Non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition

Abstract

The invention relates to a non-contact multi-target heart rate variability (HRV) detection method based on adaptive variational mode decomposition (VMD). The method comprises the following steps: firstly, performing multi-target detection on human body targets in a detected scene by using a radar technology so as to determine an accurate distance window of each target; then, a signal phase is extracted from the distance window through a differential and cross multiplication algorithm, and then the thoracic cavity displacement signal of each person to be detected is obtained. According to the method, an improved GOA algorithm is adopted to optimize VMD parameters, a new adaptive function HIE (combining permutation entropy, mutual information amount and energy loss rate) is provided to serve as a target function of GOA, and complete self-adaptive VMD decomposition of chest displacement signals of each to-be-tested person is achieved. Through the decomposition, the heartbeat signals and the breathing signals are extracted respectively, so that the heart rate variation characteristic of each person to be detected can be accurately detected. The method provides a high-precision and non-contact HRV detection means, and is suitable for a multi-target scene.

Description

Technical Field

[0001] The present invention belongs to the technical fields of millimeter wave radar sensors, heart rate variability detection, signal processing, etc., and specifically relates to a non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition. Background Art

[0002] Heart Rate Variability (HRV) refers to the change in the difference in the period of consecutive heartbeats (Inter-Beat Interval, IBI), and is an important physiological indicator that reflects the autonomic nervous system's ability to regulate heart rhythm. As a non-invasive physiological parameter, HRV is widely used to assess the overall heart health and the ability of the autonomic nervous system (ANS) responsible for regulating heart activity. Traditional HRV detection methods usually rely on electrocardiograms (ECG) or heart rate monitoring instruments. These devices have problems such as inconvenient layout and uncomfortable wearing. They are not suitable for special groups such as infants, skin burn patients, and sleep breathing disorder patients, and have great limitations.

[0003] In recent years, the rapid development of non-contact HRV detection technology has provided a new way to solve the above problems. These technologies can obtain physiological signals without directly contacting the body of the monitored object, which not only avoids the user's discomfort, but also can be applied to special groups. Such as voice signal-based, thermal imaging-based, RGB image-based, and laser-based methods, but these methods each have very obvious disadvantages, such as being easily affected by environmental factors such as light, privacy leakage, and inability to measure for a long time.

[0004] Radio frequency-based methods can effectively solve the above problems because radio frequency signals are not affected by environmental factors such as light and temperature, and can penetrate non-metallic media. They extract breathing and heartbeat information by emitting electromagnetic waves and receiving reflected signals reflected from the human chest cavity due to changes in tiny movements caused by breathing and heartbeat.

[0005] The patent with publication number CN116236188A proposes a heart rate determination method. This method determines multiple predicted heart rates through differential operations and similarity judgments. However, the HRV estimation in this method needs to be accurate to the exact time of each heartbeat, which is much more complicated than simply detecting the heart rate. Factors such as breathing, trunk movement, and environmental noise can interfere with the heartbeat signal, making the accurate estimation of HRV extremely challenging. Therefore, most existing heart rate detection methods cannot meet the high-precision requirements of HRV estimation.

[0006] The patent with publication number CN118000698A proposes a heart rate variability monitoring device and method based on millimeter wave radar. It includes a signal preprocessing module and a heart rate variability algorithm processing module. The signal preprocessing is completed by eliminating static clutter from the signal, separating the random movement of the human body, and removing the information segments damaged by movement. In the heart rate variability algorithm processing module, the chest phase composite signal is decomposed, and the parameters are selected by the sparrow search algorithm, and finally the heartbeat signal is extracted. However, the high-order harmonic components of breathing will inevitably affect the heartbeat signal. At the same time, the high-order harmonic components of breathing have similar waveforms to the heartbeat signal, which may directly lead to the wrong selection of the heartbeat signal, which will lead to a decrease in the accuracy of HRV detection.

[0007] The patent with publication number CN114732390A proposes a non-contact heart rate variability monitoring method based on frequency modulated continuous wave radar. The location of the heart of the monitored object is extracted by FFT; the motion information of the heart of the monitored object is extracted by phase correlation, and the acceleration signal is calculated; the obtained acceleration signal is smoothed, and the position of the segmentation point between each heartbeat is estimated by the peak detection method; the acceleration template signal of a single heartbeat is generated and the acceleration signal is precisely segmented to obtain the heartbeat interval of each heartbeat, and the heart rate variability index is calculated. However, the use of acceleration templates has obvious limitations. A single template cannot handle a variety of heartbeat waveforms, and the disadvantages are obvious under long-term monitoring. And this method is only applicable to a single target. In the case of multiple targets, the motion signal of the heart extracted by this method is weaker, and it is difficult to make a correct HRV estimate.

[0008] In summary, traditional HRV detection methods, such as electrocardiogram and heart rate monitoring instruments, have problems such as inconvenient layout and uncomfortable wearing, and are not suitable for special groups such as infants, skin burn patients, and sleep breathing disorder patients; some non-contact HRV detection methods, such as those based on voice signals, thermal imaging, RGB images, and lasers, are easily affected by environmental factors such as light, privacy leakage, and cannot be measured for a long time; and the existing HRV detection method based on millimeter-wave radar still has signal extraction difficulties and interference problems in multi-target scenarios. Summary of the invention

[0009] In view of the above problems, the present invention provides a method for continuous HRV monitoring that is more accurate and applicable to multi-target scenarios.

[0010] In summary, in order to overcome the interference of respiratory high-order harmonics, human trunk motion and environmental noise on heartbeat signal extraction in multi-target scenarios, the present invention proposes a non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition, and makes two important innovations in the signal processing method:

[0011] (1) A heartbeat signal extraction method named Health-VMD is proposed. This method uses the improved locust optimization algorithm (GOA) to optimize the variational mode decomposition (VMD) parameters, and can fully adaptively extract heartbeat signals from human chest displacement signals in multi-target scenes for HRV estimation.

[0012] (2) An objective function HIE that conforms to the characteristics of vital sign signals is designed for Health-VMD. The objective function consists of three indicators: permutation entropy, mutual information, and energy loss rate. It can accurately extract heartbeat signals in complex environments such as multi-targets and effectively suppress interference such as respiratory high-order harmonics and human trunk movement.

[0013] This solution can achieve high-accuracy HRV detection for multiple people, and it is contact-free and highly applicable. These advantages make this solution have important application potential and practical value in the field of HRV detection and analysis.

[0014] The method first uses radar technology to perform multi-target detection on human targets in the measured scene to determine the precise distance window of each target. Subsequently, the signal phase is extracted from the distance window through differentiation and cross-multiplication algorithm, and the chest displacement signal of each subject to be measured is obtained. The present invention uses an improved GOA algorithm to optimize the VMD parameters, and proposes a new adaptation function HIE (combining permutation entropy, mutual information and energy loss rate) as the objective function of GOA to achieve fully adaptive VMD decomposition of the chest displacement signal of each subject to be measured. Through this decomposition, the heartbeat signal and the breathing signal are extracted respectively, so that the heart rate variability characteristics of each subject to be measured can be accurately detected. The present method provides a high-precision, non-contact HRV detection method suitable for multi-target scenarios.

[0015] The technical solution specifically adopted by the present invention to solve the technical problem is:

[0016] A non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition: after obtaining the precise distance window of each human target in the measured scene by performing multi-target detection on the original radar data signal, the phase of the signal in the distance window is extracted by differentiation and cross-multiplication algorithm, so as to obtain the chest displacement signal of each subject to be tested; through the VMD method with adaptive parameters and using the adaptation function HIE for vital sign signal extraction as the objective function of GOA, a fully adaptive VMD decomposition of the chest displacement signal of each subject to be tested is realized, and the heartbeat signal and breathing signal of each subject to be tested are obtained, and then the heart rate variability characteristics of each subject to be tested are detected from the heartbeat signal.

[0017] Furthermore, the signal processing flow of the multi-target detection includes distance FFT, angle FFT, static clutter elimination, minimum unit mean constant false alarm rate detection and DBSCAN clustering.

[0018] Furthermore, before extracting the phase of the signal within the range window by using the differentiation and cross-multiplication algorithm, a least squares-based circle fitting method is used to estimate the DC component, and then the DC component is eliminated from the signal to achieve the purpose of DC offset correction.

[0019] Furthermore, the adaptive parameter VMD method optimizes the modal number and modal bandwidth control parameters of VMD through an improved GOA optimization algorithm; the improved GOA optimization algorithm introduces a nonlinear decreasing coefficient on the basis of GOA, and this coefficient changes with the increase of the number of algorithm iterations, thereby enhancing the global search capability and local search capability in the early and late stages of the iteration, respectively, thereby improving the convergence accuracy of the algorithm; and introduces the Levy flight strategy to improve the GOA algorithm, thereby preventing the algorithm from falling into local optimality by promoting population diversity.

[0020] Further, the mathematical model of the improved GOA optimization algorithm is as follows:

[0021]

[0022] Among them, Y i represents the position of the i-th locust in the locust swarm, and the superscript d represents the improved algorithm; d ij =|x i -x j | is the distance between the i-th individual and the j-th individual, N is the number of individuals in the population, and z is the function that defines the interaction force between individuals:

[0023]

[0024] Among them, p represents the strength of attraction, and q is the range of attraction scale;

[0025] ub d and lb d are the upper and lower bounds of the D-dimensional search space, respectively. represents the best individual in the current population, and parameter c is the improved nonlinear decreasing coefficient, which is calculated by the following formula;

[0026]

[0027] In the formula, l represents the current iteration number of the algorithm, and L represents the maximum iteration number;

[0028] The Levy flight strategy is used to improve the GOA algorithm, which can avoid the algorithm from falling into the local optimum by promoting population diversity.

[0029] The Levy flight is introduced to update the individual positions of locusts. In each iteration, a random 1 / 3 of the locusts are allowed to update their positions using the Levy flight strategy. The formula is as follows:

[0030]

[0031] Where size(D) represents the dimension of the problem to be solved (here it can be understood as the number of variables in the optimization problem. For example, if the optimization numbers are the number of modes and the modal bandwidth control parameters, the dimension of the problem is 2). Represents dot product, i represents the current iteration number, which is used to control the flight distance, and β represents the Levy index, so that a larger search range can be performed in the early stage of the iteration, and a smaller search range can be performed in the later stage.

[0032] Furthermore, the product of permutation entropy, mutual information, and energy loss ratio is used as the objective function to achieve parameter optimization through the GOA algorithm, as shown in the following formula:

[0033] HIE=H X ·H Y ·I(X;Y)·e

[0034] Among them, HIE represents the objective function, H X represents the permutation entropy of the respiratory component, H Y represents the permutation entropy of the heartbeat component, I(X;Y) represents the mutual information between the respiratory component and the heartbeat component, and e represents the energy loss ratio.

[0035] Furthermore, the permutation entropy formulas of the respiratory component and the heartbeat component are as follows:

[0036]

[0037] Where H represents the permutation entropy, N is the total number of permutations, and p i represents the probability of occurrence of the i-th element;

[0038] The formula for the mutual information between the respiratory component and the heartbeat component is as follows:

[0039]

[0040] Where I(X;Y) represents the mutual information between the respiratory signal X and the heartbeat signal Y, p(x,y) represents the joint probability distribution function, and p(x) and p(y) represent the marginal probability distribution functions of X and Y respectively.

[0041] The formula for energy loss ratio is as follows:

[0042]

[0043] Where f(m) represents the human chest displacement signal, u k represents the kth modal component, Σu k Represents the reconstructed signal.

[0044] Furthermore, the process of VMD decomposition is:

[0045] Firstly, the GOA parameters are initialized and several random parameter combinations are generated. Then, VMD decomposition is performed on each parameter combination to find the respiratory and heartbeat signal components whose frequencies are within the respiratory frequency range and the heartbeat frequency range. HIE is calculated and the minimum HIE and the corresponding parameter combination are recorded. The mutual information between the heartbeat component and the respiratory component is calculated respectively, and the component with the minimum mutual information is selected as the heartbeat signal component. Then, 2 / 3 of the locusts update their positions according to the mathematical model of the improved GOA optimization algorithm, and 1 / 3 of the locusts perform Levy flight. Subsequently, a new minimum HIE and the corresponding parameter combination are calculated. The parameter combination is iteratively updated according to the conditions until the end criterion is met. Finally, the optimal parameter combination is output as the global optimal solution.

[0046] And, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition as described above are implemented.

[0047] A non-transitory computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition as described above.

[0048] Compared with the prior art, the non-contact multi-target HRV detection scheme based on millimeter-wave radar proposed by the present invention and its preferred solution has significant advantages. By using millimeter-wave radar to collect signals and applying advanced processing algorithms, the scheme can monitor the HRV of multiple targets at the same time, which provides significant convenience for continuous HRV monitoring in a multi-target environment.

[0049] Compared with the method of HRV detection by calculating acceleration signals, differential enhancement algorithm and other schemes, the present invention can realize simultaneous detection of multiple people through multi-target recognition, such as distinguishing multiple targets by dimensions such as distance and angle.

[0050] Compared with the heart rate extraction method using VMD, the VMD algorithm with adaptive parameters proposed in the present invention uses an improved GOA optimization algorithm for parameter optimization. The algorithm can fully adaptively extract the heartbeat signal from the human chest displacement signal. At the same time, an objective function HIE that is more suitable for heartbeat signal extraction is proposed. This method can extract more accurate HRV information, is not easily affected by human trunk movement, environmental noise interference, and respiratory high-order harmonic components, and has stronger robustness and versatility.

[0051] Its main innovations include at least:

[0052] 1. A HRV monitoring method combined with multi-target detection is proposed to achieve simultaneous detection of heart rate variability (HRV) of multiple people. In addition, more accurate heart rate information can be obtained through HRV.

[0053] 2. A VMD decomposition method with adaptive parameters is proposed. The VMD parameters are adaptively optimized through an improved GOA optimization algorithm to adapt to different application scenarios and the physiological signal characteristics of different individuals.

[0054] 3. A new objective function HIE is proposed, which is specially designed for extracting human vital signs signals. Using it in the VMD parameter optimization algorithm can obtain more accurate heartbeat signals.

[0055] This method uses an adaptive parameter optimization algorithm and a newly proposed objective function HIE to achieve continuous HRV monitoring of multiple targets. It solves the problem that the heartbeat signal is easily affected by the high-order harmonic components of the human body's trunk movement and respiratory signals, and achieves continuous HRV monitoring of multiple targets. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0057] Figure 1 Schematic diagram of the overall solution of an embodiment of the present invention;

[0058] Figure 2Flowchart of the improved VMD algorithm provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the features and advantages of this patent more obvious and easy to understand, the following embodiments are specifically described in detail as follows:

[0060] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0061] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0062] First, the specific implementation process and steps of the non-contact multi-target HRV detection method based on millimeter wave radar provided in the embodiment of the present invention are as follows: Figure 1 As shown:

[0063] Step 1: Collecting radar raw data signals about multiple targets;

[0064] Step 2: Perform multi-target detection on the radar raw data signal, mainly to identify multiple targets and obtain the distance and azimuth of each target, including range FFT, angle FFT, static clutter elimination, minimum unit mean constant false alarm rate (SOCA-CFAR) detection and DBSCAN clustering. After this step, the radar signal detection window corresponding to each target to be detected in the detection interval can be confirmed;

[0065] Step 3: After obtaining the precise distance window of the target from the previous step, the phase of the signal in the distance window is further extracted through the Differentiate and Crossmultiply (DACM) algorithm to obtain the human chest displacement signal. In order to eliminate the influence of the DC components of the I and Q channels on the phase extraction, a DC offset compensation operation is performed;

[0066] Step 4: Using the proposed VMD method with adaptive parameters, preferably optimizing the VMD parameters through the improved GOA optimization algorithm, and using the proposed adaptation function HIE for vital sign signal extraction as the objective function of GOA, the human chest displacement signal is fully adaptively decomposed by VMD to obtain the heartbeat signal, and finally HRV estimation is performed.

[0067] The following is a detailed introduction to the multi-target HRV detection method that the present invention focuses on:

[0068] Generally, HRV detection can be divided into three main steps: target recognition, phase extraction, and heartbeat signal extraction. Among them, target recognition mainly identifies multiple targets and obtains the distance and angle of each target, and determines the detection window of each target. The specific signal processing process includes distance FFT, angle FFT, static clutter elimination, minimum unit mean constant false alarm rate (SOCA-CFAR) detection, and DBSCAN clustering. The target detection window is obtained in a flexible way. It can combine distance and azimuth information for precise spatial positioning, or only use single information (such as distance or azimuth) to simplify the process or reduce costs.

[0069] After obtaining the detection window of the target to be measured, this embodiment further extracts the phase information of the signal in the detection window through DACM phase extraction. In order to eliminate the influence of the DC components of the I and Q channels on the phase extraction, a DC offset compensation operation needs to be performed.

[0070] The invention uses a VMD method with adaptive parameters to extract heartbeat signals, and optimizes VMD parameters through an improved GOA optimization algorithm. In addition, an adaptation function HIE targeting the characteristics of vital sign signals is proposed as the objective function of GOA to improve the accuracy of heartbeat signal extraction.

[0071] (1) Target recognition: It is crucial to perform target detection before vital sign detection. For example, determining the detection window by distance. First, it is necessary to determine the distance bin where the target is located, and perform a fast Fourier transform (FFT) on each chirp in a fast time, that is, a distance FFT, to locate the target.

[0072]

[0073] In the formula, X(i,m) is the corresponding distance bin information, i is the index of the distance bin, and s IF (n,m) represents the digitized channel information of the nth ADC sample and the mth chirp. After the range FFT, the range bin with the target has a larger energy than the reflection range bin without the target. In indoor scenes, various static objects (such as walls, tables, metal objects, etc.) have strong reflections on electromagnetic waves. These static targets may generate higher range bin energy than human targets, thus affecting the detection of human targets. Therefore, it is necessary to eliminate the interference of static target clutter.

[0074] Since the frequency and phase of the static target echo signal remain basically unchanged in the received signals of the same antenna at different times, while the echo signal of the target chest cavity will change, the background clutter cancellation algorithm is used to eliminate static clutter. After the vectors of the echo signals at different times are added and averaged, the amplitude of the static target echo remains the original size, while the dynamic target echo becomes smaller by vector cancellation. The echo signals at other times are subtracted from the averaged signal, and the static target echo is subtracted, while the dynamic target echo is less affected, so that the static clutter signal can be effectively eliminated. The implementation process is: first, the intermediate frequency signals at different times on each receiving antenna are averaged to obtain a reference intermediate frequency signal; then all intermediate frequency signals are subtracted from the reference intermediate frequency signal, so that the static clutter elimination is completed, which can be expressed as:

[0075]

[0076]

[0077] Wherein, M is the number of sampling points in the slow time dimension. After the static clutter is eliminated, it is necessary to detect the target in the Range-FFT spectrum and obtain the range of the distance bin where the target is located. Since the distance bin without a reflective target only contains noise, the energy of the distance bin with a reflective target is greater than that of the distance bin without a reflective target. However, due to the different distances of different targets, it can be known from the radar principle that the near reflection energy is large and the far reflection energy is small. Therefore, it is impossible to set a predetermined energy threshold for target detection, so the CFAR algorithm is used to detect the target. The CFAR algorithm is a method that can adaptively adjust the threshold according to the interference noise level so that the false alarm probability remains at a constant value. Since there are multiple targets in the scene, in order to avoid the masking effect and reduce the missed detection rate, this embodiment uses the SOCA-CFAR algorithm to detect the target.

[0078] Since the human target has a certain volume and contains multiple reflection points, the head, chest, and limbs of the human body may generate echo signals. After CFAR detection, there will be multiple distance bins corresponding to the same target. Therefore, a clustering algorithm is needed to identify the number of targets and divide the multiple distance bins of the same target together. DBSCAN is a density-based clustering algorithm that can divide data points into different clusters according to their density distribution. It does not require the number of clusters to be specified in advance, and can identify noise data and exclude it from the clusters. Considering the uncertainty of the number of targets in actual application scenarios, the DBSCAN algorithm is used for clustering without knowing the number of clusters.

[0079] Unlike other parts of the human body, the distance between the human chest and the radar changes slowly due to breathing and heartbeat movements, resulting in obvious phase changes. Therefore, the distance bin of the human chest has a large phase variance. The distance bin with the largest phase variance within the distance bin range in each clustering result is selected, corresponding to the distance bin where the human chest movement is most obvious, for further analysis.

[0080] (2) Phase extraction: After completing human target detection, in order to restore the displacement of the human chest, it is necessary to extract phase information from the target position. However, due to the inevitable defects of circuit components, the extracted phase signal will contain a DC component, causing the phase to deviate from the true value and produce phase distortion. is the target chest distance bin information at distance bin index j, and the extracted phase can be expressed as:

[0081]

[0082] Where DC I 、DC Q The real and imaginary parts of the DC bias are respectively. The DC component is estimated by the circle fitting method based on the least squares (LS), and then eliminated in the signal to achieve the purpose of DC bias correction, which can be expressed as:

[0083]

[0084]

[0085] After DC offset compensation, the phase information of the complex signal needs to be extracted. When measuring displacements above half a wavelength, FMCW radar has a phase ambiguity problem caused by phase jumps, especially for millimeter-wave FMCW radar (wavelength is 4 mm at 77 GHz). The chest movement range caused by breathing and heartbeat is 0.2 to 12 mm, and the phase ambiguity problem is particularly serious. In general, in order to solve this problem, a phase unwrapping algorithm is usually used to calibrate the phase. However, this algorithm greatly increases the computational complexity. At the same time, if there is noise, the automatic calibration may fail. In order to solve this problem, an extended DACM algorithm is used to solve the phase discontinuity problem, which is expressed as:

[0086]

[0087] Then, the human chest displacement signal can be expressed as:

[0088]

[0089] (3) Heartbeat signal extraction: After obtaining the human chest displacement signal, the heartbeat signal must be decomposed from it. The human chest displacement signal is mainly composed of breathing signals and heartbeat signals. The chest movement range caused by breathing is 1-12 mm and the frequency is 0.1-0.5 Hz, while the chest movement range caused by heartbeat is 0.2-0.5 mm and the frequency is 0.8-2.0 Hz. The two can be regarded as quasi-periodic signals, and the human breathing and heartbeat signals have different characteristics in amplitude and frequency. Therefore, the VMD decomposition method can be used to decompose the human chest displacement signal. However, the selection of parameters in the VMD decomposition method will have a great impact on the decomposition results. Therefore, this scheme proposes an adaptive parameter VMD decomposition method, which can fully adaptively decompose the vital sign signal, use the improved GOA for parameter optimization, and propose a function HIE based on the characteristics of the vital sign signal as the objective function of GOA. In this way, the heartbeat signal can be extracted and HRV can be estimated.

[0090] The core idea of ​​VMD is to construct and solve the variational problem. Assuming that the human chest displacement signal f(m) is decomposed into K components, the decomposition sequence is guaranteed to be a modal component with a limited bandwidth and a center frequency, and the sum of the estimated bandwidths of each mode is minimized. The constraint condition is that the sum of all modes is equal to the human chest displacement signal, then the VMD constrained variational model is as follows:

[0091]

[0092] Among them, u k ={u1,u2,...,u K} are the modal functions, ω k ={ω1,ω2,...,ω K} is the center frequency of each mode.

[0093] In order to solve the above constrained optimization problem, the quadratic penalty term α and the Lagrange multiplier λ are used to transform the constrained variational problem into an unconstrained variational problem, and the augmented Lagrangian is introduced.

[0094]

[0095] The saddle point of the augmented Lagrangian is found in the iterative suboptimization sequence using the ADMM method. Specifically, for all ω ≥ 0, update

[0096]

[0097] Where l is the number of iterations, f(m), u k (m), the frequency domain expression of λ(m), and then update ω k :

[0098]

[0099] For all ω ≥ 0, update:

[0100]

[0101] In the formula, γ represents the noise tolerance. Continue the above iteration until the convergence condition is met:

[0102]

[0103] Where ε represents the convergence criterion tolerance. The setting of parameters is crucial. If the number of modes K is too large, the actual information contained in each mode may be reduced; conversely, if it is too small, the decomposition may be insufficient and the important features of the signal cannot be accurately captured. If the modal bandwidth control parameter (or quadratic penalty term) α is too large, the signal may lack detailed information; conversely, if it is too small, the mode may contain more noise. The setting of these two parameters will have a great impact on the decomposition results. Compared with these two parameters, γ and ε have less impact on the decomposition results, and the default values ​​in the original VMD algorithm are usually used. Therefore, finding the optimal parameter combination that matches the signal is the key to the VMD method.

[0104] Locusts often hunt and migrate in large-scale gatherings. Larvae move in a small range and slowly, while adult locusts can move quickly in a large space. The GOA algorithm is a new swarm intelligence optimization algorithm derived by simulating the group characteristics of locusts. Compared with differential evolution (DE), particle swarm optimization (PSO), and gray wolf optimization (GWO), the GOA algorithm has the advantages of stronger global search capabilities and faster convergence speed. Its mathematical model is shown in the formula:

[0105] Y i =S i +G i +A i (15)

[0106] Among them, Y i represents the position of the i-th locust in the locust swarm, S i is the mutual influence between the i-th locust and other individuals in the population, G i is the gravity on the i-th locust, A i is the wind force experienced by the i-th locust.

[0107] S i The expression is as follows:

[0108]

[0109] Among them, dij =|x i -x j | is the distance between the i-th individual and the j-th individual, is the unit vector from the ith individual to the jth individual, N is the number of individuals in the population, and z is the function that defines the interaction force between individuals:

[0110]

[0111] Among them, p represents the strength of attraction, and q represents the range of attraction. In this paper, p=0.5, q=1.5 are taken to limit the positions of individuals in the population to the range of [1,4] to ensure that there is mutual interaction between individuals in the population.

[0112] In order to solve the problem that the original locusts quickly reach the comfort zone but the group does not converge to the specified point. The present invention modifies the original GOA and introduces an improved nonlinear decreasing coefficient, which changes with the increase of the number of algorithm iterations, thereby enhancing the global search ability and local search ability in the early and late stages of the iteration respectively. The improved mathematical model equation is as follows:

[0113]

[0114] Among them d and lb d are the upper and lower bounds of the D-dimensional search space, respectively. Represents the optimal individual in the current population, and parameter c is the improved nonlinear decreasing coefficient, which is calculated by the following formula.

[0115]

[0116] In the formula, l represents the current iteration number of the algorithm, and L represents the maximum iteration number. The use of nonlinear weight coefficients can make the value of the inertia weight change less in the early and late iterations, so that the algorithm can strengthen the global search ability in the early iteration and have better local development ability in the late iteration, thereby improving the convergence accuracy of the algorithm.

[0117] Due to the rapid decrease in species diversity, in order to prevent the GOA algorithm from converging to the local optimum too early, the Levy flight strategy is used to improve the GOA algorithm, and the algorithm is prevented from falling into the local optimum by promoting population diversity. Levy flight is a non-Gaussian random process whose step size follows the Levy distribution. The characteristics of Levy flight are random walks with smaller step sizes, and occasionally directional mutation jumps with larger step sizes, which effectively increases the diversity of individual positions in the population and prevents the algorithm from falling into the local optimum.

[0118] The Levy distribution is defined as follows:

[0119] Levy(y)~|y-β (20)

[0120] In the formula, β represents the Levy index, and y represents the step length of the Levy flight. The Mantegna algorithm is used to simulate the step length of the Levy flight, and the calculation formula is as follows:

[0121] y=μ / |ν| 1 / β (twenty one)

[0122] Where, β = 1.5, μ and ν follow Gaussian distribution, in σ ν =1, Γ(·) represents the gamma function.

[0123] The Levy flight is introduced to update the individual positions of locusts. In each iteration, a random 1 / 3 of the locusts are allowed to update their positions using the Levy flight strategy. The formula is as follows:

[0124]

[0125] Where size(D) represents the dimension of the problem, Represents dot product, i represents the current iteration number, which is used to control the flight distance, so that a larger search range can be performed in the early stage of iteration, and a smaller search range can be performed in the later stage.

[0126] The objective function is a key factor in determining the quality of the decomposition results in the VMD method. To this end, the present invention proposes a function HIE that targets the characteristics of respiratory and heartbeat signals as the objective function of GOA. It is an index composed of permutation entropy, mutual information, and energy loss ratio. By optimizing these indicators, the optimization algorithm can better adapt to the characteristics of respiratory and heartbeat signals, thereby improving the quality and robustness of signal decomposition.

[0127] Permutation entropy is a physical quantity that describes the degree of disorder in a system. It can be used to measure the complexity or regularity of a signal. When a signal is more regular, the permutation entropy is lower. On the contrary, when a signal is more irregular or more random, the permutation entropy is higher. The human breathing and heartbeat signals can be expressed as quasi-sinusoidal signals, so their permutation entropy is generally lower. The formula is as follows:

[0128]

[0129] H represents the permutation entropy, N is the total number of permutations, and p i represents the probability of occurrence of the i-th element.

[0130] Mutual information is used to measure the degree of correlation between two signals. If the mutual information is large, it means that there is a strong correlation or mutual dependence between the two signals. On the contrary, if the mutual information is small, it means that the correlation between them is weak or almost non-existent. Respiration and heartbeat signals are independent signals. Smaller mutual information means that they are less correlated and better separated, reducing the impact of respiratory high-order harmonics on heartbeat signals. The formula is as follows:

[0131]

[0132] Where I(X; Y) represents the mutual information between the respiratory signal X and the heartbeat signal Y, p(x, y) represents the joint probability distribution function, and p(x) and p(y) represent the marginal probability distribution functions of X and Y, respectively.

[0133] Respiratory and heartbeat signals dominate the collected radar signals. The difference between the reconstructed signal after decomposition and the original signal should be as small as possible, otherwise it means that important information in the original signal is missing. Therefore, the energy loss ratio can be used as an indicator to measure the decomposition effect. A smaller energy loss ratio indicates a better decomposition quality because it shows that most of the energy of the original signal is successfully retained after decomposition. The formula for the energy loss ratio is shown as follows

[0134]

[0135] Where f(m) represents the human chest displacement signal, u k represents the kth modal component, Σu k Represents the reconstructed signal.

[0136] The parameter adaptive VMD method proposed in this method takes the product of permutation entropy, mutual information, and energy loss ratio as the objective function, and realizes parameter optimization through the GOA algorithm. For the convenience of application, the permutation entropy and mutual information are normalized and their values ​​are converted to the range of 0 to 1. As shown in the following formula:

[0137] HIE=H X ·H Y ·I(X;Y)·e (26)

[0138] Among them, HIE represents the objective function, H X represents the permutation entropy of the respiratory component, H Y represents the permutation entropy of the heartbeat component, I(X;Y) represents the mutual information between the respiratory component and the heartbeat component, and e represents the energy loss ratio.

[0139] The above model constitutes the theoretical basis of this method. The algorithm flow chart is as follows: Figure 2As shown. The process is as follows: First, initialize the GOA parameters and generate some random parameter combinations, then perform VMD decomposition on each parameter combination, find the respiratory and heartbeat signal components whose frequencies are within the respiratory frequency range and the heartbeat frequency range, calculate HIE and record the minimum HIE and the corresponding parameter combination. However, sometimes the higher harmonic components of breathing are also within the heartbeat frequency range, resulting in the wrong selection of the heartbeat component. In order to select the correct signal component, the mutual information between them and the respiratory component is calculated respectively, and the component with the minimum mutual information is selected as the heartbeat signal component. Then, 2 / 3 of the locusts update their positions according to formula (18), and 1 / 3 of the locusts perform Levy flight. Subsequently, calculate the new minimum HIE and the corresponding parameter combination. Iterate and update the parameter combination according to the conditions until the end criteria are met. Finally, output the optimal parameter combination as the global optimal solution. Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application 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 codes.

[0140] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0141] 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 1 A function specified in one or more boxes.

[0142] 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.

[0143] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0144] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

[0145] This patent is not limited to the above-mentioned optimal implementation mode. Anyone can derive various other forms of a non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition under the inspiration of this patent. All equal changes and modifications made according to the scope of the patent application of the present invention should be covered by this patent.

Claims

1. A non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition, Features: After multi-target detection is performed on the radar raw data signal to obtain the precise distance window of each human target in the measured scene, the phase of the signal in the distance window is extracted through the differentiation and cross-multiplication algorithm, thereby obtaining the chest displacement signal of each subject. Through the VMD method with adaptive parameters and using the adaptation function HIE for vital sign signal extraction as the objective function of GOA, a fully adaptive VMD decomposition of the chest displacement signal of each subject is achieved, and the heartbeat signal and breathing signal of each subject are obtained, and then the heart rate variability characteristics of each subject are detected from the heartbeat signal.

2. The non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition according to claim 1, Features: The signal processing flow of the multi-target detection includes distance FFT, angle FFT, static clutter elimination, minimum unit mean constant false alarm rate detection and DBSCAN clustering.

3. The non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition according to claim 1, Features: Before extracting the phase of the signal in the range window by using the differentiation and cross-multiplication algorithm, the DC component is estimated by using the least squares based circle fitting method, and then the DC component is eliminated in the signal to achieve the purpose of DC offset correction.

4. The non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition according to claim 1, Features: The VMD method with adaptive parameters optimizes the modal number and modal bandwidth control parameters of VMD through an improved GOA optimization algorithm; the improved GOA optimization algorithm introduces a nonlinear decreasing coefficient on the basis of GOA, and this coefficient changes with the increase of the number of algorithm iterations, thereby enhancing the global search ability and the local search ability in the early and late stages of the iteration, respectively, thereby improving the convergence accuracy of the algorithm; and the Levy flight strategy is introduced to improve the GOA algorithm, so as to avoid the algorithm from falling into the local optimum by promoting population diversity.

5. The non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition according to claim 4, Features: The mathematical model of the improved GOA optimization algorithm is as follows: Among them, Y i represents the position of the i-th locust in the locust swarm, and the superscript d represents the improved algorithm; d ij =|x i -x j | is the distance between the i-th individual and the j-th individual, N is the number of individuals in the population, and z is the function that defines the interaction force between individuals: Among them, p represents the strength of attraction, and q is the range of attraction scale; ub d and lb d are the upper and lower bounds of the D-dimensional search space, respectively. represents the best individual in the current population, and parameter c is the improved nonlinear decreasing coefficient, which is calculated by the following formula; In the formula, l represents the current iteration number of the algorithm, and L represents the maximum iteration number; The Levy flight strategy is used to improve the GOA algorithm, which can avoid the algorithm from falling into the local optimum by promoting population diversity. The Levy flight is introduced to update the individual positions of locusts. In each iteration, a random 1 / 3 of the locusts are allowed to update their positions using the Levy flight strategy. The formula is as follows: Where size(D) represents the dimension of the problem to be solved. Represents dot product, i represents the current iteration number, which is used to control the flight distance, and β represents the Levy index, so that a larger search range can be performed in the early stage of the iteration, and a smaller search range can be performed in the later stage.

6. The non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition according to claim 1, Features: The product of permutation entropy, mutual information, and energy loss ratio is used as the objective function, and parameter optimization is achieved through the GOA algorithm, as shown in the following formula: HIE=H X ·H Y ·I(X;Y)·e Among them, HIE represents the objective function, H X represents the permutation entropy of the respiratory component, H Y represents the permutation entropy of the heartbeat component, I(X;Y) represents the mutual information between the respiratory component and the heartbeat component, and e represents the energy loss ratio.

7. The non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition according to claim 6, Features: The permutation entropy formula of the respiratory component and the heartbeat component is as follows: Where H represents the permutation entropy, N is the total number of permutations, and p i represents the probability of occurrence of the i-th element; The formula for the mutual information between the respiratory component and the heartbeat component is as follows: Where I(X;Y) represents the mutual information between the respiratory signal X and the heartbeat signal Y, p(x,y) represents the joint probability distribution function, and p(x) and p(y) represent the marginal probability distribution functions of X and Y respectively. The formula for energy loss ratio is as follows: Where f(m) represents the human chest displacement signal, u k represents the kth modal component, Σu k Represents the reconstructed signal.

8. The non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition according to claim 5, Features: The process of VMD decomposition is: First, the GOA parameters are initialized and several random parameter combinations are generated. Then, VMD decomposition is performed on each parameter combination to find the respiratory and heartbeat signal components whose frequencies are within the respiratory frequency range and the heartbeat frequency range. HIE is calculated and the minimum HIE and the corresponding parameter combination are recorded. The mutual information between the heartbeat component and the breathing component is calculated respectively, and the component with the smallest mutual information is selected as the heartbeat signal component; then, 2 / 3 of the locusts update their positions according to the mathematical model of the improved GOA optimization algorithm, and 1 / 3 of the locusts perform Levy flight; Subsequently, the new minimum HIE and the corresponding parameter combination are calculated; the parameter combination is iteratively updated according to the conditions until the end criterion is met; finally, the optimal parameter combination is output as the global optimal solution.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the steps of the non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition as described in any one of claims 1-8 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the non-contact multi-target heart rate variability detection method based on adaptive variational mode decomposition as described in any one of claims 1 to 8 are implemented.

Images