#### Name

Lutsenko Yevgeniy Veniaminovich

#### Scholastic degree

•

#### Academic rank

professor

#### Honorary rank

—

#### Organization, job position

Kuban State Agrarian University

#### Web site url

## Articles count: 276

The aim of this work is to study the strength and the direction of the influence of morphological and biochemical properties of tomatoes on the quantitative, qualitative, financial and economic results of their cultivation and the degree of determinism of these results. Achieving this goal is of great scientific and practical interest for scientists, breeders and vegetable growers-practitioners. This allows breeders to obtain new high-performance varieties of tomato hybrids, and farms to choose hybrids, the cultivation of which is most effective from a financial and economic point of view. To achieve this goal, we use automated system-cognitive analysis (ASC-analysis) and its software tool which is the intelligent system called "Eidos". A numerical example based on real data on tomato hybrids has been considered in detail

Antibacterial chemotherapeutic drugs, which include antibiotics and synthetic antimicrobial agents, are widely used in veterinary medicine for the prevention and treatment of diseases caused by microorganisms. Antibacterial agents can be classified by type of action and chemical structure. It is also known that when several drugs are used in combination with each other, they interact within the body with each other, which can lead to strengthening or weakening of their action. For these reasons, it is of scientific and practical interest to develop a classification of antibiotics by their characteristics and principle of action (task 1), as well as by mutual compatibility (task 2). The article solves these problems using a new method of agglomerative cognitive clustering, implemented in automated system-cognitive analysis (ASK-analysis). This method of clustering has a number of advantages over the known traditional methods of clustering. These advantages allow us to obtain clustering results that are understandable to specialists and amenable to meaningful interpretation, which are well consistent with the experts ' assessments, their experience and intuitive expectations, which is often a problem for classical clustering methods. The article provides detailed numerical examples of solving two problems. The universal automated system called "Eidos", which is a tool of ASK-analysis, is in full open access on the author's website: http://lc.kubagro.ru/aidos/_Aidos-X.htm. Numerical examples of solving veterinary problems with the use of artificial intelligence technologies are placed as cloud Eidos-applications and are available to everyone

The authors have developed and manufactured a large
number of different designs of relative helical drums
for mixing animal feed. We have conducted 749 field
experiments with the drums of the 10 different designs
with different parameters modes of operation. In all
experiments, we measured the quality of the feed mixture.
However, directly based on empirical data, rational
choice of design features and parameters of the
operation modes of the reels is not possible. For this,
you must first develop a model reflecting these empirical
data. The construction of meaningful analytical
models of different types of drums is a difficult and
demanding scientific task, the complexity of which is
due to the large variety and complexity of forms of
drums and their mode of usage, a large number of diverse
physical factors affecting the processes in the
drum. As a consequence, the development of analytical
models associated with a large number of simplifying
assumptions that reduce their versatility and reliability.
Therefore, it is important to search of a mathematical
method and software tools provide a quick and simple
for the user to identify and influence the design of the
drum and the parameters of the operating modes on the
quality of the feed mixture directly on the basis of empirical
(experimental) data. The work proposes a solution
to this problem with the use of a new universal
innovative method of artificial intelligence: automated
system-cognitive analysis (ASC-analysis) and its programmatic
Toolkit – universal cognitive analytical
system called "Eidos". In the system of "Eidos" we have implemented a software interface that provides
direct input into the system large amounts of empirical
data from Excel file. Created on their basis in the system
of "Eidos" system-cognitive model allows the visual
form to reflect the effect of the structure of the
drum and the parameters of the operating modes on the
quality of the resulting feed mixture and to develop on
this basis the science-based and appropriate recommendations
for the rational choice of design features
and parameters of the modes relative to the screw
drums. We have also given a numerical example

The work discusses various examples of physical
systems which state is determined by the logarithmic
law - quantum and classical statistical systems and
relativistic motion in multidimensional spaces. It was
established that the Fermi-Dirac statistics and BoseEinstein-Maxwell-Boltzmann
distribution could be
described by a single equation, which follows from
Einstein's equations for systems with central
symmetry. We have built the rate of emergence of
classical and quantum systems. The interrelation
between statistical and dynamic parameters in
supergravity theory in spaces of arbitrary dimension
was established. It is shown that the description of the
motion of a large number of particles can be reduced
to the problem of motion on a hypersphere. Radial
motion in this model is reduced to the known
distributions of quantum and classical statistics. The
model of angular movement is reduced to a system of
nonlinear equations describing the interaction of a test
particle with sources logarithmic type. The HamiltonJacobi
equation was integrated under the most general
assumptions in the case of centrally-symmetric metric.
The dependence of actions on the system parameters
and metrics was found out. It is shown that in the case
of fermions the action reaches extremum in fourdimensional
space. In the case of bosons there is a
local extremum of action in spaces of any dimension

The creation of artificial intelligence systems is one
of important and perspective directions of
development of modern information technology.
Since there are many alternatives of mathematical
models of systems of artificial intelligence, there is a
need to assess the quality of these models, which
requires their comparison. To achieve this goal we
require free access to the source data and
methodology, which allows to convert these data
into a form needed for processing in artificial
intelligence. A good choice for these purposes is a
database of test problems for systems of artificial
intelligence of repository of UCI. In this work we
used the database "Iris Data Set" from the bank's
original task of artificial intelligence – UCI
repository, which solved the problem of
formalization of the subject area (development of
classification and descriptive dials and graduations
and the encoding of the source data, resulting
training sample, essentially representing a
normalized source data), synthesis and verification
statistical and system-cognitive models of the
subject area, identify colors with classes, which
serve varieties of Iris, as well as studies of the
subject area by studying its model. To solve these
problems we used the automated system-cognitive
analysis (ASC-analysis) and its programmatic
Toolkit – intellectual system called "Eidos"

Traditionally, control decisions are made by solving repeatedly the forecasting problem for different values of control factors and choosing a combination of them that ensures the transfer of the control object to the target state. However, real control objects are affected by hundreds or thousands of control factors, each of which can have dozens of values. A complete search of all possible combinations of values of control factors leads to the need to solve the problem of forecasting tens or hundreds of thousands or even millions of times to make a single decision, and this is completely unacceptable in practice. Therefore, we need a decision-making method that does not require significant computing resources. Thus, there is a contradiction between the actual and the desired, a contradiction between them, which is the problem to be solved in the work. In this work, we propose a developed algorithm for decision-making by solving the inverse forecasting problem once (automated SWOT analysis), using the results of cluster-constructive analysis of the target states of the control object and the values of factors and a single solution of the forecasting problem. This determines the relevance of the topic. The purpose of the work is to solve the problem. By decomposing the goal, we have formulated the following tasks, which are the stages of achieving the goal: cognitive-target structuring of the subject area; formalization of the subject area (development of classification and descriptive scales and gradations and formation of a training sample); synthesis, verification and increasing the reliability of the model of the control object; forecasting, decision-making and research of the control object by studying its model. The study uses the automated system-cognitive analysis and its software tools (the intelligent system called "Eidos") as a method for solving the set tasks. As a result of the work, we propose a developed decision-making algorithm, which is applicable in intelligent control systems. The main conclusion of the work is that the proposed approach has successfully solved the problem

Automated system-cognitive analysis (ASC-analysis) for images provides automatic identification of specific characteristics of the given images from the color of the pixels and image edges, the synthesis of generalized images of pictures (classes), identifying the most and the least specific image features for the class, determining values of features of images for their differentiation, deletion low-value characteristics (abstraction) from the model, problem solving for quantitative comparison of specific images with generalized images of classes and generalized images of the classes with each other, and objectives of the study of the simulated subject area by studying its model. The work discusses the new features of the ASC-analysis and its implementing intellectual system called "Eidos" for identifying features of images using their spectral analysis, formation of the generalized spectra of classes, the task of comparison of images of specific objects to classes and classes with each other in their spectra. For the first time, it became possible to form the generalized spectra of classes with weights of the colors according to their degree of specificity and unspecific features for classes, and it is not the intensity of the color in the spectrum, but the amount of information in the color on the linking the object with that color to the class. In fact, there is a question of generalization of spectral analysis by using intelligent cognitive technologies and information theory in the spectral analysis. First, everyone is talking about the fact that spectral lines contain information about which element or substance is included in the object, but no one bothered to count what exactly the amount of information is and then use it to determine the composition of the object pattern recognition methods based on the use of this information. Second, spectral analysis is traditionally used to determine the elemental and molecular composition of the object; we propose to use it not only for that, but also to identify any images. A numerical example has been given

The performance indicators of a trading company in
physical and monetary terms is significantly affected
by the types and volumes of purchased and sold
products, and which she purchased suppliers and the
consumers sold. However, the solution to the problem
of choosing the rational range of products faces
considerable cost of computational and human
resources, and lack of baseline data, and in real
dimensions this problem has no solution. The paper
proposes such a solution is very economical in costs of
different types of resources based on the application of
information theory, cognitive and control theory

A diversified corporation is a highly complex multivariable dynamic system. The application of classical forecasting methods applied to such objects has encountered a number of difficulties, due to its economic nature. In the article, we substantiate the requirements to the forecasting method; on the basis of these requirements we can select the method and its software tool

Creation of artificial intelligence systems is one of
important and perspective directions of development
of modern information technology. As there are
many alternatives to artificial intelligence systems,
there is a need to evaluate mathematical models of
these systems. In this work, we present a solution of
the problem of identifying classes of salary levels of
employees depending on their characteristics. To
achieve this goal it requires free access to test the
source data and methodology, which will help to
convert the data into the form needed for work in
artificial intelligence systems. A good choice is a
database of test problems for systems of artificial
intelligence of UCI repository. In this work we used
the database called "Wine Data Set" from the Bank's
original task of artificial intelligence from repository
UCI. The most reliable in this application was the
model of the INF4 based on semantic, according to
A. Kharkevich, integral criteria of "Amount of
knowledge". The accuracy of the model is 0,916,
which is much higher than the reliability of expert
evaluations, which is equal to about 70%. To assess
the reliability of the models in the ASC-analysis and
the system of "Eidos" we used the F-criterion of van
Ritbergen and fuzzy multiCLASS generalization
proposed by Professor E. V. Lutsenko (L-measure)