Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Boron-doped black titanium dioxide for visible-light and sacrificial-agent-free photocatalytic nitrate reduction.

Journal of colloid and interface science·2026
Same author

Action-Aware Multimodal Wavelet Fusion Network for Quantitative Elbow Motor Function Assessment Using sEMG and Robotic Kinematics.

Sensors (Basel, Switzerland)·2026
Same author

ECG-AuxNet: A Dual-Branch Spatial-Temporal Feature Fusion Framework With Auxiliary Learning for Enhanced Cardiac Disease Diagnosis.

IEEE journal of biomedical and health informatics·2026
Same author

The role of executive function for differentiating symptoms of ADHD in preschoolers.

BMC pediatrics·2026
Same author

VAM: A Parallel Cross-Modal Hybrid Network for Accurate and Interpretable Vascular Age Estimation from PPG.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Unleashing the Power of Pretrained Transformer for Dense Prediction in Physiological Signals.

IEEE journal of biomedical and health informatics·2025

Related Experiment Video

Updated: Sep 21, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.2K

Biometric recognition based on scalable end-to-end convolutional neural network using photoplethysmography: A

Daomiao Wang1, Qihan Hu1, Cuiwei Yang2

  • 1Center for Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai, 200433, PR China.

Computers in Biology and Medicine
|May 31, 2022
PubMed
Summary

Scalable 1D-CNNs enhance biometric recognition using photoplethysmography (PPG) signals from wearables. These models effectively capture long-range dependencies, improving security and performance for sensitive information.

Keywords:
Biometric recognitionConvolutional neural networksDeep learningLong-rang dependenciesPhotoplethysmography (PPG)

More Related Videos

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

33.9K
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

15.4K

Related Experiment Videos

Last Updated: Sep 21, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.2K
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

33.9K
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

15.4K

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Machine Learning

Background:

  • Photoplethysmography (PPG) is a widely used physiological signal on wearable devices for biometric recognition.
  • Current PPG recognition methods face limitations in power and computational efficiency for practical deployment on wearables.
  • 1D Convolutional Neural Networks (1D-CNNs) struggle to model long-range dependencies crucial for high-security PPG biometrics.

Purpose of the Study:

  • To investigate scalable end-to-end 1D-CNNs for capturing long-range dependencies in PPG signals.
  • To evaluate the performance of these models in parameterizing authorized templates for biometric recognition.
  • To compare the effectiveness of stacking convolution operations, non-local blocks, and attention mechanisms for improved LRD capture.

Main Methods:

  • Comparative study of seven scalable 1D-CNN models against a baseline.
  • Enlarging receptive fields through stacked convolution, non-local blocks, and attention mechanisms.
  • Utilizing three datasets (VitalDB, BIDMC, PRRB) for performance evaluation and visualization techniques (Gramian Angular Summation Field, Class Activation Map).

Main Results:

  • Scalable models demonstrated varying impacts on recognition accuracy, ranging from -0.2% to 9.9% compared to the baseline.
  • State-of-the-art performance achieved with over 97% accuracy on VitalDB.
  • Highest accuracy on BIDMC (99.5%) and PRRB (99.3%) datasets using scalable 1D-CNNs.
  • Visualizations confirmed the effect of capturing LRD in generated templates.

Conclusions:

  • Scalable 1D-CNNs offer a performance-excellent and complexity-feasible approach for PPG-based biometric recognition.
  • These models effectively address the limitations of existing methods for power-constrained wearable devices.
  • The study highlights the importance of capturing long-range dependencies for robust and secure PPG biometric systems.