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

By Brian Kenji Iwana, Seiichi Uchida. 2020

667 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Management Science and Operations Research, Optimization & Training, Probabilistic & Bayesian Methods, Signal Processing

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

1. Rohitash Chandra
2. Liang Sun
3. Jing Gao
4. Xue Wang
5. Huan Xu
6. Azal Ahmad Khan
7. Omkar Chaudhari
8. Qingsong Wen

In Management Science and Operations Research

1. Rohitash Chandra
2. Liang Sun
3. Xue Wang
4. Azal Ahmad Khan
5. Omkar Chaudhari
6. Qingsong Wen

In Optimization & Training

1. Rohitash Chandra
2. Liang Sun
3. Xue Wang
4. Azal Ahmad Khan
5. Omkar Chaudhari
6. Qingsong Wen

In Probabilistic & Bayesian Methods

1. Rohitash Chandra
2. Azal Ahmad Khan
3. Omkar Chaudhari

In Signal Processing

1. Rohitash Chandra
2. Liang Sun
3. Xue Wang
4. Azal Ahmad Khan
5. Omkar Chaudhari
6. Qingsong Wen

Citations in the corpus

• A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, methodology): “Data augmentation [37, 38, 39] is a data-level approach for enhancing machine learning models which has also been used for handling the CI problem by reducing class imbalance.”
• Time Series Data Augmentation for Deep Learning: A Survey (2020, background): “One work closely related to ours is [Iwana and Uchida, 2020] which presents a survey of existing data augmentation methods for time series classification.”