30 September 2025 in Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
The paper considers the problems of automating the construction of classification trees based on the scheme of branched feature selection. The object of research is classification trees. The subject of research is methods, algorithms, and schemes for constructing classification trees. The aim of this work is to build an effective method (scheme) for synthesizing classification tree models based on a group assessment of the importance of discrete features within a branched attribute selection. A method for constructing classification trees is proposed, which for a given training sample determines the individual information content (importance) of groups of features (and their combinations) in relation to the initial value of the classification function (data from the training sample). The developed logical tree method, when constructing the next node of the classification tree, tries to identify a group of the most closely interrelated discrete features, this reduces the overall structural complexity of the model (the number of levels of the classification tree), speeds up calculations when recognizing objects based on the model, and also increases the generalizing properties of the model and its enterprise. The proposed scheme for selecting groups of discrete traits allows using the constructed decision tree to assess the informative value (importance) of traits. The developed classification tree method is implemented programmatically and studied when solving the problem of classifying discrete objects represented by a set of features. The conducted experiments confirmed the operability of the proposed mathematical support and allow us to recommend it for use in practice in solving applied problems of classification of discrete objects based on logical classification trees. Prospects for further research may consist in creating a modified method of the logical classification tree by effectively iterating and evaluating sets of elementary features based on the proposed method, optimizing its software implementations, and experimentally studying the proposed method on a wider set of applied problems.
23 November 2021 in Ukrainian Journal of Information Technology
The study is devoted to the development of information technology for forecasting based on time series. It has been found that it is important to develop new models and forecasting methods to improve the quality of the forecast. Information technology is based on the evolutionary method of synthesis of the forecast scheme grounded on basic forecast models. The selected method allows you to consider any number of predictive models that may belong to different classes. For a given time series, the weight coefficients with which the models are included in the resulting forecast scheme are calculated by finding the solution to the optimization problem. The method of constructing the objective function for the optimization problem in the form of a linear combination of forecasting results by basic forecasting models is shown. It is proposed to find the solution to the optimization problem using a genetic algorithm. The result of the method is the forecast scheme, which is a linear combination of basic forecast models. To assess the quality of the forecast, it is suggested to use forecasting errors or forecast volatility calculated as the standard deviation. Forecast quality criteria are selected depending on the context of the task. The use of forecast volatility as a quality criterion, with repeated use of technology, will reduce the deviation of forecast values from real data. The structural scheme of information technology is developed. Structurally, information technology consists of two blocks: data processing and interpretation of the obtained values. The result of the application of the developed information technology is the production rules for determining the predicted value of the studied quantity. Experimental verification of the obtained results was performed. The problem of forecasting the number of religious organizations in Ukraine based on statistical data from 1997 to 2000 has been solved. The autoregression method and the linear regression model were chosen as the basic forecast models. Based on the results of using the developed information technology, the weights of the basic models were calculated. It is demonstrated that the obtained forecast scheme allowed to improve the average absolute percentage error and forecast volatility in comparison with the selected models. Keywords: information technology; time series; forecasting; evolutionary technologies; forecast volatility; synthesis of the forecast scheme.
30 December 2024 in EUROPEAN HUMANITIES STUDIES: State and Society
The paper shows the features of organizing online learning at Uzhgorod National University, presents the technology for creating an online course using the distance learning information platform. Modern education is characterized by a steady trend of transition to digitalization and personification of learning.Modernization of education is currently associated with the introduction of adaptive, practice-oriented and flexible educational programs. At the same time, existing platforms for creating e-learning courses do not yet have the ability to intellectualize the learning process, flexibly adapt the content of education to the individual needs of students, do not contain convenient intelligent tools to support developers of online courses, automate routine operations for structuring educational content. Approaches to the development of e-learning courses are studied, stages of development and requirements for e-learning courses are highlighted, a structural and content model of the e-learning course and a model of data collected in the e-learning process are developed. Based on the developed models, intelligent methods for creating e-learning courses, an algorithm for structuring e-learning course materials, an algorithm for hierarchical classification of training course materials by thematic blocks, and an algorithm for primary ranking of training course elements by complexity and significance are proposed. The organization of an online course and a brief description of the implementation of an online course based on an e-learning system are presented. The presented paper reflects the results of the development and implementation of an online course based on the e-learning methodology. The article presents the development of an intelligent training course using data mining mechanisms. Efficient intelligent data processing algorithms underlie the development of adaptive online learning technologies implemented in educational processes. The basic principles of synthesizing a system for evaluating the quality of online courses are developed.