SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation

Authors

  • Hyun Ryu KAIST
  • Sunjae Yoon KAIST
  • Hee Suk Yoon KAIST
  • Eunseop Yoon KAIST
  • Chang D. Yoo KAIST

DOI:

https://doi.org/10.1609/aaai.v38i13.29405

Keywords:

ML: Time-Series/Data Streams, ML: Deep Learning Algorithms

Abstract

Data augmentation is a crucial component in training neural networks to overcome the limitation imposed by data size, and several techniques have been studied for time series. Although these techniques are effective in certain tasks, they have yet to be generalized to time series benchmarks. We find that current data augmentation techniques ruin the core information contained within the frequency domain. To address this issue, we propose a simple strategy to preserve spectral information (SimPSI) in time series data augmentation. SimPSI preserves the spectral information by mixing the original and augmented input spectrum weighted by a preservation map, which indicates the importance score of each frequency. Specifically, our experimental contributions are to build three distinct preservation maps: magnitude spectrum, saliency map, and spectrum-preservative map. We apply SimPSI to various time series data augmentations and evaluate its effectiveness across a wide range of time series benchmarks. Our experimental results support that SimPSI considerably enhances the performance of time series data augmentations by preserving core spectral information. The source code used in the paper is available at https://github.com/Hyun-Ryu/simpsi.

Published

2024-03-24

How to Cite

Ryu, H., Yoon, S., Yoon, H. S., Yoon, E., & Yoo, C. D. (2024). SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(13), 14857-14865. https://doi.org/10.1609/aaai.v38i13.29405

Issue

Section

AAAI Technical Track on Machine Learning IV