Name
Lutsenko Yevgeniy Veniaminovich
Scholastic degree
•
Academic rank
professor
Honorary rank
—
Organization, job position
Kuban State Agrarian University
Web site url
Articles count: 272
In the article, on a small numerical example, we consider the similarity and difference of symptoms and syndromes according to their diagnostic meaning, i.e. according to the information they contain about the belonging of conditionals of animals to different nosological images. This problem can be solved for veterinary with the use of a new method of agglomerative cognitive clustering, implemented in Automated System-Cognitive analysis (ASC-analysis). This method of clustering differs from the known traditional methods in: a) in this method, the parameters of the generalized image of the cluster are calculated not as averages from the original objects (symptoms) or their center of gravity, but are determined using the same basic cognitive operation of ASC-analysis, which is used to form generalized images of the classes based on examples of objects and which really correctly provides a generalization; b) the similarity criterion is not the Euclidean distance or its variants, but the integral criterion of non-metric nature: "the total amount of information", the application of which is theoretically correct and gives good results in unortonormated spaces, which are usually found in practice; c) cluster analysis is carried out not on the basis of initial variables, frequency matrices or matrix of similarity (differences), depending on the units of measurement on the axes (measurement scales), but in cognitive space, in which one unit of measurement is used for all axes: the amount of information, and therefore the results of clustering do not depend on the initial units of measurement of features of objects. All this allows us to get the results of clustering, understandable to specialists and amenable to meaningful interpretation, well-consistent with the experts ' assessments, their experience and intuitive expectations, which is often a problem for classical clustering methods
Agronomy systems with good reason can be
considered as complex multiparameter natural and
technical systems. In these systems, there are
numerous and diverse physical, chemical and
biological processes. On the one hand, these processes
have a significant impact on the performance of these
systems. On the other hand, they are extremely
difficult to be described in the form of meaningful
analytical models based on equations. As a result, the
development of meaningful analytical models is
associated with a large number of simplifying
assumptions that reduce the validity of these models.
Usually we consider linear univariate models for
agronomic systems, whereas practices are necessary
for nonlinear multiparameter models. Thus, we face
the problem proposed to be solved by the application
of a phenomenological meaningful systemic cognitive
models. These models are created using automated
system-cognitive analysis (ASC-analysis) using the
intellectual system called "Eidos" directly based on
empirical data and used for the decision of tasks of
forecasting, decision support and research of the
modeled subject area. In this case, empirical data can
be large, incomplete (fragmented), noisy, presented in
different types of measuring scales (nominal, ordinal
and numerical) and in different units of measurement.
The comparability of the processing of heterogeneous
data is ensured by the fact that they are all converted
into units of measurement of the amount of
information. A numerical example has been given
The 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 consider a
solution of the problem of identifying classes of
levels of pay of employees 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 the
databases from the site: http://allexcel.ru/gotovyetablitsy-excel-besplatno.
In this work, we have used
the database called "The database table of
employees, payments calculation". The most reliable
in this application was the model of the INF4 based
on semantic appropriate measure of information of
A. Kharkevich with integral criteria of "Amount of
knowledge". The accuracy of the model is 0.960,
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 ACS-analysis and
the system called "Eidos" we have used F-criterion
of van Ritbergen and fuzzy multiclass generalization
proposed by Professor E. V. Lutsenko
Techniques of value analysis and "Direct-costing" are
well-known and popular. The ideas and principles of
value analysis and the method of "Direct costing" are
very similar, if not identical. On the one hand, these
ideas are very reasonable, well grounded theoretically
and proved its effectiveness in practice. On the other
hand, the wide use of these methods is hampered by
the difficulty of obtaining large amounts of detailed
technological and financial-economic information, as
well as the need for careful research by competent
professionals, well-versed in substantive subject area.
This is the contradiction between the desire to apply
the methods of the value analysis and "Direct costing"
and difficulty to perform it in practice. This
contradiction constitutes a real problem and may often
be discouraging and frustrating. In this work, we
propose a simple and effective solution to this
problem, theoretically well-informed with all the
necessary methodological and software tools and
widely and successfully tested in practice. The
proposed solution is based on two simple ideas: 1)
instead of collecting and holding a meaningful large
amount of technological and financial-economic
information we might apply approaches, pleasant
management theory; 2) to create systems for
automated control of natural and financial-economic
efficiency of expenses we might use the automated
system-cognitive analysis and its software tool – an
intellectual system called "Eidos". In the name of the
specialty 08.00.05 – Economics and national economy management, there are such words: "management of
enterprises, branches, complexes, innovation." The use
of the term "Management" implies that there is a
model that reflects the influence of factors on the
object of control, and there is the management system
making decisions based on this model. However, as a
rule, the dissertations in this field have nothing of this,
except only financial and economic calculations. The
article proposes an approach based on the control
theory, removing this disadvantage
From a huge number of the organisms inhabiting our
planet, insects make 70%, being the most numerous of
the invertebrate animal classes numbering more than 2
million types. It is difficult to find such place where it
would be impossible to meet representatives of this
huge class. They completely took over the entire environment
- water, the land, air. For them, it is the common
characteristic: complex instincts, omnivorous,
high fecundity, and for some of them – a public way of
life. Insects can be found at tremendous heights, reaching
the level of 5000 meters, and they inhabit the desert
where it practically never rains, not to mention the
absence of any vegetation. Deep caves where no sunlight,
nor the conditions for food and existence of living
organisms — it is also the habitat of insects, they
can be found far beyond the Arctic circle, and even on
many Islands of Antarctica, where in addition to lifeless
rock, it would seem that there is nothing else.
Among insects, one of the largest and most numerous
families are the ground beetles (Carabidae). They subtly
respond to changes in soil and vegetation, hydrothermal
and micro-climatic conditions of the environment,
which makes them a convenient model subject
to various environmental and Zoological researches.
Ground beetles belong to a large number of genera and
species, often difficult to see, in this regard, we use
many different signs to diagnose. We have taken into
consideration the coloration, body shape, external
structure, surface structure, size, and arrangement of
the genitals and chaetotaxy. Due to the fact, that the
number of ground beetles is enormous, and, using their
appearance, it is very difficult to determine their generic
identity, there is a need of automation of the
identification process, due to which we require a special
mechanism that would increase the accuracy of
these insects. In the previous work of the authors (http://ej.kubagro.ru/2016/05/pdf/01.pdf) we considered
the further possibility of using the method of
ASC- analysis to classify insects, not only in species
but also in genera, orders, thereby increasing the reliability
of determination of ground beetles, which will
be done in this article. A numerical example is given.
We also have gained a successful experience of solving
such problems in other subject areas. This article
can be considered as a continuation of the series of
works dedicated to governmental use of the automated
system-cognitive analysis (ASC-analysis) and its software
tools – the system of "Eidos"
The 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 article, we consider
a solution of the problem of identifying classes of
levels of pay to employees 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 UCI
artificial intelligence repository. In this work we
have used data base on teaching effectiveness for
three regular semesters and two summer semesters
of 151 teaching assistant (TA) assignments at the
statistics Department of the University of
Wisconsin-Madison. The most reliable in this
application was the model of the INF4. The
accuracy of the model in accordance with Lmeasure
made up 0,809, 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 in the system of "Eidos" we
use F-criterion of van Ritbergen and its fuzzy
multiclass generalization proposed by Professor E.
V. Lutsenko
The article deals with the similarity and difference of nosological images in veterinary medicine using a new method of agglomerative clustering implemented in Automated system-cognitive analysis (ASC-analysis) on a small numerical example. This method is called Agglomerative cognitive clustering. This method differs from the known traditional facts: a) parameters of a generalized image of the cluster are computed not as averages from the original objects (classes) or their center of gravity, and are defined using the same underlying cognitive operations of ASC-analysis, which is used for the formation of generalized images of the classes on the basis of examples of objects and which is really correct and provides a synthesis; b) as a criterion of similarity we do not use Euclidean distance or its variants, and the integral criterion of non-metric nature: "the total amount of information", the use of which is theoretically correct and gives good results in non-orthonormal spaces, which are usually found in practice; c) cluster analysis is not based on the original variables, matrices of frequency or a matrix of similarities (differences) dependent on the measurement units of the axes, and in the cognitive space in which all the axes (descriptive scales) use the same unit of measurement: the quantity of information, and therefore, the clustering results do not depend on the original units of measurement features. All this makes it possible to obtain clustering results that are understandable to specialists and can be interpreted in a meaningful way that is in line with experts' assessments, their experience and intuitive expectations, which is often a problem for classical clustering methods
HOW TO SOLVE THE TASK OF CLASSIFICATION OF TYPES OF RIFLE AMMUNITION USING THE METHOD OF ASCANALYSIS
In forensics there is an urgent need to determine the
type of rifle (automatic, rifle, large caliber pistol) depending
on its used ammunition found at the scene of
the use of weapons. We offer a solution to this problem
with the use of new innovative method of artificial
intelligence: automated system-cognitive analysis
(ASC-analysis) and its program toolkitwhich is a universal
cognitive analytical system called "Eidos". In
the "Eidos" system we have implemented the software
interface that allows posting of images and identifying
their outer contours. By multivariable typing, the system
creates a systemic-cognitive model, the use of
which, if the model is sufficiently accurate, may be
helpful in solving problems of system identification,
prediction, classification, decision support and research
of the modeled object by studying its model.
For this task the following stages: 1) input images of
ammunitions into the "Eidos" system and creation of
their mathematical models; 2) the synthesis and verification
of the models of generalized images of ammunition
for types of weapons based on the contour images
of specific munitions (multiparameter typing); 3) improving
the quality of the model by separating classes
for typical and atypical parts; 4) quantification of the
similarities-the differences between specific types of
munitions with generic images of different types of
ammunition of the weapon (system identification); 5)
quantification of the similarity-differences between
types of ammunition, i.e. cluster-constructive analysis
of generalized images of ammunition. A numerical example is given. We also possess a successful experience
of solving similar problems in other subject areas
Classic quantitative measure of the reliability of the models: F-measure by van Rijsbergen is based on counting the total number of correctly and incorrectly classified and not classified objects in the training sample. In multiclass classification systems, the facility can simultaneously apply to multiple classes. Accordingly, when the synthesis of the model description is used for formation of generalized images of many of the classes it belongs to. When using the model for classification, it is determined by the degree of similarity or divergence of the object with all classes, and a true-positive decision may be the membership of the object to several classes. The result of this classification may be that the object is not just rightly or wrongly relates or does not relate to different classes, both in the classical F-measure, but rightly or wrongly relates or does not relate to them in varying degrees. However, the classic F-measure does not count the fact that the object may in fact simultaneously belongs to multiple classes (multicrossover) and the fact that the classification result can be obtained with a different degree of similarity-differences of object classes (blurring). In the numerical example, the author states that with true-positive and true-negative decisions, the module similarities-differences of the object classes are much higher than for false-positive and false-negative decisions. It would therefore be rational to the extent that the reliability of the model to take into account not just the fact of true or false positive or negative decisions, but also to take into account the degree of confidence of the classifier in these decisions. In classifying big data we have revealed a large number of false-positive decisions with a low level of similarity, which, however, in total, contribute to reducing the reliability of the model. To overcome this problem, we propose a L2-measure, in which instead of the sum of levels of similarity we use the average similarity by different classifications. Thus, this work offers measures of the reliability of the models, called L1-measure and the L2 measure, mitigating and overcoming the shortcomings of the F-measures; these measures are described mathematically and their application is demonstrated on a simple numerical example. In the intellectual system called "Eidos", which is a software toolkit for the automated system-cognitive analysis (ASC-analysis), we have implemented all these measures of the reliability of the models: F, L1 and L2
Application of classical forecasting methods applied to a diversified corporation faces some certain difficulties, due to its economic nature. Unlike other businesses, diversified corporations are characterized by multidimensional arrays of data with a high degree of distortion and fragmentation of the information due to the cumulative effect of the incompleteness and distortion of accounting information from its enterprises. Under these conditions, the applied methods and tools must have high resolution and to work effectively with large databases with incomplete information, to ensure correct common comparable quantitative processing of the heterogeneous nature of the factors measured in different units. It is therefore necessary to select or develop some methods that can work with poorly formalized complex tasks. This fact substantiates the relevance of the problem of developing models, methods and tools for solving the problem of forecasting the development of diversified corporations. This article compares methods of forecasting and encourages using the ask analysis which has a good theoretical justification for the meaningful interpretation of a knowledge model based on information theory; high accuracy and independence of calculation results of the unit of measurement baseline data through the use of not the correlation matrix, as in statistical systems, and matrices of knowledge. A well-developed and available Toolkit of the ASK-analysis which is an intellectual system called "Eidos" (created by E. V. Lutsenko, 1994) allows, on the basis of fragmented, noisy source data of various nature (numeric, text) to create models of large dimension. The ASK-analysis and the system of "Eidos" have been widely and successfully used in economics, engineering, agriculture, sociology and other fields. These features of the ASK-analysis have led to the fact that it was chosen as the method of forecasting of dynamics of indicators of the corporation