Time Series Data Augmentation for Deep Learning: A Survey

By Qingsong Wen, Liang Sun, Xiaomin Song, Jing Gao, Xue Wang, Huan Xu. International Joint Conference on Artificial Intelligence, 2020

844 citations recorded by the source corpus.

Deep learning performs remarkably well on many time series analysis tasks recently. The superior performance of deep neural networks relies heavily on a large number of training data to avoid overfitting. However, the labeled data of many real-world time series applications may be limited such as classification in medical time series and anomaly detection in AIOps. As an effective way to enhance the size and quality of the training data, data augmentation is crucial to the successful application of deep learning models on time series data. In this paper, we systematically review different data augmentation methods for time series. We propose a taxonomy for the reviewed methods, and then provide a structured review for these methods by highlighting their strengths and limitations. We also empirically compare different data augmentation methods for different tasks including time series classification, anomaly detection, and forecasting. Finally, we discuss and highlight five future directions to provide useful research guidance.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/e5cd9e7bd60954a0523cc849ad6c92c0ede2d271

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data (2021, background): “Many scholars have published relevant research results discussing the class-imbalanced problem at the algorithm level [52]–[54].”
Data-centric Artificial Intelligence: A Survey (2023, neutral): “The early surveys only focus on specific aspects of data-centric AI rather than providing a comprehensive overview, such as data augmentation [69, 204, 238], data labeling [266], and feature selection [129].”
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting (2022, background): “OPs (including Legendre, Laguerre, Chebyshev, etc.) and other orthogonal basis (Fourier and Multiwavelets) are widely studied in numerous ﬁelds and recently brought in deep learning Wang et al. (2018); Gupta et al. (2021); Zhou et al. (2022); Voelker et al. (2019); Gu et al. (2020).”
A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, methodology): “Data augmentation methods have also been used for time series [204] and tabular datasets for a wide rage of applications.”
Data Augmentation techniques in time series domain: a survey and taxonomy (2022, methodology): “Previous works were centred on a specific model or approximation, with works such as [21, 22, 16].”
A Survey on Data Augmentation for Text Classification (2021, neutral): “[6] and is adapted for the text classification domain.”
Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review (2023, background): “Data augmentation [410], [411] and representation learning could [412] be two promising future research directions to mitigate the data inconsistency problem at the edge.”
A survey of uncertainty in deep neural networks (2021, neutral): “The most important approaches for modeling this separation are Bayesian inference [30], [20], [37], [9], [38], ensemble approaches [31], [39], [40], test time data augmentation approaches [41], [42], or single deterministic networks containing explicit components to represent the model and the data ”
An empirical survey of data augmentation for time series classification with neural networks (2020, background): “While data augmentation is a common practice in image recognition with neural networks, it is not established as a normal procedure for time series recognition [18].”
Transformers in Time Series: A Survey (2022, background): “…2021; Benidis et al. , 2022; Torres et al. , 2021 ] , classiﬁcation [ Is-mail Fawaz et al. , 2019 ] , anomaly detection [ Choi et al. , 2021; Bl ´ azquez-Garc ´ ıa et al. , 2021 ] , and data augmentation [ Wen et al. , 2021b ] , but there is no comprehensive survey for Transformers in time series.”