Metric time series classification using weighted dynamic warping relative to centroids of classes

The paper discusses the problem of metric time series analysis and classification. The proposed classification model uses a matrix of distances between time series which is built with a fixed distance function. The dimension of this distance matrix is very high and all related calculations are time-consuming. The problem of reducing computational complexity is solved by selecting reference objects and using them for describing classes. The model that uses dynamic time warping for building reference objects or centroids is chosen as the basic model. This paper introduces a function of weights for each centroid that influences calculation of the distance measure. Time series of different analytic functions and time series of human activity from an accelerometer of a mobile phone are used as the objects for classification. The properties and the classification result of this model are investigated and compared with the properties of the basic model.