GENDIS: Genetic Discovery of Shapelets

  title={GENDIS: Genetic Discovery of Shapelets},
  author={Gilles Vandewiele and Femke Ongenae and Filip De Turck},
  journal={Sensors (Basel, Switzerland)},
In the time series classification domain, shapelets are subsequences that are discriminative of a certain class. It has been shown that classifiers are able to achieve state-of-the-art results by taking the distances from the input time series to different discriminative shapelets as the input. Additionally, these shapelets can be visualized and thus possess an interpretable characteristic, making them appealing in critical domains, where longitudinal data are ubiquitous. In this study, a new… 

Convolutional Shapelet Transform: A new approach for time series shapelets

This work presents a new formulation of time series shapelets including the notion of dilation, and a shapelet extraction method based on convolutional kernels, which is able to target the discriminant informations identified by convolutionAL kernels.

Shapelet Selection for Efficient Time Series Classification by Dynamic Time Warping

The proposed shapelet selection method uses DTW(dynamic time warping) searches for frequent patterns occurring in time series through the warping path of DTW and uses it as shapelets and achieves excellent performance in classification accuracy.

Random Dilated Shapelet Transform: A New Approach for Time Series Shapelets

A new formulation of time series shapelets including the notion of dilation is presented, and a new shapelet feature is introduced to enhance their discriminative power for classification.

A Customized Machine Learning Algorithm for Discovering the Shapes of Recovery: Was the Global Financial Crisis Different?

In this paper, we modify a conventional machine learning technique to classify recession-and-recovery events emerging in the countries’ business cycles. We do this by analyzing output dynamics in

Fast Shapelet Learning for Power System Dominant Instability Mode Identification

A fast shapelet learning method to extract features from the original voltage and rotor angle curves and then classify them through a machine learning (ML) model is proposed to overcome the huge time complexity of the shapelet transformation method.



Learning time-series shapelets

A new mathematical formalization of the task via a classification objective function is proposed and a tailored stochastic gradient learning algorithm is applied and can learn true top-K shapelets by capturing their interaction.

Logical-shapelets: an expressive primitive for time series classification

This work introduces a novel algorithm that finds shapelets in less time than current methods by an order of magnitude, and shows for the first time an augmented shapelet representation that distinguishes the data based on conjunctions or disjunctions of shapelets.

Learning multivariate shapelets with multi-layer neural networks for interpretable time-series classification

A novel architecture for shapelets learning is developed, by embedding them as trainable weights in a multi-layer Neural Network and leading the model to automatically select smaller sets of uncorrelated shapelets, thus requiring no additional manual optimization on typically important hyper-parameters such as number and length.

Binary Shapelet Transform for Multiclass Time Series Classification

A one vs all encoding scheme is evaluated which simplifies the quality assessment calculations, speeds up the execution through facilitating more frequent early abandon and increases accuracy for multi-class problems.

Fast Shapelets: A Scalable Algorithm for Discovering Time Series Shapelets

This work proposes a fast shapelet discovery algorithm that outperforms the current state-of-the-art by two or three orders of magnitude, while producing models with accuracy that is not perceptibly different.

Localized Random Shapelets

This paper designs an interpretable shapelet model that takes into account the localization of the shapelets in the time series and designs a hierarchical feature selection process using regularization that has competitive performance compared to state-of-the-art shapelet-based classifiers, while providing better interpretability.

A shapelet transform for time series classification

This work describes a means of extracting the k best shapelets from a data set in a single pass, and then uses these shapelets to transform data by calculating the distances from a series to each shapelet.

Time series shapelets: a new primitive for data mining

A new time series primitive, time series shapelets, is introduced, which can be interpretable, more accurate and significantly faster than state-of-the-art classifiers.

Scalable Discovery of Time-Series Shapelets

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, and incorporates a supervised shapelet selection that filters out only those candidates that improve classification accuracy.

Efficient Learning of Timeseries Shapelets

The shapelet discovery task is reformulated as a numerical optimization problem and the shapelet positions are learned by combining the generalized eigenvector method and fused lasso regularizer to encourage a sparse and blocky solution.