+7 (495) 987 43 74 ext. 3304
Join us -              
Рус   |   Eng

Authors

Borisov Vadim V.

Degree
Professor, department of Computer Engineering, the Branch of National Research University MPEI in Smolensk
E-mail
vbor67@mail.ru
Location
Smolensk, Russia
Articles

Rubrication of text documents based on fuzzy difference relations

One of the key areas of informatization of public authorities is to develop and implement the systems of automated processing the electronic appeals (applications, complaints, suggestions) of individuals and legal entities that arrive on official websites and portals of government. The rubrication plays an important role in solving this problem. It consists in the appeals’ distribution according to thematic rubrics determining the directions of the activity of departments carrying out processing and preparation of the corresponding response. The results of the analysis of the specific features of such text messages (small size, markup lack, the errors’ presence, thesaurus unsteadiness, etc.) confirmed the impossibility of using traditional approaches to rubrication and justified the feasibility of using data mining methods. The article proposes a new approach to the analysis and rubrication of electronic unstructured text documents arrived on official websites and portals of public authorities. It involves the formation of a tree-like structure of the rubric field, based on fuzzy relationships of differences between the syntactic characteristics of documents. The analysis is based on determining the fuzzy correspondence of these documents by their syntactic characteristics with the values of the clusters’ centers. It is carried out sequentially from the root to the leaves of the constructed fuzzy decision tree. The proposed rubrication method is programmatically implemented and tested in the automated processing and analysis of appeals (applications, complaints and suggestions) of citizens entering the Administration of Smolensk Region. This made it possible to ensure prompt and high-quality updating of rubrics and document analysis under conditions of non-stationary composition of the thesaurus and the importance of rubric words. Read more...

Fuzzy cognitive modeling of heterogeneous electromechanical systems

The article presents a method of fuzzy cognitive modeling for heterogeneous electromechanical systems (HEMSs) in the management of innovative design solutions. During the operation of the HEMSs, as a result of their operational aging, the properties of the windings parametric matrices and the HEMSs vector space properties change. Periodic testing of the HEMSs vector space allows obtaining reliable information about the current technical condition of the HEMSs, about its changes during operation and about the risks of operating capability loss. At the same time (I) the presence of proportional changes in signals during sequential testing indicates the homogeneous operational aging of the HEMSs and its rate; (II) a disproportionate change in one of the signals indicates the damage or the development of a heterogeneous aging process; (III) a change in signals with a change in the angular position of the rotor indicates worn bearings or damage of the HEMSs rotor. The article presents the HEMSs model, describes the method for the topological research of the vector space and the method for forming the diagnostic matrices. The deviations of their elements are fuzzy due to the uncertainty of the load, influencing environmental factors and unstable supply voltages. Therefore, for predictive estimation of the HEMSs state, it is proposed to use fuzzy relational cognitive models that allow implementing a completely fuzzy approach to modeling problem situations in these systems. The presented data confirm the growth of the HEMSs heterogeneity under conditions of uncertainty of external influences. The proposed method for predictive estimation of the HEMSs state, based on fuzzy relational cognitive models, provides resistance to an increase in the uncertainty of the estimation results for various models of system dynamics due to a reasonable set of fuzzy vector-matrix operations. Read more...

Modeling of educational processes based on neuro-fuzzy temporal Petri nets

The article is devoted to the implementation of a method for modeling processes in complex educational systems based on the proposed variety of neuro-fuzzy temporal Petri nets. The article considers educational systems of the level of higher educational institutions, which, of course, belong to the class of complex systems. The need for a method, models and modeling tools is dictated by the fact that modern educational processes require constant modernization, due to the constantly growing volumes of information, changes in legislation, stricter requirements for specialists, rapid development of technologies, constant discoveries in various fields, as well as the influence of external factors. Requirements for the tools for modeling processes in complex systems are formulated, the use of Petri nets as the basis of such models is substantiated. The existing educational processes are considered on the example of the cycle of training in the master's program of the Belarusian-Russian University. The model of educational and information-analytical learning processes in the master's program based on the neuro-fuzzy temporal Petri net is presented. The proposed method allows to increase the flexibility of the choice of individual trajectories of training in the master's program, the effectiveness of elective disciplines and to make the transition to an integrated approach in the preparation of undergraduates. The proposed method can also be used as a basis for monitoring the state and control of information and analytical processes in educational systems. An approach to the construction of software-instrumental environment for the design and modification of information-analytical processes is described, aimed, among other things, at bridging the semantic gap between experts, architects and developers of information-analytical processes. A subsystem for the formation of a neuro-fuzzy temporal model of processes within the framework of a software-instrumental environment is considered. Read more...

Fuzzy relational cognitive temporal models for analyzing and state prediction of complex technical systems

The effectiveness of fuzzy cognitive modeling methods for analyzing and predicting the state of complex technical systems (STS) is justified by the following reasons: significant interdependence, non-linear nature and incompleteness of information about the mutual influence of the analyzed parameters of the CTS; a variety of effects of internal and external factors on the CTS; complexity and cost of conducting experimental studies during the operation of these systems. The main limitations of fuzzy cognitive models for modeling STS dynamics are: the complexity of taking into account the mutual influence of parameters with their different time lags relative to each other; the need for their constant operational adjustment and training of component models for all parameters during the operation of the CTS. In this paper, Fuzzy Relational Cognitive Temporal Models (FRCTM) are developed. These models combine the advantages of various types of fuzzy cognitive models, and at the same time neutralize the main limitations of the analysis and prediction of the state of the CTS, which are inherent in the well- known fuzzy cognitive models. The paper also proposes models of system dynamics that take into account the specifics of the FRCTM. We have also developed an approach and implemented a method for calculating fuzzy dependencies in vector-matrix form for dynamic modeling of the CTS. The proposed method makes it possible to solve the problems of increasing the uncertainty of the results and the output of fuzzy values of the FRCTM concepts beyond the ranges of the base sets due to the execution of mass iterative computations. An example of modeling heterogeneous electromechanical systems based on FRCTM is given. The results obtained are the basis for solving a whole range of tasks of analysis, predictive evaluation, modeling of different scenarios of the functioning and development of heterogeneous electromechanical systems for various system factors, operating modes and external conditions. Read more...

Modeling and design of information-analytical production processes based on neuro-fuzzy temporal Petri nets

The article is devoted to the issues of modeling and designing information-analytical processes corresponding to the production and technological processes at the enterprise. In the modern conditions of the functioning of the market, the enterprise faces important tasks of embedding in global supply chains, responding to an increase in the need for personalized products and, most importantly, reducing costs and improving product quality. In addition to solving these problems, the enterprise has to deal with such problems as: overproduction, waiting and wasted time, defects and marriage. Despite the fact that economic efficiency is put at the forefront, in order to ensure the sustainable development of an enterprise, it is necessary the criteria of environmental friendliness, accident-free operation and social efficiency. Enterprises, whose competitive advantages are flexibility and response speed to market needs, require tools for the operational management of production and technological processes. For effective functioning within a complex system, planning and implementation of production and technological processes must be supported by appropriate information-analytical processes that provide the collection and analysis of information, as well as modeling and making control decisions for the production and technological process. Production management is carried out in the form of strategic, tactical and operational planning, which puts forward additional requirements for modeling tools and management decision support. A variety of neuro-fuzzy Petri nets with temporal fuzzy neurons is proposed. An example of building a model of the production process and the corresponding information-analytical processes is considered. The developed specialized software for modeling production and technological processes and the implementation of information- analytical processes, including modules for forming an ontological model of a complex system and processes, obtaining data, a neural network supervisor, building a model of a production- technological process and corresponding information-analytical processes using the mechanism constructors based on neuro-fuzzy temporal Petri nets is considered. Read more...

Rubrication of text documents based on fuzzy difference relations

One of the key areas of informatization of public authorities is to develop and implement the systems of automated processing the electronic appeals (applications, complaints, suggestions) of individuals and legal entities that arrive on official websites and portals of government. The rubrication plays an important role in solving this problem. It consists in the appeals’ distribution according to thematic rubrics determining the directions of the activity of departments carrying out processing and preparation of the corresponding response. The results of the analysis of the specific features of such text messages (small size, markup lack, the errors’ presence, thesaurus unsteadiness, etc.) confirmed the impossibility of using traditional approaches to rubrication and justified the feasibility of using data mining methods. The article proposes a new approach to the analysis and rubrication of electronic unstructured text documents arrived on official websites and portals of public authorities. It involves the formation of a tree-like structure of the rubric field, based on fuzzy relationships of differences between the syntactic characteristics of documents. The analysis is based on determining the fuzzy correspondence of these documents by their syntactic characteristics with the values of the clusters’ centers. It is carried out sequentially from the root to the leaves of the constructed fuzzy decision tree. The proposed rubrication method is programmatically implemented and tested in the automated processing and analysis of appeals (applications, complaints and suggestions) of citizens entering the Administration of Smolensk Region. This made it possible to ensure prompt and high-quality updating of rubrics and document analysis under conditions of non-stationary composition of the thesaurus and the importance of rubric words. Read more...

Solving the inverse kinematics problem for sequential robot manipulators based on fuzzy numerical methods

Nowadays the introduction of robotic systems is one of the most common forms of the technological operations automation in various spheres of human activity. Among the robotic systems a special place is occupied by sequential multi-link robotic manipulators (SRM). SRM have become widespread due to relatively small dimensions and high maneuverability, which makes their use indispensable to solve various tasks. In practice, the effectiveness of the functioning of the SRM can be influenced by various types of external environment fuzzy factors. Among the external factors there is a group affecting the ability to determine the exact target position. Such factors often affect technical vision systems. This problem is especially relevant for special purpose mobile robots operating in aggressive environmental conditions. A situation similar to the described one also occurs when a medical robot manipulator is used for minimally invasive surgery, when the role of the control and monitoring system is assumed by an operator. In this regard, the organization of effective control taking into account influence of the external fuzzy factors, that prevent the correct recognition of the target position of the SRM instrument, is an urgent problem. The authors consider the solution of the inverse kinematics problem for SRM based on the use of fuzzy numerical methods, taking into account the possible occurrence of singular configurations in the process of solving. Read more...