Evolving SimGANs to Improve Abnormal Electrocardiogram Classification
Not on the map. Why?
Abstract (arXiv)
Machine Learning models are used in a wide variety of domains. However, machine learning methods often require a large amount of data in order to be successful. This is especially troublesome in domains where collecting real-world data is difficult and/or expensive. Data simulators do exist for many of these domains, but they do not sufficiently reflect the real world data due to factors such as a lack of real-world noise. Recently generative adversarial networks (GANs) have been modified to refine simulated image data into data that better fits the real world distribution, using the SimGAN method. While evolutionary computing has been used for GAN evolution, there are currently no frameworks that can evolve a SimGAN. In this paper we (1) extend the SimGAN method to refine one-dimensional data, (2) modify Easy Cartesian Genetic Programming (ezCGP), an evolutionary computing framework, to create SimGANs that more accurately refine simulated data, and (3) create new feature-based quantitative metrics to evaluate refined data. We also use our framework to augment an electrocardiogram (ECG) dataset, a domain that suffers from the issues previously mentioned. In particular, while healthy ECGs can be simulated there are no current simulators of abnormal ECGs. We show that by using an evolved SimGAN to refine simulated healthy ECG data to mimic real-world abnormal ECGs, we can improve the accuracy of abnormal ECG classifiers.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 33 references that are in the map. First posted on arXiv 12 May 2022.
Builds on
17 of 33 references.
References · 17
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2022Generative Adversarial Networkscited by 5,627
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2016Improved Techniques for Training GANscited by 2,970
- 2017Improved Training of Wasserstein GANscited by 2,235
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
- 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
- 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 288
- 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 213
- 2018Evolutionary Generative Adversarial Networkscited by 42
5 more
- 2020SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classificationcited by 32
- 2019COEGAN: Evaluating the Coevolution Effect in Generative Adversarial Networkscited by 13
- 2019Spatial Evolutionary Generative Adversarial Networkscited by 10
- 2018Skill Rating for Generative Modelscited by 4
- 2021Evolving GAN Formulations for Higher Quality Image Synthesiscited by 3
Built on by
Citing papers per year: 2023: 1.
1 paper.