Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 5

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  metoda GMDH
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
PL
W artykule przedstawiono zalety i ograniczenia metody predykcji procesów złożonych reprezentowanych przez szeregi czasowe, opartej na metodzie GMDH i korzystającej z właściwości funkcji wrażliwości. Użycie funkcji wrażliwości ma zapewnić zwiększenie precyzji predykcji w stosunku do metody podstawowej, dzięki informacjom o kierunku i szybkości zmian wartości zmiennych szeregu, zawartych w funkcjach wrażliwości. Na wejściu potrzebna jest niewielka ilości danych (siedem). Metoda wykazuje zwiększenie skuteczności w stosunku do GMDH nawet przy wykorzystaniu wielomianów Kołmogorowa-Gabora jedynie drugiego stopnia.
EN
In this paper, there are presented the advantages and limitations of the prediction method of complex processes (presented in the form of the time series) which is based on the Russian researcher A. G. Ivakhnenko-GMDH method and uses the properties of the first and second-order sensitivity functions. Sensitivity function is used to ensure an increase of the precision of the prediction in relation to the basic method, thanks to the information about direction and changes in the values of the time series variables and the speed of these changes included in them. We need only small amount of input data (seven) opposed to the other regression methods using large amounts of information in order to study the statistical relationship between time series variables. On the basis of several alternative (partial) models we receive several outputs for every time-series variable, from which we choose the best (terms previously fixed criteria) [1]. Figures 1, 4, 6 and 7 show the results of the prediction of the best partial models for one or two steps forward. Others show values of the sensitivity functions indicating an influence on the studied variables. Results of the prediction without using the sensitivity function differ significantly from the expected values, therefore, are not shown in the drawings. The method shows an increase in efficacy in comparison with GMDH even for second degree Kolomogorov-Gabor polynomials.
EN
In this article we will try to prove that the prediction of behaviour of complex objects belongs to that part of contemporary Informatics, which deals with intelligent data analysis on large datasets. We note that the methods based on the creation of extrapolation functions are shown to be most effective for the prediction of the behaviour of objects, in particular, complex objects. Among these methods, one ofthe most promising is the Group Method of Data Han-dling (GMDH), which despite some incomenience has many advantages for effective exploration of knowledge in inaccurate and changing conditions during the tests.
PL
W niniejszym artykule dokonano próby, z punktu widzenia retrospekcji historycznej, przedstawienia korzeni problematyki badan systemów złożonych sztucznego pochodzenia i udowodnienia tezy o tym, e badania złoonych obiektów i systemów oparte na koncepcji tak zwanej symulacji indukcyjnej udostepniają badaczom efektywne sposoby dokładnego odzwierciedlenia zasadniczych cech omówionych obiektów i systemów. Dla ilustracji podejścia opartego na koncepcji symulacji indukcyjnej wybrano metode grupowania argumentów (GMDH).
EN
The complex system concept is discussed from a historical viewpoint. It is shown that the concept has an inter-disciplinary meaning and it is amenable to theoretical generalization on the systems analysis level. A possible definition of the complex system concept is presented as well as the conclusion on the effectiveness of the use of inductive simulation methods to the study of the mentioned systems are discussed. The GMDH method is analyzed as an example of an inductive approach suitable for the solution of problems of prediction of complex system behavior.
EN
The paper presents the results of computer simulations performed using the historical quotes on several securities (WIG20, S&P500, Dow Jones, DAX, EUR/USD, gold, oil, etc.) in order to analyse the possibility of finding such variables, that can be explained in terms of the others better, than the rest. It is assumed, that the ultimate goal of every investment strategy is finding the opportunity of gaining a financial profit (always considering the risk). Such opportunity is being sought by investigating the possibility of using each variable (each security) in turn as the one to be predicted. In order to reach that goal, authors use several variants of one of the algorithms belonging to the. Group Method of Data Handling (GMDH), namely the combinatorial algorithm. The results reveal some interesting features of regression models, indicating the prospect of further applications of the method.
EN
This paper concerns the problem of parameters estimation for a certain model, aiming at the approximation of output variable at the acceptable accuracy level. What distinguishes the way this common scientific task is here dealt with, is the usage of GMDH - Group Method of Data Handling (or more specifically the GMDH-based algorithm developed by the authors), which allows for simultaneous determination of both the structure and numerical characteristics of the model. The feature space under consideration is the matrix of repetitively observed attributes, describing the physical characteristics of voice samples, collected in order to determine the frequency of laryngeal tone for the purpose of medical diagnosis.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.