Skip to Main content Skip to Navigation
Journal articles

Interpretable time series kernel analytics by pre-image estimation

Abstract : Kernel methods are known to be effective to analyse complex objects by implicitly embedding them into some feature space. To interpret and analyse the obtained results, it is often required to restore in the input space the results obtained in the feature space, by using pre-image estimation methods. This work proposes a new closed-form pre-image estimation method for time series kernel analytics that consists of two steps. In the first step, a time warp function, driven by distance constraints in the feature space, is defined to embed time series in a metric space where analytics can be performed conveniently. In the second step, the time series pre-image estimation is cast as learning a linear (or a nonlinear) transformation that ensures a local isometry between the time series embedding space and the feature space. The proposed method is compared to the state of the art through three major tasks that require pre-image estimation: 1) time series averaging, 2) time series reconstruction and denoising and 3) time series representation learning. The extensive experiments conducted on 33 publicly-available datasets show the benefits of the pre-image estimation for time series kernel analytics.
Complete list of metadata

https://hal-normandie-univ.archives-ouvertes.fr/hal-03088295
Contributor : Paul Honeine <>
Submitted on : Saturday, December 26, 2020 - 12:24:15 AM
Last modification on : Tuesday, March 23, 2021 - 9:28:03 AM
Long-term archiving on: : Monday, March 29, 2021 - 4:41:38 PM

File

20.ts_preimage.pdf
Files produced by the author(s)

Identifiers

Citation

Thi Phuong Thao Tran, Ahlame Douzal-Chouakria, Saeed Varasteh Yazdi, Paul Honeine, Patrick Gallinari. Interpretable time series kernel analytics by pre-image estimation. Artificial Intelligence, Elsevier, 2020, 286, pp.103342. ⟨10.1016/j.artint.2020.103342⟩. ⟨hal-03088295⟩

Share

Metrics