
Main / Aleksei Sergeevich Katasev
Author: "Aleksei Sergeevich Katasev"
Aleksei Sergeevich Katasev, Kazan National Research Technical University named after A.N. TupolevKAI, Candidate of Science in Engineering; graduated from the Faculty of Physics and Mathematics of the Elabuga State Pedagogical Institute; Associate Professor of the Information Security Systems Department of the Kazan National Research Technical University named after A.N. TupolevKAI; an author of scientific works in the field of mathematical modeling, data analysis and development of intelligent decision support systems. [email: Kat_726@mail.ru]A. Katasev


Neurofuzzy Model and Software Complex for Automation of Forming Fuzzy Rules for Objects State Assessing
This article deals with the task of objects state assessing in uncertainty. To solve it, the need to use of fuzzy knowledge bases and fuzzy inference algorithms as part of fuzzy expert systems is being actualized. As a tool for a knowledge base formation, a neurofuzzy model is proposed. The proposed type of fuzzy rules and the logical inference algorithm on the rules for object state assessing are described. A structure of a fuzzy neural network consisting of six layers is proposed, each of which implements a corresponding stage of the logical inference algorithm. As a result of learning a fuzzy neural network, a system of fuzzy rules is formed, which make up the knowledge base for object state assessing. On the basis of the proposed neurofuzzy model, a software complex was implemented for automating the processes of forming fuzzy rules. The main components of the software complex are the knowledge base generation module and the fuzzy inference module. As an approbation of the neurofuzzy model, the formation of fuzzy rules for water lines state assessing at the pumping stations in reservoir pressure maintenance systems has been carried out. The results of the testing confirmed the high efficiency of the neurofuzzy model and the possibility of its practical use for the formation of fuzzy rules in various subject areas. Neurofuzzy model, fuzzy neural network, fuzzy rules formation, knowledge base, object state assessment, decisionmaking support.



Sections: Information systems
Subjects: Information systems, Artificial intelligence. 
Nafis Gishkullovich Talipov, Kazan National Research Technical University named after A.N. TupolevKAI, Candidate of Science in Engineering; graduated from the Pacific Higher Naval School named after S.O. Makarov; Associate Professor of the Information Security Systems Department of the Kazan National Research Technical University named after A.N. TupolevKAI (KNRTUKAI); an author of scientific works in the field of mathematical modeling, decision support systems, fuzzy methods of rational choice of alternatives. [email: talipovng@gmail.com]N. Talipov,
Aleksei Sergeevich Katasev, Kazan National Research Technical University named after A.N. TupolevKAI, Candidate of Science in Engineering; graduated from the Faculty of Physics and Mathematics of Elabuga State Pedagogical Institute; Associate Professor of the Information Security Systems Department of the KNRTUKAI; an author of scientific works in the field of mathematical modeling, data mining, decision support systems. [email: Kat_726@mail.ru]A. Katasev,
Sofia Sergeevna Kildeeva, Kazan National Research Technical University named after A.N. TupolevKAI, graduated from the Institute of Computer Technologies and Information Security of the KNRTUKAI; Master Student of the Information Security Systems Department of the KNRTUKAI; an author of scientific works in the field of mathematical modeling. [email: Sofipi@mail.ru]S. Kildeeva,
Dina Vladimirovna Kataseva, Kazan National Research Technical University named after A.N. TupolevKAI, graduated from the Faculty of Enterprise Economics of the Kazan State Financial and Economic Institute; Senior Lecturer of the Information Security Systems Department of the KNRTUKAI; an author of scientific works in the field of mathematical modeling, analysis and forecasting of time series. [email: 415pisarevadv@mail.ru]D. Kataseva


Automation of Tasks Distribution Process in Electronic Document Management Systems Based on Fuzzyproduction Model
This article solves the problem of tasks distribution to performers in electronic document management systems. A fuzzy product model is being developed to solve this problem. Its construction required fuzzyproduct rules type choice, their construction methodology development, an output on rules algorithm, as well as methods for membership functions constructing and fuzzy rules reliability determining. On the basis of the proposed methods and algorithms, a software package was developed, that supports decisionmaking in task performer’s choice. The software package structure, the developed model adequacy experiments results, as well as its practical use results are presented. Electronic document management, task distribution, fuzzy product model, software complex, decision making.



Sections: Information systems
Subjects: Information systems. 
Amir Muratovich Akhmetvaleev, Kazan National Research Technical University named after A.N. TupolevKAI, Postgraduate Student of Kazan National Research Technical University named after A.N. TupolevKAI; graduated from the Faculty of Technical Cybernetics and Informatics of the Kazan State Technical University named after A.N. TupolevKAI; an author of scientific works in the field of mathematical modelling, data analysis and machine learning methods. [email: amir.akhmetvaleev@gmail.com]A. Akhmetvaleev,
Aleksei Sergeevich Katasev, Kazan National Research Technical University named after A.N. TupolevKAI, Candidate of Engineering; graduated from the Faculty of Physics and Mathematics of Elabuga State Pedagogical Institute; Associate Professor of the Information Security Systems Department of Kazan National Research Technical University named after A.N. TupolevKAI; an author of scientific works in the field of mathematical modelling, data analysis and development of intelligent decision support systems. [email: Kat_726@mail.ru]A. Katasev


Instrumental Software Complex for Automation to Determine the Functional State of Intoxication of a Person
This article actualizes the need to determine the functional state of a person. Its decision is based on the application of the pupillometry method, which allows to determine the state of a person by his pupillary reaction to light changes. In order to automate the processes of determining the functional state of a person, an instrumental program complex is developed, based on the use of the neural network model. Its structure, composition and characteristics of components are described. The functioning of the program complex is considered on the example of the modules of neural network model construction, estimation of its accuracy on the basis of bootstrapping method, structural optimization of the model, and determining the functional state of a person. A number of researches and experiments were conducted on the basis of the program complex. The results of the influence of the number of stages of bootstrapping on the accuracy of the neural network model, the results of reduction of neural networks, the comparison of the accuracy of the model with the accuracy of other classification methods are presented. The results of the research showed the effectiveness of the neural network model and the possibility of its practical use to determine the functional state of the person in various subject areas. Human functional state, papillomometry, neural network model, genetic algorithm, bootstrapping.



Sections: Artificial intelligence
Subjects: Artificial intelligence, Information systems. 
Amir Muratovich Akhmetvaleev, Kazan National Research Technical University named after A.N. Tupolev, Akhmetvaleev, graduated from the Faculty of Technical Cybernetics and Informatics of Kazan National Research Technical University named after A.N. Tupolev; Postgraduate student of Kazan National Research Technical University named after A.N. Tupolev; an author of scientific works in the field of mathematical modelling, data analysis and machine learning methods. [email: amir.akhmetvaleev@gmail.com]A. Akhmetvaleev, Aleksei Sergeevich Katasev, Kazan National Research Technical University named after A.N. Tupolev, Candidate of Engineering; graduated from the Faculty of Physics and Mathematics of Elabuga State Pedagogical Institute; Associate Professor at the Department of Information Security Systems of Kazan National Research Technical University named after A.N. Tupolev; an author of scientific works in the field of mathematical modelling, data analysis and development of intelligent decision support systems. [email: Kat_726@mail.ru]A. Katasev


Neuro Network Model and Software Package for Human Functional State Determining
The article considers the problem of determining the functional state of intoxication of a person. For its solution, the authors propose a method based on the analysis of data pupillograms  time series characterizing the dynamics of changing the size of the pupils of the person on lightpulse exposure. As a tool for data mining and model building in order to determine the functional state of the person the authors propose to use the mathematical apparatus of artificial neural network  single layer perceptron. The original neural network model is proposed, and its adequacy is evaluated. In order to improve the efficiency of its practical use, a method of reduction of a neural network structure based on genetic algorithm is being developed. The proposed method is a twostage genetic optimization that allows to determine the significant input features for a neural network on a given input feature space in order to optimize the structure of neurons in the hidden layer. The results of the experiments on the basis of the developed program complex have shown high efficiency of determination of the person functional state based on the reduced neural network model. The model can be effectively used in intelligent surveillance systems in public safety systems, as well as in medical diagnostics as a tool for contactless determination of the functional state of intoxication of a person. Neural network model, determination of the functional state, genetic algorithm, pupillometry, evaluation of data quality, data cleaning.



Sections: Artificial intelligence
Subjects: Artificial intelligence, Information systems. 
