3345

2934

كارشناسي ارشد

هوش مصنوعي

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1385

دوازده، 103، [ II ] ص.: مصور، جدول، نمودار

جواد عسكري

پروفسور كارولوكس

فارسي به انگليسي

محمد داورپناه جزي، توكلي

1396/10/27

كتابنامه

برق و كامپيوتر

مهندسي برق و كامپيوتر

ID2934

به فارسي و انگليسي : قابل رؤيت در نسخه ديجيتال

AbstractApplying intelligent methods for analysis and decision making is becoming popular Modern computers with powerful processors have enabled machine learningalgorithms to be used for system identification or at least their governing concepts One common problem in decision making is the prediction of future behavior of asystem To have a good and accurate prediction first we need to be assured of thepredictability of the system In this thesis after being assured of the predictability ofsystem using intelligent tests the possibility of random behavior is rejected Usedtests include independence test probability of return to zero first return to zero andBrock Dechert Scheinkman algorithm In these tests we compare system outputs vs random walks outputs Then discussion is continued about volatility and chaos to finda reason for rejection of random outputs and predictability Using Singular SpectrumAnalysis and predicting each component using neural networks the prediction isperformed Locally linear fuzzy neural networks show the best result To make abetter prediction we should select the range of recurrence False Nearest Neighborsand Neighbors Cardinality methods are used to select these limits Some foreignexchange rates as important macroeconomic indices are chosen as the test bench foralgorithms The results of this research show non random and deterministic data andalso lower sensitivity to initial conditions in these macroeconomic time series

جواد عسكري

پروفسور كارولوكس

محمد داورپناه جزي، توكلي