ABSTRACT
There is a vast literature on time series classification where the time series under consideration must be aligned in a particular way. The discrimination methods find certain features in the time series such as structural breaks and then discrimination is based on the presence or absence of these features. A decision tree is a combination of mathematical and computational techniques to assist in the description and classification of a given set of data associated with variables. The attributes that appear near the top of the tree typically indicate they are more important in making classifications. Creating a binary decision tree is a process of dividing up the input space by some sort of splitting. A Gaussian mixture model (GMM) is a parametric density function represented as a weighted sum of Gaussian component densities. GMM parameters are estimated from training data using the iterative expectation-maximisation (EM) algorithm.
