to the dynamic taxi service pricing based on data mining from the large database of cases accumulated in the company. We believe that historical data on decisions made by experienced managers in the past contain valuable information on the most subtle parameters that influence decision making, but cannot be t...

In the present paper we propose an approach to support the process of requirements management in the agile environment. The approach is based on the combination of intelligent tools such as text parsing, domain ontology and ontology-guidance. The text parsing method is used to extract facts from the requirements document using the ontology guidance...

Stable clustering is a very desirable property for the dynamical knowledge base consisting of cases indexed through the domain ontology both because the cases are constantly added to the knowledge base, and the ontology structure can be revised from time to time. An approach has been developed for the stable hierarchical clustering of cases based o...

The paper proposes an ontology-based approach to support for requirements traceability in Agile development. The task of supporting the requirements traceability in a software development project is considered as a part of requirements engineering process. A brief overview of the benefits of requirements traceability usage is given. The expediency...

The paper presents an approach to organizing the detection of conflicts between requirements based on an ontological model and a system of production rules. Requirements in the form of plain text are converted to instances of OWL ontologies for analysis. There are three basic elements “subject”, “action” and “object” in the requirements. These elem...

In present paper we propose an approach to automatic generation of test data set based on application of the genetic algorithm. We consider original procedure for computation of the weights of code operations used to formulate the fitness function being the sum of these weights. Terminal objective and result of fitness function selection is maximiz...

In present paper we consider a combination of CBR with the Domain Ontology and Data Mining. The proposed approach to integration CBR with the Ontology, as a result, gives a numerical matrix that characterize the semantic relationship of cases with the domain concepts. Then it is possible to apply methods of cluster analysis, classification and regr...

Decision trees are widely used in the field of machine learning and artificial intelligence. Such popularity is due to the fact that with the help of decision trees graphic models, text rules can be built and they are easily understood by the final user. Because of the inaccuracy of observations, uncertainties, the data, collected in the environmen...

The state of art and the progress in application of semantic technologies in the field of scientific and research activity have been analyzed. Even elementary empirical comparison has shown that the semantic search engines are superior in all respects to conventional search technologies. However, semantic information technologies are insufficiently...

The article proposes an approach to the improvement of transfer, storage and retrieval of knowledge in the field of IT consultation. The approach is based on the integration of case-based reasoning and the ontology. The description of the main concepts of the ontology has been presented. A class Precedent structure is proposed that allows to enter...

Decision trees are widely used in the field of machine learning and artificial intelligence. Such popularity is due to the fact that with the help of decision trees graphic models, text rules can be built and they are easily understood by the final user. Because of the inaccuracy of observations, uncertainties, the data, collected in the environmen...

The paper presents an approach to the Support of the requirements engineering process in the field of software development process by applying OWL ontology. A brief overview of the capabilities of using ontologies for intellectual support of the process of requirements engineering is given. The main features of requirements engineering for Scrum pr...

The paper suggests a new approach to the selection of correlated concepts for the ontology. It is based on the principal component analysis, but, unlike the standard approach, not Pearson correlation coefficients, but other correlation measures are used. This is due to the fact that the selection of concepts is based on data on the semantic associa...

Software testing has always been a time-consuming process, without obvious results but not less important than any other stage of software engineering. One of the major issues of testing is the development of initial test data that allow complete evaluate the program code and find most important parts of the program. Intelligent technologies, in pa...

In the present paper we present an approach to facilitation of decision-making in the decision support systems (DSS). The approach is based on the transformation of knowledge from the implicit presentation in the form of cases stored in the case bases to the explicit presentation in the form of rules stored in the rule bases. The efficient method o...

The article considers an approach that facilitates the improvement of the transfer, storage and retrieval of knowledge in the field of user support in IT departments. The proposed approach is based on the integration of the case-based reasoning approach and the ontology. The description of the main concepts of ontology is presented. A Precedent cla...

In present paper we consider scheduling problem for the arrangement of oil and gas field. The primary challenge determining associated problems in this area is computation of the optimal schedules of wells (well bushes) construction using different drilling equipment. We adapt unrelated parallel machine scheduling with release dates to solve the pr...

We consider an approach to automatic knowledge acquisition through machine learning based on integration of two basic paradigms of reasoning – case-based and rule-based reasoning. Case-based reasoning allows to use high-performance database technology for storing and accumulating cases, while rule-based reasoning is the most developed technology fo...

In present paper we propose an approach to support knowledge transformation in the knowledge-based systems facilitating transition of knowledge from the tacit form to the explicit one and vice versa. The approach is based on the dynamic integration of case-based and rule-based knowledge representation model with use of artificial intelligence metho...

In the present paper, we propose an approach to facilitation of decision-making in the field of IT-consulting. The approach is based on knowledge representation in the form of cases containing past history about decision making. We also proposed an ontology to store the cases as instances of classes. Classification of cases in the ontology is execu...

In this paper we propose approaches to optimal scheduling of unrelated parallel machines with release dates. One approach is based on the scheme of dynamic programming modified with adaptive narrowing of search domain ensuring its computational effectiveness. We discussed complexity of the exact schedules synthesis and compared it with approximate,...

The paper describes an information system development project for the Russian Ministry of Emergency Situations (MES, whose international operations body is known as EMERCOM), which was attended by the representatives of both the IT industry and the academia. Besides the general description of the system, we put forward OLAP and Data Mining-based ap...

In present paper we consider the advantages and disadvantages of case-based reasoning (CBR) approach for knowledge representation of the application domain. One of the CBR shortcomings is the insufficient speed of real-time retrieval of cases, as well as the insufficient relevance of the retrieved cases to the current situation. To solve these prob...

Many Web-site owners turn to Web Studios for help in solving the problems of their web projects’ support, mostly on a subscriber basis. If the Web Studio is professionally engaged in technical support of web projects, then it can have dozens and hundreds of clients, who create hundreds of job requests per month. However, Web Studio’s human resource...

In this paper we propose approaches to optimal scheduling of unrelated parallel machines with release dates. One approach is based on the scheme of dynamic programming modified with adaptive narrowing of search domain ensuring its computational effectiveness. We discussed complexity of the exact schedules synthesis and compared it with approximate,...

In present paper we propose an approach to support of knowledge spiral in the knowledge management systems in organizations facilitating transition of knowledge from implicit form to explicit one and vice versa. The approach is based on the transformation of knowledge from one knowledge representation model to another on the basis of artificial int...

The paper provides reflections on feasibility of online data mining (ODM) and its employment in decision-making and control. Besides reviewing existing works in different domains of Data Mining, we also report experiences from ongoing project dedicated to monitoring labour market with the aid of dedicated intelligent information system. Benefits of...

The paper researches novel approach towards estimating relevance between cases in case-based reasoning system. Fuzzy linguistic rules are used as a tool for representing knowledge about cases relevance. The results suggest that the proposed hybrid system employing case model and fuzzy logic can work with even a small number of cases, while yielding...

In present paper the approach to testing generically both local and global identifiability of linear large scale systems based on rank and order conditions is further developed. This method was initially proposed for the most general case of parametrization when estimated parameters are the elements of system matrices with linear constraints on the...

The HCI has understandably become user-centric, but if we are to consider human operator and computer device as even components of a human-computer system and seek to maximize its overall efficacy with AI methods, we would need to optimize information flows between the two. In the paper, we would like to call to the discussion on defining and measu...

The paper presents a knowledge-based approach to requirements engineering process. We propose an ontology as a tool for requirements specification verification and validation. Requirements types are the classes of the ontology. Requirements statements are the instances. A special structure of classes, the Protégé tool 'DL Query', and relations impl...

This study is an exploration in measuring quantities of information transferred in the course of interaction in human-machine systems, which deemed necessary as fundamental support for interface design. We put forwards several possible measures found in previous research works, including the infamous Hick's law, and validate their applicability wit...

We propose to develop novel approaches in the field of computer-aided web interface design, which is based on Kansei (" emotional ") Engineering that already has recognized results, e.g. in auto-manufacturing industry. The idea is to establish formal relations between key aspects of software requirements and design resolutions, based in particular...

The paper describes an approach to form a harmonized model of requirements for a specific software development project. Such a model is intended to resolve the contradictions caused by different understanding of the "program requirements" definition, as well as to coordinate the various models of requirements types that underlie certain types of do...

The paper describes an ongoing project dedicated to the development of the intelligent information system for collecting, processing, and analyzing unstructured web data to be used in decision-making, which is currently applied for labor market management. While technological issues associated with web scrapping are more or less resolved, and data...

In this paper we describe some notable issues and experiences from the development of the information system for the Russian Ministry of Emergency Situations (MES, whose international operations body is known as EMERCOM), where practical and academic perspectives and contributions were merged. One of the main challenges was integrating data from ge...

The present report introduces a novel module of the QuBiLS-MIDAS software for the distributed computation of the 3D Multi-Linear algebraic molecular indices. The main motivation for developing this module is to deal with the computational complexity experienced during the calculation of the descriptors over large datasets. To accomplish this task,...

The paper describes novel approach to constructing decision-making support system based on multi-dimensional model of information space for the process of interaction between higher education system and regional labor market. The particular features of the proposed approach are: accumulation of data with the use of web-scrapping intelligent informa...

The paper is dedicated to the application of web data extraction technologies to facilitate decision support. As the Internet becomes a scrapable representation of the real world, the need to utilize online data arises in many specialized fields that search engines generally won't cover. The considerations on feasibility of employing automated web...

The paper discusses the drawbacks associated with modern web developers' shortage of expertise in working with both unstructured and structured data. While data structures design is generally unnecessary in smaller, highly dynamic and visual presentation-oriented IT projects, it becomes crucial in complex enterprise intranet systems development. Cu...

The approach to solving the tasks of production planning and scheduling has been proposed. Mathematical model for synthesis of optimal schedules for multi-stage parallel-serial service systems has been presented. Decomposition of the initial system into separate parallel service systems has been executed.

The paper describes an application of indexing—the technology currently widely used for processing and comparing textual information—to multi-dimensional entities of knowledge domains. We propose a model for building a frame-based ontology, which contains a domain conceptual model as well as a controlled vocabulary of "base terms" used for indexing...

The paper suggests the development of a knowledge-based system (KBS) to support web interface design via organizing somehow dispersed HCI-related knowledge and providing it on a context basis. The frame-based ontology was created with Protégé-Frames editor and CLIPS inference engine to serve as the core for the KBS, producing web design guidelines...

Design guidelines, which come from the extensive body of knowledge currently formed in HCI and usability engineering domains, remain poorly integrated. Guidelines and design patterns from various sources may contradict or duplicate each other, lack links to origins and justification, as well as contextual associations to concrete problems. The pape...

The paper suggests a model for selection tasks that are widespread in modern interaction on the WWW, as well as the means to evaluate performance as human processor throughput. Selection tasks are considered the combination of choice and movement stages, which are traditionally modelled with Hick-Hyman and Fitts' laws respectively. However, as the...

В последнее время, по мере удешевления компьютерной техники и доступа к сети Интернет, фи-нансовый фактор всё менее является барьером против использования информационных технологий (ИТ), во всяком случае, для жителей крупных и средних городов. На первый план выходит проблема сложности взаимодействия с компьютерами, вызываемая, не в последнюю очеред...

Предложена онтология, основанная на фреймовой модели в рамках применения методов из сферы искусственного интеллекта для представления знаний в области проектирования человеко-компьютерного взаимодействия, которая может применяться как в интеллектуальной системе, поддерживающей процесс создания средств электронной коммерции, так и в целях обучения....

The paper describes the work in progress towards the development of knowledge-based system (KBS) to support developers in ensuring the quality of software requirements. Ambiguity, contradictoriness, incompleteness, poor traceability and adjustability were identified as currently most severe problems with requirements, as well as certain ignorance t...

The article proposes an original approach to solving multi-criteria decision making based on the methodology of artificial intelligence. Multiagent approach is used to create a friendly user interface with a database and knowledgebase. Special feature of the fuzzy model is using the methodology of time series smoothing to obtain an informative set...

The paper suggests an application of knowledge engineering methods to support web design-related decisions and enhance usability for e-commerce software products. A prototype of a frame-based ontology was designed with Protégé editor to integrate somehow scattered and discrepant knowledge in the fields of HCI, usability engineering, web design, etc...

The paper describes the application of artificial intelligence methods to create a knowledge-based system supporting HCI-related activities in e-commerce software development process. A frame-based ontology was built to represent various levels of HCI knowledge, such as models, principles, and guidelines , and deliver them depending on a concrete i...

The number of older adults is rapidly growing worldwide and online, and they are identified as a distinct group in HCI. An experiment was undertaken with 28 participants of different ages, studying the degree of applicability of Fitts and Hicks laws. Seniors predictable slower movement performance was supplemented by higher accuracy that was howeve...

We take a new approach to studying the structural global identifiability of linear dynamic models in the state space using the concept of separators of the parameter space. We offer some criteria for the truth of separators which are based on specially constructed matrices, thereby avoiding the laborious analytic solution of a systemof nonlinear al...

Investigation of structural identifiability of even linear dynamical models requires complicated algebraic manipulations with use of computer algebra methods. In present work very efficient approach to testing both local and global identifiability of system parameters is offered which does not require too complex algebraic computations and therefor...

In practice we often have several model structures-candidates to describe the same phenomenon. In that case the task of selecting the best model structure (discrimination between the models) arises. But if the model structures are indistinguishable by input-output behavior, any attempt of discriminating between them is meaningless. Investigation of...

The rank and order conditions previously developed for analysis of the structural local identifiability of models with unknown parameters of the state matrix are extended to a broader class of models whose observation and control matrices may contain unknown parameters. The approach proposed is shown to be especially effective for models with a sta...

The paper presents generalization of new approach to qualitative testing of structural identifiability of state space models. The approach compares favourably with numerous methods proposed for studying identifiability because it does not involve unfeasible symbolic computations and thus allows to test both local and global identifiability of large...

The problem of distinguishability of state space model structures from input-output observations of the system is considered. We prove the proposition allowing to significantly simplify the system of algebraic equations solved in the symbolic form and, hence, to reduce the amount of required analytical computations. Two examples are given to illust...

First Page of the Article

The structural identification of linear dynamical models is considered. The necessary and sufficient conditions of identifiability are obtained (rank and order conditions). The procedure of generating the rank matrix is developed. An illustrative example of application of the method is given