Separation method and device of sign signals, electronic equipment and storage medium

Abstract

The application discloses a kind of methods, devices, electronic equipment and storage medium of sign signal separation, applied to signal processing field, comprising: obtaining sign signal;According to the related parameters of whale optimization algorithm, the first position parameter of preset population quantity is obtained;According to position parameter and variational mode decomposition algorithm, sign signal is decomposed, and intrinsic mode function component set is obtained;According to intrinsic mode function component set, obtain fuzzy entropy;According to fuzzy entropy, the first position parameter is iteratively optimized by the whale optimization algorithm of global search strategy, and the second position parameter is obtained;According to the second position parameter and variational mode decomposition algorithm, sign signal is decomposed and reconstructed, and heartbeat sign signal and respiratory sign signal are obtained.The application embodiment is optimized to the position parameter of variational mode decomposition algorithm by the whale optimization algorithm of global search strategy, reduces the occurrence of signal over-decomposition and under-decomposition in separation process, improves the accuracy of separation result.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of signal processing, in particular to a vital sign signal separation method and device, electronic equipment and storage medium. BACKGROUND

[0002] The vital sign information mainly refers to respiration, heartbeat, blood pressure and body temperature, and in particular, the respiration and heartbeat signals are important indicators for measuring the health condition of a human body. In addition, the respiration and heartbeat signals are important indicators for assisting in judging the severity and risk level of a patient's condition. There are usually multiple different signals in the vital sign signals, and therefore, it is crucial to accurately separate and extract different frequency signals from the above vital sign detection signals.

[0003] In the prior art, the vital sign signal separation method usually adopts a variational mode decomposition algorithm to separate signals. However, this method needs to manually set related parameters, and inappropriate related parameters can easily lead to over-decomposition and under-decomposition of signals, resulting in loss and redundancy of information, and making the signal separation result have a large deviation. SUMMARY

[0004] The present application provides a vital sign signal separation method, device, electronic equipment and storage medium, which can optimize the related parameters of the variational mode decomposition algorithm and improve the accuracy of the vital sign signal separation result.

[0005] In a first aspect, the present application provides a vital sign signal separation method, comprising:

[0006] Obtaining a vital sign signal and initializing related parameters of a whale optimization algorithm;

[0007] According to the related parameters, a first position parameter of a preset population number is obtained;

[0008] According to the first position parameter and a variational mode decomposition algorithm, the vital sign signal is decomposed to obtain an intrinsic mode function component set of the preset population number;

[0009] According to the intrinsic mode function component set of the preset population number, a fuzzy entropy is obtained;

[0010] According to the fuzzy entropy, the first position parameter is iteratively optimized by a whale optimization algorithm of a global search strategy to obtain a second position parameter;

[0011] According to the second position parameter and the variational mode decomposition algorithm, the vital sign signal is decomposed and reconstructed to obtain a heartbeat vital sign signal and a respiration vital sign signal.

[0012] According to the method for separating a vital sign signal provided in the embodiment of the first aspect of the present application, at least the following beneficial effects are achieved: in the process of separating the vital sign signal, the method takes fuzzy entropy as a measurement index, iteratively optimizes the related parameters, i.e., the first position parameters, of the variational mode decomposition algorithm by using the whale optimization algorithm of the global search strategy, obtains the second position parameters, and enables the variational mode decomposition algorithm under the second position parameters to separate the vital sign signal. The embodiment of the present application optimizes the position parameters of the variational mode decomposition algorithm by using the whale optimization algorithm of the global search strategy, reduces the occurrence of over-decomposition and under-decomposition of the signal in the separation process, makes the information in the heartbeat vital sign signal and the respiratory vital sign signal obtained after the separation more concise and complete, and improves the accuracy of the signal separation result.

[0013] According to some embodiments of the first aspect of the present application, the first position parameters include the number of components and a penalty factor, and the step of decomposing the vital sign signal according to the first position parameters and the variational mode decomposition algorithm to obtain the preset population number of intrinsic mode function component sets comprises:

[0014] For each of the first position parameters, the preset number of intrinsic mode function components, mode center frequencies and Lagrange multipliers are iteratively updated in sequence according to the vital sign signal and the penalty factor until the preset number of intrinsic mode function components meet the iteration constraint condition.

[0015] According to the preset number of intrinsic mode function components at the end of the iteration, the preset population number of intrinsic mode function component sets is obtained.

[0016] According to some embodiments of the first aspect of the present application, the step of obtaining the preset population number of fuzzy entropies according to the preset population number of intrinsic mode function component sets comprises:

[0017] obtaining a preset dimension;

[0018] reconstructing the preset population number of intrinsic mode function component sets according to the preset dimension to obtain a preset population number of reconstructed vector sets, the number of vectors of the reconstructed vector sets being determined by the number of elements of the intrinsic mode function component set and the preset dimension;

[0019] obtaining a preset population number of membership average value sets according to the reconstructed vector set;

[0020] obtaining the preset population number of fuzzy entropies according to the preset population number of membership average value sets.

[0021] According to some embodiments of the first aspect of the present application, the step of obtaining a preset population number of membership average value sets according to the reconstructed vector set comprises:

[0022] For each of the reconstruction vector sets, a distance between any two of the reconstruction vectors is calculated;

[0023] According to the distance between any two of the reconstruction vectors, a plurality of fuzzy membership degrees of the reconstruction vector set is obtained;

[0024] According to the plurality of fuzzy membership degrees, a membership average of the reconstruction vector set is obtained, and a plurality of the membership averages is taken as a membership average set.

[0025] According to some embodiments of the first aspect of the application, the iterative optimization of the first position parameter according to the fuzzy entropy by the whale optimization algorithm of the global search strategy to obtain a second position parameter comprises:

[0026] According to the fuzzy entropy, a first individual optimal position is obtained;

[0027] According to an optimal neighborhood disturbance strategy, the first individual optimal position is updated by optimal neighborhood disturbance to obtain a second individual optimal position;

[0028] According to the current iteration number of the whale optimization algorithm and a preset iteration number, a hoop coefficient of the whale optimization algorithm is obtained;

[0029] According to the random search coefficient and the hoop coefficient, a search mode of the whale optimization algorithm is determined;

[0030] According to the search mode of the whale optimization algorithm, the second individual optimal position is updated to obtain a third individual optimal position;

[0031] When the current iteration number is less than the preset iteration number, the third individual optimal position is updated as the first individual optimal position;

[0032] When the current iteration number is equal to the preset iteration number, the third individual optimal position obtained by the last iteration update is taken as the second position parameter.

[0033] According to some embodiments of the first aspect of the application, the determination of the search mode of the whale optimization algorithm according to the random search coefficient and the hoop coefficient comprises:

[0034] When the hoop coefficient is greater than or equal to 1 and the random search coefficient is less than 0.5, the search mode of the whale optimization algorithm is determined to be a surround-prey search mode;

[0035] When the hoop coefficient is greater than or equal to 1 and the random search coefficient is greater than or equal to 0.5, the search mode of the whale optimization algorithm is determined to be a rotation search mode;

[0036] When the enclosure coefficient is less than 1, it is determined that the search mode of the whale optimization algorithm is a random search mode.

[0037] According to some embodiments of the first aspect of the application, the reconstructing the heartbeat and respiration signals from the vital sign signal according to the second position parameter and the variational mode decomposition algorithm comprises:

[0038] According to some embodiments of the first aspect of the application, the reconstructing the heartbeat and respiration signals from the vital sign signal according to the second position parameter and the variational mode decomposition algorithm comprises:

[0039] According to some embodiments of the first aspect of the application, the reconstructing the heartbeat and respiration signals from the vital sign signal according to the second position parameter and the variational mode decomposition algorithm comprises:

[0040] In a second aspect, the embodiments of the application provide a vital sign signal separation device, comprising:

[0041] A signal acquisition unit, configured to acquire a vital sign signal and initialize related parameters of a whale optimization algorithm;

[0042] A parameter setting unit, configured to obtain a first position parameter of a preset population number according to the related parameters;

[0043] A signal decomposition unit, configured to decompose the vital sign signal according to the first position parameter and a variational mode decomposition algorithm to obtain an intrinsic mode function component set of the preset population number;

[0044] An index calculation unit, configured to obtain a fuzzy entropy of the preset population number according to the intrinsic mode function component set of the preset population number;

[0045] A whale optimization unit, configured to iteratively optimize the first position parameter by a whale optimization algorithm of a global search strategy according to the fuzzy entropy to obtain a second position parameter;

[0046] A signal reconstruction unit, configured to reconstruct the heartbeat and respiration signals from the vital sign signal according to the second position parameter and the variational mode decomposition algorithm.

[0047] Since the vital sign signal separation device provided by the second aspect applies the vital sign signal separation method of any one of the first aspect, it has all the beneficial effects of the first aspect of the application.

[0048] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the method for separating a vital signal according to any one of the first aspect.

[0049] Since the processor of the third aspect executes the computer program to perform the method for separating a vital signal according to any one of the first aspect, all the beneficial effects of the first aspect of the embodiments of the present application are achieved.

[0050] In a fourth aspect, the embodiments of the present application provide a computer storage medium comprising computer executable instructions for performing the method for separating a vital signal according to any one of the first aspect.

[0051] Since the computer storage medium of the fourth aspect can perform the method for separating a vital signal according to any one of the first aspect, all the beneficial effects of the first aspect of the embodiments of the present application are achieved.

[0052] Additional aspects and advantages of the present application will be made apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or related description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0054] Figure 1 is a structural block diagram of the vital signal separation device provided by the embodiments of the present application;

[0055] Figure 2 is a main flowchart of the vital signal separation method provided by the embodiments of the present application;

[0056] Figure 3 is a flowchart of signal decomposition of the vital signal separation method provided by the embodiments of the present application;

[0057] Figure 4 is a flowchart of index calculation of the vital signal separation method provided by the embodiments of the present application;

[0058] Figure 5 is a flowchart of membership average value calculation of the vital signal separation method provided by the embodiments of the present application;

[0059] Figure 6is a flowchart of whale optimization of a method for separating a sign signal provided by embodiments of the present application;

[0060] Figure 7 is a flowchart of determining a search mode of a method for separating a sign signal provided by embodiments of the present application;

[0061] Figure 8 is a flowchart of signal reconstruction of a method for separating a sign signal provided by embodiments of the present application;

[0062] Figure 9 is a flowchart of a method for separating a sign signal provided by embodiments of the present application;

[0063] Figure 10 is a schematic diagram of a system architecture platform for separating a sign signal provided by embodiments of the present application. DETAILED DESCRIPTION

[0064] In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0065] It is noted that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be performed in an order different from that in the flowcharts. The terms "first", "second", etc. in the specification and claims and the above-described drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0066] It should also be understood that the reference to "one embodiment" or "some embodiments" in the description of the application herein means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearances of the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", etc. in various places in the specification are not necessarily all referring to the same embodiment, unless otherwise specifically noted. The terms "comprise", "comprising", "have", "having", "include", "including", "contain", "containing", and variants thereof are meant to be open-ended terms that do not exclude additional, unrecited elements or method steps.

[0067] The vital sign information mainly refers to respiration, heartbeat, blood pressure, body temperature and the like, and in particular, the respiration and heartbeat signals are important indexes for measuring the health condition of a human body. In addition, the respiration signal and the heartbeat signal are important indexes for assisting in judging the severity and danger level of a patient. There are usually various different signals in the vital sign signal, and therefore, it is crucial to accurately separate and extract signals of different frequencies from the vital sign detection signal.

[0068] In the prior art, the vital sign signal separation method usually adopts a variational mode decomposition algorithm to separate signals, however, this method needs to set relevant parameters subjectively, and inappropriate relevant parameters can easily lead to over-decomposition and under-decomposition of signals, thereby causing loss and redundancy of information, and making the signal separation result have a large deviation.

[0069] Based on this, the present application provides a vital sign signal separation method, device, electronic equipment and storage medium. The vital sign signal separation method provided by the present application can improve the accuracy of the vital sign signal separation result by optimizing the position parameters of the variational mode decomposition algorithm through the whale optimization algorithm of the global search strategy.

[0070] Reference Figure 1 , Figure 1 is a structural block diagram of a vital sign signal separation device provided by the present application. The vital sign signal separation device provided by the present application comprises a signal acquisition unit 100, a parameter setting unit 200, a signal decomposition unit 300, an index calculation unit 400, a whale optimization unit 500 and a signal reconstruction unit 600.

[0071] The signal acquisition unit 100 is in communication connection with the parameter setting unit 200, the signal decomposition unit 300 and the signal reconstruction unit 600, and the signal acquisition unit 100 is configured to acquire vital sign signals and initialize relevant parameters of the whale optimization algorithm.

[0072] The parameter setting unit 200 is in communication connection with the signal acquisition unit 100 and the signal decomposition unit 300, and the parameter setting unit 200 is configured to obtain first position parameters of a preset population number according to the relevant parameters of the whale optimization algorithm.

[0073] The signal decomposition unit 300 is in communication connection with the signal acquisition unit 100, the parameter setting unit 200 and the index calculation unit 400, and the signal decomposition unit 300 is configured to decompose the vital sign signals according to the position parameters of the preset population number and the variational mode decomposition algorithm, to obtain an intrinsic mode function component set of the preset population number.

[0074] The index calculation unit 400 is in communication connection with the signal decomposition unit 300 and the whale optimization unit 500, and the index calculation unit 400 is configured to obtain fuzzy entropy of the preset population number according to the intrinsic mode function component set of the preset population number.

[0075] The whale optimization unit 500 is in communication connection with the index calculation unit 400 and the signal reconstruction unit 600. The whale optimization unit 500 is configured to perform iterative optimization on the first position parameter according to the fuzzy entropy by using the whale optimization algorithm of the global search strategy, and obtain a second position parameter.

[0076] The signal reconstruction unit 600 is in communication connection with the signal acquisition unit 100 and the whale optimization unit 500. The signal reconstruction unit 600 is configured to perform decomposition and reconstruction on the vital sign signal according to the second position parameter and the variational modal decomposition algorithm, and obtain a heartbeat vital sign signal and a breathing vital sign signal.

[0077] It should be noted that the signal acquisition unit 100 acquires the vital sign signal and initializes the related parameters of the whale optimization algorithm, sends the vital sign signal to the signal decomposition unit 300 and the signal reconstruction unit 600, and sends the related parameters of the whale optimization algorithm to the parameter setting unit 200. The parameter setting unit 200 obtains the first position parameter of the preset population number according to the received related parameters of the whale optimization algorithm. The signal decomposition unit 300 performs decomposition on the vital sign signal according to the first position parameter of the preset population number from the parameter setting unit 200 and the variational modal decomposition algorithm, and obtains the intrinsic modal function component set of the preset population number. The index calculation unit 400 is configured to obtain the fuzzy entropy of the preset population number according to the intrinsic modal function component set of the preset population number, and send the fuzzy entropy to the whale optimization unit 500. The whale optimization unit 500 performs iterative optimization on the first position parameter according to the fuzzy entropy of the preset population number by using the whale optimization algorithm of the global search strategy, and sends the second position parameter obtained after the optimization to the signal reconstruction unit 600. The signal reconstruction unit 600 performs decomposition and reconstruction on the vital sign signal according to the second position parameter and the variational modal decomposition algorithm, and obtains the heartbeat vital sign signal and the breathing vital sign signal, thereby realizing the separation of the vital sign signal.

[0078] The apparatus and application scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems with the evolution of system architecture and the appearance of new application scenarios.

[0079] Those skilled in the art can understand that, Figure 1 The apparatus structure shown in the above-mentioned embodiments does not constitute a limitation on the embodiments of the present application, and can include more or fewer components than those shown in the figure, or combine certain components, or different component arrangements.

[0080] In Figure 1In the device structure shown, each module can call its stored simulation analysis program respectively to perform the separation method of the physical signal.

[0081] Based on the above device, each embodiment of the separation method of the physical signal provided in the embodiments of the present application is proposed.

[0082] Reference Figure 2 , Figure 2 is the main flowchart of the separation method of the physical signal provided in the embodiments of the present application. The separation method of the physical signal provided in the embodiments of the present application includes but is not limited to the following steps:

[0083] Step S100, acquiring the physical signal and initializing the related parameters of the whale optimization algorithm.

[0084] Step S200, obtaining the first position parameter of the preset population quantity according to the related parameters.

[0085] Step S300, decomposing the physical signal according to the first position parameter and the variational modal decomposition algorithm to obtain the intrinsic modal function component set of the preset population quantity.

[0086] Step S400, obtaining the fuzzy entropy of the preset population quantity according to the intrinsic modal function component set of the preset population quantity.

[0087] Step S500, iteratively optimizing the first position parameter by the whale optimization algorithm with global search strategy according to the fuzzy entropy to obtain the second position parameter.

[0088] Step S600, decomposing and reconstructing the physical signal according to the second position parameter and the variational modal decomposition algorithm to obtain the heartbeat physical signal and the breathing physical signal.

[0089] It should be noted that in the separation process of the physical signal, the separation method of the physical signal provided in the embodiments of the present application takes the fuzzy entropy as the measurement index, iteratively optimizes the related parameters of the variational modal decomposition algorithm, i.e. the first position parameter, by the whale optimization algorithm with global search strategy to obtain the second position parameter, so that the variational modal decomposition algorithm under the second position parameter can realize the separation of the physical signal. The embodiments of the present application optimize the position parameter of the variational modal decomposition algorithm by the whale optimization algorithm with global search strategy, reduce the occurrence of over-decomposition and under-decomposition of the signal in the separation process, make the information in the separated heartbeat physical signal and breathing physical signal more concise and complete, and improve the accuracy of the signal separation result.

[0090] It should be noted that the whale optimization algorithm is a swarm intelligence optimization algorithm, which finds the optimal solution by simulating the search process of whales in the ocean to catch food. However, there are also disadvantages of traditional group optimization algorithms, such as insufficient global search capability, low algorithm optimization precision, and the like. The whale optimization algorithm using the global search strategy in the embodiments can adjust the optimal position influence, optimize the convergence speed, improve the global optimal search capability, and solve the algorithm premature problem.

[0091] It can be understood that, with reference to Figure 3 , Figure 3 is a flowchart of signal decomposition of the method for separating a vital signal provided by the embodiments. The position parameters include the number of components and the penalty factor, and step S300 includes but is not limited to the following steps:

[0092] Step S310, for each first position parameter, the preset number of component intrinsic mode function components, modal center frequencies, and Lagrange multipliers are sequentially iteratively updated according to the vital signal and the penalty factor, until the component intrinsic mode function components meet the iteration constraint condition.

[0093] Step S320, according to the component intrinsic mode function components at the end of iteration, the set of intrinsic mode function components of the preset population quantity is obtained.

[0094] It should be noted that the position parameters include the number of components and the penalty factor, and the number of components is the number of intrinsic mode function components in the set of intrinsic mode function components.

[0095] It should be noted that, in order to reduce the redundancy of calculation, step S100 further sets the range of the first position parameters, i.e., the number of components and the penalty factor. The first position parameters obtained in step S300, i.e., the first position parameters set in step S200, are within the set range.

[0096] It should be noted that the variational modal decomposition algorithm adopts a completely non-recursive modal decomposition, and discards the recursive solution idea used in the traditional signal decomposition algorithm. The core idea is to construct and solve a variational problem. The variational problem is constructed as follows: assuming that the original signal, i.e., the vital signal f, is decomposed into K intrinsic mode function components, the intrinsic mode function component is a finite bandwidth signal with a center frequency, and the sum of the estimated bandwidths of each mode is minimum, the constraint condition is that the sum of all modes is equal to the original signal, and the corresponding constraint variational expression, i.e., the expression of the iteration constraint condition, is:

[0097]

[0098] wherein μ k is the intrinsic mode function component, ω k is the modal center frequency, For gradient calculation, δ t The function is the Dirac delta function, * represents the convolution symbol, and (δ(t)+j / πt)*μ k (t) represents the sum of μ k (t) represents the heating result after Hilbert transform, and f represents the original signal.

[0099] To solve the constrained optimization problem described above, the constrained variational problem is transformed into an unconstrained variational problem. By introducing a penalty factor α and Lagrange multipliers λ, the augmented Lagrange expression is obtained as follows:

[0100]

[0101] This application first analyzes the Lagrange multiplier λ and the eigenmode function components μ of the number of components K. k Modal center frequency ω k Initialize, intrinsic mode function components μ k With modal center frequency ω k One-to-one correspondence.

[0102] Since step S200 obtains the location parameters of the preset population size, i.e. the number of components and the penalty factor are known.

[0103] For each first position parameter in the game, first consider the eigenmode function components μ k and modal center frequency ω k The calculation is performed using the following formula:

[0104]

[0105]

[0106] in, For μ k The result is obtained through Fourier transform. For each position parameter, K eigenmode function components μ can be obtained in each iteration. k and the corresponding modal center frequency ω k .

[0107] The intrinsic mode function component μ k and modal center frequency ω k The update causes the Lagrange multiplier λ to update, and the update formula is as follows:

[0108]

[0109] Where γ is the noise margin. The result obtained by Fourier transforming λ. The result of f is obtained by Fourier transform, and is taken as 0 when there is strong noise in the signal.

[0110] repeating iterative updating is performed on the intrinsic mode function components μ k , the modal center frequency ω k and the Lagrange multiplier λ until the intrinsic mode function components of the component number meet the iteration constraint condition, and the constraint condition is as follows:

[0111]

[0112] According to the above steps, the vital sign signal is decomposed according to the first position parameter of the preset population number, and the intrinsic mode function component set of the preset population number can be obtained.

[0113] It can be understood that, with reference to Figure 4 , Figure 4 is a flowchart of index calculation of the vital sign signal separation method provided by the embodiment of the application. Step S400 includes but is not limited to the following steps:

[0114] Step S410, obtaining a preset dimension.

[0115] Step S420, reconstructing the intrinsic mode function component set of the preset population number according to the preset dimension, to obtain a reconstructed vector set of the preset population number, and the vector number of the reconstructed vector set is determined by the element number of the intrinsic mode function component set and the preset dimension.

[0116] Step S430, obtaining a membership average value set of the preset population number according to the reconstructed vector set.

[0117] Step S440, obtaining a fuzzy entropy of the preset population number according to the membership average value set.

[0118] It should be noted that the whale optimization algorithm with global search strategy is used to realize adaptive optimization of the related parameters of the variable mode decomposition algorithm, and in the algorithm, the focus of parameter optimization is to select a suitable fitness function. As a signal sequence complexity index, the greater the value, the greater the signal complexity; otherwise, the complexity is smaller.

[0119] It should be noted that for an N-dimensional time sequence {μ(j), 1≤j≤N}, i.e., the intrinsic mode function component set, if the preset dimension is m, the reconstructed vector set is represented as follows:

[0120]

[0121] Wherein, μ0(i) is the mean value of consecutive m μ(i), X(i) is the reconstructed vector, and N can represent the component number of the intrinsic mode function component set.

[0122] According to the reconstruction vector set of the preset population quantity, a membership average value set of the preset population quantity is obtained, and then according to the membership average value set of the preset population quantity, a fuzzy entropy of the preset population quantity is obtained, and the fuzzy entropy is expressed as follows:

[0123]

[0124] Wherein, φ m (n,r) is the membership average.

[0125] It can be understood that, referring to Figure 5 , Figure 5 is the flowchart of the membership average value calculation of the separation method of the vital sign signal provided by the embodiment of the application. Step S430 includes but is not limited to the following steps:

[0126] Step S431, for each reconstruction vector set, the distance between any two reconstruction vectors is calculated.

[0127] Step S432, according to the distance between any two reconstruction vectors, a plurality of fuzzy memberships of the reconstruction vector set is obtained.

[0128] Step S433, according to the plurality of fuzzy memberships, the membership average value of the reconstruction vector set is obtained, and the plurality of membership average values are taken as the membership average value set.

[0129] It should be noted that, for each reconstruction vector set, the distance between any two reconstruction vectors is calculated first, and the calculation formula is as follows:

[0130]

[0131] Wherein, is the distance between two m-dimensional vectors, and is the absolute value of the maximum corresponding original difference value. Then, the fuzzy membership function is introduced, and the membership is calculated. m (n,r) is calculated.

[0132]

[0133]

[0134] The membership average value set corresponding to the reconstruction vector set of the preset population quantity is calculated, so that the membership average value of the preset population quantity can be obtained, which is convenient for the calculation of the fuzzy entropy.

[0135] According to the above steps, the membership average value set of each reconstruction vector set is calculated, so that the membership average value set of the preset population quantity can be obtained.

[0136] It can be understood that, with reference to Figure 6 , Figure 6 is a flowchart of whale optimization of a sign signal separation method provided by the embodiment of the application, and step S500 includes but is not limited to the following steps:

[0137] Step S510, obtaining a first individual optimal position according to fuzzy entropy.

[0138] Step S520, performing optimal neighborhood disturbance update on the first individual optimal position according to an optimal neighborhood disturbance strategy to obtain a second individual optimal position.

[0139] Step S530, obtaining a whale optimization algorithm's enclosure coefficient according to a current iteration number and a preset iteration number of the whale optimization algorithm.

[0140] Step S540, determining a search mode of the whale optimization algorithm according to a random search coefficient and the enclosure coefficient.

[0141] Step S550, updating the second individual optimal position according to the search mode of the whale optimization algorithm to obtain a third individual optimal position.

[0142] Step S560, when the current iteration number is less than the preset iteration number, updating the third individual optimal position as the first individual optimal position.

[0143] Step S570, when the current iteration number is equal to the preset iteration number, obtaining a second position parameter according to the third individual optimal position obtained through the last iteration update.

[0144] It should be noted that the fuzzy entropy obtained through step S400 is sorted, the smaller the fuzzy entropy is, the smaller the complexity of the sequence is, and the corresponding position parameter is optimal, and the first position parameter corresponding to the individual with the smallest fuzzy entropy is selected as the first individual optimal position. During the whale updating position process, the optimal position is updated less frequently, which leads to low search efficiency of the algorithm and easy occurrence of local optimal solution. The optimal neighborhood disturbance strategy is adopted to randomly search around the optimal position, so as to improve the convergence speed of the algorithm and avoid prematureness of the algorithm, and the expression formula of the optimal neighborhood disturbance strategy is as follows:

[0145]

[0146] wherein, X * is a global optimal position, X(t) represents the current optimal position, that is, the first individual optimal position, rand1 and rand2 are random numbers in [0, 1], X%(t) is a new position searched randomly, and t is the current iteration number. If the newly generated position X%(t) is better than the optimal position, the positions are exchanged, the second individual optimal position is X%(t), otherwise the optimal position remains unchanged and is still X* .

[0147] According to the current iteration number and the preset iteration number of the whale optimization algorithm, a circle coefficient of the whale optimization algorithm is obtained. Then, according to the random search coefficient and the circle coefficient, a search mode of the whale optimization algorithm is determined, and the second individual optimal position is updated according to the search mode to obtain a third individual optimal position. When the current iteration number is less than the preset iteration number, the third individual optimal position is updated as the first individual optimal position. When the current iteration number is equal to the preset iteration number, a second position parameter is obtained according to the third individual optimal position updated by the last iteration, and the second position parameter can improve the accuracy of the variational modal decomposition algorithm and facilitate the decomposition of the sign signal.

[0148] It can be understood that, with reference to Figure 7 , Figure 7 is a flowchart of determining a search mode of the sign signal separation method provided by the embodiment of the application. Step S540 includes but is not limited to the following steps:

[0149] Step S541, when the circle coefficient is greater than or equal to 1 and the random search coefficient is less than 0.5, the search mode of the whale optimization algorithm is determined as a surround-prey search mode.

[0150] Step S542, when the circle coefficient is greater than or equal to 1 and the random search coefficient is greater than or equal to 0.5, the search mode of the whale optimization algorithm is determined as a rotation search mode.

[0151] Step S543, when the circle coefficient is less than 1, the search mode of the whale optimization algorithm is determined as a random search mode.

[0152] It should be noted that, when the circle coefficient is greater than or equal to 1, the expression formula of the whale optimization algorithm is as follows:

[0153]

[0154] When the circle coefficient is less than 1, the search mode of the whale optimization algorithm is a random search mode, and the specific model is as follows:

[0155] X(t+1)=w(t)X rand (t)-A·|C·X rand (t)-X(t)|

[0156] Wherein, t is the current iteration number, X is the whale position, X * is the global optimal position, X rand ​The random whale position is a randomly generated whale position, the position of which is not fixed, b is a constant, l is a [-1, 1] random number, p is a random search coefficient, specifically a random number between [0, 1], when p < 0.5, it is a mathematical model of surrounding prey, that is, the search mode of the current whale optimization algorithm is a surrounding prey search mode, when p >= 0.5, it is a mathematical model of rotating search, that is, the search mode of the current whale optimization algorithm is a rotating search mode. When the surrounding ring coefficient is less than 1, it is a random search mathematical model, that is, the search mode of the current whale optimization algorithm is a random search mode. In addition, omega is an adaptive weight, A and C are coefficient matrices, and A is a surrounding ring coefficient matrix, the absolute value of which is a surrounding ring, and the specific expression formula is as follows:

[0157]

[0158]

[0159] Wherein, r1, r2 are [0, 1] random numbers, t max is the maximum iteration number, that is, the preset iteration number, a is the convergence factor. In addition, in order to solve the problem that the spiral movement mode of the whale rotating search caused by the constant b is too single, a variable spiral position update is introduced, the parameter b is set to increase with the iteration number, the spiral shape is adaptively changed from large to small, and thus the global search ability is improved. The new rotating search mathematical model is:

[0160]

[0161] According to the whale positions obtained by the above three search modes, compared with the second individual optimal position, if the newly generated position is better than the second individual optimal position, the exchange is performed, the third individual optimal position is the newly generated whale position, otherwise the optimal position remains unchanged, that is, the third individual optimal position is the second individual optimal position.

[0162] It should be noted that the whale optimization algorithm is a swarm intelligence optimization algorithm, which finds the optimal solution by simulating the search process of whales in the ocean to catch food. However, there are also disadvantages of traditional swarm optimization algorithms, such as insufficient global search ability, low algorithm optimization precision and the like. The global search strategy of the whale optimization algorithm of the present application introduces an adaptive weight, adjusts the influence of the optimal position, optimizes the convergence speed, uses a variable spiral position update, adjusts the spiral shape, improves the global optimal search ability, and uses optimal field disturbance to avoid falling into local optimum and solve the algorithm premature problem.

[0163] It can be understood that, with reference to Figure 8 , Figure 8 is a flowchart of signal reconstruction of the method for separating a body signal provided by the embodiment of the present application. Step S600 includes but is not limited to the following steps:

[0164] Step S610, decompose the sign signal according to the second position parameter and the variational modal decomposition algorithm to obtain a plurality of intrinsic modal function components.

[0165] Step S620, reconstruct the plurality of intrinsic modal function components according to the modal discrimination criterion to obtain the heartbeat sign signal and the respiratory sign signal.

[0166] It should be noted that the optimized position parameter is the current optimal position parameter, and the sign signal is decomposed according to the second position parameter through the variational modal decomposition algorithm to obtain a plurality of intrinsic modal function components.

[0167] It should be noted that in actual measurement, the amplitude of the respiratory sign signal is about 10 times the amplitude of the heartbeat sign signal, and the respiratory harmonic close to the heartbeat frequency is likely to have a similar amplitude, so it is particularly important to determine which intrinsic modal function component the main components of the respiratory and heartbeat sign signals are in. According to the modal discrimination criterion, the energy proportion of the respiratory and heartbeat sign signals in each intrinsic modal function component is calculated, and the sign signal is reconstructed using the intrinsic modal function component that meets the condition. According to the fact that the respiratory frequency band of a healthy adult is 0.2 to 0.5 hertz, and the heartbeat frequency band is 0.8 to 2.0 hertz, the energy percentage of the respiratory and heartbeat in each intrinsic modal function component is calculated in the frequency domain, and the expression is as follows:

[0168]

[0169] wherein E(k) is the frequency energy of the kth intrinsic modal function component, E r (k) and E h (k) represent the energy in the respiratory and heartbeat frequency band in the kth intrinsic modal function component, respectively, δ r and δ h represent the energy ratio threshold for judging the respiratory and heartbeat, respectively. According to research, when δ r and δ h take the value of 0.5, the extraction effect of the respiratory and heartbeat sign signals reaches the best. In the embodiment of the application, δ r and δ h take the value of 0.5, and the intrinsic modal function components that meet the modal discrimination criterion are added to obtain the reconstructed respiratory and heartbeat sign signals. The reconstructed respiratory sign signal s r (n) and the heartbeat sign signal s h (n) are expressed as follows:

[0170]

[0171]

[0172] It should be noted that the Fourier transform is performed on the reconstructed respiratory sign signal and heartbeat sign signal, so as to obtain the estimated frequency of the sign signal.

[0173] It should be noted that, with reference to Figure 9 , Figure 9 is a flowchart of the separation method of the sign signal provided by the embodiment of the application. The embodiment of the application first initializes the related parameters of the whale optimization algorithm of the global search strategy, including the preset population quantity, the preset iteration number, etc., the dimension, and sets the first position parameter, i.e., the range of the component number K and the penalty factor α. Then, the sign signal is subjected to variational mode decomposition, and the fuzzy entropy is calculated. The fuzzy entropy describes the degree of fuzziness of a time signal sequence. The smaller the fuzzy entropy is, the smaller the complexity of the sequence is, and the optimal component number K and the penalty factor α are corresponded. The current optimal whale position is recorded as the first optimal individual position. Then, the optimal neighborhood disturbance strategy is used to update the first individual optimal position to obtain the second individual optimal position. Then, the search mode of the whale optimization algorithm is selected according to the encircling coefficient and the random search coefficient. When the encircling coefficient is greater than or equal to 1 and the random search coefficient is less than 0.5, the search mode of the whale optimization algorithm is determined to be the encircling prey search mode. When the encircling coefficient is greater than or equal to 1 and the random search coefficient is greater than or equal to 0.5, the search mode of the whale optimization algorithm is determined to be the rotating search mode. When the encircling coefficient is less than 1, the search mode of the whale optimization algorithm is determined to be the random search mode. The second individual optimal position is updated according to the search mode of the whale optimization algorithm to obtain the third individual optimal position. When the current iteration number is less than the preset iteration number, the third individual optimal position is updated as the first individual optimal position. Until the current iteration number is equal to the preset iteration number, the second position parameter is obtained according to the third individual optimal position updated by the last iteration. The second position parameter obtained by optimization can be used for variational mode decomposition.

[0174] It should be noted that the component number and the penalty factor are optimized in the application, so the dimension is 2. According to the preset population quantity, the preset iteration number and the dimension, the preset population quantity, the preset iteration number, etc. can be calculated, and then the calculation amount of the algorithm can be judged.

[0175] It should be noted that the linear frequency modulation continuous wave radar is a radar system that obtains target information according to the frequency difference and phase difference between the transmitted signal and the echo signal by frequency modulation of the continuous wave. The radar can divide the obtained radar signal into multiple angle and distance scales. Compared with wireless radar and continuous wave radar, the captured information has more details. Based on the above characteristics, unlike the continuous wave radar, the linear frequency modulation continuous wave radar can isolate the noise of the non-interest region and has the potential to monitor the health status of different individuals at the same time. Unlike audio and video equipment, it does not infringe on the privacy of users. Compared with pulse radar and other devices, the linear frequency modulation continuous wave radar has a large time-band product and can achieve the same signal-to-noise ratio as pulse radar and other radar devices with low peak power. Therefore, the linear frequency modulation continuous wave radar does not need to integrate high-power and high-voltage devices, which makes the linear frequency modulation continuous wave radar system simple in structure and easy to integrate in a single chip. The amplitudes of the local vibrations on the body surface caused by breathing and heartbeat are about 5 mm and 200-500 um respectively, and the millimeter-level wavelength is conducive to monitoring small-amplitude vibrations, so as to accurately monitor physiological signs and judge the breathing mode of the human body. Therefore, the sign signal is collected by the linear frequency modulation continuous wave radar in the embodiments of the present application.

[0176] It should be noted that the linear frequency modulation continuous wave radar sensor used in the embodiments of the present application uses an STM32 microprocessor as a processing chip, and the antenna module uses two transmitting antennas and three receiving antennas. The processed data can be sent to the upper computer through the serial port or sent to the mobile device through the wireless module.

[0177] It should be noted that the embodiments of the present application need to perform constant false alarm processing, distance dimension Fourier transform and phase unwrapping on the signals collected by the linear frequency modulation continuous wave radar to obtain the sign signal.

[0178] It should be noted that the separation method of the sign signal provided in the embodiments of the present application takes fuzzy entropy as a measurement index. In the separation process of the sign signal, the position parameters of the variational mode decomposition algorithm are iteratively optimized by the whale optimization algorithm with a global search strategy, so that the variational mode decomposition algorithm under the position parameters can realize the separation of the sign signal. The position parameters of the variational mode decomposition algorithm are optimized by the whale optimization algorithm with a global search strategy in the embodiments of the present application, which reduces the occurrence of signal over-decomposition and under-decomposition in the separation process, makes the information in the heartbeat sign signal and the breathing sign signal obtained by separation more concise and complete, and improves the accuracy of the signal separation result.

[0179] In addition, with reference to Figure 10 the system architecture platform for separating the sign signal provided in the embodiments of the present application.

[0180] The system architecture platform of the embodiments of the present application comprises one or more processors and a memory, Figure 10 For example, one processor and one memory are taken as an example.

[0181] The processor and the memory can be connected through a bus or other means, Figure 10 For example, connection through a bus is taken as an example.

[0182] The memory, as a non-transitory computer readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory disposed remotely with respect to the processor, and these remote memories can be connected to the system architecture platform through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0183] Those skilled in the art can understand that the system architecture platform can be applied to existing communication network systems and subsequent evolved mobile communication network systems, and the embodiments of the present application do not make specific limitations thereto.

[0184] Those skilled in the art can understand that, Figure 10 The device structure shown in the above embodiments does not constitute a limitation on the system architecture platform, and can include more or fewer components than those shown in the figure, or combine certain components, or different component arrangements.

[0185] The system architecture platform can be a standalone system architecture platform, or a cloud system architecture platform providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks, and basic cloud computing services such as big data and artificial intelligence platforms.

[0186] In addition, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the step S100 to step S400 of the separation method of the vital sign signal.

[0187] The processor and the memory can be connected through a bus or other means.

[0188] The memory, as a non-transitory computer readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory disposed remotely with respect to the processor, which can be connected to the processor through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0189] The non-transitory software programs and instructions required to implement the target tracking method of the above-mentioned embodiments are stored in the memory, and when executed by the processor, the separation method of the above-mentioned embodiments is executed, for example, the method steps S100 to S600 in the above-described Figure 2 are executed.

[0190] The apparatus embodiments described above are only illustrative, and the units described as separate components can or can not be physically separated, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment scheme.

[0191] In addition, one embodiment of the present embodiment also provides a computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are executed by a processor or a controller, so that the above-mentioned processor executes the separation method of the above-mentioned embodiments, for example, the method steps S100 to S600 in the above-described Figure 2 , Figure 3 the method steps 310 to S320 in the above-described , Figure 4 the method steps S410 to S440 in the above-described , Figure 5 the method steps S431 and S433 in the above-described , Figure 6 the method steps S510 to S570 in the above-described , Figure 7 the method steps S541 to S543 in the above-described , Figure 8 the method steps S610 to S620 in the above-described .

[0192] As will be appreciated by one of ordinary skill in the art, all or some steps, systems of the above-disclosed methods can be implemented as software, firmware, hardware, or any suitable combination thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application- specific integrated circuit. Such software can be distributed on computer readable media, which can comprise computer storage media (or non-transitory media), and communication media (or transitory media). As is well known to those of ordinary skill in the art, the term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media include, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Further, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and includes any information delivery media.

[0193] The above is the specific description of the preferred implementation of the embodiments of the present application, but the embodiments of the present application are not limited to the above implementation, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the embodiments of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the embodiments of the present application.

Claims

1. A method for separating vital signs signals, characterized in that, include: Acquire vital signs and initialize relevant parameters of the whale optimization algorithm, including preset population size, preset dimension, and preset number of iterations; Based on the relevant parameters, the first position parameter of the preset population size is obtained; The eigensignal signal is decomposed according to the first position parameter and the variational mode decomposition algorithm to obtain the set of eigenmode function components of the preset population size; Based on the set of eigenmode function components of the preset population size, the fuzzy entropy of the preset population size is obtained; Based on the fuzzy entropy, the first position parameter is iteratively optimized using the whale optimization algorithm with a global search strategy to obtain the second position parameter; The eigensignal signal is decomposed according to the second position parameter and the variational mode decomposition algorithm to obtain multiple intrinsic mode function components; For each intrinsic mode function component, based on the frequency domain energy of the intrinsic mode function component, the energy of the intrinsic mode function component located in the respiratory frequency band, and the energy of the intrinsic mode function component located in the heartbeat frequency band, the component type of the intrinsic mode function component is determined, and the component type includes heartbeat type and respiratory type; Based on the multiple intrinsic mode function components corresponding to the heartbeat type, determine the heartbeat vital signs signal; Based on the multiple intrinsic mode function components corresponding to the breathing type, respiratory sign signals are determined; Wherein, obtaining the fuzzy entropy of the preset population size based on the eigenmode function component set of the preset population size includes: Obtain the preset dimension; The intrinsic mode function component set of the preset population size is reconstructed according to the preset dimension to obtain the reconstructed vector set of the preset population size. The number of vectors in the reconstructed vector set is determined by the number of elements in the intrinsic mode function component set and the preset dimension. Based on the reconstructed vector set, the set of average membership degrees for the preset population size is obtained; Based on the set of average membership values, the fuzzy entropy of the preset population size is obtained.

2. The method for separating vital signs signals according to claim 1, characterized in that, The first position parameter includes the number of components and a penalty factor. The step of decomposing the eigensignal signal according to the first position parameter and a variational mode decomposition algorithm to obtain the eigenmode function component set of the preset population size includes: For each of the first position parameters, based on the vital signs signal and the penalty factor, the intrinsic mode function components, modal center frequencies and Lagrange multipliers of the preset number of components are iteratively updated sequentially until the intrinsic mode function components of the preset number of components satisfy the iterative constraint conditions. The set of intrinsic mode function components of the preset population size is obtained based on the number of each component at the end of the iteration.

3. The method for separating vital signs signals according to claim 1, characterized in that, The step of obtaining the set of average membership degrees for the preset population size based on the reconstructed vector set includes: For each set of reconstructed vectors, calculate the distance between any two reconstructed vectors; Based on the distance between any two of the reconstructed vectors, multiple fuzzy membership degrees of the reconstructed vector set are obtained; Based on the multiple fuzzy membership degrees, the average membership degree of the reconstructed vector set is obtained, and the multiple average membership degrees are used as a set of average membership degrees.

4. The method for separating vital signs signals according to claim 1, characterized in that, The step of iteratively optimizing the first position parameter based on the fuzzy entropy using a whale optimization algorithm with a global search strategy to obtain the second position parameter includes: Based on the fuzzy entropy, the optimal position of the first volume is obtained; The optimal position of the first individual is updated by performing optimal neighborhood perturbation based on the optimal neighborhood perturbation strategy, and the optimal position of the second individual is obtained. The encirclement coefficient of the whale optimization algorithm is obtained based on the current iteration number and the preset iteration number. The search method of the whale optimization algorithm is determined based on the random search coefficient and the encirclement coefficient. The optimal position of the second individual is updated according to the search method of the whale optimization algorithm to obtain the optimal position of the third individual; When the current iteration count is less than the preset iteration count, the optimal position of the third body is updated as the optimal position of the first body; When the current iteration number is equal to the preset iteration number, the second position parameter is obtained based on the optimal position of the third body obtained from the last iteration update.

5. The method for separating vital signs signals according to claim 4, characterized in that, The step of determining the search method of the whale optimization algorithm based on the random search coefficient and the encirclement coefficient includes: When the encirclement coefficient is greater than or equal to 1 and the random search coefficient is less than 0.5, the search method of the whale optimization algorithm is determined to be the encirclement prey search method. When the bounding circle coefficient is greater than or equal to 1 and the random search coefficient is greater than or equal to 0.5, the search method of the whale optimization algorithm is determined to be the rotation search method. When the encirclement coefficient is less than 1, the search method of the whale optimization algorithm is determined to be a random search method.

6. A device for separating vital signs signals, characterized in that, include: The signal acquisition unit is used to acquire vital signs signals and initialize relevant parameters of the whale optimization algorithm. The relevant parameters include a preset population size, a preset dimension, and a preset number of iterations. A parameter setting unit is used to obtain a first position parameter of the preset population size based on the relevant parameters. The signal decomposition unit is used to decompose the vital signs signal according to the first position parameter and the variational mode decomposition algorithm to obtain the intrinsic mode function component set of the preset population size; An index calculation unit is used to obtain the fuzzy entropy of the preset population size based on the intrinsic mode function component set of the preset population size. A whale optimization unit is used to iteratively optimize the first position parameter based on the fuzzy entropy using a whale optimization algorithm with a global search strategy to obtain the second position parameter. A signal reconstruction unit is configured to decompose the vital signs signal according to the second position parameters and the variational mode decomposition algorithm to obtain multiple intrinsic mode function components; for each intrinsic mode function component, based on the frequency domain energy of the intrinsic mode function component, the energy of the intrinsic mode function component located in the respiratory frequency band, and the energy of the intrinsic mode function component located in the heartbeat frequency band, the component type includes heartbeat type and respiratory type; Based on the multiple intrinsic mode function components corresponding to the heartbeat type, determine the heartbeat vital signs signal; Based on the multiple intrinsic mode function components corresponding to the breathing type, respiratory sign signals are determined; Wherein, obtaining the fuzzy entropy of the preset population size based on the eigenmode function component set of the preset population size includes: Obtain the preset dimension; The intrinsic mode function component set of the preset population size is reconstructed according to the preset dimension to obtain the reconstructed vector set of the preset population size. The number of vectors in the reconstructed vector set is determined by the number of elements in the intrinsic mode function component set and the preset dimension. Based on the reconstructed vector set, the set of average membership degrees for the preset population size is obtained; Based on the set of average membership values, the fuzzy entropy of the preset population size is obtained.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method for separating vital signs signals as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for separating vital signs signals as described in any one of claims 1 to 5.

Images