Autoencoder Neural Networks for Outlier Correction in ECG- Based Biometric Identification

@article{Karpinski2018AutoencoderNN,
  title={Autoencoder Neural Networks for Outlier Correction in ECG- Based Biometric Identification},
  author={Mikolai Karpinski and V. V. Khoma and Valerii Dudvkevych and Yuriv Khoma and Dmytro Sabodashko},
  journal={2018 IEEE 4th International Symposium on Wireless Systems within the International Conferences on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS-SWS)},
  year={2018},
  pages={210-215}
}
  • Mikolai Karpinski, V. V. Khoma, +2 authors Dmytro Sabodashko
  • Published in
    IEEE 4th International…
    2018
  • Computer Science
  • The paper presents a novel method based on autoencoder neural networks for detection and correction of ECG heartbeats outliers. [...] Key Method, optimal autoencoder architecture for the detecting of electrocardiogram (ECG) outliers was chosen. In order to validate our method., we used the open source Physionet ECG-ID database. Results obtained in the paper have been compared to previously developed techniques. On the one hand autoencoder demonstrates slightly higher error rate., but is much easier to…Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 18 REFERENCES

    Principal Component Analysis

    • Ian T. Jolliffe
    • Computer Science
    • International Encyclopedia of Statistical Science
    • 2011
    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Biometrie identification from raw ECG signal using deep learning techniques

    Deep learning The MIT Press, 2016

    • Ian Goodfellow, Yoshua Bengio, Aaron Courville
    • 2016
    VIEW 1 EXCERPT

    EEG artifact removal-state-of-the-art and guidelines.

    VIEW 2 EXCERPTS

    Individual identification via electrocardiogram analysis

    VIEW 1 EXCERPT