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.
[1]
Aaron C. Courville,et al.
Improved Training of Wasserstein GANs
,
2017,
NIPS.
[2]
Gunnar Rätsch,et al.
Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
,
2017,
ArXiv.
[3]
Juan Ramos-Castro,et al.
Differences in QRS Locations due to ECG Lead: Relationship with Breathing
,
2014
.
[4]
Jeffrey M. Hausdorff,et al.
Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol
,
2000
.
[5]
Tonio Ball,et al.
EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals
,
2018,
ArXiv.
[6]
David A. Clifton,et al.
Towards a Robust Estimation of Respiratory Rate from Pulse Oximeters
,
2016
.