《Neural network and fuzzy logic techniques for time series forecasting》.pdf

NEURAL NETWORK FUZZY LOGIC TECHNIQUES FORTIME SERIES FORECASTING GeorgiosLezos, and Monte Tu11 GEORGIOSLEZOS Graduate Student School of Electrical Computer Engineering University of Oklahoma 414 Carson Engineering Center, 202 Wesi doyd, Room 219 N O ~ I ~OK.X I , 73019-1023 PHONE:(405) 325-8620 FAX: (405) 325-7066 E-Mail: pelezos@? MONTE TULL Associate Professor School of Electrical Computer Engineering University of Oklahoma 414 Carson Engineering Center, 202 West Boyd, Room 219 N O ~ XOK.I , 73019-1023 PHONE:(405) 325-4278 FAX: (405) 325-7066 E-Mail: tull@, 191 NEUML NETWORK FUZZY LOGIC TECHNIQUES FOR TIME SERIESFORECASTING ABSTRACT Prediction is a typical example of a generalization problem. The goal of prediction is to accurately forecast the short-term evolution of the system based on past information.Neural network and fuzzylogic techniques are used because they both have good generalization capabilities. The embedding dimension (number of inputs) and the time lag selectionproblem is treated in this paper. It is proposed, that the selection of the appropriate embedding dimension and time lag for the input/output space construction plays an important role in the performance of the above networks. It is shown that the “traditionally accepted” choices for the embedding dimension and time lag are not optimal. The proposed method offers an improvement over the traditionally accepte