void TranslateInstance(Frame frame)
{
// Create a new Linear kernel
IKernel kernel = new Linear();
// Create a new Multi-class Support Vector Machine with one input,
// using the linear kernel and for four disjoint classes.
var machine = new MulticlassSupportVectorMachine(5, kernel, numOfClasses);
// Create the Multi-class learning algorithm for the machine
var teacher = new MulticlassSupportVectorLearning(machine, inputs, outputs);
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
teacher.Algorithm = (svm, classInputs, classOutputs, i, j) =>
new SequentialMinimalOptimization(svm, classInputs, classOutputs);
// Run the learning algorithm
double error = teacher.Run(); // output should be 0
double[] distances = new double[5];
distances = LeapEventListener.getDistances(frame);
int decision = machine.Compute(distances); //svm AI
output.Text = output.Text + Char2SvmClass.class2svm(decision);
}
private void TranslateBtn_Click(object sender, EventArgs e)
{
double[] distances = new double[5];
distances = LeapEventListener.getDistances(currentFrame);
if (LeapEventListener.isZeros(distances) == true)
{
MessageBox.Show("The frame is null.\n Try reconnecting the Leap device", "Application Error",
MessageBoxButtons.OKCancel, MessageBoxIcon.Warning);
}
else
{
// Create a new Linear kernel
IKernel kernel = new Linear();
// Create a new Multi-class Support Vector Machine with one input,
// using the linear kernel and for four disjoint classes.
var machine = new MulticlassSupportVectorMachine(5, kernel, numOfClasses);
// Create the Multi-class learning algorithm for the machine
var teacher = new MulticlassSupportVectorLearning(machine, inputs, outputs);
// Configure the learning algorithm to use SMO to train the
// underlying SVMs in each of the binary class subproblems.
teacher.Algorithm = (svm, classInputs, classOutputs, i, j) =>
new SequentialMinimalOptimization(svm, classInputs, classOutputs);
// Run the learning algorithm
double error = teacher.Run(); // output should be 0
int decision = machine.Compute(distances); //svm AI
output.Text = output.Text + Char2SvmClass.class2svm(decision);
}
}
private void InitializeSVM()
{
// ============================================== Database ==============================================
connection = new OleDbConnection();
command = new OleDbCommand();
double thumb, index, middle, ring, pinky;
int svmClass = 0;
connection.ConnectionString = @"Provider=Microsoft.ACE.OLEDB.12.0;Data Source=|DataDirectory|\SVMdataset.accdb";
command.Connection = connection;
string q = "select * from DataSet";
command.CommandText = q;
connection.Open();
dr = command.ExecuteReader();
int k = 0;
DataTable dt = new DataTable();
dt.Load(dr);
outputs = new int[dt.Rows.Count];
inputs = new double[dt.Rows.Count][];
dr = command.ExecuteReader();
if (dr.HasRows) // run over the table and put it on the list
{
while (dr.Read())
{
char c = Convert.ToChar(dr[1]);
svmClass = Char2SvmClass.char2class(c);//static method that converts the char to a class ;
thumb = Convert.ToDouble(dr[2]);
index = Convert.ToDouble(dr[3]);
middle = Convert.ToDouble(dr[4]);
ring = Convert.ToDouble(dr[5]);
pinky = Convert.ToDouble(dr[6]);
inputs[k] = new double[] { thumb, index, middle, ring, pinky };
outputs[k] = svmClass;
k++;
}
}
connection.Close();
//get from DB the number of classes
command.Connection = connection;
q = "select Distinct DataSet.Letter from DataSet";
command.CommandText = q;
connection.Open();
dr = command.ExecuteReader();
dt = new DataTable();
dt.Load(dr);
numOfClasses = dt.Rows.Count;
connection.Close();
}
