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

Search research articles

Related Experiment Videos

Non-Contact Blood Pressure Prediction Using Radar with a Lightweight Temporal Multi-Scale Feature Fusion Network.

Yuhan Liu¹, Tianlin Zhang¹, Yonggang Luo²

¹School of Optoelectronic Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.

Sensors (Basel, Switzerland)

|June 12, 2026

Summary

Related Concept Videos

Assessing Blood pressure using a doppler ultrasound

Assessing Blood pressure using a doppler ultrasound

To obtain accurate blood pressure measurements in clinical settings, especially when traditional methods are insufficient, healthcare professionals utilize the Doppler ultrasound technique. This method uses high-frequency sound waves to detect blood flow within the arteries, which is crucial for patients with conditions that complicate circulatory system assessment.
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:

Measurement of Blood Pressure

Measurement of Blood Pressure

Assessing blood pressure is a standard procedure executed in virtually all medical environments. The method utilized today was established over a hundred years ago by an innovative Russian doctor, Dr. Nikolai Korotkoff. The soft ticking noise, known as Korotkoff sounds, heard while taking blood pressure readings results from turbulent blood flow within the vessels. The apparatus required for this procedure includes a sphygmomanometer, a blood pressure cuff attached to a gauge, and a stethoscope.

You might also read

Related Articles

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

Sort by

Same author

Genomic surveillance and molecular evolution of SARS-CoV-2 in Zhangzhou, China (2022-2025).

Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases·2026

Same author

Longwave-transparent low-emissivity material.

Science advances·2026

Same author

Global prevalence of dry Eye: A systematic review and meta-analysis.

Contact lens & anterior eye : the journal of the British Contact Lens Association·2026

Same author

Clinical characteristics and therapies of multi-organ immune related adverse events.

Clinical and experimental medicine·2026

Same author

Electroacupuncture alleviates pain by activating the MD2/TLR4/NF-κB pathway in the ST36 acupoint.

Frontiers in immunology·2026

Same author

Redefining Dendritic Cell Vaccines: Synergistically Co-priming DC and B Cells With Nanoparticles Loading Whole Cell Antigens Maximizes the Efficacy of DC Vaccines.

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

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

This summary is machine-generated.

A new lightweight network (LULMNet) enables accurate, non-contact blood pressure monitoring by effectively analyzing radar signals. This method shows promise for continuous hypertension screening and management.

Area of Science:

Biomedical Engineering
Signal Processing
Artificial Intelligence

Background:

Hypertension is a critical global health concern requiring continuous monitoring for early detection and intervention.
Existing radar-based non-contact blood pressure methods struggle with multi-scale temporal feature utilization and model complexity.

Purpose of the Study:

To develop a lightweight network, LULMNet, for accurate non-contact blood pressure prediction and waveform reconstruction.
To address limitations in existing methods concerning temporal feature extraction and model complexity.

Main Methods:

A two-stage training strategy using a lightweight one-dimensional U-Net (1D U-Net) for feature extraction and waveform reconstruction.
Multi-scale feature fusion from the 1D U-Net encoder, followed by LSTM-based temporal modeling and regression for SBP and DBP estimation.

Keywords:

blood pressure prediction hypertension neural network non-contact measurement radar

Related Experiment Videos

Utilized Global Average Pooling (GAP) and a two-layer fully connected prediction head.

Main Results:

Achieved high accuracy with errors of 3.21 ± 4.94 mmHg for SBP and 2.25 ± 3.39 mmHg for DBP, meeting the BHS Grade A standard.
Obtained a low Normalized Mean Absolute Error (NMAE) of 0.044 for blood pressure waveform reconstruction.
Maintained low model complexity with 3.0 M parameters and 0.37 G FLOPs.

Conclusions:

LULMNet offers a computationally efficient and accurate solution for non-contact continuous blood pressure monitoring.
The model demonstrates significant potential for practical application in hypertension screening and management.
The proposed method effectively fuses multi-scale temporal features for improved prediction accuracy.