private void Predict()
{
TrainingValue tmp = new TrainingValue();
tmp.Features = new double[FEATURE_COUNT];
FillTrainingValue(ref tmp, fftResults);
int result = trainer.Predict(tmp);
predictedMuscleState = (MuscleState)result;
}
private void RunFFT()
{
readingsMean.Clear();
for (int i = 0; i < af7.Count; i++)
{
readingsMean.Add(af7[i] + tp9[i] + tp10[i] + af8[i] / FEATURE_COUNT);
}
CalculateFFT(readingsMean, FFTResults);
CalculateFFT(af7, AF7FFT);
CalculateFFT(af8, AF8FFT);
CalculateFFT(tp9, TP9FFT);
CalculateFFT(tp10, TP10FFT);
if (!Training || (Training && ignore == 0))
{
TrainingValue trainingValue = new TrainingValue((int)Status, FEATURE_COUNT);
trainingValue.Features[0] = PSD(TP9FFT, FREQ_STEP);
trainingValue.Features[1] = PSD(AF7FFT, FREQ_STEP);
trainingValue.Features[2] = PSD(AF8FFT, FREQ_STEP);
trainingValue.Features[3] = PSD(TP10FFT, FREQ_STEP);
if (!Training && trainer != null && trainer.Trained)
{
Status = (EyesStatus)trainer.Predict(trainingValue);
}
if (training || keepTrainingData)
{
TrainingValues.Add(trainingValue);
}
}
else if (Training && ignore != 0)
{
ignore--;
}
}
public static void CrossValidate(List <List <TrainingValue> > dataSets, List <int> ks, int featureSize, List <string> filenames)
{
List <ClassifierType> types = new List <ClassifierType> {
ClassifierType.Bayes,
ClassifierType.DecisionTree,
ClassifierType.LDA,
ClassifierType.SVM,
};
double[] typeAvgs = new double[types.Count];
int dataSetIndex = 0;
foreach (List <TrainingValue> data in dataSets)
{
Console.WriteLine("\nFile: " + filenames[dataSetIndex++]);
int typeIndex = 0;
foreach (ClassifierType type in types)
{
Console.WriteLine("\nClassifier: " + type);
Console.WriteLine("========================================\n");
double typeAvg = 0;
foreach (int k in ks)
{
int toDiscard = data.Count % k;
data.RemoveRange(data.Count - toDiscard, toDiscard);
int sampleSize = data.Count / k;
List <TrainingValue> workingCopy = new List <TrainingValue>();
double avg = 0;
for (int index = 0; index < k; index++)
{
workingCopy.AddRange(data);
List <TrainingValue> sample = workingCopy.GetRange(index * sampleSize, sampleSize);
workingCopy.RemoveRange(index * sampleSize, sampleSize);
Trainer trainer = new Trainer(featureSize, type);
trainer.Train(workingCopy);
int[,] confMat = new int[2, 2];
foreach (TrainingValue predValue in sample)
{
int result = trainer.Predict(predValue);
int i = (predValue.State == 1) ? 1 : 0;
int j = (result == 1) ? 1 : 0;
confMat[i, j]++;
}
avg += (confMat[0, 0] + confMat[1, 1]) / (double)sampleSize;
workingCopy.Clear();
}
avg /= k;
typeAvg += avg;
Console.WriteLine("k = " + k + ": " + avg);
}
typeAvgs[typeIndex++] += typeAvg / ks.Count;
Console.WriteLine("Total average: " + typeAvg / ks.Count);
Console.WriteLine("");
}
}
Console.WriteLine("\n\nClasifiers precision");
Console.WriteLine("========================================\n");
int aux = 0;
foreach (ClassifierType type in types)
{
Console.WriteLine(type + ": " + typeAvgs[aux++] / dataSets.Count);
}
}