Search Results for author: Eoin Brophy

Found 8 papers, 3 papers with code

Generation of Synthetic Electronic Health Records Using a Federated GAN

no code implementations6 Sep 2021 John Weldon, Tomas Ward, Eoin Brophy

It was shown that there was no significant reduction in the quality of the synthetic EHR when we moved between training a single central model and training on separate data silos with individual models before combining them into a central model.

Federated Learning Synthetic Data Generation

Generative adversarial networks in time series: A survey and taxonomy

1 code implementation23 Jul 2021 Eoin Brophy, Zhengwei Wang, Qi She, Tomas Ward

We propose a taxonomy of discrete-variant GANs and continuous-variant GANs, in which GANs deal with discrete time series and continuous time series data.

Time Series

Estimation of Continuous Blood Pressure from PPG via a Federated Learning Approach

1 code implementation24 Feb 2021 Eoin Brophy, Maarten De Vos, Geraldine Boylan, Tomas Ward

To our knowledge, this framework is the first example of a GAN capable of continuous ABP generation from an input PPG signal that also uses a federated learning methodology.

Federated Learning Time Series

Optimised Convolutional Neural Networks for Heart Rate Estimation and Human Activity Recognition in Wrist Worn Sensing Applications

no code implementations30 Mar 2020 Eoin Brophy, Willie Muehlhausen, Alan F. Smeaton, Tomas E. Ward

These same sampling frequencies also yielded a robust heart rate estimation which was comparative with that achieved at the more energy-intensive rate of 256 Hz.

Activity Recognition Heart rate estimation +1

Synthesis of Realistic ECG using Generative Adversarial Networks

3 code implementations19 Sep 2019 Anne Marie Delaney, Eoin Brophy, Tomas E. Ward

Finally, we discuss the privacy concerns associated with sharing synthetic data produced by GANs and test their ability to withstand a simple membership inference attack.

De-identification Inference Attack +2

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

no code implementations14 Feb 2019 Eoin Brophy, Zhengwei Wang, Tomas E. Ward

In the recent years Generative Adversarial Networks (GANs) have demonstrated significant progress in generating authentic looking data.

Time Series

Cannot find the paper you are looking for? You can Submit a new open access paper.