This document discusses simulated annealing and genetic algorithms for solving optimization problems. It includes code for implementing simulated annealing with a traveling salesman problem. It also includes code for implementing a genetic algorithm with classes for individuals, populations, crossover, mutation, selection and fitness evaluation. The genetic algorithm code finds a solution to a problem by evolving a population of individuals over generations.

1. Inteligência Artificial
Aula 4
Nauber Gois

3. SIMULATED ANNEALING

4. MODELAGEM DO PROBLEMA

5. MODELAGEM DO PROBLEMA

6. public class SimulatedAnnealing {
private static Travel travel = new Travel(10);

7. public static double simulateAnnealing(double startingTemperature, int numberOfIterations, double
coolingRate) {
System.out.println("Starting SA with temperature: " + startingTemperature + ", # of iterations: " +
numberOfIterations + " and colling rate: " + coolingRate);
double t = startingTemperature;
travel.generateInitialTravel();
double bestDistance = travel.getDistance();
System.out.println("Initial distance of travel: " + bestDistance);
Travel bestSolution = travel;
Travel currentSolution = bestSolution;
for (int i = 0; i < numberOfIterations; i++) {
if (t > 0.1) {
currentSolution.swapCities();
double currentDistance = currentSolution.getDistance();
if (currentDistance < bestDistance) {
bestDistance = currentDistance;
} else if (Math.exp((bestDistance - currentDistance) / t) < Math.random()) {
currentSolution.revertSwap();
}
t *= coolingRate;
} else {
continue;
}
if (i % 100 == 0) {
System.out.println("Iteration #" + i);
}
}
return bestDistance;
}

10. Main APP

11. Algoritmos Genéticos

13. @Data
public class Individual {
protected int defaultGeneLength = 64;
private byte[] genes = new
byte[defaultGeneLength];
private int fitness = 0;

14. public Individual() {
for (int i = 0; i < genes.length; i++) {
byte gene = (byte)
Math.round(Math.random());
genes[i] = gene;
}
}

15. protected byte getSingleGene(int index) {
return genes[index];
}
protected void setSingleGene(int index, byte value) {
genes[index] = value;
fitness = 0;
}
public int getFitness() {
if (fitness == 0) {
fitness =
SimpleGeneticAlgorithm.getFitness(this);
}
return fitness;
}

16. @Override
public String toString() {
String geneString = "";
for (int i = 0; i < genes.length; i++) {
geneString += getSingleGene(i);
}
return geneString;
}

17. public class Population {
private List<Individual> individuals;
public Population(int size, boolean createNew) {
individuals = new ArrayList<>();
if (createNew) {
createNewPopulation(size);
}
}
protected Individual getIndividual(int index) {
return individuals.get(index);
}
protected Individual getFittest() {
Individual fittest = individuals.get(0);
for (int i = 0; i < individuals.size(); i++) {
if (fittest.getFitness() <= getIndividual(i).getFitness()) {
fittest = getIndividual(i);
}
}
return fittest;
}

18. private void createNewPopulation(int size) {
for (int i = 0; i < size; i++) {
Individual newIndividual = new Individual();
individuals.add(i, newIndividual);
}
}
}

19. public class SimpleGeneticAlgorithm {
private static final double uniformRate = 0.5;
private static final double mutationRate = 0.025;
private static final int tournamentSize = 5;
private static final boolean elitism = true;
private static byte[] solution = new byte[64];

20. public boolean runAlgorithm(int populationSize, String solution) {
if (solution.length() != SimpleGeneticAlgorithm.solution.length) {
throw new RuntimeException("The solution needs to have " +
SimpleGeneticAlgorithm.solution.length + " bytes");
}
setSolution(solution);
Population myPop = new Population(populationSize, true);
int generationCount = 1;
while (myPop.getFittest().getFitness() < getMaxFitness()) {
System.out.println("Generation: " + generationCount + " Correct
genes found: " + myPop.getFittest().getFitness());
myPop = evolvePopulation(myPop);
generationCount++;
}
System.out.println("Solution found!");
System.out.println("Generation: " + generationCount);
System.out.println("Genes: ");
System.out.println(myPop.getFittest());
return true;
}

21. public Population evolvePopulation(Population pop) {
int elitismOffset;
Population newPopulation = new Population(pop.getIndividuals().size(), false);
if (elitism) {
newPopulation.getIndividuals().add(0, pop.getFittest());
elitismOffset = 1;
} else {
elitismOffset = 0;
}
for (int i = elitismOffset; i < pop.getIndividuals().size(); i++) {
Individual indiv1 = tournamentSelection(pop);
Individual indiv2 = tournamentSelection(pop);
Individual newIndiv = crossover(indiv1, indiv2);
newPopulation.getIndividuals().add(i, newIndiv);
}
for (int i = elitismOffset; i < newPopulation.getIndividuals().size(); i++) {
mutate(newPopulation.getIndividual(i));
}
return newPopulation;
}

22. private Individual crossover(Individual indiv1, Individual
indiv2) {
Individual newSol = new Individual();
for (int i = 0; i < newSol.getDefaultGeneLength(); i++) {
if (Math.random() <= uniformRate) {
newSol.setSingleGene(i, indiv1.getSingleGene(i));
} else {
newSol.setSingleGene(i, indiv2.getSingleGene(i));
}
}
return newSol;
}
private void mutate(Individual indiv) {
for (int i = 0; i < indiv.getDefaultGeneLength(); i++) {
if (Math.random() <= mutationRate) {
byte gene = (byte) Math.round(Math.random());
indiv.setSingleGene(i, gene);
}
}
}

24. private Individual tournamentSelection(Population pop) {
Population tournament = new Population(tournamentSize, false);
for (int i = 0; i < tournamentSize; i++) {
int randomId = (int) (Math.random() *
pop.getIndividuals().size());
tournament.getIndividuals().add(i, pop.getIndividual(randomId));
}
Individual fittest = tournament.getFittest();
return fittest;
}
protected static int getFitness(Individual individual) {
int fitness = 0;
for (int i = 0; i < individual.getDefaultGeneLength() && i <
solution.length; i++) {
if (individual.getSingleGene(i) == solution[i]) {
fitness++;
}
}
return fitness;
}

25. protected int getMaxFitness() {
int maxFitness = solution.length;
return maxFitness;
}
protected void setSolution(String newSolution) {
solution = new byte[newSolution.length()];
for (int i = 0; i < newSolution.length(); i++) {
String character = newSolution.substring(i, i + 1);
if (character.contains("0") || character.contains("1")) {
solution[i] = Byte.parseByte(character);
} else {
solution[i] = 0;
}
}
}

79. Agentes Inteligente

80. Requisitos para um agente inteligente

81. public class BookBuyerAgent extends Agent {
protected void setup() {
// Printout a welcome message
System.out.println(“Hello! Buyer-agent
“+getAID().getName()+” is ready.”);
}
}

82. SUGESTÃO

83. Próxima Aula Ant Colony