What is it about?
A new adaptation technique based on diversity control for self-adaptive Differential Evolution Algorithm. The self adaptation is done using fuzzy system.
Featured Image
Why is it important?
Generally, Differential Evolution suffers from premature convergence or stagnation. In order to avoid this the diversity of the population must to controlled, so the population is able to escape the local optimum. Diversity control can be achieved by controlling the crossover rate and scaling factor to balance exploration and exploitation.
Perspectives
Balance between exploration and exploitation is very important in DE to avoid premature convergence. In this work a methodology using fuzzy systems is used to achieve the balance. Thus the proposed algorithm overcomes stagnation of population and provides better results for a range of varied benchmark functions.
Dr MIruna Joe Amali
KLN College of Engineering
Read the Original
This page is a summary of: Fuzzy logic-based diversity-controlled self-adaptive differential evolution, Engineering Optimization, August 2013, Taylor & Francis,
DOI: 10.1080/0305215x.2012.713356.
You can read the full text:
Contributors
The following have contributed to this page
