CoChat

An empirical survey of data augmentation for time series classification with neural networks

Open access
Iwana, Brian Kenji, Uchida, Seiichi · 2021 · PLOS ONE

The DOI matches its Crossref record; 120 of the 121 references it cites were found in a registry or an index.

Abstract

In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0254841

Cites

120 of 120 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 Examples of random transformation-based data augmentation on the OliveOil dataset. The dotted blue lines are the original patterns and the solid red lines are the generated patterns.
Fig 1 Examples of random transformation-based data augmentation on the OliveOil dataset. The dotted blue lines are the original patterns and the solid red lines are the generated patterns.CC BY · PubMed Central
Fig 2 Taxonomy of time series data augmentation.
Fig 2 Taxonomy of time series data augmentation.CC BY · PubMed Central
Fig 3 The architectures of the neural networks used to evaluate the data augmentation methods.
Fig 3 The architectures of the neural networks used to evaluate the data augmentation methods.CC BY · PubMed Central
Fig 4 Visualization of the GunPoint dataset using PCA and the compared augmentation methods. The solid shapes are the original time series, the hollow shapes are the generated time series, and the colors indicate different classes.
Fig 4 Visualization of the GunPoint dataset using PCA and the compared augmentation methods. The solid shapes are the original time series, the hollow shapes are the generated time series, and the colors indicate different classes.CC BY · PubMed Central
Fig 5 Spearman’s Rank Correlation Coefficients between change in accuracy (Δ Acc) and various dataset characteristics. The top row in red is the change in accuracy and the subsequent rows are the correlations.
Fig 5 Spearman’s Rank Correlation Coefficients between change in accuracy (Δ Acc) and various dataset characteristics. The top row in red is the change in accuracy and the subsequent rows are the correlations.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 120 references

Research works printed but not linked: 5

  1. H Ding, 2008, Querying and mining of time series data, Proc Very Larg Data Base Endow, 1, 1542
  2. HA Dau, 2018, The UCR time series classification archive
  3. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. In: NeurIPS; 2014. p. 2672–2680.
  4. Ohashi H, Ahmed S, Akiyama T, Sato T, Nguyen P, Nakamura K, et al. Augmenting wearable sensor data with physical constraint for DNN-based human-action recognition. In: ICML Workshops; 2017.
  5. RB Cleveland, 1990, STL: A seasonal-trend decomposition, J Official Stat, 6, 3

Cited by

Items 301–400 of 798

Metadata

Authors
Iwana, B. K., & Uchida, S.
Affiliations
Kyushu University (JP)
Corresponding author
Iwana, Brian Kenji
Venue
PLOS ONE
Published
2021-07-15
Volume
16
Issue
7
Pages
e0254841
ISSN
1932-6203 (ISSN-L)
OpenAlex
W3046296398
Cited by
725
References
121
Citations by year
2026: 115 · 2025: 157 · 2024: 160 · 2023: 141 · 2022: 111 · 2021: 37
FWCI
52.44
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Kyushu University Institutional Repository (QIR) (Kyushu University) (acceptedVersion, other-oa)
  • arXiv (Cornell University) (submittedVersion)
  • Institutional Repositories DataBase (IRDB) (submittedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • arXiv (Cornell University)
Funders
Ministry of Education, Culture, Sports, Science and Technology (JP17H06100, JP21K17808)
Topics
  • Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
  • Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
  • Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
Keywords
time series data augmentation, time series classification, artificial neural networks, small datasets, generative models
MeSH terms
Big Data, Algorithms, Humans, Pattern Recognition, Automated, Surveys and Questionnaires, Time Factors, Neural Networks, Computer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.