Classification of time series by shapelet transformation

By Jon Hills, Jason Lines, Edgaras Baranauskas, James Mapp, Anthony J. Bagnall. Data mining and knowledge discovery, 2013

561 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f3f5cb24b7a71911702c640bb765b44d0fc03d30

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Signal Processing

Citations in the corpus

Time series classification with ensembles of elastic distance measures (2015, methodology): “Hills et al. (2013) propose a shapelet transformation that separates the shapelet discovery from the classifier by finding the top k shapelets on a single run (in contrast to the decision tree, which searches for the best shapelet at each node).”
Deep learning for time series classification: a review (2018, methodology): “Hence, recent contributions have focused on developing ensemblingmethods that significantly outperforms the NN coupled with DTW (NN-DTW) (Bagnall et al. 2016; Hills et al. 2014; Bostrom and Bagnall 2015; Lines et al. 2016; Schäfer 2015; Kate 2016; Deng et al. 2013; Baydogan et al. 2013).”
Using dynamic time warping distances as features for improved time series classification (2016, result): “Also, some papers, for example, (Gudmundsson et al. 2008) and (Hills et al. 2013), do not compare with the 1NN-DTW-R error rates available from (Keogh et al. 2011).”
InceptionTime: Finding AlexNet for time series classification (2019, methodology): “Another type of ensemble classifiers is shapelet based algorithms, such as in Hills et al. (2014), where discriminative subsequences (shapelets) are extracted from the training set and fed to off-the-shelf classifiers such as Support Vector Machines and Random Forests.”
Learning time-series shapelets (2014, methodology): “• Shapelet Tree Methods, constructed from shapelets whose qualities are measured using: i) Information gain quality criterion (IG) [17, 11], ii) Kruskall-Wallis quality criterion (KW) [8], iii) F-Stats quality criterion (FST) [10] and iv) the Mood’s Median Criterion (MM) [8].”
The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances (2016, background): “Hills et al. (2014) propose a shapelet transformation that separates the shapelet discovery from the classifier by finding the top k shapelets on a single run (in contrast to the decision tree, which searches for the best shapelet at each node).”
Time-Series Classification with COTE: The Collective of Transformation-Based Ensembles (2015, methodology): “The motivation for COTE comes from our recent research [10], [11], [12] which has explored two key ideas for TSC.”
The UCR time series archive (2018, background): “Moreover, one can always place detailed spreadsheets online or in an accompanying, cited technical report, as many papers do these days [10], [18].”
Spatio-Temporal Data Mining (2017, background): “Another approach to incorporate the temporal context of time-series features in classification problems is the use of shapelets (Hills et al. 2014; Ye and Keogh 2009).”