Cross-Domain Adaptation for Biometric Identification Using Photoplethysmogram

Eugene Lee, Annie Ho, Yi Ting Wang, Cheng Han Huang, Chen-Yi Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

The adoption of biomedical signals such as photoplethysmogram (PPG) and electrocardiogram (ECG) for health parameter estimation on wearable devices is growing in tandem with the increase of attention in mobile healthcare. In our work, we use PPG signals extracted from PPG sensors which are used for biometric identification. A challenge for biometric identification using PPG signal is the variation in domain (placement of sensors, wavelengths, device variation, etc.). In this work, we propose the use of both unsupervised and semi-supervised adversarial learning techniques for cross-domain adaptation. As such algorithm will be deployed on wearable devices, we propose a compact model meeting tight memory footprint limitation. All experiments will be simulated using a public dataset (TROIKA) and our in-house dataset. By introducing a cross-domain adaptation approach across sensors, we observe an accuracy gain of 4.15% on our in-house dataset. The proposed semi-supervised learning technique gives an additional accuracy boost of 2.02%.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1289-1293
Number of pages5
ISBN (Electronic)9781509066315
ISBN (Print)978-1-5090-6632-2
DOIs
StatePublished - May 2020
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: 4 May 20208 May 2020

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN (Print)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
CountrySpain
CityBarcelona
Period4/05/208/05/20

Keywords

  • biometric identification
  • Cross-domain adaptation
  • deep learning
  • photoplethysmogram

Fingerprint Dive into the research topics of 'Cross-Domain Adaptation for Biometric Identification Using Photoplethysmogram'. Together they form a unique fingerprint.

Cite this