Millimeter-Wave Radar Vital Sign Estimation with Signal Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing radar-based vital sign estimation systems face challenges such as susceptibility to multiple reflections, multipath effects, motion artifacts, random body movements, and intermodulation products, which affect the accuracy and reliability of heartbeat and respiration rate measurements.
Innovation Solution
The system employs a millimeter-wave radar to generate a time-domain displacement signal from in-phase and quadrature signals, compensates for random body movements and intermodulation products, classifies the signals as high or low quality, and uses a deep neural network to discard low-quality data, thereby improving the accuracy of vital sign estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radar-based vital sign estimation is performed using traditional signal processing methods, then the system can detect heartbeat and respiration rates, but the measurements are affected by noise, multiple reflections, multipath effects, motion artifacts, and intermodulation products, reducing accuracy and reliability
Solution Approach 1:
The system transforms the raw radar signal from time domain to frequency domain through Fourier transform, then to instantaneous frequency domain, changing the parameter representation to enable better separation of vital sign frequencies from noise and interference components
Solution Approach 2:
The signal processing is divided into multiple stages: initial Fourier transform to obtain frequency spectrum, identification of intermodulation products, ellipse fitting for phase extraction, instantaneous frequency analysis, and final classification. Each stage segments the processing to address specific types of interference separately
Solution Approach 3:
The system identifies and utilizes the characteristic frequencies of intermodulation products (sum and difference frequencies of heartbeat and respiration) to inform the classification process. By detecting these harmful interference patterns, the system can exclude contaminated signal segments, converting the harmful effect into a useful classification criterion
2Reliability
If all detected signals are processed for vital sign estimation, then the system maintains continuous monitoring capability, but low-quality data with motion artifacts and random body movements reduces overall measurement reliability
Solution Approach 1:
The system performs preliminary classification of signal quality before final vital sign extraction. By evaluating signal characteristics (frequency content, ellipse quality, motion consistency) in advance, the system identifies and excludes low-quality segments before they can contaminate the final measurement, ensuring only reliable data contributes to the output
Solution Approach 2:
The system extracts and removes problematic signal components including intermodulation products, random body movement artifacts, and multipath reflections through targeted filtering and exclusion criteria applied at different processing stages, leaving only the clean vital sign signals for final measurement
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
This approach enables contactless and non-invasive monitoring of vital signs with enhanced accuracy by filtering out noise and motion artifacts, leading to more reliable heartbeat and respiration rate measurements.
Implementation Method 1
A radar system, and in particular a millimeter-wave radar, may be used to monitor vital signs
Implementation Method 2
receiving a reflection of the frequency modulated signal
Implementation Method 3
determining a distance based on a time delay and/or frequency difference between the transmission and reception of the frequency modulated signal
Data Source
Figure 1~2
Figure 3~4
Figure 5~8
AI summary
In an embodiment, a method includes: receiving radar signals with a millimeter-wave radar; generating range data based on the received radar signals; detecting a target based on the range data; performing ellipse fitting on in-phase (I) and quadrature (Q) signals associated with the detected target to generate compensated I and Q signals associated with the detected target; classifying the compensated I and Q signals; when the classification of the compensated I and Q signals correspond to a first class, determining a displacement signal based on the compensated I and Q signals, and determining a vital sign based on the displacement signal; and when the classification of the compensated I and Q signals correspond to a second class, discarding the compensated I and Q signals.