5 Hits in 3.5 sec

SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification [article]

Tomer Golany, Daniel Freedman, Kira Radinsky
2020 arXiv   pre-print
Generating training examples for supervised tasks is a long sought after goal in AI. We study the problem of heart signal electrocardiogram (ECG) synthesis for improved heartbeat classification.  ...  We study how to incorporate this knowledge into the generative process by leveraging a biological simulator for the task of ECG classification.  ...  The approach presented here is not specific to cardiac cycles; it applies equally well to any system described mathematically by differential equations.  ... 
arXiv:2006.15353v1 fatcat:rnc7mfb5dbhvdk2s5gzne22fy4

Evolving SimGANs to Improve Abnormal Electrocardiogram Classification [article]

Gabriel Wang, Anish Thite, Rodd Talebi, Anthony D'Achille, Alex Mussa, Jason Zutty
2022 pre-print
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.  ...  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.  ...  The resultant synthetic data generated was shown to improve ECG classification when using the new synthetic data for training ECG classifiers.  ... 
doi:10.1145/3520304.3534048 arXiv:2205.10116v1 fatcat:mzxcbrhwkffb3o4pbuhdbqygbq

Representation Learning and Pattern Recognition in Cognitive Biometrics: A Survey

Min Wang, Xuefei Yin, Yanming Zhu, Jiankun Hu
2022 Sensors  
There is a major need to summarize the latest developments in this field. Existing surveys have mainly focused on a small subset of cognitive biometric modalities, such as EEG and ECG.  ...  A taxonomy is designed to structure the corresponding knowledge and guide the survey from signal acquisition and pre-processing to representation learning and pattern recognition.  ...  The ECG simulation knowledge learned by the simGAN has been proved to improve ECG classification. Shin et al. [146] proposed a GAN that uses ECG as input to generate photoplethysmogram (PPG).  ... 
doi:10.3390/s22145111 pmid:35890799 pmcid:PMC9320620 fatcat:7cniceltrbfkjk6hxfqij5yegm

Generative Adversarial Networks for Spatio-temporal Data: A Survey [article]

Nan Gao, Hao Xue, Wei Shao, Sichen Zhao, Kyle Kai Qin, Arian Prabowo, Mohammad Saiedur Rahaman, Flora D. Salim
2021 arXiv   pre-print
Generative Adversarial Networks (GANs) have shown remarkable success in producing realistic-looking images in the computer vision area.  ...  Recently, GAN-based techniques are shown to be promising for spatio-temporal-based applications such as trajectory prediction, events generation and time-series data imputation.  ...  [52] proposed the simulator-based GANs for ECG synthesis to improve a supervised classification.  ... 
arXiv:2008.08903v3 fatcat:pbhxbfgw65bodksjdmwazwo4dq

Spatiotemporal Data Mining: A Survey on Challenges and Open Problems [article]

Ali Hamdi, Khaled Shaban, Abdelkarim Erradi, Amr Mohamed, Shakila Khan Rumi, Flora Salim
2021 arXiv   pre-print
We explain issues related to STDM tasks of classification, clustering, hotspot detection, association and pattern mining, outlier detection, visualisation, visual analytics, and computer vision tasks.  ...  We attempt to fill this gap by providing a comprehensive literature survey on state-of-the-art advances in STDM.  ...  Golany, T., Radinsky, K., Freedman, D.: Simgans: Simulator-based generative adversarial networks for ecg synthesis to improve deep ecg classification.  ... 
arXiv:2103.17128v1 fatcat:ci5pt5bytndr5inolznjsaizpi