Loading web-font TeX/Main/Regular
Disentangled Adversarial Autoencoder for Subject-Invariant Physiological Feature Extraction | IEEE Journals & Magazine | IEEE Xplore

Disentangled Adversarial Autoencoder for Subject-Invariant Physiological Feature Extraction


Abstract:

Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner. One major cha...Show More

Abstract:

Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner. One major challenge of physiological sensing lies in the variability of biosignals across different users and tasks. To address this issue, we propose an adversarial feature extractor for transfer learning to exploit disentangled universal representations. We consider the trade-off between task-relevant features and user-discriminative information by introducing additional adversary and nuisance networks in order to manipulate the latent representations such that the learned feature extractor is applicable to unknown users and various tasks. Results on cross-subject transfer evaluations exhibit the benefits of the proposed framework, with up to 8.8\% improvement in average accuracy of classification, and demonstrate adaptability to a broader range of subjects.
Published in: IEEE Signal Processing Letters ( Volume: 27)
Page(s): 1565 - 1569
Date of Publication: 31 August 2020

ISSN Information:

PubMed ID: 33746496

Funding Agency:


References

References is not available for this document.