Scientific Journal of KubSAU

One of the key problems facing medicine is the correct diagnosis given in a timely manner. For all the existence of medicine, humanity has accumulated a lot of knowledge in this area. According to this knowledge, new specialists are trained. But there is so much information that it is sometimes impossible to find the right information in it in time, and this can cost the person who came to see a doctor very expensive. In this specialist comes to the rescue computer. Information technologies, training in information bases perfectly cope with the task of identifying the disease and providing the most appropriate information

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 the intellectual system called "Eidos", which is a software toolkit for the automated system-cognitive analysis (ASC-analysis), we use initially proposed by its developers measure of the reliability of the models, which is essentially a fuzzy multiclass generalization of the classical F-measure (it is proposed to call it the L-measure). In this article, L-measure is mathematically described and its application is demonstrated on a simple numerical example

In the article the method and the results of investigating the information properties of the celestial bodies of the solar system are described. Is proposed the new for contemporary astronomy tool of knowledge, which includes intellectual information technology and the multichannel receiver distributed in the space and time, as which were used 20007 subjects. This allowed to open and to begin a study the new previously unknown phenomena of nature. It is in particular established that interaction of the group of subjects with the space environment has substantive nature. The reaction of each subject to the position of the celestial bodies of the solar system at the moment of birth was recorded and was processed for this. Each subject reacted via selection of one or several of 37 social categories, which composes totally 86314 cases. By statistical processing discovered, that the parameter of the dispersion of the information of the signs of celestial bodies (integral informativeness) depends on position of an ascendant - degree of the solar zodiac ascending in the east at the moment of a birth, and it depends on the distance to the celestial bodies as well. The mechanisms of the influence of celestial bodies on the group of subjects are discussed.

On the one hand, man is a physical object and a person. Therefore, we interact with the reality, on one hand, directly as a physical object, but on the other hand as a person, i.e. indirectly through our psyche. On the basis of information from the senses, the consciousness of a person creates a subjective model of reality. A man mistakes his subjective model of reality for reality itself, i.e. unnecessarily assigns an ontological status, by the hypostatizations. In fact, as the reality a man perceives not reality itself, but only its subjective model of that reality. As a result, as a physical object, a person lives in the physical world, and as a person he lives in his subjective model of physical and social reality created on the basis of information coming to his senses directly and from the media. This work considers the process of formation of subjective 3D models reality based of large numbers of 2D images, a distinction is made in the content of terms: "Seeing" and "Sensing"; it also analyzes the transformation of objective facts into subjective perceptions of consciousness and back. As a result of hypostatizations of subjective models of reality, we may observe the same effects as in virtual reality (a reality effect; the effect of the presence; the effect of depersonalization; the effect of virtualization goals, values, and motivations). So, there is every reason to consider different subjective models of reality generated by different forms of consciousness, the virtual models. We study various consequences of these statements

This work is a continuation of the author's series of works on cognitive veterinary medicine. The present period is characterized by the appearance of huge volumes of texts in different languages in the open access, generated by people. Currently, these texts are accumulated in various electronic libraries and bibliographic databases (WoS, Scopus, RSCI, etc.), as well as on the Internet on various sites. All these texts have specific authors, dates and can belong simultaneously to many non-alternative categories and genres, in particular: educational; scientific; artistic; political; news; chats; forums and many others. The solution of the generalized problem of attribution of texts is of great scientific and practical interest, i.e. studying these texts, which would reveal their probable authors, date of creation, the ownership of these texts to the above generalized categories or genres, and might evaluate the similarities - differences of authors and texts according to their content, highlight key words etc. To solve all these problems it seems necessary to form the generalized linguistic images of texts into groups (classes), i.e. to form semantic kernels of classes. A special case of this problem is the creation of the semantic kernel in various scientific specialties of the HAC of the Russian Federation and the automatic classification of scientific texts in the areas of science. Traditionally, this task is solved by dissertation councils, i.e. experts, on the basis of expert assessments, i.e. in an informal way, on the basis of experience, intuition and professional competence. However, the traditional approach has a number of serious drawbacks that impose significant limitations on the quality and volume of analysis. Currently, there are all grounds to consider these restrictions as unacceptable, because they can be overcome. Thus, there is a problem, the solutions of which are the subject of consideration in this article. Therefore, the efforts of researchers and developers to overcome them are relevant. Therefore, the aim of the work is to develop an automated technology (method and tools), as well as methods of their application for the formation of the semantic core of veterinary medicine by automated system-cognitive analysis of passports of scientific specialties of the HAC of the Russian Federation and automatic classification of texts in the areas of science. A detailed numerical example of solving the problem on real data has been given as well

The article describes a numerical example of creating intellectual application designed to predict solar flares of different classes on the basis of the history of their development in the environment of "Eidos" system. As the source data, we used the database of UCI repository

In the article we have offered the technology and the methodology for the formulation and the solution of the problem of forecasting scenarios of changes in yield sunflower seeds at the level of a region and its districts, on the basis of the system-cognitive model that is different from the traditional: a high degree of formalization of the model of knowledge; the possibil-ity of the synthesis matrix transfer function of the object of forecasting directly on the basis of empirical data; correct work with incomplete (fragmented) and noisy data. For the first time, the study of the system-cognitive model of artificial ecosystems of sunflower in the Krasnodar Region, which is correctly regarded as the study of the ecosystem, as the verification of this model has shown its high adequacy has been conduct-ed

In this article, for the first time, the synthesis and veri-fication of the system-cognitive model of artificial ecosystems of sunflower crops in the Krasnodar region (at the levels of regions and in the whole region) are carried out. On the basis of the developed models, there are solved tasks: 1. Forecasting scenario of sun-flower yield for the period from 1 to 5 years. 2. The scientific study of artificial ecosystems of sunflower crops in the Krasnodar region (at the levels of regions and in the whole region)

In this article application of a new method of an artificial intellect is examined: systemic-cognitive analysis and its toolkit - "Eidos" system are used for an estimation of level of nonspecific resistance of an organism of patient on the basis of the preoperative information about it received by a method of cardio respiratory synchronism (CRS) and forecasting of duration of the postoperative rehabilitation period on this basis. In the 2nd part of the article it is considered: forecasting and decision support of problem solving, including shaping and an output of informational portraits of classes, worth of factors and their value for forecasting and decision making problem solving, outputs are made, outlooks are planned, hypotheses are stated

In this article application of a new method of an artificial intellect is examined: systemic-cognitive analysis and its toolkit - "Eidos" system are used for an estimation of level of nonspecific resistance of an organism of patient on the basis of the preoperative information about it received by a method of cardio respiratory synchronism (CRS) and forecasting of duration of the postoperative rehabilitation period on this basis. In the 1st part of the given article it is considered: entering in a problem, the generalized structure of "Eidos" system, cognitive structurization of a data domain, data domain formalization, preparation of training sample, semantic information model synthesis, a raise of performance and verification (reliability estimation) of the given model