Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

High dynamic range structured illumination microscopy based on multi-channel fusion and dual-phase binary fringe.

Optics express·2026

Same author

M1 macrophage-derived exosomal miR-155-5p exacerbates aortic dissection via SMAD5-Mediated regulation of vascular smooth muscle cell phenotype.

Bioactive materials·2026

Same author

Synthetic Chimeric Antigen Lysosome-Associated Receptor Redirects Targeted Protein to Degradation.

Journal of the American Chemical Society·2026

Same author

EAGP: an efficient generative augmentation framework for phage protein classification under severe class imbalance.

Bioinformatics (Oxford, England)·2026

Same author

A high-linearity, low-power 10-mm MEMS fast steering mirror with enhanced shock robustness for space laser communications.

Optics letters·2026

Same author

Synergistic Remodeling of Tumor Immune Microenvironment via a DNA Nanodevice Integrating STING Activation and Lysosome-Targeted PD-L1 Degradation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Search research articles

Related Experiment Video

Updated: Jun 2, 2025

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Published on: September 5, 2012

Spiking-PhysFormer: Camera-based remote photoplethysmography with parallel spike-driven transformer.

Mingxuan Liu¹, Jiankai Tang¹, Yongli Chen²

¹Tsinghua University, Beijing, China.

Neural Networks : the Official Journal of the International Neural Network Society

|January 16, 2025

Summary

This summary is machine-generated.

This study introduces Spiking Neural Networks (SNNs) for energy-efficient remote photoplethysmography (rPPG) on mobile devices. The novel Spiking-PhysFormer model significantly reduces power consumption while maintaining accurate physiological signal measurement from facial videos.

Keywords:

Biomedical signal Brain-inspired neural networks Remote photoplethysmography Transformer

More Related Videos

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

Related Experiment Videos

Last Updated: Jun 2, 2025

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Optical Recording of Suprathreshold Neural Activity with Single-cell and Single-spike Resolution

Published on: September 5, 2012

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

Area of Science:

Biomedical Engineering
Computer Science
Artificial Intelligence

Background:

Camera-based remote photoplethysmography (rPPG) utilizes Artificial Neural Networks (ANNs) for accurate physiological signal measurement from facial videos.
High computational demands of existing ANN-based rPPG methods limit their deployment on resource-constrained mobile devices.
Spiking Neural Networks (SNNs) offer energy-efficient deep learning through their binary, event-driven architecture.

Purpose of the Study:

To introduce SNNs into rPPG for the first time, developing an energy-efficient hybrid neural network (HNN) model named Spiking-PhysFormer.
To reduce the power consumption of rPPG systems for practical mobile device applications.
To maintain or improve the accuracy of physiological signal extraction (e.g., heart rate, respiration rate) compared to existing methods.

Main Methods:

Proposed a hybrid neural network (HNN) model, Spiking-PhysFormer, integrating ANN and SNN components.
Developed a parallel spike transformer block to enhance spatio-temporal feature aggregation in SNNs.
Introduced a simplified spiking self-attention mechanism, omitting the value parameter to reduce computational load without performance degradation.

Main Results:

The Spiking-PhysFormer achieved a 10.1% reduction in overall power consumption compared to the PhysFormer model.
Power consumption within the transformer blocks was reduced by a factor of 12.2.
The model demonstrated comparable performance to PhysFormer and other ANN-based models across four benchmark datasets (PURE, UBFC-rPPG, UBFC-Phys, MMPD).

Conclusions:

The proposed Spiking-PhysFormer effectively leverages SNNs for energy-efficient rPPG, addressing the limitations of traditional ANNs on mobile devices.
The hybrid approach and simplified SNN mechanisms offer a promising direction for low-power, accurate physiological monitoring.
This work paves the way for deploying advanced rPPG techniques on edge devices with limited computational resources.