public override void Train(IForecastingDataSets datasets)
{
OnStartRunning(new ComponentRunEventArgs(datasets));
AnnModelParameter para = mParameter as AnnModelParameter;
LinearLayer inputLayer = new LinearLayer(datasets.InputData[0].Length);
SigmoidLayer hiddenLayer = new SigmoidLayer(para.HiddenNeuronsCount[0]);
SigmoidLayer outputLayer = new SigmoidLayer(1);
new BackpropagationConnector(inputLayer, hiddenLayer).Initializer = new RandomFunction(0d, 0.3d);
new BackpropagationConnector(hiddenLayer, outputLayer).Initializer = new RandomFunction(0d, 0.3d);
network = new BackpropagationNetwork(inputLayer, outputLayer);
network.SetLearningRate(para.LearningRate);
network.JitterEpoch = para.JitterEpoch;
network.JitterNoiseLimit = para.JitterNoiseLimit;
network.EndEpochEvent += new TrainingEpochEventHandler(
delegate(object senderNetwork, TrainingEpochEventArgs args)
{
// TODO: trainning error needs to be calculated
OnRunningEpoch(new AnnModelRunEpochEventArgs(args.TrainingIteration + 1, 0));
});
network.Learn(ForecastingDataSets.ConvertToTrainingSet(datasets), para.Iterations);
datasets.ForecastedData = new double[datasets.InputData.Length][];
for (int i = 0; i < datasets.InputData.Length; i++)
{
datasets.ForecastedData[i] = new double[1];
datasets.ForecastedData[i][0] = Forecast(datasets.InputData[i]);
}
OnFinishRunning(new ComponentRunEventArgs(datasets));
}
public NeuralNetworkModel(AnnModelParameter parameter)
: base(parameter)
{
Orgnization = "HUST WREIS";
ID = "80056193-8885-4BCA-B402-457DB4A9CCB4";
Name = "Neural Network";
Descriptions = "";
}
public BpANNModel(AnnModelParameter parameter)
{
Orgnization = "HUST WREIS";
ID = "2F710E58-91E8-4CF4-A721-A7FA243D0D69";
Name = "Artificial Neuron Network";
Descriptions = "";
mAnnModelParameter = parameter;
mAnnModelParameter.Component = this;
}
public static IForecastingModel CreateForecastingModel(string name)
{
IForecastingModel model = null;
switch (name)
{
case "Artificial Neural Network":
AnnModelParameter annPara = new AnnModelParameter();
model = new NeuralNetworkModel(annPara);
break;
case "HIGANN":
AnnModelParameter annPara1 = new AnnModelParameter();
model = new NeuralNetworkModel(annPara1);
break;
case "Support Vector Machine":
Heiflow.AI.SVM.Parameter p = new Heiflow.AI.SVM.Parameter();
model = new SVMModel(p);
break;
case "Multiple Linear Regression":
ModelParameter mp = new ModelParameter();
model = new MLRModel(mp);
break;
case "Genetic Programming":
GPModelParameter para = new GPModelParameter();
model = new GPModel(para);
break;
case "Model Tree":
Rule root = new Rule(5, 0.47035, RuleType.Interior);
Rule right = new Rule(RuleType.RightLeaf);
root.RightChild = right;
Rule left = new Rule(5, 0.30445, RuleType.Interior);
root.LeftChild = left;
Rule left1 = new Rule(RuleType.LeftLeaf);
left.LeftChild = left1;
Rule right1 = new Rule(9, 0.156, RuleType.Interior);
left.RightChild = right1;
Rule right1_left = new Rule(RuleType.LeftLeaf);
right1.LeftChild = right1_left;
Rule right1_right = new Rule(RuleType.RightLeaf);
right1.RightChild = right1_right;
HybridModelParameter hmp = new HybridModelParameter(root);
model = new HybridModel(hmp);
break;
}
return(model);
}
