Time Series Data Augmentation for Deep Learning: A Survey
It provides a structured overview for researchers and practitioners working with time series data in domains like healthcare and AIOps, but it is incremental as it synthesizes existing methods rather than introducing new ones.
This survey systematically reviews data augmentation methods for time series data, proposing a taxonomy and comparing them empirically across tasks like classification and anomaly detection to address the challenge of limited labeled data in deep learning applications.
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.