2010 China-Ireland International Conferenceon Information and CommunicationsTechnologies (CIICT2010 E-BOOK)

Wuhan,China,10.10-10.11,2010

ISBN: 978-1-935068-30-3 Scientific Research Publishing, USA

E-Book 200pp Pub. Date: October 2010

Category: Engineering

Price: $40

Title: Investigating the Effect of Stochastic Replacement Rates on GeneRepair Templates
Source: 2010 China-Ireland International Conferenceon Information and CommunicationsTechnologies (CIICT2010 E-BOOK) (pp 81-85)
Author(s): Donagh Hatton, Dept. of Computer Science; National University of Ireland, Maynooth; Co. Kildare, Ireland
Diarmuid P. O’ Donoghue, Dept. of Computer Science; National University of Ireland, Maynooth; Co. Kildare, Ireland
Amy Fitzgerald, Dept. of Computer Science; National University of Ireland, Maynooth; Co. Kildare, Ireland
Abstract: This paper examines modifications to a genetic repair technique that allows an evolutionary algorithm to handle constraints. In 2005, Lolle et al published controversial findings showing that the model plant Arabidopsis thaliana is able to repair genetic errors using information inherited from ancestors other than the immediate parents (non-Mendelian inheritance). It has previously been shown that a genetic repair operator (GeneRepair) can be used to repair invalid individuals in an evolutionary algorithm and that the grandparent template outperforms the parent template. We examine a greater variety of template ancestries, including low and high template replacement rates. Best results were produced using the stochastic replacement strategy with low template replacement rates.
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top