Time-Series prediction data

I assume you mean that now that you have the entire network trained how to submit new data to it. Basically create some sort of an object where you can pass in your ten values for each point and then once the object has queued up enough data you could recieved the window input data to the network.

That would be a nice utility to add.

You can use :

For multiple inputs :
https://github.com/fxmozart/encog-dotnet-core/blob/Latest/encog-core-cs/...

For single input networks :
You can use the one that is in one of the examples :


public static IMLDataSet ProcessDoubleSerieIntoIMLDataset(double[] data, int _inputWindow, int _predictWindow)
{
var result = new BasicMLDataSet();
int totalWindowSize = _inputWindow + _predictWindow;
int stopPoint = data.Length - totalWindowSize;
for (int i = 0; i < stopPoint; i++)
{
var inputData = new BasicMLData(_inputWindow);
var idealData = new BasicMLData(_predictWindow);
int index = i;
// handle input window
for (int j = 0; j < _inputWindow; j++)
{
inputData[j] = data[index++];
}
// handle predict window
for (int j = 0; j < _predictWindow; j++)
{
idealData[j] = data[index++];
}
var pair = new BasicMLDataPair(inputData, idealData);
result.Add(pair);
}
return result;
}