Search academic texts

Information × Registration Number 0224U001228, 0121U107499 , R & D reports Title Development of methods and tools for analysis and prediction of dynamic behavior of nonlinear objects popup.stage_title Head Liovkin Valerii M., Registration Date 19-01-2024 Organization Zaporizhzhya Polytechnic National University popup.description2  ): Intelligent systems, supporting decision-making, should not only find patterns in the available data, but also predict the future state of objects, characterized by the lack of a fully formalized mathematical model, which in turn is due to the large number of features, complex dependences between features and output parameters, nonlinearity. Therefore, the logical way is to create models for predicting dynamic behavior based on observations of complex objects, a promising solution for which is the usage of machine learning methods. But such a solution is simultaneously highly iterative, often has a low level of data generalization and logical transparency of created models, and observational data may be expanded in the future by new data which contradict the created model, thus requiring re-synthesizing the predictive model, so methods are highly resource-intensive, complicating its application. The application of a systems approach allows to define solving the urgent scientific and applied problem of the development of new methods for predicting the dynamic behavior of nonlinear objects simultaneously based on machine learning methods and parallel computing to eliminate these shortcomings. Product Description popup.authors Golub Tetiana V Kolpakova Tetiana O. Leoshchenko Serhii D. Lovkin Vаlerii M. Olenchenko Ihor I popup.nrat_date 2024-01-19 Close