FRUITS: Feature Extraction Using Iterated Sums for Time Series Classification
This work addresses time series classification, a common problem in fields like finance and healthcare, but it appears incremental as it builds on existing signature methods with a new feature extraction approach.
The authors tackled time series classification by introducing a pipeline that extracts features using the iterated-sums signature (ISS) and applies a linear classifier, achieving competitive accuracy and speed with state-of-the-art methods on the UCR archive.
We introduce a pipeline for time series classification that extracts features based on the iterated-sums signature (ISS) and then applies a linear classifier. These features are intrinsically nonlinear, capture chronological information, and, under certain settings, are invariant to time-warping. We are competitive with state-of-the-art methods on the UCR archive, both in terms of accuracy and speed. We make our code available at \url{https://github.com/irkri/fruits}.