Random pairwise shapelets forest: an effective classifier for time series

Shapelet is a discriminative subsequence of time series. An advanced shapelet-based method is to embed shapelet into the accurate and fast random forest. However, there are several limitations. First, random shapelet forest requires a large training cost for split threshold searching. Second, a single shapelet provides limited information for only one branch of the decision tree, resulting in insufficient accuracy. Third, the randomized ensemble decreases comprehensibility. For that, this paper presents Random Pairwise Shapelets Forest (RPSF). RPSF combines a pair of shapelets from different classes to construct random forest. It omits threshold searching to be more efficient, includes more information about each node of the forest to be more effective. Moreover, a discriminability measure, Decomposed Mean Decrease Impurity, is proposed to identify the influential region for each class. Extensive experiments show that RPSF is competitive compared with other methods, while it improves the training speed of shapelet-based forest.