Model-Free Forecasting of Random Processes
by Complexing Their Analogues

A. G. Ivakhnenko*, N. N. Bogachenko**, and Li Tyan Min***

* Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, pr. Akademika Glushkova 20, Kiev,
252207 Ukraine

** Research Institute of Coal Fields, pr. Stachki 1, Rostov-on-Don, 344010 Russia

*** University of Science and Technology, Hausgong, Ukkhan, Hubei, China

Abstract—The problem of optimizing the analogue complexing algorithm for forecasting random processes is
discussed. Quite accurate forecasts can be made by sorting discrete values of: (1) the number of factors, (2) the
number of instants of time taken into account, (3) the number of analogues being complexed, and (4) values of
analogue weighting coefficients. The accuracy can be increased by using neural networks with active neurons.

Pleiades Publishing home page | journal home page | top

If you have any problems with this server, contact webmaster.