research centers


Search results: Found 2

Listing 1 - 2 of 2
Sort by

Article
Optimal Population Size for Genetic Algorithm Using Fuzzy System
أفضل حجم مجتمع للخوارزمية الجينية باستخدام النظام المضبب

Author: Emad S. Jabber عماد شعـلان جبر
Journal: basrah journal of science البصرة للعلوم ISSN: 18140343 Year: 2007 Volume: 25 Issue: 2A english Pages: 66-77
Publisher: Basrah University جامعة البصرة

Loading...
Loading...
Abstract

A genetic algorithm (GA) uses the idea of biological evolution to seek good solutions to problems with very large search spaces. It has the following parameters: population size, crossover rate, and mutation rate. The selection of the initial parameters for a GA is very difficult. Some attempts to find optimal combination of parameters used trial and error methods or combination approaches, while others used a GA to find optimal parameters for another GA.The current work uses fuzzy system to determine optimal population size for any problem which is used the Genetic Algorithm. Two combinatorial problems with a large search space are used to test the effectiveness of the current work. The results are validated and GA is shown to be effective for the tested problems

تستخدم الخوارزمية الجينية فكرة التطور البايولوجي للبحث عن حلول جيده للمسألة مع مجالات بحثية واسعة ،حيث إنها تمتلك المعلمات التالية : حجم المجتمع، معدل التزاوج و معدل الطفرة . تعتبر عملية اختيار المعلمات الابتدائية للخوارزمية الجينية صعبة جدا، حيث هنالك بعض المحاولات لإيجاد التوافق الأمثل للمعلمات منها استخدام طريقة التجربة والخطأ وطرق توافقية، بينما تستخدم طرق أخرى الخوارزمية الجينية لإيجاد المعلمات المثلى لخوارزمية جينية أخرى. العمل الحالي يستخدم النظام المضبب لتحديد أمثل حجم مجتمع لأي مسالة تستخدم الخوارزمية الجينية. استخدمت مسألتان توافقيتان تمتلكان فضاء بحث واسع لاختبار تأثيرات العمل الحالي، حيث أظهرت الخوارزمية الجينية فاعلية للمسائل التي تم اختبارها و كانت النتائج قانونية


Article
SIMULATING AN EVOLUTION STRATEGY TO FORECAST TIME SERIES ARMA(1,1) MODEL

Author: Basa’d Ali Hussain
Journal: Al-Nahrain Journal of Science مجلة النهرين للعلوم ISSN: (print)26635453,(online)26635461 Year: 2007 Volume: 10 Issue: 1 Pages: 167-175
Publisher: Al-Nahrain University جامعة النهرين

Loading...
Loading...
Abstract

This paper presents a multi-member evolution strategy to forecast future value of observed time series model. The proposed method is simple and straight forward and doesn't required any problem specific parameter tuning of the problem. The experiments designed based on simulate for different values of sample size (n=25,50,100),model parameters set ( ) and set to ( ) and use lead time for forecasting future value equal to (l=1,2,3).The value of take equal to (15,100) beside this, there is anther experiment designed for simulating one of method which is known as Box –Jenkins with same values of sample size, model parameters and leads time(l) for number of replicate (RR=1000). Results of this study has cleared by numbers of figures and tables, which are made to clear compression between ES-algorithm and B.J method based on computing values of FMSE (Forecasting Mean Square Error ) & Thiels' (U- statistic) ,statistics used as tools to measures reliability of ES- algorithm and also used to clear accuracy of ES algorithm results. Table(1), tables (2-7) and figures (4 -9) results of statistics show the reliability of algorithm to producing individuals which give reasonably predictions of future values of time series for different values of sample size and lead time values of model parameters.

Listing 1 - 2 of 2
Sort by
Narrow your search

Resource type

article (2)


Language

English (1)


Year
From To Submit

2007 (2)