public static void RunMain()
{
int maxIterations = 2000;
int dimension = 2;
int popSize = 200;
double[] lowerBounds = new double[] { -2.048, -2.048 };
double[] upperBounds = new double[] { 2.048, 2.048 };
SimpleParticle finalSolution;
ParticleSwarm <SimpleParticle> .Solve(popSize, dimension, (solution, constraints) =>
{
// this is the Rosenbrock Saddle cost function
double[] positions = solution.Positions;
double x0 = positions[0];
double x1 = positions[1];
double cost = 100 * Math.Pow(x0 *x0 - x1, 2) + Math.Pow(1 - x0, 2);
return(cost);
}, lowerBounds, upperBounds, out finalSolution, maxIterations);
}
private void Run(object payload)
{
var castedPayload = payload as AsyncPsoPayload;
if (castedPayload == null)
throw new Exception("Niepoprawny typ parametru");
var settings = castedPayload.Settings;
Function mathFunction;
switch(settings.MathFunction)
{
case Enums.MathFunctions.Ackley:
mathFunction = new Ackley();
break;
case Enums.MathFunctions.Rastrigin:
mathFunction = new Rastrigin();
break;
case Enums.MathFunctions.Rosenbrock:
mathFunction = new Rosenbrock();
break;
default:
throw new ArgumentException("Wskazana funkcja nie została zaimplementowana");
}
ParticleSwarm p = new ParticleSwarm(settings.ParticleCount,
mathFunction,
settings.Inertia,
settings.COneValue,
settings.CTwoValue,
settings.MaxSpeed,
settings.Tightness,
settings.TightnessLevel);
if (settings.IsLiczbaIteracji)
{
List<DataPoint> bestPos = new List<DataPoint>();
for (int i = 0; i < settings.IterationCount; i++)
{
if (settings.IsLivePlot && bestPos.Count == settings.IterationCount / 10)
{
castedPayload.UpdatePlotFunction(bestPos);
bestPos = new List<DataPoint>();
}
bestPos.Add(new DataPoint(i, p.BestFitness));
p.Iteration();
}
if (bestPos.Count > 0)
castedPayload.UpdatePlotFunction(bestPos);
}
else
{
var isRunning = true;
_timer = new System.Timers.Timer(settings.TimeInSeconds * 1000);
_timer.Elapsed += (s, e) => { isRunning = false; };
_timer.Start();
List<DataPoint> bestPos = new List<DataPoint>();
int i = 0;
while (isRunning)
{
bestPos.Add(new DataPoint(i++, p.BestFitness));
p.Iteration();
if (settings.IsLivePlot && i % 5000 == 0)
{
castedPayload.UpdatePlotFunction(bestPos);
Thread.Sleep(150);
bestPos = new List<DataPoint>();
}
}
if (bestPos.Count > 0)
castedPayload.UpdatePlotFunction(bestPos);
}
castedPayload.CalculationFinished();
}
protected TravellingSalesmanMap Map;// { get; set; }
//Referencia a melhor particula atualmente
//public TSPParticle gBest;
/*
* public TSPParticle(TSPParticle particle) : base() {
* this.Position = particle.Position;
* this.Velocity = particle.Velocity;
* this.Fitness = particle.Fitness;
* }
*
* private TSPParticle() : base() {
*
* }
*/
private TSPParticle(ParticleSwarm containingSwarm, TravellingSalesmanMap Map)
: base(containingSwarm)
{
this.Map = Map;
}
/// <summary>
/// Before we start solver prepare all neccessery information
/// </summary>
/// <param name="termSet"></param>
/// <param name="funSet"></param>
/// <param name="annParams"></param>
public override void PrepareAlgorithm(Experiment expData, ANNParameters annParams = null)
{
if (annParams == null || expData == null)
{
throw new Exception("Argument value cannot be null");
}
//reset iteration and network
if (m_Network == null)
{
m_IterationCounter = 0;
//depending on the type of the colum create adequate neural network
var colType = expData.GetOutputColumnType();
if (colType == ColumnDataType.Binary)//Binary Clasification
{
m_Network = new BCNeuralNetwork(annParams, expData.GetColumnInputCount_FromNormalizedValue(), expData.GetColumnOutputCount_FromNormalizedValue());
}
else//multiclass classification
{
m_Network = new MCNeuralNetwork(annParams, expData.GetColumnInputCount_FromNormalizedValue(), expData.GetColumnOutputCount_FromNormalizedValue());
}
m_Network.InitializeNetwork();
}
//
m_Experiment = expData;
PSOParameters swarm = null;
if (m_Parameters != null)
{
swarm = m_Parameters.m_PSOParameters;
}
else
{
m_psoAlgorithm = null;
swarm = annParams.m_PSOParameters;
}
//
m_Parameters = annParams;
m_Parameters.m_PSOParameters = swarm;
m_expRowCount = m_Experiment.GetRowCount();
IsAlgorthmPrepared = true;
StopIteration = false;
float newfitness = 0;
if (m_psoAlgorithm == null)
{
//initilaize swarm
m_Parameters.m_PSOParameters.m_Dimension = m_Network.GetWeightsAndBiasCout();
m_psoAlgorithm = new ParticleSwarm(m_Parameters.m_PSOParameters, CrossEntropy);
//init
newfitness = m_psoAlgorithm.InitSwarm();
}
// else
newfitness = m_psoAlgorithm.RunSwarm();
var model = CalculateModel(false);
//Send report for iteration
var rp = new ProgressIndicatorEventArgs()
{
ReportType = ProgramState.Started,
LearningError = newfitness,
CurrentIteration = 0,
LearnOutput = model,
};
ReportProgress(rp);
}
