Transfer learning for time series classification using synthetic data generation

Yarden Rotem, Nathaniel Shimoni, Lior Rokach, Bracha Shapira
7/16/2022
cs.LG

No official code found. Best implementation: YR234/TL-for-TSC (13 stars, last commit 2023-08-12).

Abstract

In this paper, we propose an innovative Transfer learning for Time series classification method. Instead of using an existing dataset from the UCR archive as the source dataset, we generated a 15,000,000 synthetic univariate time series dataset that was created using our unique synthetic time series generator algorithm which can generate data with diverse patterns and angles and different sequence lengths. Furthermore, instead of using classification tasks provided by the UCR archive as the source task as previous studies did,we used our own 55 regression tasks as the source tasks, which produced better results than selecting classification tasks from the UCR archive

View on arXivView PDF

Code Implementations(1)

YR234/TL-for-TSCCommunity100%
135Python, Jupyter NotebookSep 5, 20213 years ago

Similar Papers

Fast Classification of Large Time Series Datasets

84% match2023

Are Synthetic Time-series Data Really not as Good as Real Data?

84% match2024

Towards Editing Time Series

83% match2026

MIHT: A Hoeffding Tree for Time Series Classification using Multiple Instance Learning

82% match2026

Enhancing Algorithm Performance Understanding through tsMorph: Generating Semi-Synthetic Time Series for Robust Forecasting Evaluation

82% match1 repo2023

Curricular and Cyclical Loss for Time Series Learning Strategy

82% match2023

Cite this paper

@article{rotem2022transfer,
  title  = {Transfer learning for time series classification using synthetic data generation},
  author = {Yarden Rotem and Nathaniel Shimoni and Lior Rokach and Bracha Shapira},
  year   = {2022},
  eprint = {2207.07897},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.07897v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.07897.svg)](https://codeofpaper.com/paper/2207.07897)

Discussion