Vital sign monitoring method based on principal component analysis

Through principal component analysis and adaptive filtering technology, the problem of microwave radar distinguishing the location of the thoracic cavity and abdominal when monitoring human vital signs is solved, which significantly improves the accuracy and accuracy of respiratory rate and heart rate monitoring.

CN119014846APending Publication Date: 2024-11-26XIAMEN KUANGSHI TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411383400.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

When monitoring human vital signs, existing microwave radars are difficult to accurately distinguish between the location of the chest cavity and the abdominal area, resulting in inaccurate monitoring results of respiratory rate and heart rate, and changes in movement will lead to data deviations.

Method used

The method based on principal component analysis is adopted to judge the human body's position through the frequency domain characteristics of the radar microwave echo signal, extract the abdominal breathing characteristics, adaptively filter to separate the chest micromovement signal, and reconstruct the phase data to improve monitoring accuracy.

Benefits of technology

Improve the accuracy and accuracy of vital sign monitoring, distinguish between thoracic and abdominal breathing, suppress noise, and ensure the accuracy of breathing frequency and heart rate calculations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119014846A_ABST
    Figure CN119014846A_ABST
Patent Text Reader

Abstract

The invention discloses a vital sign monitoring method based on principal component analysis, and the method comprises the steps: transmitting a radar microwave signal to a target human body, receiving a path of radar microwave echo signal, and extracting the frequency domain characteristics of the radar microwave echo signal; judging whether the human body is in the bed according to the frequency domain characteristics of the radar microwave echo signals, and if so, extracting abdominal respiration characteristics according to the frequency domain characteristics of the radar microwave echo signals; analyzing to obtain thoracic cavity phase data according to the radar microwave echo signals where the abdominal respiration characteristics are located, and reconstructing the thoracic cavity phase data to obtain reconstructed thoracic cavity phase data; and calculating the heart rate and respiratory rate of the human body according to the reconstructed thoracic cavity phase data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of vital sign monitoring, and in particular to a vital sign monitoring method based on principal component analysis. Background Art

[0002] Microwave radar is a non-contact sensing technology that can be used to detect human vital signs, such as breathing rate and heart rate. Generally, the radar transmitter transmits electromagnetic wave signals to the human target. When the electromagnetic wave signals touch the human body, they will be reflected back to the radar receiver. These reflected electromagnetic wave signals will produce a weak frequency shift due to human breathing and other movements. The human breathing rate and heart rate can be obtained by analyzing the phase of these frequency shifts.

[0003] In a real environment, when a person is lying on a bed, the chest cavity of the person needs to be monitored before the respiratory rate and heart rate can be monitored. However, the existing technology is not accurate enough in searching and determining the chest position, and because the movement amplitude of the chest and abdomen positions when different individuals breathe is not much different, therefore, during the microwave radar monitoring process, the microwave radar data of the abdomen and chest are usually monitored together, and overlap in the returned microwave radar signal at the same time. The monitoring signal processing methods of the two positions are completely different. Direct mixing will lead to inaccurate calculation results of respiratory rate and heart rate monitoring. In addition, because the chest or abdomen position of the human body will change due to movements such as moving and turning over, static monitoring will lead to the selection of the wrong body part and cause deviation in data analysis.

[0004] The purpose of the present invention is to design a vital sign monitoring method based on principal component analysis in view of the above-mentioned problems in the prior art. Summary of the invention

[0005] In view of this, the purpose of the present invention is to propose a vital sign monitoring method based on principal component analysis, which can solve the above-mentioned problems.

[0006] The present invention provides a vital sign monitoring method based on principal component analysis, comprising:

[0007] Send a radar microwave signal to the target human body, receive a radar microwave echo signal, and extract the frequency domain characteristics of the radar microwave echo signal;

[0008] Judging whether the human body is in bed according to the frequency domain characteristics of the radar microwave echo signal, if yes, extracting the abdominal breathing characteristics according to the frequency domain characteristics of the radar microwave echo signal;

[0009] The chest cavity phase data is obtained by analyzing the radar microwave echo signal of the abdominal breathing characteristics, and the chest cavity phase data is reconstructed to obtain the reconstructed chest cavity phase data;

[0010] The human heart rate and respiratory rate are calculated based on the reconstructed chest phase data.

[0011] Further, the extracting frequency domain features of the radar microwave echo signal includes:

[0012] Performing intermediate frequency signal sampling on the radar microwave echo signal to obtain a radar microwave digital signal;

[0013] Perform 2D FFT calculation on the radar microwave digital signal to obtain the frequency domain characteristics of the radar microwave digital signal.

[0014] Further, judging whether the human body is in bed according to the frequency domain characteristics of the radar microwave echo signal includes:

[0015] Comparing the frequency domain characteristics of the radar microwave digital signal with the frequency domain characteristics of the unmanned background to obtain a characteristic difference;

[0016] If the feature difference exceeds the first threshold, the human body is in bed, otherwise the human body is not in bed.

[0017] Further, the extracting of abdominal breathing features according to the frequency domain features of the radar microwave echo signal includes:

[0018] performing cancellation processing on the radar microwave digital signal to obtain an enhanced radar microwave digital signal;

[0019] Perform 1D FTT calculation on the enhanced radar microwave digital signal to obtain the frequency domain characteristics of the enhanced radar microwave digital signal;

[0020] The frequency domain characteristics of the enhanced radar microwave digital signal are analyzed to obtain abdominal breathing characteristics.

[0021] Further, the analysis of the frequency domain characteristics of the enhanced radar microwave digital signal to obtain the abdominal breathing characteristics includes:

[0022] Inputting the frequency domain feature of the enhanced radar microwave digital signal into a pre-trained abdominal breathing feature recognition model for determination, and obtaining a determination result of whether the feature is an abdominal breathing feature;

[0023] If the feature is an abdominal breathing feature, marking the microwave radar signal where the abdominal breathing feature is located;

[0024] If the feature is not a breathing feature, the rotating radar will emit radar microwave signals to the human body until the abdominal breathing feature is found.

[0025] Further, the chest cavity phase data obtained by analyzing the radar microwave echo signal based on the abdominal breathing characteristics includes:

[0026] Adaptively filtering the enhanced radar microwave digital signal according to the abdominal breathing characteristics to obtain chest micro-motion data;

[0027] The phase in the chest micro-motion data is extracted to obtain the chest phase data.

[0028] Further, the step of adaptively filtering the enhanced radar microwave digital signal according to the abdominal breathing characteristics to obtain chest micro-motion data includes:

[0029] The abdominal breathing feature is determined as a reference signal a(n), and the reference signal a(n) is input into an adaptive filter to obtain an abdominal signal component y(n), and the calculation formula is:

[0030]

[0031] Where w(i) is the filter weight and M is the filter length;

[0032] The abdominal signal component y(n) is filtered from the microwave radar signal to obtain the chest micro-motion data e(n), and the calculation formula is:

[0033] e(n)=s(n)-y(n)

[0034] Among them, s(n) is the microwave radar signal, that is, a mixed signal of abdominal breathing data and chest micro-motion data.

[0035] Furthermore, before inputting the reference signal a(n) into the adaptive filter to obtain the abdomen signal component y(n), the following steps are performed:

[0036] The adaptive filter weights are updated using the least mean square algorithm, and the calculation formula is:

[0037] w(n+1)=w(n)+2·μ·e(n)·a(n)

[0038] Among them, μ is the step size factor.

[0039] Further, the reconstructing the chest phase data to obtain the reconstructed chest phase data includes:

[0040] Reorganize the chest phase data into a matrix and extract chest eigenvalues ​​and eigenvectors;

[0041] Remove the noise in the chest cavity eigenvalues ​​and eigenvectors, and retain the eigenvalues ​​and eigenvectors of respiratory frequency and heart rate;

[0042] The eigenvalues ​​and eigenvectors of the respiratory frequency and heart rate are reconstructed respectively to obtain reconstructed respiratory frequency phase data and heart rate phase data.

[0043] Further, the calculating of the heart rate and respiratory rate of the human body according to the reconstructed chest phase data includes:

[0044] Filtering the reconstructed respiratory frequency phase data and heart rate phase data to obtain standard respiratory frequency phase data and standard heart rate phase data;

[0045] The number of breaths is calculated based on the standard respiratory frequency phase data, and the number of heart beats is calculated based on the standard heart rate phase data.

[0046] Beneficial effects of the present invention:

[0047] First, it determines whether the human body is in bed through the frequency domain characteristics of the radar microwave echo signal, and further determines the position of the human abdomen by rotating the radar to find the abdominal breathing characteristics, and then eliminates the interference or background signal components of the radar microwave echo signal and enhances the target signal (here it is the signal changes caused by the human body, especially abdominal breathing). This processing helps to highlight the target features and thus improve detection accuracy.

[0048] Secondly, the chest phase data is obtained by analyzing the radar microwave echo signal where the abdominal breathing characteristics are located. The abdominal signal component is extracted from the mixed signal through adaptive filtering, and then the relatively weak chest micro-motion signal is separated. By effectively separating the chest micro-motion signal, the accuracy and precision of heart rate and respiratory rate monitoring are significantly improved, and the influence of different breathing methods of different people is solved by distinguishing between chest breathing and abdominal breathing.

[0049] Third, by reconstructing the chest phase data, the process of extracting and reconstructing the phase processing enhances the respiratory frequency and heart rate parts of the signal and suppresses the noise. The phase reconstruction is performed through eigenvalues ​​and eigenvectors, which solves the distortion problem in signal processing and ensures more accurate subsequent calculation of respiratory frequency and heart rate. For the reconstructed signal, filtering in a specific frequency band can enhance the characteristics of the target signal, making the peaks of the heart rate and respiratory frequency more obvious, which is convenient for accurate counting. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a flow chart of the main steps of the first embodiment.

[0052] Figure 2 It is an overall step flow chart of the first embodiment. DETAILED DESCRIPTION

[0053] In order to facilitate understanding by those skilled in the art, the structure of the present invention is further described in detail with reference to the embodiments and the accompanying drawings. It should be understood that the steps mentioned in the present embodiment, unless otherwise specified in their order, can be adjusted in order according to actual needs, and can even be executed simultaneously or partially simultaneously.

[0054] Embodiment 1

[0055] like Figure 1 and Figure 2 As shown, an embodiment of the present invention provides a vital sign monitoring method based on principal component analysis, comprising:

[0056] S1 sends a radar microwave signal to the target human body, receives a radar microwave echo signal, and extracts the frequency domain characteristics of the radar microwave echo signal;

[0057] S101 performs intermediate frequency signal sampling on the radar microwave echo signal to obtain a radar microwave digital signal;

[0058] S102 performs 2D FFT calculation on the radar microwave digital signal to obtain frequency domain characteristics of the radar microwave digital signal.

[0059] In this step, the radar is installed at an appropriate position according to the position of the human body and the bed, so that the radar beam is facing the chest of the person, and the microwave radar signal is sent to the chest of the target person through the radar. This application adopts a one-transmit-one-receive frequency-modulated continuous wave radar with only one receiving antenna and one transmitting antenna. By sampling the intermediate frequency signal of the radar microwave reflection signal, the accuracy of the microwave signal in the process of converting from analog to digital is ensured, and the uncertainty and noise interference in the analog signal processing are effectively eliminated. Through two-dimensional fast Fourier transform (2D FFT) calculation, the time domain of the radar microwave echo signal can be converted to the frequency domain, thereby effectively extracting the frequency domain characteristics of the signal, which helps to distinguish and analyze specific frequency components in the signal, especially when detecting and identifying target human features.

[0060] S2 determines whether the human body is in bed according to the frequency domain characteristics of the radar microwave echo signal, and if so, extracts the abdominal breathing characteristics according to the frequency domain characteristics of the radar microwave echo signal;

[0061] S201 compares the frequency domain characteristics of the radar microwave digital signal with the frequency domain characteristics of the unmanned background to obtain a characteristic difference;

[0062] S202: If the feature difference exceeds the first threshold, the human body is in bed; otherwise, the human body is not in bed.

[0063] In this step, by comparing the frequency domain characteristics of the radar microwave digital signal with the frequency domain characteristics of the unmanned background, the signal changes caused by the presence of the human body can be identified. When the human body is in bed, it will cause specific reflections and variations in the microwave signal, which can be reflected in the frequency domain characteristics. By comparing the collected return signal with the signal of the unmanned background, the interference of environmental noise can also be effectively eliminated.

[0064] S203 performs cancellation processing on the radar microwave digital signal to obtain an enhanced radar microwave digital signal;

[0065] S204 performs 1D FTT calculation on the enhanced radar microwave digital signal to obtain frequency domain characteristics of the enhanced radar microwave digital signal;

[0066] In this step, cancellation processing is a technique used to remove specific frequency bands or signal components. Cancellation can suppress interference or background signal components and enhance target signals (in this case, signal changes caused by the human body, especially abdominal breathing). This processing helps to highlight target features and thus improve detection accuracy. Performing a one-dimensional fast Fourier transform (1D FTT) helps capture periodic changes caused by abdominal breathing, because the impact of respiratory motion on radar signals is manifested in the frequency domain as energy changes within a specific frequency range.

[0067] S205 analyzes the frequency domain characteristics of the enhanced radar microwave digital signal to obtain abdominal breathing characteristics.

[0068] S2051: inputting the frequency domain feature of the enhanced radar microwave digital signal into a pre-trained abdominal breathing feature recognition model for determination, and obtaining a determination result of whether the feature is an abdominal breathing feature;

[0069] S2052 If the feature is an abdominal breathing feature, marking the microwave radar signal where the abdominal breathing feature is located;

[0070] S2053 If the feature is not a breathing feature, the rotating radar emits a radar microwave signal to the human body until the abdominal breathing feature is found.

[0071] In this step, since the position of the human chest or abdomen will change due to movements such as moving and turning over, static monitoring will result in the selection of the wrong body part and cause deviations in data analysis. Furthermore, since the abdominal breathing frequency is greater than the chest breathing frequency and the frequency performance is more obvious, the abdominal breathing frequency is used to determine the location of the human abdomen. The radar in this application has a rotation function. Only after confirming that the current position is the abdomen will the monitored radar echo signal be used for subsequent judgment. By using a pre-trained model to determine whether the frequency domain characteristics of the enhanced radar microwave signal are abdominal breathing characteristics, the accuracy can be improved. During the training process, the model has learned the pattern of identifying this feature, which can improve detection accuracy in complex or high-noise environments.

[0072] The abdominal breathing feature recognition model is trained through the following steps:

[0073] A number of radar microwave monitoring signal fragments of different body shapes, genders and ages are collected, and 2D FFT calculation is performed on the radar microwave monitoring signal fragments, and the frequency domain characteristics of each radar microwave signal are extracted to form abdominal breathing feature recognition samples, and the abdominal breathing feature recognition samples are labeled as containing "abdominal breathing features" and not containing "abdominal breathing features" to form an abdominal breathing feature recognition sample data set, and the labeled signal fragments are classified into positive samples containing "abdominal breathing features" and negative samples not containing "abdominal breathing features" to ensure that the ratio of positive and negative samples is reasonable to avoid deviations during model training; the abdominal breathing feature recognition model is constructed through a neural network model, and the abdominal breathing feature recognition model is trained through the abdominal breathing feature recognition sample training set to obtain the parameters of the abdominal breathing feature recognition model.

[0074] S3 obtains chest cavity phase data according to the radar microwave echo signal analysis of the abdominal breathing characteristics, reconstructs the chest cavity phase data, and obtains reconstructed chest cavity phase data;

[0075] S301 adaptively filters the enhanced radar microwave digital signal according to the abdominal breathing characteristics to obtain chest micro-motion data;

[0076] S3011 determines the abdominal breathing feature as a reference signal a(n), inputs the reference signal a(n) into an adaptive filter, and obtains an abdominal signal component y(n), and the calculation formula is:

[0077]

[0078] Where w(i) is the filter weight and M is the filter length;

[0079] S3012 filters the abdominal signal component y(n) from the microwave radar signal to obtain the chest micro-motion data e(n), and the calculation formula is:

[0080] e(n)=s(n)-y(n)

[0081] Among them, s(n) is the microwave radar signal, that is, a mixed signal of abdominal breathing data and chest micro-motion data.

[0082] Furthermore, before inputting the reference signal a(n) into the adaptive filter to obtain the abdomen signal component y(n), the following steps are performed:

[0083] The adaptive filter weights are updated using the least mean square algorithm, and the calculation formula is:

[0084] w(n+1)=w(n)+2·μ·e(n)·a(n)

[0085] Among them, μ is the step size factor.

[0086] In this step, abdominal breathing and chest micro-movements (such as small changes in breathing and heart rate) exist simultaneously in the microwave radar echo signal, resulting in signal superposition. This step extracts the abdominal signal component from the mixed signal through adaptive filtering, and then separates the relatively weak chest micro-motion signal. By effectively separating the chest micro-motion signal and distinguishing between chest breathing and abdominal breathing, the influence of different breathing methods of different people is solved, which significantly improves the accuracy and precision of heart rate and respiratory rate monitoring. The use of adaptive filtering and the least mean square algorithm allows the system to automatically adjust the weights, dynamically adapt to the signal differences in different individuals or different environmental changes, and achieve a wider range of application scenarios.

[0087] S302 extracts the phase in the chest micro-motion data to obtain chest phase data.

[0088] Further, the reconstructing the chest phase data to obtain the reconstructed chest phase data includes:

[0089] Reorganize the chest phase data into a matrix and extract chest eigenvalues ​​and eigenvectors;

[0090] Remove the noise in the chest cavity eigenvalues ​​and eigenvectors, and retain the eigenvalues ​​and eigenvectors of respiratory frequency and heart rate;

[0091] The eigenvalues ​​and eigenvectors of the respiratory frequency and heart rate are reconstructed respectively to obtain reconstructed respiratory frequency phase data and heart rate phase data.

[0092] In this step, the process of extracting and reconstructing phase processing enhances the respiratory frequency and heart rate parts of the signal and suppresses noise. Phase reconstruction is performed through eigenvalues ​​and eigenvectors, which solves the distortion problem in signal processing and ensures more accurate subsequent calculation of respiratory frequency and heart rate.

[0093] S4 calculates the heart rate and respiratory rate of the human body based on the reconstructed chest phase data.

[0094] S401 filters the reconstructed respiratory frequency phase data and heart rate phase data to obtain standard respiratory frequency phase data and standard heart rate phase data;

[0095] S402 calculates the number of respirations according to the standard respiratory frequency phase data, and calculates the number of heartbeats according to the standard heart rate phase data.

[0096] In this step, even after reconstruction, there may still be some residual noise and false signals in the signal (for example, interference introduced by sensor errors or environmental factors) or periodic errors that may be introduced during the phase reconstruction process. Filtering again helps to further reduce these interfering error signals and make the monitored features more accurate. For the reconstructed signal, filtering in a specific frequency band can enhance the characteristics of the target signal, making the peaks of the heart rate and respiratory rate more obvious, which is convenient for accurate counting.

[0097] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0101] It should be noted that in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0102] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0103] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0104] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0105] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms should not be understood as necessarily referring to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

Claims

1. A vital sign monitoring method based on principal component analysis, characterized in that: include: Send a radar microwave signal to the target human body, receive a radar microwave echo signal, and extract the frequency domain characteristics of the radar microwave echo signal; Judging whether the human body is in bed according to the frequency domain characteristics of the radar microwave echo signal, if yes, extracting the abdominal breathing characteristics according to the frequency domain characteristics of the radar microwave echo signal; The chest cavity phase data is obtained by analyzing the radar microwave echo signal of the abdominal breathing characteristics, and the chest cavity phase data is reconstructed to obtain the reconstructed chest cavity phase data; The human heart rate and respiratory rate are calculated based on the reconstructed chest phase data.

2. The method for monitoring vital signs based on principal component analysis according to claim 1, characterized in that: The frequency domain feature extraction of radar microwave echo signal includes: Performing intermediate frequency signal sampling on the radar microwave echo signal to obtain a radar microwave digital signal; Perform 2D FFT calculation on the radar microwave digital signal to obtain the frequency domain characteristics of the radar microwave digital signal.

3. The method for monitoring vital signs based on principal component analysis according to claim 2, characterized in that: The step of judging whether a human body is in bed according to the frequency domain characteristics of the radar microwave echo signal comprises: Comparing the frequency domain characteristics of the radar microwave digital signal with the frequency domain characteristics of the unmanned background to obtain a characteristic difference; If the feature difference exceeds the first threshold, the human body is in bed, otherwise the human body is not in bed.

4. The method for monitoring vital signs based on principal component analysis according to claim 2, characterized in that: The step of extracting abdominal breathing features according to the frequency domain features of the radar microwave echo signal comprises: performing cancellation processing on the radar microwave digital signal to obtain an enhanced radar microwave digital signal; Perform 1D FTT calculation on the enhanced radar microwave digital signal to obtain the frequency domain characteristics of the enhanced radar microwave digital signal; The frequency domain characteristics of the enhanced radar microwave digital signal are analyzed to obtain abdominal breathing characteristics.

5. The method for monitoring vital signs based on principal component analysis according to claim 4, characterized in that: The analyzing the frequency domain characteristics of the enhanced radar microwave digital signal to obtain the abdominal breathing characteristics includes: Inputting the frequency domain feature of the enhanced radar microwave digital signal into a pre-trained abdominal breathing feature recognition model for determination, and obtaining a determination result of whether the feature is an abdominal breathing feature; If the feature is an abdominal breathing feature, marking the microwave radar signal where the abdominal breathing feature is located; If the feature is not a breathing feature, the rotating radar will emit radar microwave signals to the human body until the abdominal breathing feature is found.

6. The method for monitoring vital signs based on principal component analysis according to claim 5, characterized in that: The chest cavity phase data obtained by analyzing the radar microwave echo signal based on the abdominal breathing characteristics includes: Adaptively filtering the enhanced radar microwave digital signal according to the abdominal breathing characteristics to obtain chest micro-motion data; The phase in the chest micro-motion data is extracted to obtain the chest phase data.

7. The method for monitoring vital signs based on principal component analysis according to claim 6, characterized in that: The step of adaptively filtering the enhanced radar microwave digital signal according to the abdominal breathing characteristics to obtain chest micro-motion data comprises: The abdominal breathing feature is determined as a reference signal a(n), and the reference signal a(n) is input into an adaptive filter to obtain an abdominal signal component y(n), and the calculation formula is: Where w(i) is the filter weight and M is the filter length; The abdominal signal component y(n) is filtered from the microwave radar signal to obtain the chest micro-motion data e(n), and the calculation formula is: e(n)=s(n)-y(n) Among them, s(n) is the microwave radar signal, that is, a mixed signal of abdominal breathing data and chest micro-motion data.

8. The method for monitoring vital signs based on principal component analysis according to claim 7, characterized in that: The reference signal a(n) is input into the adaptive filter to obtain the abdominal signal component y(n) before performing: The adaptive filter weights are updated using the least mean square algorithm, and the calculation formula is: w(n+1)=w(n)+2·μ·e(n)·a(n) Among them, μ is the step size factor.

9. The method for monitoring vital signs based on principal component analysis according to claim 7, characterized in that: The reconstructing the chest cavity phase data to obtain the reconstructed chest cavity phase data includes: Reorganize the chest phase data into a matrix and extract chest eigenvalues ​​and eigenvectors; Remove the noise in the chest cavity eigenvalues ​​and eigenvectors, and retain the eigenvalues ​​and eigenvectors of respiratory frequency and heart rate; The eigenvalues ​​and eigenvectors of the respiratory frequency and heart rate are reconstructed respectively to obtain reconstructed respiratory frequency phase data and heart rate phase data.

10. The method for monitoring vital signs based on principal component analysis according to claim 9, characterized in that: Calculating the heart rate and respiratory rate of the human body according to the reconstructed chest phase data includes: Filtering the reconstructed respiratory frequency phase data and heart rate phase data to obtain standard respiratory frequency phase data and standard heart rate phase data; The number of breaths is calculated based on the standard respiratory frequency phase data, and the number of heart beats is calculated based on the standard heart rate phase data.