Characteristic Subspace Learning for Time Series Classification

Abstract

This paper presents a novel time series classification algorithm. It exploits time-delay embedding to transform time series into a set of points as a distribution, and attempt to classify time series by classifying corresponding distributions. It proposes a novel geometrical feature, i.e. characteristic subspace, from embedding points for classification, and leverages class-weighted support vector machine (SVM) to learn for it. An efficient boosting strategy is also developed to enable a linear time training. The experiments show great potentials of this novel algorithm on accuracy, efficiency and interpretability.