Dimitri Radzievski

The description of the program for the investigation and the analysis of the aircrafts’ emergency flights by records of board recording systems, so-called “ black boxes ”, is carried out. The program provides the visualization on the screen, and the scoring of flight situations observable in the cabin, i.e. the equipment information of values of all parameters as images of real devices, conditions and signals of the aircraft’s control systems, talks with control points, and also a real image of the attitude of the aircraft’s three-dimensional figure.

The problem of the computerized recognition and evaluation of the ecological condition of the ambient air using artificial intelligence methods is considered. The recognition and evaluation are performed on the basis of the ecological monitoring data.

The solution of this problem will make possible to reveal changes in the atmospheric air composition in real time, to mark out the atmospheric component of these changes against the background of natural processes and to accomplish regulation and control airing to the improvement of the air quality.

The problem of the diseases early detection basing on the computer analysis and on the recognition of the form of erythrocytes image is considered. The erythrocytes image processing is carried out, and the features, on the basis of processing and recognition of the erythrocytes image are developed.

An information system for analysis of plane scenes, which is able to create a verbal symbolic description of a given scene, is considered. Such a symbolic description makes possible to decrease significantly the amount of information contained in a scene image, without damaging the essentials needed at decision-making.

The verbal scene description will effect a significant saving of a computer memory capacity needed for the information storage, and will also shorten a time of information dispatching trough communication channels. The considered system will provide a possibility of a man-and-system interaction using a natural language. This will help to specify some features necessary at making well-grounded decisions.

The ecological state of the environment is one of the most important factors that determine the influence of the nature on living organism, mostly on the health of human beings. That’s why the protection of the environment is one of the most urgent issues that are put to be solved.

The question for recognizing and estimating of the ecological state of the environment that should be settled in the real time scale is raised in the work.

It is shown that for effective governing of the environment both the information about the current state of the environment and the future condition and also the information about the reson causing the breaches of the current state are needed.

To solve the problem, the program model of the intelligence system for recognizing and estimating the ecological condition of the environment is made that realizes the integral estimation of the quality of the ecological state of the environment.

On the base of the estimation controlling of the ecological state of the environment for the purpose of its quality improvement is carried out.

The task of integral assessment of the ecological status of non-living components of the environment is considered. The task contains subtasks such as identification, forecasting and cause-and-effect analysis of the situation. An environmental monitoring software training model is built to solve the task. The system describes classes of different states of non-living components (concept model). The concept model is formed in the learning process and represents the knowledge of the system. The system performs cause-and-effect analysis, which identifies the causes that cause negative changes in the environment. The information obtained forms the situation on the basis of which a decision is made regarding the quality management of the environment.

The problem of assessing the area of the environment in terms of its use for specific purposes is considered. Such an assessment takes into account environmental, climatic, physical, biotic and many other factors. It is carried out on the basis of many criteria and can be solved, for example, by the method of multi-criteria assessment based on the theory of fuzzy sets, and solved with the participation of experts.

Some issues of application of knowledge to the problems of complex system control are considered. The knowledge is presented as a set of relations between verbal descriptions of objects under control and solutions. It is suggested to use key words in order to obtain descriptions invariant to word invertions in input sentences.

We solve a problem of dividing situational descriptions into classes according to a number of possible solutions. A generalized description is related to each class. These descriptions make it possible to recognize a new sentence which does not belong to a training set. Control decisions are made on the basis of recognitions of input sentences.

On the basis of the conceptual approach to the methods of solving the non-formalized tasks of diagnosis of the complex systems are proposed. Diagnostics of the condition of a system is considered as a problem of classification and recognition and creation of the generalized description of classe is carried out by training on examples. The proposed methods provide reference of new states to a certain class (extrapolation) both for quantitative and qualitative values of features. On the basis of these methods non-formalized task of differential diagnostics of migraine and a tension headache was solved.

The article considers the problem of an assessment of an ecological state of the environment. It is shown that information received as a result of diagnostics of an ecological state of environment is insufficient for its adequate assessment. Information received on the basis of forecasting and the causal analysis of an ecological state of the environment is necessary for the solution of a task as well. The authors offer the model of intellectual system using methods of mathematical logic, Boolean algebra and the discriminant analysis.

Here is considered the problem of making decisions for managing complex systems. It is shown that the solution of such problems is not possible by means of traditional mathematical methods or busting techniques. In order to solve such problems production models of knowledge and recognition models are used. We also consider the relationship between the set of the control object states and the set of possible solutions generated by the control system. It is shown that the relation between these sets should be brought into line with Ashby’s law of requisite variety. The methods for solving this problem and corresponding recommendations are suggested.

On the basis of the conceptual approach the methods of solving the non-formalized tasks of diagnosis the

complex systems state are proposed. Diagnosing of a system state is considered as a problem of classifi cation

and recognition, and creation of the generalized description of classes is carried out by training on examples. The

proposed methods provide reference of new states to a certain class (extrapolation) both for quantitative, and for

qualitative features. On the basis of these methods non- formalized task of differential diagnostics of migraine and

a tension headache has been solved.

The question of the knowledge organization in intelligent information systems for solving nonformalized problems of diagnosing is considered in the paper. The method of diagnosing the state of complex systems that works with both quantitative and qualitative data is offered. The descriptions of classes of states resulting from the application of this method are high-informative predicates – a disjunction of conjunctions, each of which is characterized by the certainty factor. It allows to use the production model with certainty factors for representation of heuristic knowledge which effectively works in the conditions of fuzziness, uncertainty and incompleteness of data and knowledge

The problem of data processing in the tasks of medical diagnostics is considered as one of the problems of data mining. As a data mining method, a logical recognition method based on a conceptual approach is proposed, as well as a quantitative feature binarization algorithm that ensures the effectiveness of the classifier rule in terms of both diagnostic and differentiating abilities.

A huge amount of heterogeneous data generated by modern medicine, require the development of new technologies for data analysis in order to discover certain patterns and hidden knowledge. Methods of data mining provide new opportunities for solving of this actual task. In the paper features of the medical data and the main tasks associated with their analysis and processing are considered. A brief overview of data mining methods an algorithms, most often used in medicine, are given; their advantages and disadvantages are considered. Data mining applications for solving various problems of medical diagnosis and prediction, as well as the most actual directions of development of data mining technologies in medicine are given.

The task of medical data analysis as one of the data mining tasks is considered. As methods of solving it, methods of machine learning are offered - a logical method of classification based on a conceptual approach and feedforward neural networks. To train the network, a learning algorithm with error correction is used. Based on the results of the application of these methods, the intelligent system for diagnosing and predicting primary headaches are constructed. This intelligent system is used to support decision-making by a doctor.

The task of medical data analysis is considered in order to identify frequent symptoms and symptom sets for each disease. For data analysis, the association rule mining method is used, which allows to assess the specificity of the symptoms found and the confidence of the diagnostic rules based on the identified associations. The proposed method was used to process the clinical data of a number of endocrinological diseases. Based on the obtained association rules, a knowledge base of the medical intelligent system designed for diagnosing endocrinological diseases was formed.

An intellectual system for diagnosing diseases, using medical knowledge and capable of learning, is considered. As a knowledge model, a semantic network is used, also presented in the form of a matrix of relations. Both the network and the matrix define the relationship between symptoms and their causes. The weights are assigned to the arcs of the network and the corresponding matrix. These coefficients are formed in the learning process. To make a decision on establishing a diagnosis, the formation of a linear function and a block for choosing a maximum, as well as the theory of fuzzy sets and the Jager method are used. The use of this model is shown on the example of solving the problem of diagnosing primary headaches.

Doctoral Thesis Referee

Master Theses Supervisor

Doctoral Thesis Supervisor/Co-supervisor

Scientific editor of monographs in foreign languages

Scientific editor of a monograph in Georgian

Editor-in-Chief of a peer-reviewed or professional journal / proceedings

Review of a scientific professional journal / proceedings

Member of the editorial board of a peer-reviewed scientific or professional journal / proceedings

Participation in a project / grant funded by an international organization

Participation in a project / grant funded from the state budget

Patent authorship

Membership of the Georgian National Academy of Science or Georgian Academy of Agricultural Sciences

Membership of an international professional organization

Membership of the Conference Organizing / Program Committee

National Award / Sectoral Award, Order, Medal, etc.

Honorary title

Monograph

Handbook

Research articles in high impact factor and local Scientific Journals

Publication in Scientific Conference Proceedings Indexed in Web of Science and Scopus