Blood oxygen saturation detection method

Abstract

The invention discloses a blood oxygen saturation detection method and relates to the technical field of computers. The blood oxygen saturation degree detection method comprises the steps that a fifth signal is obtained; obtaining a sixth signal by using the fifth signal; obtaining a third signal by using the fifth signal and the sixth signal; obtaining a fourth signal by using the fifth signal and the sixth signal; obtaining a first signal by using the third signal and the fourth signal; obtaining an alternating-current component and a direct-current component of the first signal by using the first signal; obtaining a ninth signal; obtaining a tenth signal by using the ninth signal; obtaining a seventh signal by using the ninth signal and the tenth signal; obtaining an eighth signal by using the ninth signal and the tenth signal; obtaining a second signal by using the seventh signal and the eighth signal; obtaining an alternating-current component and a direct-current component of the second signal by using the second signal; the oxyhemoglobin saturation is obtained. The oxyhemoglobin saturation detection method can be used for detecting the oxyhemoglobin saturation.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a blood oxygen saturation detection method. Background Art

[0002] Blood oxygen saturation, usually expressed as S p O2 refers to the percentage of oxygen combined with hemoglobin in the blood, which can reflect the functional status of the respiratory and circulatory systems. Summary of the invention

[0003] In order to detect blood oxygen saturation, the present application provides a blood oxygen saturation detection method. The method comprises:

[0004] Get the fifth signal;

[0005] obtaining a sixth signal using the fifth signal;

[0006] obtaining a third signal using the fifth signal and the sixth signal;

[0007] obtaining a fourth signal using the fifth signal and the sixth signal;

[0008] Obtaining the first signal using the third signal and the fourth signal;

[0009] Using the first signal, obtaining an alternating current component of the first signal and a direct current component of the first signal;

[0010] Get the ninth signal;

[0011] using the ninth signal to obtain a tenth signal;

[0012] obtaining a seventh signal using the ninth signal and the tenth signal;

[0013] obtaining an eighth signal using the ninth signal and the tenth signal;

[0014] obtaining a second signal using the seventh signal and the eighth signal;

[0015] Using the second signal to obtain an AC component of the second signal and a DC component of the second signal;

[0016] Get blood oxygen saturation.

[0017] The blood oxygen saturation detection method proposed in this application can detect blood oxygen saturation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of the blood oxygen saturation detection method of the present application. DETAILED DESCRIPTION

[0019] The blood oxygen saturation detection method of the present application is described in detail below with reference to the accompanying drawings.

[0020] The present application provides a method for detecting blood oxygen saturation. Figure 1 As shown, the method includes:

[0021] Get the fifth signal;

[0022] using the fifth signal to obtain a sixth signal;

[0023] obtaining a third signal using the fifth signal and the sixth signal;

[0024] obtaining a fourth signal using the fifth signal and the sixth signal;

[0025] Obtaining the first signal using the third signal and the fourth signal;

[0026] Using the first signal, obtaining an alternating current component of the first signal and a direct current component of the first signal;

[0027] Get the ninth signal;

[0028] using the ninth signal to obtain a tenth signal;

[0029] obtaining a seventh signal using the ninth signal and the tenth signal;

[0030] obtaining an eighth signal using the ninth signal and the tenth signal;

[0031] obtaining a second signal using the seventh signal and the eighth signal;

[0032] Using the second signal to obtain an AC component of the second signal and a DC component of the second signal;

[0033] Get blood oxygen saturation.

[0034] The fifth signal may be a red light PPG (photoplethysmo-graphic) signal, which may be obtained after the person to be tested wears a blood oxygen saturation detection device.

[0035] The red light may be red light having a wavelength of 660 nm.

[0036] The blood oxygen saturation detection device may be a wearable blood oxygen saturation detection device, such as a sports bracelet.

[0037] The fifth signal may also be a pre-processed red light PPG signal.

[0038] The sixth signal can be obtained by using the fifth signal through the following method:

[0039] Obtaining the period M1 of the fifth signal d1(n) according to its autocorrelation function;

[0040] The fifth signal d1(n) is arranged into a first matrix H1 with M1 columns:

[0041]

[0042] Where n = n1M1 + M1;

[0043] Perform SVD (Singular Value Decomposition) on the first matrix to obtain:

[0044] H1=U1Λ1V * 1,

[0045] Among them, H1 is the first matrix of N1×M1, N1=n1+1; U1 is the unitary matrix of N1×N1; V1 is the unitary matrix of M1×M1, V * 1 is the conjugate transposed matrix of V1; Λ1 is the semi-positive definite diagonal matrix of N1×M1;

[0046] Replace the element with the largest value and the element with the second largest value in the matrix Λ1 (i.e., the top two elements in descending order) with 0 to obtain Λ1′;

[0047] For U1Λ1′V * 1 Perform inverse SVD transformation to obtain the second matrix H1′:

[0048] H1′=U1Λ1′V * 1;

[0049] The second matrix H1′ is converted into a one-dimensional signal, and the one-dimensional signal is the sixth signal.

[0050] The sixth signal can also be obtained by using the fifth signal through the following method:

[0051] k1 first Gaussian white noises with amplitude μ1 are added to the fifth signal d1(n) Get k1 new signals, perform EMD decomposition (Empirical Mode Decomposition) on the k1 new signals respectively, average the k1 first-order IMFs (Intrinsic Mode Components) obtained by decomposition, and get the first-order first eigenmode component:

[0052]

[0053] Among them, IMF1(n) is the first-order first eigenmode component, E1(*) is the first-order IMF obtained by EMD decomposition;

[0054] get:

[0055] r1(n)=d1(n)-IMF1(n);

[0056] Add k2 second Gaussian white noises with amplitude μ2 to r1(n) respectively The first-order intrinsic mode component of is obtained to obtain k2 new signals, and the k2 new signals are decomposed by EMD respectively. The k2 first-order IMFs obtained by decomposition are averaged to obtain the second-order first intrinsic mode component:

[0057]

[0058] Among them, IMF2(n) is the second-order first eigenmode component, E1(*) is the first-order IMF obtained by EMD decomposition;

[0059] get:

[0060] r2(n)=r1(n)-IMF2(n);

[0061] Add k3 third Gaussian white noises with amplitude μ3 to r2(n) The second-order eigenmode components of k3 new signals are obtained, and the k3 new signals are decomposed by EMD respectively. The k3 first-order IMFs obtained by decomposition are averaged to obtain the third-order first eigenmode component:

[0062]

[0063] Among them, IMF3(n) is the third-order first eigenmode component, E1(*) is the first-order IMF obtained by EMD decomposition, and E2(*) is the second-order IMF obtained by EMD decomposition;

[0064] get:

[0065] r3(n)=r2(n)-IMF3(n);

[0066] And so on, continue to iterate the decomposition until:

[0067] exist Add The amplitude is The m1th Gaussian white noise The m1-1 order eigenmode component is obtained A new signal, yes The new signals are decomposed by EMD respectively, and the decomposed The first-order IMFs are averaged to obtain the m1-order first eigenmode component:

[0068]

[0069] in, is the first eigenmode component of order m1, E1(*) is the first-order IMF obtained by EMD decomposition, It is the m1-1 order IMF obtained by EMD decomposition;

[0070] get:

[0071]

[0072] in, The following conditions must be met: The number of extreme points is 2.

[0073] In one embodiment,

[0074] In another embodiment, the first Gaussian white noise Second Gaussian white noise Third Gaussian white noise ...m1th Gaussian white noise are the same.

[0075] The sixth signal x1(n) can be obtained by adding the first eigenmode components of each order whose screening values ​​are greater than the first threshold.

[0076] The first threshold may be preset.

[0077] i-th a The screening value of the first eigenmode component can be obtained as follows:

[0078] right After coarse-graining processing, a new sequence signal y5(j5) is obtained:

[0079]

[0080] in, represents rounding down, l5=(j5-1)*s5+1, s5 is the first scale factor; For the i a The first eigenmode component, i a =1, 2, ... m1;

[0081] The sequence signal y5(j5) obtained by coarse-graining processing is reconstructed in phase space to obtain the fifth matrix H5:

[0082]

[0083] Where τ5 is the first time delay, m5 is the first embedding dimension,

[0084] The row vector Y5(i b) are arranged in ascending order according to their values, and a new row vector Y5′(i b ), and obtain the sixth matrix H5′:

[0085]

[0086] Y5′(i b ) is replaced by the element in the row vector Y5(i b ) in the index value, and get the row vector Y5″(i b ), and get the seventh matrix H5″:

[0087]

[0088] Among them, i b =1,2,...,p5,Y5′(i b ) in the row vector Y5(i b ) can be the index value of the element in the row vector Y5(i b )

[0089] A row vector Y5″(i b ) is an index sequence, for example, i b =1, Y5″(1) is an index sequence; if two row vectors Y5″(i b ) are exactly the same, then they are the same index sequence. For example, if Y5″(1) and Y5″(2) are exactly the same, then Y5″(1) and Y5″(2) are the same index sequence. b ) are not completely identical, then they are different types of index sequences. For example, if Y5″(3) and Y5″(4) are not completely identical, then Y5″(3) and Y5″(4) are different types of index sequences.

[0090] calculate

[0091]

[0092] Get the i a The screening value of the first eigenmode component of the i-th order; where MQP is a The screening value of the first eigenmode component of order, is the probability of occurrence of each index sequence, a MQP is the number of different index sequences contained in the seventh matrix H5″, that is, the seventh matrix H5″ contains a MQP Different index sequences.

[0093] The third signal can be obtained by using the fifth signal and the sixth signal through the following formula:

[0094] e2(n)=d1(n)-w1 T (n)x1(n)

[0095] Among them, e2(n) is the third signal, d1(n) is the fifth signal, x1(n) is the sixth signal, w1(n) is the first filter weight vector coefficient, w1 T (n) is the transposed vector of w1(n).

[0096] The fourth signal can be obtained by using the fifth signal and the sixth signal through the following formula:

[0097] e3(n)=d1(n)-w2 T (n)x1(n)

[0098] Among them, e3(n) is the fourth signal, d1(n) is the fifth signal, x1(n) is the sixth signal, w2(n) is the second filter weight vector coefficient, w2 T (n) is the transposed vector of w2(n).

[0099] The first signal can be obtained by using the third signal and the fourth signal through the following formula:

[0100] e1(n)=λ1(n)e2(n)+[1-λ1(n)]e3(n)

[0101] Wherein, e1(n) is the first signal, e2(n) is the third signal, e3(n) is the fourth signal, and λ1(n) can be obtained by the following formula:

[0102]

[0103] Among them, α1(n) can be obtained by the following formula:

[0104] α1(n)=α1(n-1)+μ α1 ·λ1(n-1)[1-λ1(n-1)]·[e2(n-1)-e1(n-1)]·[e3(n-1)-e2(n-1)],

[0105] in, is the first step length parameter.

[0106] Obtaining the AC component of the first signal and the DC component of the first signal using the first signal can be achieved through existing technologies, which will not be described in detail here.

[0107] The ninth signal may be an infrared light PPG (photoplethysmo-graphic) signal, which may be obtained after the person to be tested wears a blood oxygen saturation detection device.

[0108] The infrared light may be infrared light having a wavelength of 940 nm.

[0109] The blood oxygen saturation detection device may be a wearable blood oxygen saturation detection device, such as a sports bracelet.

[0110] The ninth signal may also be a pre-processed infrared light PPG signal.

[0111] The tenth signal can be obtained by using the ninth signal through the following method:

[0112] Obtaining the period M2 of the ninth signal d2(n) according to its autocorrelation function;

[0113] The ninth signal d2(n) is arranged into a third matrix H2 with M2 columns:

[0114]

[0115] Where n = n2M2 + M2;

[0116] Perform SVD (Singular Value Decomposition) on the third matrix to obtain:

[0117] H2=U2Λ2V * 2,

[0118] Among them, H2 is the third matrix of N2×M2, N2=n2+1; U2 is the unitary matrix of N2×N2; V2 is the unitary matrix of M2×M2, V * 2 is the conjugate transposed matrix of V2; Λ2 is a semi-positive definite diagonal matrix of N2×M2;

[0119] Replace the element with the largest value and the element with the second largest value in the matrix Λ2 (that is, the two elements ranked first in descending order) with 0 to obtain Λ′2;

[0120] For U2Λ′2V * 2 Perform inverse SVD transformation to obtain the fourth matrix H2′:

[0121] H2′=U2Λ′2V * 2;

[0122] The fourth matrix H2′ is converted into a one-dimensional signal, which is the tenth signal.

[0123] The seventh signal can be obtained by using the ninth signal and the tenth signal through the following formula:

[0124] e5(n)=d2(n)-w3 T (n)x2(n),

[0125] Among them, e5(n) is the seventh signal, d2(n) is the ninth signal, x2(n) is the tenth signal, w3(n) is the third filter weight vector coefficient, w3 T (n) is the transposed vector of w3(n).

[0126] The eighth signal can be obtained by using the ninth signal and the tenth signal through the following formula:

[0127] e6(n)=d2(n)-w4 T (n)x2(n),

[0128] Among them, e6(n) is the eighth signal, d2(n) is the ninth signal, x2(n) is the tenth signal, w4(n) is the second filter weight vector coefficient, w4 T (n) is the transposed vector of w4(n).

[0129] The second signal can be obtained by using the seventh signal and the eighth signal through the following formula:

[0130] e4(n)=λ2(n)e5(n)+[1-λ2(n)]e6(n),

[0131] Among them, e4(n) is the second signal, e5(n) is the seventh signal, e6(n) is the eighth signal, and λ2(n) can be obtained by the following formula:

[0132]

[0133] Among them, α2(n) can be obtained by the following formula:

[0134]

[0135] in, is the second step length parameter.

[0136] Obtaining the AC component of the second signal and the DC component of the second signal using the second signal can be achieved through existing technologies, which will not be described in detail here.

[0137] The blood oxygen saturation can be obtained by using the AC component and the DC component of the first signal and the AC component and the DC component of the second signal through the following formula:

[0138] S P O2=AR 2 +BR+C,

[0139] Among them, S P O2 is the blood oxygen saturation, A is the first empirical coefficient, B is the second empirical coefficient, C is the third empirical coefficient, and R is calculated by the following formula:

[0140]

[0141] Among them, AC1 is the AC component of the first signal, DC1 is the DC component of the first signal, AC2 is the AC component of the second signal, and DC2 is the DC component of the second signal.

[0142] In one embodiment, the first empirical coefficient A is -22.537, the second empirical coefficient B is 1.4389, and the third empirical coefficient C is 103.78.

Claims

1. A method for detecting blood oxygen saturation, characterized in that: include: Get the fifth signal; using the fifth signal to obtain a sixth signal; obtaining a third signal using the fifth signal and the sixth signal; obtaining a fourth signal using the fifth signal and the sixth signal; Obtaining the first signal using the third signal and the fourth signal; Using the first signal, obtaining an alternating current component of the first signal and a direct current component of the first signal; Get the ninth signal; using the ninth signal to obtain a tenth signal; obtaining a seventh signal using the ninth signal and the tenth signal; obtaining an eighth signal using the ninth signal and the tenth signal; obtaining a second signal using the seventh signal and the eighth signal; Using the second signal to obtain an AC component of the second signal and a DC component of the second signal; Get blood oxygen saturation.

2. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The fifth signal may be a red light PPG signal.

3. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The obtaining the sixth signal by using the fifth signal comprises: Obtaining the period M1 of the fifth signal d1(n) according to its autocorrelation function; The fifth signal d1(n) is arranged into a first matrix H1 with M1 columns: Where n = n1M1+M1; Perform SVD decomposition on the first matrix and get: H1=U1Λ1V * 1, Among them, H1 is the first matrix of N1×M1, N1=n1+1; U1 is the unitary matrix of N1×N1; V1 is the unitary matrix of M1×M1, V * 1 is the conjugate transposed matrix of V1; Λ1 is the semi-positive definite diagonal matrix of N1×M1; Replace the element with the largest value and the element with the second largest value in the matrix Λ1 with 0 to obtain Λ1′; For U1Λ1′V * 1 Perform inverse SVD transformation to obtain the second matrix H1′: H1′=U1Λ1′V * 1; The second matrix H1′ is converted into a one-dimensional signal, and the one-dimensional signal is the sixth signal.

4. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The obtaining of the third signal by using the fifth signal and the sixth signal comprises: The third signal is obtained by using the fifth signal and the sixth signal through the following formula: Wherein, e2(n) is the third signal, d1(n) is the fifth signal, x1(n) is the sixth signal, w1(n) is the first filter weight vector coefficient, is the transposed vector of w1(n).

5. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The obtaining of the fourth signal by using the fifth signal and the sixth signal comprises: The fourth signal is obtained by using the fifth signal and the sixth signal through the following formula: Wherein, e3(n) is the fourth signal, d1(n) is the fifth signal, x1(n) is the sixth signal, w2(n) is the second filter weight vector coefficient, is the transposed vector of w2(n).

6. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The obtaining of the first signal by using the third signal and the fourth signal comprises: The first signal is obtained by using the third signal and the fourth signal through the following formula: e1(n)=λ1(n)e2(n)+[1-λ1(n)]e3(n), Wherein, e1(n) is the first signal, e2(n) is the third signal, e3(n) is the fourth signal, and λ1(n) can be obtained by the following formula: Among them, α1(n) can be obtained by the following formula: in, is the first step length parameter.

7. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The obtaining of the seventh signal by using the ninth signal and the tenth signal comprises: The seventh signal is obtained by using the ninth signal and the tenth signal through the following formula: Among them, e5(n) is the seventh signal, d2(n) is the ninth signal, x2(n) is the tenth signal, and w3(n) is the third filter weight vector coefficient. is the transposed vector of w3(n).

8. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The obtaining the eighth signal by using the ninth signal and the tenth signal comprises: The eighth signal is obtained by using the ninth signal and the tenth signal through the following formula: Among them, e6(n) is the eighth signal, d2(n) is the ninth signal, x2(n) is the tenth signal, w4(n) is the second filter weight vector coefficient, is the transposed vector of w4(n).

9. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The obtaining the second signal by using the seventh signal and the eighth signal comprises: The second signal is obtained by using the seventh signal and the eighth signal through the following formula: e4(n)=λ2(n)e5(n)+[1-λ2(n)]e6(n), Among them, e4(n) is the second signal, e5(n) is the seventh signal, e6(n) is the eighth signal, and λ2(n) can be obtained by the following formula: Among them, α2(n) can be obtained by the following formula: in, is the second step length parameter.

10. The method for detecting blood oxygen saturation according to claim 1, characterized in that: The obtaining of blood oxygen saturation comprises: The blood oxygen saturation is obtained by using the AC component and the DC component of the first signal and the AC component and the DC component of the second signal through the following formula: S P O2=AR 2 +BR+C, Among them, S P O2 is the blood oxygen saturation, A is the first empirical coefficient, B is the second empirical coefficient, C is the third empirical coefficient, and R is calculated by the following formula: Among them, AC1 is the AC component of the first signal, DC1 is the DC component of the first signal, AC2 is the AC component of the second signal, and DC2 is the DC component of the second signal.

Images