3758

3552

كارشناسي ارشد

سيستم هاي اقتصادي - اجتماعي

اصفهان : دانشگاه صنعتي اصفهان ،دانشكده صنايع و سيستمها

1386

ده ،111 ،[II]ص.:مصور،نمودار،جدول

ص.ع. به فارسي و انگليسي

مهندسي صنايع و سيستم ها

ID3552

به فارسي و انگليسي :قابل رؤيت در نسخه ديجيتال

AbstractIn this thesis we develop a version of minority game Minority game as an agent based modelhas been introduced for analyzing some complicated systems The model is able to recognizethe agents in different environments such as financial markets road traffic and transferringthe packets through the Internet and variety other of cases It is a competitive mechanism for determining how to take advantage of limited resources Inthe standard form the agents in minority game make decisions using strategy tables Thesetables are developed based on the history of the market In the standard form of minoritygame the learning of agents takes place through the process of virtual rating We equipped theagent of to two layer perceptron neural networks instead of strategy tables Back propagationalgorithm is used as the method of learning of the neural network Eventually an analogysurvey of the agents performance is carried out between the previous and the new Resultsdemonstrate that applying two layer perceptron neural networks yields better decisionsaccording to reduced agent attendance and that it enhances performance averages

محمد رضا زماني

اكبر توكلي

رضا حجازي