Manual jclec

Knowledge Discovery and Intelligent Systems

JCLEC 4 Tutorial

CONTENTS

1 Introduction 1.1 What is JCLEC? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.2 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1.3 Class hierarchy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

5 5 6 7

2 Genetic algorithms using binaryencoding: Knapsack problem 2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2.2 Problem definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

9 9 9

2.3 Genetic algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.4 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.5 Results. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

3 Genetic algorithms using integer encoding: Traveling Salesman Problem 21 3.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 3.2 Problem definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 3.3 Genetic algorithm . . . . . . . . . . . . . . . . . . . . . .. . . . . . . . . . 23 3.4 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 3.5 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30

4 Genetic algorithms using real encoding: Optimization of real functions 35

4

CONTENTS 4.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 4.2 Problemdefinition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 4.3 Genetic algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 4.3.1 4.3.2 4.3.3 4.3.4 Common configuration . . . . . . . . . . . . . . . . . . . . . . . . . 36 Generational genetic algorithm . . . . . . . . . . . . . . . . . . . . 37 Steady state genetic algorithm . . . . . . . . . . . . . . . . .. . . . 37 Multimodal algorithms . . . . . . . . . . . . . . . . . . . . . . . . . 38

4.4 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 4.5 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 4.5.1 4.5.2 4.5.3 4.5.4 4.5.5 4.5.6 4.5.7 Generational genetic algorithm . . . . . . . . . . . . . . . . . . . . 42 Steady stategenetic algorithm . . . . . . . . . . . . . . . . . . . . . 45 Multimodal algorithms . . . . . . . . . . . . . . . . . . . . . . . . . 46 Global results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 Generational vs Steady State . . . . . . . . . . . . . . . . . . . . . 52 Sharing vs Clearing . . . . . . . . . . . . . . . . . . . . . . . . . . . 53 General comparison . . . . . . . . .. . . . . . . . . . . . . . . . . . 53

4.6 Study of effect of the alpha value in BLX-α crossover operator . . . . . . . 54 5 Genetic programming: a symbolic regression problem 55

5.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 5.2 Problem definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 5.3 Implementation . . . . . . . . . .. . . . . . . . . . . . . . . . . . . . . . . 56 5.4 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63

1. INTRODUCTION 1.1 What is JCLEC?

JCLEC is a software system for Evolutionary Computation (EC) research, developed in the Java programming language. It provides a high-level software environment to do any kind of Evolutionary Algorithm (EA), withsupport for genetic algorithms (binary, integer and real encoding), genetic programming (Koza style, strongly typed, and grammar based) and evolutionary programming. JCLEC architecture follows strong principles of object oriented programming, where abstractions are represented by loosely coupled objects and where it is common and easy to reuse code. JCLEC provide an EC environment that its main...