Quick and Easy Time Series Generation with Established Image-based GANs
This provides a simple method for time series generation, but it is incremental as it applies existing GAN techniques to a new data type without major innovations.
The authors tackled the problem of generating single-channel time series data by adapting established image-based GANs, specifically using Wasserstein GANs with gradient penalty, and demonstrated successful generation of sinusoidal, PPG, and ECG data with up to 4096 data points per series.
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.