Touchless Heart Rate Variability Detection via Radar Chest Displacement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for measuring heart rate variability (HRV) require physical contact, such as electrode pads or wearable devices, which are inconvenient and limit the ease of use.

Innovation Solution

A contactless method using a radar unit to detect chest displacement and extract inter-beat interval (IBI) data, processed by a neural network to infer HRV without physical contact.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If ECG or PPG methods are used to measure HRV, then measurement precision is improved, but ease of operation deteriorates due to required physical contact

Engineering Contradiction:
ImproveHRV measurement precisionVSAvoidease of use
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces mechanical contact-based measurement systems (ECG electrodes, PPG optical sensors requiring skin contact) with a radar-based electromagnetic detection system. The radar unit detects chest displacement through radio wave reflection without physical contact, thereby maintaining measurement precision while eliminating the need for electrode pads or wearable devices.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces radar waves as an intermediary medium to transfer information about chest displacement from the subject to the measurement system. The radar unit transmits radio waves that reflect off the chest, and the reflected waves carry displacement information back to the sensor, enabling contactless measurement while preserving accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If contactless radar detection is used, then ease of operation is improved, but measurement precision deteriorates due to low signal-to-noise ratio

Engineering Contradiction:
Improveease of useVSAvoidsignal-to-noise ratio
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent extracts the heartbeat signal from the composite radar signal by separating it from respiration and other noise components. The system processes the raw radar displacement data to isolate the cardiac-related displacement patterns, effectively extracting the useful heartbeat information while removing distracting respiration and movement noise.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent performs preliminary signal processing and noise filtering on the radar data before HRV analysis. By pre-processing the displacement signal to remove respiration components and other artifacts beforehand, the system prepares cleaner data for subsequent heartbeat interval detection, thereby improving measurement precision despite the contactless nature of detection.

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The method effectively separates heartbeat and respiration signals, overcoming low signal-to-noise ratios, and provides accurate HRV measurements through a non-invasive, touchless system.

Implementation Method 1

the sensor is a radar unit configured to transmit a radio wave on the object and detect a reflection of the radio wave

Methodology Applied
Scientific EffectRadar: Radar

Data Source

PatentUS12268529B2Systems and methods for touchless detection of heart rate variability
Publication Date: 2025.04.08 WISTRON CORP
  • US12268529B2 patent drawing
  • US12268529B2 patent drawing
  • US12268529B2 patent drawing

AI summary

An apparatus and a method for detecting heartbeat include a sensor configured to detect displacements of an object without contacting the object wherein the object displaces corresponding the a human's heartbeat, a data processing unit configured to extract a feature dataset from the detected displacement data, and a neural network configured to inference inter beat intervals from the extracted feature dataset using a pre-trained model.