Quick and Easy Time Series Generation with Established Image-based GANs

By Eoin Brophy, Zhengwei Wang, Tomás Ward. 2019

46 citations recorded by the source corpus.

In the recent years Generative Adversarial Networks (GANs) have demonstrated significant progress in generating authentic looking data. In this work we introduce our simple method to exploit the advancements in well established image-based GANs to synthesise single channel time series data. We implement Wasserstein GANs (WGANs) with gradient penalty due to their stability in training to synthesise three different types of data; sinusoidal data, photoplethysmograph (PPG) data and electrocardiograph (ECG) data. The length of the returned time series data is limited only by the image resolution, we use an image size of 64x64 pixels which yields 4096 data points. We present both visual and quantitative evidence that our novel method can successfully generate time series data using image-based GANs.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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. Zhengwei Wang
2. Qi She
3. Tomás Ward
4. Eoin Brophy
5. Qingyun She
6. Alan F. Smeaton
7. Graham F. Healy
8. Mohit Bansal

In Computer Vision and Pattern Recognition

1. Qi She
2. Zhengwei Wang
3. Tomás Ward
4. Qingyun She
5. Eoin Brophy
6. Alan F. Smeaton
7. Graham F. Healy

In Signal Processing

1. Qi She
2. Tomás Ward
3. Zhengwei Wang
4. Alan F. Smeaton
5. Qingyun She
6. Graham F. Healy
7. Eoin Brophy

Citations in the corpus

• Generative Adversarial Networks (2021, neutral): “It was proved successful in many domains such as computer vision [14, 29, 25, 38], semantic segmentation [39, 27, 70, 24], time-series synthesis [9, 23], image editing [61, 36, 19, 3, 75], natural language processing [15, 28, 22], text-to-image generation [59, 58, 54], and many more.”
• Synthetic-Neuroscore: Using a neuro-AI interface for evaluating generative adversarial networks (2019, methodology): “Specifically, GANs have been widely applied to various domains such as computer vision [3], natural language processing [4], speech synthesis [5] and time series synthesis [6].”
• Generative Adversarial Networks in Time Series: A Systematic Literature Review (2022, methodology): “designed a GAN based approach for multivariate time series imputation [42], see Figure 14 for an example of imputed data from a toy experiment [12].”
• Generative Adversarial Networks: A Survey and Taxonomy (2019, methodology): “GANs have been applied to various domains such as computer vision [7]–[14], natural language processing [15]–[18], time series synthesis [19]–[23], semantic segmentation [24]–[28] etc. GANs belong to the family of generative models.”