Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций
Конференция: Applied Methods of Statistical Analysis. Statistical Computation and Simulation - AMSA'2019; Novosibirsk; Novosibirsk
Год издания: 2019
Ключевые слова: identi cation, forecasting, mathematical modeling, T-models, T-processes
Аннотация: The article is devoted to the construction of a new class of models in the context of lack of priori information. It centers around multidimensional inertialess objects, when the components of the output vector are stochastically dependent, but the nature of this dependence is unknown. In the process of building a model it is necesПоказать полностьюsary to accomplish the solution of implicit functions when the inputs and outputs vectors are non-linear. It should be noted that the form of these functions with an accuracy of the parameters vector is unknown. In this regard, it is necessary to use T-models, when the prediction of output variables is carried out using known input.
Журнал: Applied Methods of Statistical Analysis. Statistical Computation and Simulation - AMSA'2019
Номера страниц: 299-305
Место издания: Novosibirsk
Издатель: Новосибирский государственный технический университет