Volodymyr Ivanovich Lytvynenko

Kherson National Technical University · Department of Informatiс and Computer Sciences

This work discusses the problem of forecasting the tertiary structure of a protein, based on its primary sequence. The problem is that science, with all its computing power and a set of experimental data, has not learned to build models that describe the process of protein molecule coagulation and predict the tertiary structure of a protein, based...

The article presents an inductive model of objective clustering based on the MeanShift clustering technique. The algorithm for breaking an assortment of original data into two evenly powerful subsets is employed. The balance criterion is handled as an external criterion. To test the functioning of the proposed model, the “Jain” and “Flame” data set...

The paper proposes an application of Bayesian methodology to analyze the attachment effectiveness in the national economy. The methods for creation the BNs structure, their parametric learning, validation, and scenario analysis are examined. The research results show that at the highest level of capital investments, the financial activity result wi...

The methods for protein structure prediction are based on the thermodynamic hypothesis, according to which the free energy of the “protein-solvent” system is minimal in the folded state of protein. By predicting the tertiary protein structure, it is theoretically possible to predict its action. This problem is considered as a global optimization is...

Mass spectrometry is one of the fundamental analytical techniques of our time. As a rule, the primary processing of mass spectrometric data in modern quadrupole mass spectrometers from leading manufacturers is successfully carried out by both hardware and software. However, the task of extracting mass spectra of complex sources, such as multi-atomi...

The construction of an intelligent system for determining the concentration of iron in the coagulant by its color on the basis of a neural network is considered. Based on the analysis of different types of neural networks, the most suitable neural network architecture was selected to solve the problem of determining the concentration of iron in the...

The article presents the results of research concerning development of inductive algorithm for hierarchical Bayesian clustering of gene expression of patients with two types of brain tumors and healthy individuals. The study carried out comparative studies of the clustering quality of inductive and classical methods of Bayesian hierarchical cluster...

In this paper, we propose a methodology for using dynamic Bayesian networks (DBN) in the tasks of assessing the success of an investment project. The methods of constructing DBN, their parametric learning, validation and scenario analysis of “What-if” are considered. A dynamic Bayesian model has been developed for scenario analysis and forecasting...

This paper presents the studies’ results on the probability-determined models development based on Bayesian networks to estimate the economic development measure of Ukraine. Considering that one of the difficulties in the Bayesian networks development is the exponential increase in the parameters amount in conditional probability tables (CPT), this...

In the research, a dynamic BN (DBN) was designed to assess general trends in the level of regional competitiveness depending on economic detectors. This dynamic model is built on the basis of a trained, already verified static Bayesian network for assessing the country’s competitiveness. In contradistinction to an approach based on entrance from a...

This book includes 46 scientific papers presented at the conference and reflecting the latest research in the fields of data mining, machine learning and decision-making. The international scientific conference “Intellectual Systems of Decision-Making and Problems of Computational Intelligence” was held in the Kherson region, Ukraine, from May 25 t...

Numerical methods for expanding the field of applicability of chromatography-mass spectrometry in the case of poorly separated signals are considered. We found that the existence of additive noise in the initial mixed mass spectrum gives rise to the noise component of the weight coefficients of its components with an undetermined probability distri...

The leading role in addressing public health belongs to physical therapy specialists, the purpose of professional activity of which is the comprehensive restoration of the functional state of the person by means of physical and health technologies. Mastering such technologies is one of the components of the professional training of these specialist...

Expand and deepening of detailed researches into the problems of training future primary teachers in physical education is very necessary under modern conditions. Scientists pay special attention to the creation and introduction of active methods of study, the skilful use of which would contribute to increasing efficiency in the acquisition by stud...

The progressive humanity understood: medicine has relative possibilities of eliminating the consequences of destructive processes in the human body and psyche, while prevention, propaedeutics and other forms of prevention are relevant not consequences, but causes. Doctors should abandon the monopoly on improving health and move to cooperate with hu...

The direct method features of finding the weight coefficients of the mixed molecular spectrum components on the basis of their reference samples are considered in this paper. It has been established that the presence of additive noise in the output mixed spectrum generates a noise component with an unidentified probability distribution law in the f...

The paper deals with the problem of protein tertiary structure prediction based on its primary sequence. From the point of view of the optimization problem, the problem of protein folding is reduced to the search for confirmation with minimal energy. To solve this problem, a hybrid artificial immune system has been proposed in the form of a combina...

In this paper, for solving the problem of forecasting non-stationary time series, hybrid learning methods for GMDH-neural networks are proposed. Training methods combine artificial immune systems with members of the evolutionary algorithm family, in particular, gene expression programming systems. The following hybrid computational methods for the...

This paper proposed a methodology for the use of static and dynamic Bayesian networks (BN) in the problems of localizing the distribution of narcotic substances. Methods for constructing the BN structure, their parametric training, validation, sensitivity analysis and “What-if” scenario analysis are considered. A model of dynamic Bayesian networks...

This article offers a modern approach to the policy of competitiveness of the national economy at the regional level. Based on the results and experience of domestic and foreign economists the author offers a system of indicators of regional activity and a method for determination of the integrated index of the competitiveness level in the region....

Context. The problem of the data clustering within the framework of the objective clustering inductive technology is considered. Practical implementation of the obtained hybrid model based on the complex use of R and KNIME tools is performed. The object of the study is the hybrid model of the data clustering based on the complex use of both DBSCAN...

Mostly, diagnosis at a system level intends to identify only permanently faulty units. In the paper, we consider the case when both permanently and intermittently faulty units can occur in the system. Identification of intermittently faulty units has some specifics which we have considered in this paper. We also suggest the method which allows for...

The paper presents the technology of gene expression profiles reducing based on the complex use of fuzzy logic methods, statistical criteria and Shannon entropy. Simulation of the reducing process has been performed with the use of gene expression profiles of lung cancer patients. The variance and the average absolute value were changed within the...

System level diagnosis is an abstraction of high level and, thus, its practical implementation to particular cases of complex systems is the task which requires additional investigations, both theoretical and modeling. Mostly, diagnosis at system level intends to identify only permanently faulty units. In the paper, we consider the case when both p...

The paper presents the hybrid model of the objective clustering inductive technology based on complex using of the self-organizing SOTA and the density DBSCAN clustering algorithms. The inductive methods of complex systems analysis were used as the basis to implement the objective clustering inductive technology of gene expression profiles. To esti...

The paper presents the technology of gene expression profiles filtering based on the wavelet analysis methods. A structural block-chart of the wavelet-filtering process, which involves concurrent calculation of Shannon entropy for both the filtered data and allocated noise component is proposed. Simulation of the wavelet-filtering process was perfo...

The paper presents the research concerning comparison analysis of biclustering algorithms effectiveness with the use of artificial data and gene expression profiles. Internal biclustering quality criterion is proposed as the result of the simulation. The change of this criterion has high correlation with Jaccard index, which was calculated for perf...

Aim. Development of an inductive technology of objective clustering of gene expression profiles based on a self-organizing SOTA clustering algorithm. Methods. Inductive methods of complex system analysis were used to implement the inductive technology of objective clustering of gene expression profiles. The optimal parameters of clustering algorith...

Technology of high dimensional data features objective clustering based on the methods of complex systems inductive modeling is presented in the paper. Architecture of the objective clustering inductive technology as a block diagram of step-by-step implementation of the objects clustering procedure was developed. Method of criterial evaluation of c...

The inductive model of the objective clustering of objects based on the k-means algorithm clustering is presented in the paper. The algorithm for division of initial data into two equal power subsets is proposed and practically implemented. The difference between the mass centres of the appropriate clusters in different clustering is proposed to us...

The paper concerns system level self-diagnosis (SLSD). SLSD aims at diagnosing systems composed by units with the requirement that they are able to test each other by exchanging information through available links. At this level of diagnosis, each particular test is considered as atomic. It means that the details of a test are abstracted (not consi...

Researches on an optimization of the filtration process of DNA nucleotides gene expression profiles are presented in the article. The data of lung cancer patients E-GEOD-68571 of Array Express database were used as experimental data. Filtration was carried out under the terms of the expression detecting of corresponding gene, herewith the variance...

Aim. The article is dedicated to optimization of the DNA microarray data processing, which is aimed at improving the quality of object clustering. Methods. Data preprocessing was performed with program R using Bioconductor package. Modelling the clustering process was made in the software environment KNIME using the program WEKA functions. Results....

The paper deals with the problem of developing probabilistic algorithm for system level self-diagnosis. The main goal of the suggested algorithm is to minimize the mean time of its executing. The algorithm is based on the computing of the posterior probability of fault-free state of each system unit. Final decision about unit's state is made on the...

The inference of gene regulatory networks is one of the main challenges in systems biology. In this paper we address the problem of finding gene regulatory networks from experimental DNA microarray data. We suggest to use a multi-objective clonal selection algorithm to identify the parameters of a non-linear system given by the observed data. Not o...

Babichev S., Osypenko V., Taif M., Lytvynenko V. Індуктивне моделювання складних систем, випуск 7, 2015 5 UDC 004.048 Досліджена можливість застосування бікластерного аналізу в системах кластеризації об'єктів складної біологічної природи. Бікластерізація проводилася за алгоритмом ВССС пакету "biclust" програмного середовища R, кластеризація об'єкті...

This paper describes principles of implementation of basic entities on system level of self-diagnosis (especially self-checking) in Python programming languages. The first part discusses usability of Python for representation and simulation of complex systems (comparing it primarily with the most important competitor in the field of universal progr...

Article is devoted to sequence, structure and strategy of solving the problem of self-diagnosis of homogeneous systems. Considered in detail the problem of the development of algorithms for system self-test level. The conditions and requirements to obtain the correct diagnosis.

In most extended in Poland PC burners an individual air excess ratio rules an amount of pollution generated, yet there is a lack of method that allows measurement of output parameters. It is therefore necessary to use indirect methods, which could primarily include acoustic, and optical methods. These methods are non-invasive and can provide virtua...

Artykuł dotyczy problemu modelowania procesu powstawania koalicji. Jako rozwiązanie zaproponowano sieci Petriego, ponieważ zapewniają prosty sposób graficznej reprezentacji procedury tworzenia koalicji, pozwalają na łatwe wprowadzanie zmian w procedurze modelowania i wiele wysokiej jakości narzędzi do modelowania. Autorzy nie opisują pełnej procedu...

Autodiagnostyka na poziomie systemu jest szeroko opisywana w literaturze. Celem jest diagnostyka systemy składającego się z jednostek od których wymaga się aby miały możliwość wzajemnego testowania za pośrednictwem dostępnych połączeń. W artykule przedstawiono uproszczony model oparty na diagramie przejść który daje ogólny pogląd, jak sprawdzanie,...

In the paper, a classification method is proposed. It is based on Combined Swarm Negative Selection Algorithm, which was originally designed for binary classification problems. The accuracy of developed algorithm was tested in an experimental way with the use of microarray data sets. The experiments confirmed that direction of changes introduced in...

72 %, що вказує на високу точність запропонованого способу. Ключові слова: алгоритм клонального відбору, радіальна базисна функція, метод " один проти всіх " , прогнозування, вторинна структура білка. In this paper we propose the methodology of team radial-basis networks synthesis for solving the problem of protein secondary structure prediction us...

This paper proposes an approach to solving the problem of image segmentation of cells with high noise level. For this purpose used the technique of dynamic clustering algorithm and clonal selection. The proposed method presupposes the existence of a priori information about the shape of the cell. For a description of the cell boundaries used the mo...

Clustering algorithm based on clonal selection principle named clonal selection clustering algorithm (CSCA) is proposed in this paper. The new proposed algorithm is data driven and self-adaptive, it adjusts its parameters to the data to make the classification operation as fast as possible. The performance of CSCA is evaluated by comparing it with...

In pulverised coal (PC) burners that are most widespread in Poland an individual air excess ratio rules an amount of pollution generated, yet there is a lack of method that allows measurement of output parameters of a burner. It is therefore necessary to use indirect methods, which could primarily include acoustic, and optical methods. These method...

The unique approach to solving the problem of choosing experts groups in the system information-analytical research based on the use of induetive modeling paradigm to solving the cluster analysis tasks is proposed. This approach can also been used in many fields of applied researches pertaining to the problems of structuring, classification, cluste...

The way of the decision of a problem of classification by means of immune algorithm which is based on a principle of cooperation of antibodies of a population is offered. The formal description of structure of an antibody and ways of their association within the limits of a population in the computer network functioning as a unit is given. The way...