timeseries_classification_data_stream

#TimeSeriesClassificationDataStream

##Description The TimeSeriesClassificationDataStream is the main data structure for recording, labeling, managing, saving, and loading datasets that can be used to test the continuous classification abilities of the GRT supervised temporal learning algorithms.

This class replaces the LabelledContinuousTimeSeriesClassificationData as of GRT revision 380.

##Suitable Classification Algorithms The TimeSeriesClassificationDataStream data structure should be used to test the following GRT classification algorithms:

• Dynamic Time Warping (DTW)
• Discrete Hidden Markov Model (HMM)
• Continuous Hidden Markov Model (HMM)

##Things To Know There are two key things you should know about the TimeSeriesClassificationDataStream class.

• You should set the number of input dimensions of your dataset before you try and add samples to the training dataset (see the example below for how to do this).
• Unlike many of the other labelled classification data structures, you can use the class label of 0 when you add a new sample to your dataset. This is because the TimeSeriesClassificationDataStream can contain sections of data that are not valid gestures (this way you can really test if your classification pipeline works with 'real' data). You should reserve the class label of 0 for any movements that are not valid gestures as the class label of 0 is reserved for the special null gesture class. This tutorial provides more information about the null gesture class.

##Example TimeSeriesClassificationDataStream