SPROCKET: Extending ROCKET to Distance-Based Time-Series Transformations With Prototypes

TL;DR

SPROCKET introduces a prototype-based feature transformation for time series classification, achieving competitive accuracy and robustness, and surpassing previous ensemble methods like HYDRA-MR on standard benchmarks.

Contribution

It presents SPROCKET, a novel feature engineering approach using prototypes, extending ROCKET for improved performance in time series classification.

Findings

SPROCKET performs comparably to existing convolutional algorithms.

MR-HY-SP ensemble outperforms HYDRA-MR in accuracy.

Prototype-based transformations enhance robustness.

Abstract

Classical Time Series Classification algorithms are dominated by feature engineering strategies. One of the most prominent of these transforms is ROCKET, which achieves strong performance through random kernel features. We introduce SPROCKET (Selected Prototype Random Convolutional Kernel Transform), which implements a new feature engineering strategy based on prototypes. On a majority of the UCR and UEA Time Series Classification archives, SPROCKET achieves performance comparable to existing convolutional algorithms and the new MR-HY-SP ( MultiROCKET-HYDRA-SPROCKET) ensemble's average accuracy ranking exceeds HYDRA-MR, the previous best convolutional ensemble's performance. These experimental results demonstrate that prototype-based feature transformation can enhance both accuracy and robustness in time series classification.