Department of Electronic Engineering NUIG

1
Department of Electronic Engineering NUIG

• Direct Evolution of Patterns using Genetic
  Algorithms

By John Brennan Supervisor John Maher
2
Overview

• Project Specifications
• Introduction to Genetic Algorithms
• Flowchart of a Genetic Algorithm
• Implicit Embryogeny
• Program Design
• GUI Design
• GA Parameters

3
Project Specifications

• Review of Implicit Embryogeny proposed by Kumar
  plus 2 other authors
• Write a Java GA to solve 1s max problem
• Demonstrate some Java 2D GUI features
• Extend the developed GUI to include GA
  functionality
• Design and verify demonstrator of Implicit
  Embryogeny
• Include Implicit Embryogeny within the developed
  GUI
• Add additional frame to user to define target
  phenotype
• Compare and contrast directly evolved patterns
  with implicitly derived patterns
• Further modify the GUI to integrate in the DEV1
  algorithm

4
Introduction to Genetic Algorithms

• A Genetic Algorithm is a programming technique
  that imitates biological evolution to solve
  complex problems
• A GA performs the following
• It takes a set of potential solutions (a
  population)
• Using a selection mechanism new offspring are
  created from nominated parents
• Genetic Operators are carried out on the
  offspring
• The fitness of the modified offspring is
  evaluated
• New offspring replaces previous population (a
  generation)

5
Flowchart of a Genetic Algorithm
Genome String Fitness
A 1011 127
B 1111 255
C 1010 87
Evaluated Offspring
Generate Parents
Population
F() Fitness Function
Selection Mechanism - Roulette Wheel
- Tournament
Altered Offspring
Generate Offspring
Genetic Operators
6
Implicit Embryogeny

• An Embryogeny is a process of growth where
  genotypes (evolved parameter values) are mapped
  onto phenotypes (solutions to problems)
• Implicit embrogenies uses interacting rules to
  solve complex problems
• The flow of activation is dynamic, parallel and
  adaptive
• This project will use a developmental encoding
  coding to evolve tessellating tiles similar to
  work completed by Kumar and Bentely
• The scalability problem will also be demonstrated
  as the problem size increases (by increasing the
  size of the phenotype grid)

7
Program Design

• GUI to be visually impressive and user friendly
• Execute Genetic Algorithms and display results in
  real time
• Include frames to perform the following
• Allow user to graphically view GA progress in
  real time
• User can input GA parameters
• Allow user to define target phenotype
• Integrate DEV1 Algorithm
• To be programmed/designed in Java using J2SE and
  Java Swing

8
GUI Design

• The main display of this program illustrates the
  ideal evolved tessellated tiles vs. the current
  output of the processing Genetic Algorithm
• The progress of the evolving pattern will be
  displayed in real time as the GA is executed

9
GA Parameters

• As explained, the user will be able to input
  specific parameters for the Genetic Algorithm
• The GA will be executed according to these
  constraints
• Further development will integrate DEV1 Algorithm