Scalable Discovery of Time-Series Shapelets

2015/03/11 by Grabocka, Josif, Wistuba, Martin, Schmidt-Thieme, Lars
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.1503.03238

Abstract

Time-series classification is an important problem for the data mining community due to the wide range of application domains involving time-series data. A recent paradigm, called shapelets, represents patterns that are highly predictive for the target variable. Shapelets are discovered by measuring the prediction accuracy of a set of potential (shapelet) candidates. The candidates typically consist of all the segments of a dataset, therefore, the discovery of shapelets is computationally expensive. This paper proposes a novel method that avoids measuring the prediction accuracy of similar candidates in Euclidean distance space, through an online clustering pruning technique. In addition, our algorithm incorporates a supervised shapelet selection that filters out only those candidates that improve classification accuracy. Empirical evidence on 45 datasets from the UCR collection demonstrate that our method is 3-4 orders of magnitudes faster than the fastest existing shapelet-discovery method, while providing better prediction accuracy.

Related

• SE-shapelets: Semi-supervised Clustering of Time Series Using Representative Shapelets
• Ensembles of Randomized Time Series Shapelets Provide Improved Accuracy while Reducing Computational Costs
• Ultra-Fast Shapelets for Time Series Classification
• Fast Randomized Model Generation for Shapelet-Based Time Series Classification
• AUTOSHAPE: An Autoencoder-Shapelet Approach for Time Series Clustering