Interpretable time series classification using linear models and multi-resolution multi-domain symbolic representations
From MaRDI portal
Abstract: The time series classification literature has expanded rapidly over the last decade, with many new classification approaches published each year. Prior research has mostly focused on improving the accuracy and efficiency of classifiers, with interpretability being somewhat neglected. This aspect of classifiers has become critical for many application domains and the introduction of the EU GDPR legislation in 2018 is likely to further emphasize the importance of interpretable learning algorithms. Currently, state-of-the-art classification accuracy is achieved with very complex models based on large ensembles (COTE) or deep neural networks (FCN). These approaches are not efficient with regard to either time or space, are difficult to interpret and cannot be applied to variable-length time series, requiring pre-processing of the original series to a set fixed-length. In this paper we propose new time series classification algorithms to address these gaps. Our approach is based on symbolic representations of time series, efficient sequence mining algorithms and linear classification models. Our linear models are as accurate as deep learning models but are more efficient regarding running time and memory, can work with variable-length time series and can be interpreted by highlighting the discriminative symbolic features on the original time series. We show that our multi-resolution multi-domain linear classifier (mtSS-SEQL+LR) achieves a similar accuracy to the state-of-the-art COTE ensemble, and to recent deep learning methods (FCN, ResNet), but uses a fraction of the time and memory required by either COTE or deep models. To further analyse the interpretability of our classifier, we present a case study on a human motion dataset collected by the authors. We release all the results, source code and data to encourage reproducibility.
Recommendations
- Time series shapelets: a novel technique that allows accurate, interpretable and fast classification
- Scalable time series classification
- Learning a symbolic representation for multivariate time series classification
- Learning multivariate shapelets with multi-layer neural networks for interpretable time-series classification
- scientific article; zbMATH DE number 1897899
Cites work
- An extension on ``Statistical comparisons of classifiers over multiple data sets for all pairwise comparisons
- Deep learning for time series classification: a review
- Dimensionality reduction for fast similarity search in large time series databases
- Scalable time series classification
- Should we really use post-hoc tests based on mean-ranks?
- Statistical comparisons of classifiers over multiple data sets
- The BOSS is concerned with time series classification in the presence of noise
- Time series classification with ensembles of elastic distance measures
- Time series shapelets: a novel technique that allows accurate, interpretable and fast classification
- Using dynamic time warping distances as features for improved time series classification
Cited in
(8)- Learning a symbolic representation for multivariate time series classification
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels
- Bake off redux: a review and experimental evaluation of recent time series classification algorithms
- Scalable classifier-agnostic channel selection for multivariate time series classification
- Interpretable classification of time-series data using efficient enumerative techniques
- HIVE-COTE 2.0: a new meta ensemble for time series classification
- Co-eye: a multi-resolution ensemble classifier for symbolically approximated time series
- The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances
This page was built for publication: Interpretable time series classification using linear models and multi-resolution multi-domain symbolic representations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2218362)
