EFFICIENT LEARNING OF TIME SERIES SHAPELETS

Moreover, our algorithm has fewer redundant shape-like shapelets and is more convenient to interpret classification decisions. Second, they must determine how many shapelets are needed beforehand, which is difficult without prior knowledge. Bagnall Data Mining and Knowledge Discovery Citations Publications citing this paper. Recently, time series classification with shapelets, due to their high discriminative ability and good interpretability, has attracted considerable interests within the research community. Boosting the kernelized shapelets: Kwok , Jacek M.

Articles by Zicheng Fang. Kwok and Jacek M. Citations Publications citing this paper. Previously, shapelet generating approaches extracted shapelets from training time series or learned shapelets with many parameters. In this paper, we take an entirely different approach and reformulate the shapelet discovery task as a numerical optimization problem. Showing of 25 references.

Showing of 8 citations. References Publications referenced by this paper.

Efficient Learning of Timeseries Shapelets

Extensive experimentation on 15 datasets demonstrates that our algorithm is more accurate against 6 baselines and outperforms 2 orders of magnitude in terms of efficiency. Moreover, the concept of coverage is proposed to measure the quality of candidates, based on which we design a method efficcient compute the optimal number of shapelets.

Recently, time series classification with shapelets, due to their high discriminative ability and good interpretability, has attracted considerable interests within the research community. Moreover, our algorithm has fewer redundant shape-like shapelets and is more convenient to interpret classification decisions. In this paper, we take an entirely different approach and reformulate the shapelet discovery task as a numerical optimization problem.

  MST3K HOBGOBLINS FULL EPISODE

Previously, shapelet generating approaches extracted shapelets from training time series or learned shapelets with many parameters. Citations Publications citing this paper. First, searching or learning shapelets in the raw time series space incurs a huge computation cost.

Existing methods perform a combinatorial search for shapelet discovery. KwokLesrning M.

Even with speedup heuristics such as pruning, clustering, and dimensionality reduction, the search remains computationally expensive. Showing of 25 references. Second, they must determine how many shapelets are needed beforehand, which is difficult without prior knowledge.

There was a problem providing the content you requested

To overcome these challenges, in this paper, we propose a novel algorithm to learn shapelets. We first discover shapelet candidates from the Piecewise Aggregate Approximation PAA word space, which is much more efficient than searching in the raw time series space.

Kwok and Jacek M. Bagnall Data Mining and Knowledge Discovery From This Paper Figures, tables, sedies topics from this paper. Zurada Published in AAAI In timeseries classification, shapelets are subsequences of timeseries with high discriminative power. Distributed optimization and statistical learning via the alternating direction method of multipliers. Skip to search form Skip to main content. By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy PolicyTerms of Serviceand Dataset License.

  PUNJABI FILM MARHI DA DEEVA

Articles by Zicheng Fang. For example, it may cost several hours to deal with only hundreds of time series.

Efficient Learning Interpretable Shapelets for Accurate Time Series Classification

Foundations and Trends in Machine Learning 3 1: BarnaghiAntonio F. After that, we apply the logistic regression classifier to adjust the shapelets. Articles by Peng Wang. Boosting the kernelized shapelets: Articles by Wei Wang.

Although they can achieve higher accuracy than other approaches, they still confront some challenges.