Browsing by Author "Ramos, M."

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    A new identification method for use in nonlinear prediction
    (IOS PRESS, 2001) Montoya, F.; Cipriano, A.; Ramos, M.
    This paper presents a new identification method for fuzzy models used in nonlinear prediction. The structure and parameters of the fuzzy model are obtained, using input-output data, by minimization of the prediction error. The predictive capacity of the fuzzy model is compared with other linear and non-linear models analyzing an illustrative example. The results show that the new method presents a better behavior.
  • Thumbnail Image
    Item
  • Thumbnail Image
    Item
    Evidence of hysteresis in propofol pharmacodynamics
    (2018) Sepúlveda, P.O.; Carrasco, V.E.; Tapia, L.F.; Ramos, M.; Cruz, F.; Conget, P.; Olivares, Q.F.; Cortínez Fernández, Luis Ignacio
  • No Thumbnail Available
    Item
    Fuzzy modelling of pulp density in a mineral grinding plant
    (IEEE, 1994) Cipriano, Aldo; Ramos, M.; Munoz, C.; Guarini Hermann, Marcelo Walter; Guesalaga, A.
    This paper describes an identification algorithm of fuzzy models and its application to the modeling of the pulp density in a mineral grinding plant. The parameters of the fuzzy model are estimated using information obtained from a process simulator. The performance of the fuzzy model is only slightly superior to that of a conventional linear model
  • No Thumbnail Available
    Item
    One day ahead load forecasting by recurrent neural networks
    (C R L PUBLISHING LTD, 1997) Prina, J.; Cipriano, A.; Cardenoso, V.; Alonso, L.; Olmedo, J.C.; Ramos, M.
    In recent years, many applications of neural network methodologies to power system problems have been reported. Among them, short term load forecasting has been one of the most popular. Multilayer perceptron networks have constituted the preferred architecture, achieving successful results. However this network model generally fails to deal with the temporal characteristics of the load signal, being more suitable for static pattern recognition tasks. Dynamic or recurrent networks have shown better capabilities for time signals modeling and forecasting. This paper presents the application of a recurrent network model, which uses a very limited amount of data, to the load forecasting problem. Particularly, the Elman, recurrent model was applied to the 24 hour ahead load forecasting for the Chilean Central Interconnected System (SIC). The load values are considered as a time series, taking advantage of the temporal processing capabilities of this neural network model.