Aleksandr Gozhyj

The article proposes a methodology for modeling and forecasting economic, financial and environmental processes, based on the principles of system analysis and combined models, including linear and non-linear regression models, as well as probabilistic models in the form of Bayesian networks. The basis of the methodology is tracking the computation...

The article describes a hybrid power plant control system based on machine learning technologies. The hybrid power plant is based on solar panels and a wind generator. This article suggests using a neural network to track the maximum power point for more efficient charge control. This is a method of regulating the battery charge to increase the amo...

The article discusses issues related to the construction and implementation of search web services. Algebra for modeling and building web services is presented. As the basic operations for algebra are used: sequence, alternative selection and cycle. In addition, combined operations are determined based on the basic ones. The operations were chosen...

The article discusses the methodology for solving forecasting problems using machine learning methods. The issues of accounting and correct processing of nonlinear non-stationary processes in the problems of modeling and forecasting time series in various fields are considered. The stages and methods of solving machine learning problems are analyze...

The article provides information on the modification of the Lauritzen-Spiegelhalter (LS) method for constructing a probabilistic inference in the Bayesian network. Modification of the method consists in a new way of filling tables of conditional probabilities. The method consists of two stages: the first stage – the construction of a combined tree,...

The article discusses the algorithms of the Monte Carlo method with Markov chains (MCMC). These are the Metropolis-Hastings and Gibbs algorithms. Descriptions and the main features of the algorithms application are given. The MCMC methods are developed to model sets of vectors corresponding to multidimensional probability distributions. The main ap...

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...

This study explores a method for managing web content based on intelligent technologies, as a stage of the content life cycle in e-commerce systems. The method of content management describes the processes of creating web resources and simplifies the technology of managing web resources in conditions of uncertainty. Also, the main problems of e-com...

The paper describes the integrated processing method of heterogeneous information resources of web systems, which allows for further integration and management. Our method involves the decomposition of the overall process on subprocesses of value integration, data syntax, semantics, and structure. The advantage of this approach to integration proce...

The article deals with the issues of handling uncertainties in the problems of modeling and forecasting dynamic systems within the framework of the dynamic planning methodology. To analyze and take into account possible structural, statistical and parametric uncertainties, the Kalman filter, various methods for calculating missing data, numerous me...

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...