English

PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification

Machine Learning 2021-09-27 v1

Abstract

The classification of time-series data is pivotal for streaming data and comes with many challenges. Although the amount of publicly available datasets increases rapidly, deep neural models are only exploited in a few areas. Traditional methods are still used very often compared to deep neural models. These methods get preferred in safety-critical, financial, or medical fields because of their interpretable results. However, their performance and scale-ability are limited, and finding suitable explanations for time-series classification tasks is challenging due to the concepts hidden in the numerical time-series data. Visualizing complete time-series results in a cognitive overload concerning our perception and leads to confusion. Therefore, we believe that patch-wise processing of the data results in a more interpretable representation. We propose a novel hybrid approach that utilizes deep neural networks and traditional machine learning algorithms to introduce an interpretable and scale-able time-series classification approach. Our method first performs a fine-grained classification for the patches followed by sample level classification.

Keywords

Cite

@article{arxiv.2102.05917,
  title  = {PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification},
  author = {Dominique Mercier and Andreas Dengel and Sheraz Ahmed},
  journal= {arXiv preprint arXiv:2102.05917},
  year   = {2021}
}

Comments

8 pages, 8 figures, 6 tables, submitted to IJCNN 2021

R2 v1 2026-06-23T23:03:49.225Z