Time series modelling and prediction using fuzzy trend information
暂无分享,去创建一个
Thispaperpresentsanovelapproachto modellingtimeseriesdatasetsusingfuzzy trendinformation. A time series is describedusingnaturallinguistic termssuchas rising more steeplyandfalling lesssteeply. Thesenaturalshape descriptorsenableus to producea glassboxmodelof the series.Thelinguistic shapedescriptorsarerepresentedin our systemby a new featurecalledthe trendfuzzyset. All trend fuzzysetsare derived from a window on the time seriesandassuchdescribethe shapeof the serieswithin that window. Eachwindow canhave membershipin any numberof differenttrendfuzzysets. Predictionusingthese trendfuzzysetsis performedusingtheFril evidentiallogic rule. Examplesof seriespredictionareshown usingsine waveandsunspotime seriesdata.
[1] Jf Baldwin,et al. Recurrent fuzzy rules for belief updating , 1998 .
[2] D. Rumelhart,et al. Predicting sunspots and exchange rates with connectionist networks , 1991 .
[3] James F. Baldwin,et al. Semantic unification with fuzzy concepts in FRIL , 1992, Int. J. Intell. Syst..
[4] Trevor P Martin,et al. Fril- Fuzzy and Evidential Reasoning in Artificial Intelligence , 1995 .