Fuzzy Time Series Model Based On Autocorrelation Theory And Evidential Theory

Fuzzy Time Series Model(FTSM),which has been applied in many fields,is one of effective method to deal with the uncertainty and fuzzy problems.Nowadays,many researchers have proposed many ways to improve the FTSM from different angle such as the partition of the domain,how to build the Fuzzy Logical Rules Matrix,the order of model and so on.This paper focuses on the Fuzzy Time Series Model from the following angles.First,The choice of the order of Fuzzy Time Series model has,to some extent,an influence on the accuracy of the forecasted result.This paper establishes relationship between Autoregressive Model and Fuzzy Time series model so as to apply autocorrelation theory to the selection of the order of Fuzzy Time Series Model(FTSM).Therefore,instead of listing the forecasted results generated by Nth order model respectively,we can choose the order of FTSM with a simpler method.In order to verify the effectiveness of the proposed method,the data of macula from 1701 to 1722 has been used in the experiment.It turns out the new method is an effective way to select the order of FTSM.In addition to,this paper is going to study the multi-variables one order FTSM based on the Evidence Theory,which is good at dealing with infomation infusion problems.So we can bring the information the factors give us together to forecast the future trend of the data.As for the Evidence Theory,we focus on the value of each evidences and in order to measure the weight of evidences,Bhattacharyya coefficient is applied to compute the similarity between evidences so that we can change them into the weight of evidence.Then we build a multi-variable fuzzy time series model by combining the modified evidence theory and a numerical example is used to verify the availability of the new model.