A vital sign detection method and apparatus
By combining radar sensors and support vector machine models, the problems of high cost and complex operation of contact instruments have been solved, enabling non-contact and accurate detection of vital signs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG DAHUA TECH CO LTD
- Filing Date
- 2023-02-21
- Publication Date
- 2026-06-26
AI Technical Summary
Existing contact-based instruments for vital sign detection are costly and complex to operate, and it is difficult to accurately determine whether the subject has vital signs in the detection area.
Data is collected using radar sensors, and the distance-energy and distance-phase mapping relationships are determined through data processing. A support vector machine model is used to determine whether there are vital signs in the vital sign area. Combined with specified parameters such as the proportion of high-frequency signals, the support vector machine model is trained for on-site learning and recognition.
It enables accurate detection of vital signs under non-contact conditions, reduces costs, simplifies operation, and improves detection accuracy.
Smart Images
Figure CN116421163B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of radar detection technology, and in particular to a method and apparatus for detecting vital signs. Background Technology
[0002] With the improvement of living standards, people are paying more attention to their health, especially community-based elderly care institutions, which are increasingly focusing on monitoring the health of the elderly. Vital signs are an important indicator of health. Currently, health monitoring typically involves contact-based instruments to collect vital sign parameters such as respiration and heart rate. However, for most users, contact-based instruments are costly and complex to operate. Therefore, there is a need for a vital sign detection method that can simply and accurately detect human vital signs. Summary of the Invention
[0003] This application provides a method and apparatus for detecting vital signs, which can accurately determine whether vital signs exist in the area to be detected.
[0004] In a first aspect, one embodiment of this application provides a method for detecting vital signs, the method comprising:
[0005] Data on the area of vital signs to be detected is collected using radar sensors;
[0006] The data is processed to obtain the distance-energy mapping relationship of the moving target after removing static targets in the area of the vital signs to be detected, and the distance-phase mapping relationship of the moving target;
[0007] Based on the distance-energy mapping relationship and the distance-phase mapping relationship, at least one specified parameter corresponding to a distance is determined; wherein, the specified parameter includes at least the proportion of high-frequency signals;
[0008] Input the specified parameters corresponding to the at least one distance into a pre-built support vector machine model to obtain the vital sign detection results output by the support vector machine model;
[0009] The support vector machine model is used to determine whether the subject is experiencing respiratory arrest in the area of the vital signs to be detected or whether the subject is not in the area of the vital signs to be detected.
[0010] Compared to existing technologies, this application determines at least one specified parameter corresponding to a distance, and then uses this specified parameter as input to a support vector machine (SVM) model. This allows for accurate determination of the presence of vital signs in the region to be detected, based on specified parameters that include at least the proportion of high-frequency signals. Furthermore, the SVM model can learn and recognize the application scenario during model training, resulting in a more accurate output in practical applications.
[0011] In one possible design, the specified parameters may further include one or more of the following parameters:
[0012] Energy intensity of respiratory frequency band, energy intensity of heart rate frequency band, maximum energy intensity of heart rate frequency band, variance of energy intensity of heart rate frequency band, and variance of maximum energy intensity of heart rate frequency band.
[0013] This application defines one or more of the following parameters as specified parameters: respiratory frequency band energy intensity, heart rate frequency band energy intensity, maximum heart rate frequency band energy intensity, variance of heart rate frequency band energy intensity, and variance of maximum heart rate frequency band energy intensity. Using the defined specified parameters, it is possible to accurately determine whether there are vital signs in the area to be detected.
[0014] In one possible design, the support vector machine model is constructed in the following way:
[0015] Obtain specified parameters for at least one distance sample and corresponding labels for the at least one distance sample, wherein the labels include whether the subject to be tested is experiencing respiratory arrest in the area of the vital signs to be detected or whether the subject to be tested is not in the area of the vital signs to be detected;
[0016] The specified parameters of the at least one distance sample are input into the support vector machine model so that the support vector machine model outputs the predicted label of the at least one distance sample;
[0017] The support vector machine model is trained based on the loss between the predicted label and the labeled label.
[0018] This application uses at least one specified parameter of a distance sample and at least one label corresponding to the distance sample to train the support vector machine model. By using multiple specified parameters for each distance sample, the trained support vector machine model can be more accurate in identifying whether there are vital signs in the region to be detected.
[0019] In one possible design, when the radar sensor collects data on the area of vital signs to be detected, there is a sampling time difference. Static targets in the area of vital signs to be detected are removed using the following method:
[0020] Based on the energy intensity and phase value corresponding to the current sampling time, a first value is obtained; and based on the energy intensity and phase value corresponding to the previous time, a second value is obtained.
[0021] Perform modulo operations on the first value and the second value respectively;
[0022] The static targets in the area of vital signs to be detected are removed by using the difference between the modulo operation result of the first value and the modulo operation result of the second value.
[0023] This application first performs a modulo operation on the first and second values, and then removes the static target based on the difference after the modulo operation. This reduces the problem of large energy difference caused by sampling time difference, and by reducing energy intensity, the static target can be accurately removed.
[0024] In one possible design, the radar sensor acquires data of the area to be detected for vital signs in the following manner: multi-antenna transmission and multi-antenna reception.
[0025] The method further includes:
[0026] Beamforming is performed on the data received by multiple receivers of the radar sensor.
[0027] This application first acquires data through multi-antenna transmission and multi-antenna reception, and then performs beamforming on the data received from multiple receivers, thereby reducing the field of view of the radar sensor receiver. The reduced field of view allows for accurate acquisition of data on the area of vital signs to be detected.
[0028] Secondly, one embodiment of this application provides a vital signs detection device, the device comprising:
[0029] The data acquisition module is used to acquire data on the area of vital signs to be detected based on radar sensors;
[0030] The mapping relationship determination module is used to process the data to obtain the distance-energy mapping relationship of the moving target after removing the static target in the area of the vital signs to be detected, and to obtain the distance-phase mapping relationship of the moving target;
[0031] The parameter determination module is used to determine at least one specified parameter corresponding to a distance based on the distance-energy mapping relationship and the distance-phase mapping relationship; wherein, the specified parameter includes at least the proportion of high-frequency signals;
[0032] The detection result module is used to input the specified parameters corresponding to the at least one distance into a pre-built support vector machine model to obtain the vital sign detection results output by the support vector machine model.
[0033] The support vector machine model is used to determine whether the subject is experiencing respiratory arrest in the area of the vital signs to be detected or whether the subject is not in the area of the vital signs to be detected.
[0034] In one possible design, the specified parameters may further include one or more of the following parameters:
[0035] Energy intensity of respiratory frequency band, energy intensity of heart rate frequency band, maximum energy intensity of heart rate frequency band, variance of energy intensity of heart rate frequency band, and variance of maximum energy intensity of heart rate frequency band.
[0036] In one possible design, the support vector machine model is constructed in the following way:
[0037] Obtain specified parameters for at least one distance sample and corresponding labels for the at least one distance sample, wherein the labels include whether the subject to be tested is experiencing respiratory arrest in the area of the vital signs to be detected or whether the subject to be tested is not in the area of the vital signs to be detected;
[0038] The specified parameters of the at least one distance sample are input into the support vector machine model so that the support vector machine model outputs the predicted label of the at least one distance sample;
[0039] The support vector machine model is trained based on the loss between the predicted label and the labeled label.
[0040] In one possible design, when the radar sensor collects data on the area of vital signs to be detected, there is a sampling time difference. The mapping relationship determination module removes static targets from the area of vital signs to be detected in the following way:
[0041] Based on the energy intensity and phase value corresponding to the current sampling time, a first value is obtained; and based on the energy intensity and phase value corresponding to the previous time, a second value is obtained.
[0042] Perform modulo operations on the first value and the second value respectively;
[0043] The static targets in the area of vital signs to be detected are removed by using the difference between the modulo operation result of the first value and the modulo operation result of the second value.
[0044] In one possible design, the radar sensor in the acquisition module acquires data of the area to be detected vital signs in the following way: multi-antenna transmission and multi-antenna reception.
[0045] The device further includes:
[0046] Beamforming is performed on the data received by multiple receivers of the radar sensor.
[0047] Thirdly, one embodiment of this application also provides an electronic device, including:
[0048] processor;
[0049] Memory used to store the processor's executable instructions;
[0050] The processor is configured to execute the instructions to implement any of the methods provided in the first aspect of this application.
[0051] Fourthly, one embodiment of this application also provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform any of the methods provided in the first aspect of this application.
[0052] Fifthly, one embodiment of this application provides a computer program product including a computer program / instructions that, when executed by a processor, implement any of the methods provided in the first aspect of this application.
[0053] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0054] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0055] Figure 1a This application provides a schematic diagram of the distance-energy mapping relationship during normal human breathing, as shown in one embodiment.
[0056] Figure 1b A schematic diagram of the distance-energy mapping relationship when a person pauses breathing, provided as an embodiment of this application;
[0057] Figure 1c A schematic diagram of the distance-energy mapping relationship is provided in one embodiment of this application when the person is not in the area of the vital signs to be detected;
[0058] Figure 2a A schematic diagram of the heart rate frequency band-energy mapping relationship provided in an embodiment of this application when the subject to be tested is not in the area of the vital signs to be detected;
[0059] Figure 2b A schematic diagram of the heart rate frequency band-energy mapping relationship provided in an embodiment of this application when the subject to be tested is not in the area of the vital signs to be detected;
[0060] Figure 2c A schematic diagram of the heart rate frequency band-energy mapping relationship provided in an embodiment of this application when the subject to be tested is not in the area of the vital signs to be detected;
[0061] Figure 3a A schematic diagram of the heart rate frequency band-energy mapping relationship of a subject under respiratory arrest in the area of the vital signs to be detected, provided as an embodiment of this application;
[0062] Figure 3b A schematic diagram of the heart rate frequency band-energy mapping relationship of a subject under respiratory arrest in the area of the vital signs to be detected, provided as an embodiment of this application;
[0063] Figure 3c A schematic diagram of the heart rate frequency band-energy mapping relationship of a subject under respiratory arrest in the area of the vital signs to be detected, provided as an embodiment of this application;
[0064] Figure 4a A schematic diagram showing the proportion of high-frequency signals in the area of vital signs to be detected in a subject under respiratory arrest, provided as an embodiment of this application;
[0065] Figure 4b A schematic diagram showing the proportion of high-frequency signals when the subject is not in the area of the vital signs to be detected, as provided in an embodiment of this application;
[0066] Figure 5 This is a schematic diagram of the support vector machine model construction process provided in an embodiment of this application;
[0067] Figure 6 This is a schematic flowchart of a vital signs detection method provided in one embodiment of this application;
[0068] Figure 7 This is a schematic diagram of the distance-energy mapping relationship provided in an embodiment of this application;
[0069] Figure 8 This is a schematic flowchart of a static target removal method provided in an embodiment of this application;
[0070] Figure 9 This is a schematic diagram of the distance-energy mapping relationship provided in an embodiment of this application;
[0071] Figure 10a This is a schematic diagram of radar sensor data acquisition provided in an embodiment of this application;
[0072] Figure 10b This is a schematic diagram of radar sensor data acquisition provided in an embodiment of this application;
[0073] Figure 11 This is a schematic diagram of the horizontal angle before and after modification of the radar sensor data acquisition range provided in an embodiment of this application;
[0074] Figure 12 A schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0075] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.
[0076] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data used can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0077] As living standards improve, people are paying more attention to their health, especially in community-based elderly care institutions, which are increasingly focusing on monitoring the health of the elderly. Vital signs are an important indicator of health, and currently, health monitoring typically involves collecting vital signs such as respiration and heart rate using contact-based instruments. However, for most users, contact-based instruments are expensive and complex to operate.
[0078] Therefore, this application provides a method and apparatus for detecting vital signs. The method involves collecting data using a radar sensor, processing the data, determining at least one specified parameter corresponding to a distance, and then using the determined specified parameter as the input to a support vector machine model. Based on the specified parameter, which includes at least the proportion of high-frequency signals, it can accurately determine whether there are vital signs in the area to be detected.
[0079] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation steps as shown in the following embodiments or drawings, the method may include more or fewer operation steps based on conventional or non-inventive methods. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application.
[0080] The inventive concept of this application is that, during the data acquisition process of radar sensors for detecting vital signs, a single-delay canceller is used to filter out static targets, thereby reducing the impact of highly reflective targets in the area to be detected on ranging. However, in two scenarios—where the person being detected is in the area of respiratory arrest and the person is not in the area of the area of the detected vital signs—the above method may lead to erroneous results.
[0081] Using the area of the vital signs to be detected as the bed and the person to be tested as the subject as an example, such as... Figure 1a As shown, when a person is breathing normally, the energy intensity corresponding to the collected distance parameter will have a significant peak, such as... Figure 1b As shown, when a person stops breathing, the peak energy intensity corresponding to the collected distance parameter decreases significantly. And as... Figure 1c As shown, when the person is not in the area where the vital signs to be detected are being monitored, the peak value of the reflected signal energy intensity corresponding to the bed is compared with... Figure 1b The peak values of the medium energy intensities are close, which may lead to misjudgments when determining whether a person is in respiratory arrest or is not in the area of the vital signs to be detected.
[0082] To address the aforementioned issues, when training the support vector machine model, it learns two scenarios: the subject pausing breathing within the target vital signs region and the subject not within the target vital signs region. This allows for accurate differentiation between these two scenarios. Furthermore, extracting more feature parameters further enhances the accuracy of the training process.
[0083] The following sections will introduce the scheme of this application in three parts: determination of specified parameters, training of support vector machine model, and detection of vital signs.
[0084] I. Determining the Specified Parameters
[0085] In the data acquisition process for detecting vital signs using radar sensors, the received wave signals from the radar sensor receiver undergo one-dimensional Fourier transform and static target removal to obtain a range-energy mapping relationship. Then, phase extraction and phase unwrapping are performed on each range to obtain a range-phase mapping relationship.
[0086] For example, suppose a one-dimensional Fourier transform is performed on the first wave signal of each frame acquired by the radar sensor, the number of points in the Fourier transform is 80, and a total of 256 frames of data are detected. Then, by removing static targets from the two consecutive frames of data and accumulating the 256 frames of data, the following result is obtained: Figure 1a The distance-energy mapping relationship is shown. Phase extraction is performed on each distance, and phase unwrapping is then performed to obtain an 80*256 distance-phase mapping relationship. For example, it can include phase changes caused by heart rate and respiration. Since heart rate and respiration occur in different frequency bands, an Infinite Impulse Response (IIR) filter can be used to distinguish the phases of heart rate and respiration.
[0087] As described above, after determining the distance-energy mapping relationship and the distance-phase mapping relationship, at least one specified parameter corresponding to a distance is determined based on these relationships. The specified parameter may include one or more of the following parameters:
[0088] BreathPower (energy intensity in the respiratory band), HeartPower (energy intensity in the heart rate band), HeartIdx (maximum energy intensity in the heart rate band), HeartPowerVar (variance of energy intensity in the heart rate band), HeartIdxVar (variance of maximum energy intensity in the heart rate band), and HighSigProp (proportion of high-frequency signals).
[0089] For example, such as Figure 2a As shown, this occurs when the person to be tested is not in the area where vital signs are to be detected. Figure 1a The heart rate frequency band-energy mapping relationship corresponding to the point preceding the peak energy intensity point. For example... Figure 2b As shown, this occurs when the person to be tested is not in the area where vital signs are to be detected. Figure 1a The energy intensity peak point corresponds to the heart rate frequency band-energy mapping relationship. For example... Figure 2c As shown, this occurs when the person to be tested is not in the area where vital signs are to be detected. Figure 1a The heart rate frequency band-energy mapping relationship corresponding to the point after the peak energy intensity point.
[0090] Similarly, such as Figure 3a As shown, this is a case of respiratory arrest in the area of the vital signs to be tested. Figure 1a The heart rate frequency band-energy mapping relationship corresponding to the point preceding the peak energy intensity point. For example... Figure 3b As shown, this is a case of respiratory arrest in the area of the vital signs to be tested. Figure 1a The energy intensity peak point corresponds to the heart rate frequency band-energy mapping relationship. For example... Figure 3c As shown, this is a case of respiratory arrest in the area of the vital signs to be tested. Figure 1a The heart rate frequency band-energy mapping relationship corresponding to the point after the peak energy intensity point.
[0091] During the detection of vital signs, even if the subject is holding their breath, there will still be faint breathing; therefore, the energy intensity of the respiratory frequency band can be used as a specified parameter. When the subject is holding their breath, breathing will weaken, but the heartbeat will not stop; therefore, the energy intensity of the heart rate frequency band can also be used as a specified parameter. Furthermore, because the subject is not in the area of the vital signs being detected, there is still some noise signal within the detected heart rate frequency band. This results in no order of magnitude among the multiple energy intensities and the maximum energy intensity within the heart rate frequency band; therefore, variance can be used to reflect this disorder.
[0092] Optionally, based on the distance-phase mapping relationship and IIR filter, the phase change within the heart rate frequency band at any distance is obtained. Then, the power change is obtained through Fourier transform, and the final energy intensity HeartPower is obtained by accumulating the energy intensity within the frequency band. HeartIdx is determined by the location of the highest point after the Fourier transform. BreathPower can refer to the determination process of HeartPower, the difference being the frequency band. The determination process of HeartPowerVar and HeartIdxVar can be as follows: define a 20-frame data buffer, store the HeartPowerBuff and HeartIdxBuff of the previous 20 frames of HeartPower and HeartIdx at the current moment, and calculate HeartPowerVar and HeartIdxVar using the variance formula.
[0093] like Figure 4a As shown, because the subject experiences respiratory arrest in the area of the vital signs to be detected, the energy intensity corresponding to the high-frequency component (greater than 2Hz) of the phase change accounts for a relatively small proportion of the total energy intensity. However, as... Figure 4b As shown, when the subject is not in the area of the vital signs to be detected, the energy intensity of the high-frequency component (greater than 2Hz) in the phase change accounts for a larger proportion of the total energy intensity. Therefore, the proportion of high-frequency signals can also be used as a specified parameter.
[0094] II. Support Vector Machine Model Training
[0095] As can be seen from the above description, after determining the specified parameters, such as Figure 5 As shown, the support vector machine model can be constructed in the following way:
[0096] S501, obtain at least one specified parameter of a distance sample and at least one label corresponding to a distance sample, the label including whether the subject is in the area of the vital signs to be detected and is not in the area of the vital signs to be detected.
[0097] For example, data corresponding to apnea in the area of the vital signs to be tested is marked as 1, and data corresponding to apnea not in the area of the vital signs to be tested is marked as 0.
[0098] S502, input the specified parameters of at least one distance sample into the support vector machine model so that the support vector machine model outputs the predicted label of at least one distance sample.
[0099] S503 trains a support vector machine model based on the loss between predicted and labeled labels.
[0100] Suppose the training sample set is D = {(x1,y1),(x2,y2),…,(xm,ym)}; y i ∈{-1,+1}, where xi represents a one-dimensional vector consisting of at least one specified parameter of the i-th distance sample, i is any positive integer between 1 and m, and yi represents the label corresponding to the i-th distance sample.
[0101] The support vector machine model is trained using a sample set to obtain the decision function for the optimal hyperplane. The hyperplane can be expressed by a linear equation according to Formula 1:
[0102] ω T Formula 1: x+b=0
[0103] Where ω = (ω1; ω2; ...; ωd) is the normal vector, which determines the direction of the hyperplane; b is the displacement term, which determines the distance between the hyperplane and the origin; and x is an element in the sample set.
[0104] The hyperplane can be determined based on the normal vector ω and the displacement b, denoted as (ω, b). The distance from any point x in the sample space to the hyperplane (ω, b) is expressed by Formula 2:
[0105]
[0106] If the hyperplane training is correct, for (x) i ,y i Let )∈D, then:
[0107]
[0108] The training samples closest to the hyperplane ensure that the equality in Equation 3 holds and can be called "support vectors". The sum of the distances from two out-of-class support vectors to the hyperplane is:
[0109]
[0110] The above distances are called the "margin". To find the dividing hyperplane with the "maximum margin", that is, to find the constraint parameters ω and b that satisfy Equation 3, such that γ is maximized, i.e.:
[0111]
[0112] sty i (ω T x i +b)≥1, i=1,2,…m. Formula 5
[0113] To maximize the interval, we only need to maximize |ω| -1 This is equivalent to minimizing ||ω|| 2 Therefore, Formula 5 can also be expressed as:
[0114]
[0115] sty i (ω T x i +b)≥1, i=1,2,…m. Formula Six
[0116] The model corresponding to the dividing hyperplane is obtained through Formula 6:
[0117] f(x)=ω T Formula 7 for x+b
[0118] Applying the Lagrange multiplier method to Equation 6 involves adding a Lagrange multiplier α to each constraint in Equation 6. i If ≥0, then the Lagrange function can be expressed as:
[0119]
[0120] Setting the partial derivatives of L(ω,b,α) with respect to ω and b to 0, we get:
[0121]
[0122]
[0123] Substituting Equation 9 into Equation 8, we can eliminate ω and b in L(ω,b,α). Then, considering the constraints of Equation 10, we obtain the dual problem of Equation 10:
[0124]
[0125]
[0126] α i ≥0, i=1,2,…,m.
[0127] After solving for α, we can find ω and b to obtain the model:
[0128]
[0129] The inner product of sample x and the sample set can be represented by a Gaussian kernel function.
[0130]
[0131] Where K represents the Euclidean distance from x to z, x is a sample, z is another sample at the center of the kernel function, and σ is the width of the Gaussian kernel function, which is a configurable constant.
[0132] Add an adjustable slack variable ζ to the Gaussian kernel function. i Given ≥0 and the penalty factor C, the problem of finding the minimum value in Formula 6 becomes:
[0133]
[0134] sty i (ω T x i +b)≥1-ζ i Formula Fourteen, i = 1, 2, ..., m.
[0135] Then the constraint condition of Formula 11 becomes:
[0136]
[0137]
[0138] The classification decision function is shown in Formula 16, where f(x) represents the decision function corresponding to the optimal separating hyperplane:
[0139]
[0140] In summary, we obtain the decision function f(x) after the support vector machine model has been trained. Here, during the training process of the support vector machine model, if the loss between the predicted label and the labeled label is too large, the aforementioned slack variable ζ can be adjusted. i ≥0 and penalty factor C, or check if there are any erroneous samples in the training samples.
[0141] Optionally, after obtaining the decision function f(x) after the support vector machine model training is completed, in order to verify the classification accuracy of the decision function, x'i from another set of validation samples D2 = {(x'1,y1),(x'2,y2),…,(x'm,ym)} can be input into the decision function f(x) to obtain the statistical result F = {(x'1,f1),(x'2,f2),…,(x'm,fm)}. By comparing whether fi in the same sample F is equal to the original yi, a percentage result is obtained. If the percentage result does not meet the preset threshold, the above slack variable ζ can be further adjusted. i The training sample is ≥0 and the penalty factor C is checked, or the training samples are checked for erroneous samples, and finally the trained support vector machine model is obtained.
[0142] III. Vital Signs Monitoring
[0143] As described above, after the support vector machine model has been trained, the reference... Figure 6 This application provides a method for detecting vital signs, including the following steps:
[0144] S601 collects data on the area of vital signs to be detected based on radar sensors.
[0145] S602, perform data processing to obtain the distance-energy mapping relationship of moving targets after removing static targets from the area of vital signs to be detected.
[0146] The data processing procedure can be found in the description of the data processing procedure in the determination of specified parameters, and will not be repeated here.
[0147] S603, determine whether the maximum energy intensity in the distance-energy mapping relationship is greater than the first preset energy intensity. If yes, proceed to step S604; otherwise, proceed to step S605.
[0148] S604, vital signs are present in the area to be detected.
[0149] S605, determine the distance-phase mapping relationship based on the distance-energy mapping relationship.
[0150] S606, determine at least one specified parameter corresponding to a distance; wherein the specified parameter includes at least the proportion of high-frequency signals.
[0151] S607, input at least one specified parameter corresponding to the distance into the pre-built support vector machine model to obtain the vital sign detection results output by the support vector machine model.
[0152] S608, if the vital signs test result is 1, then the person being tested is experiencing respiratory arrest in the area of the vital signs to be tested; if the vital signs test result is 0, then the person being tested is not in the area of the vital signs to be tested.
[0153] In summary, this application, by determining at least one specified parameter corresponding to a distance, and then using this determined specified parameter as input to a support vector machine (SVM) model, can accurately determine whether a vital sign exists in the region to be detected, based on specified parameters including at least the proportion of high-frequency signals. Furthermore, the SVM model can also perform on-site learning and recognition of the application scenario during model training, enabling the obtained SVM model to produce more accurate output results in practical applications after training.
[0154] In addition, in practical applications, such as Figure 7 As shown, even when the subject is not within the detection range of vital signs, the subject can still be detected within a distance range of 60-80, but in real-world scenarios, the subject is not present. Therefore, the specified parameters described above can also include the range energy intensity, RangePower. To address this issue, considering the sampling time difference when the radar sensor collects data from the detection range of vital signs, different sampling times can lead to random phase differences.
[0155]
[0156] The phase change in the data collected by the radar sensor is shown in Formula 17, where t is the time before the current sampling time, T is the current sampling time, fR is the frequency point corresponding to the target distance, ΔR(T) is the change of target distance with T, R0 is the initial distance, and λ is the wavelength. Due to the difference in the initial frequency of each frame of data, a random time Δt is introduced during the time sampling process, thus introducing a random phase difference: Although the phase difference is small, a large change in energy intensity will occur when there are strong reflective objects in the area to be detected: S p =Ae j*2π*(fRΔt) Where A is the reflection intensity of the target, and when Δt is 0, S p The value is 0, and as Δt increases, S p It will also increase. Therefore, as Figure 8 As shown, static targets in the area of vital signs to be detected are removed using the following method:
[0157] S801, based on the energy intensity and phase value corresponding to the current sampling time, obtain the first value; and based on the energy intensity and phase value corresponding to the previous time, obtain the second value;
[0158] S802, perform modulo operations on the first and second values respectively;
[0159] S803, using the difference between the modulo operation result of the first value and the modulo operation result of the second value, removes static targets in the area of vital signs to be detected.
[0160] For example, the difference between the modulo operation result of the first value and the modulo operation result of the second value is calculated using Formula 18.
[0161]
[0162]
[0163] This can reduce the energy intensity difference caused by the aforementioned phase difference. For example... Figure 9 As shown, it does not exist after adjustment. Figure 7 The peak energy intensity shown is the peak value.
[0164] Furthermore, to more accurately detect the area of vital signs to be detected, the radar sensor can also collect data of the area of vital signs to be detected through multi-antenna transmission and multi-antenna reception. Beamforming is then performed on the data received from multiple receivers of the radar sensor, thus making the range of data collection more precise. For example... Figure 10a As shown, this represents the data acquisition range of a radar sensor using a single antenna for transmitting and a single antenna for receiving data. Figure 10b The diagram shows the data acquisition range of a radar sensor using multiple antennas for transmitting and receiving data. For example, assuming the area to be detected as a vital sign is the bed, the table and chairs next to the bed might also be captured. These tables and chairs would then be false, highly reflective targets, thus affecting the detection results.
[0165] For example, the range of data collected by the radar sensor is determined in the following manner:
[0166] LambaRX = [0, 0.5, 1, 1.5]
[0167] SignalVector=[RX0data,RX1data,RX2data,RX3data]
[0168]
[0169] Angle = 0;
[0170] S = SignalVector * SignalVector
[0171] Where LambaRX is a multiple of the wavelength λ, SignalVector is the signal vector of the four radar sensor receiving channels, and SteeringVector is the steering vector at angle Angle (0°). Figure 11 As shown, Figure 10a , Figure 10b Modify the horizontal angle before and after the radar sensor's data acquisition range. This modification can also increase the gain of the radar sensor's receiver.
[0172] Having introduced the vital signs detection method and apparatus according to exemplary embodiments of this application, we will now introduce an electronic device according to another exemplary embodiment of this application.
[0173] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."
[0174] In some possible implementations, the electronic device according to this application may include at least one processor and at least one memory. The memory stores program code that, when executed by the processor, causes the processor to perform the steps of the vital signs detection method according to the various exemplary embodiments of this application described above. For example, the processor may perform steps such as those in the vital signs detection method.
[0175] The following reference Figure 12 To describe an electronic device 120 according to this embodiment of the present application. Figure 12 The electronic device 120 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0176] like Figure 12 As shown, the electronic device 120 is presented in the form of a general electronic device. The components of the electronic device 120 may include, but are not limited to: at least one processor 121, at least one memory 122, and a bus 123 connecting different system components (including memory 122 and processor 121).
[0177] Bus 123 represents one or more of several types of bus structures, including memory bus or memory controller, peripheral bus, processor, or local bus using any of the multiple bus structures.
[0178] The memory 122 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 1221 and / or cache memory 1222, and may further include read-only memory (ROM) 1223.
[0179] The memory 122 may also include a program / utility 1225 having a set (at least one) of program modules 1224, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.
[0180] Electronic device 120 can also communicate with one or more external devices 124 (e.g., keyboard, pointing device, etc.), and with one or more devices that enable a user to interact with electronic device 120, and / or with any device that enables electronic device 120 to communicate with one or more other electronic devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 125. Furthermore, electronic device 120 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 126. As shown, network adapter 126 communicates with other modules used in electronic device 120 via bus 123. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 120, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0181] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 122 including instructions, which can be executed by a processor 121 to perform the above-described method. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.
[0182] In an exemplary embodiment, a computer program product is also provided, including a computer program / instructions that, when executed by a processor 121, implement any of the vital signs detection methods provided in this application.
[0183] In an exemplary embodiment, various aspects of the vital signs detection method provided in this application can also be implemented in the form of a program product, which includes program code. When the program product is run on a computer device, the program code is used to cause the computer device to perform the steps in the vital signs detection method according to the various exemplary embodiments of this application described above.
[0184] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0185] The program product for vital sign detection according to the embodiments of this application can be a portable compact disc read-only memory (CD-ROM) and include program code, and can run on an electronic device. However, the program product of this application is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0186] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take many forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0187] The program code contained on the readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wired, fiber optic, RF, etc., or any suitable combination thereof.
[0188] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java and C++, and conventional procedural programming languages such as C or similar languages. The program code can execute entirely on the user's electronic device, partially on the user's device, as a standalone software package, partially on the user's electronic device and partially on a remote electronic device, or entirely on a remote electronic device or server. In cases involving remote electronic devices, the remote electronic device can be connected to the user's electronic device via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external electronic device (e.g., via the Internet using an Internet service provider).
[0189] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.
[0190] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.
[0191] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0192] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable electronic device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable electronic device, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.
[0193] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable electronic device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.
[0194] These computer program instructions may also be loaded onto a computer or other programmable electronic device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable device, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.
[0195] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.
[0196] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.
Claims
1. A vital signs detection device, characterized in that, The device includes: The data acquisition module is used to acquire data on the area of vital signs to be detected based on radar sensors; The mapping relationship determination module is used to determine the following when the radar sensor collects data on the area of vital signs to be detected, and there is a sampling time difference: Based on the energy intensity and phase value corresponding to the current sampling time, a first value is obtained; and based on the energy intensity and phase value corresponding to the previous sampling time, a second value is obtained; modulo operations are performed on the first value and the second value respectively; using the difference between the modulo operation results of the first value and the second value, static targets in the area of vital signs to be detected are removed, resulting in the range-energy mapping relationship of the moving target after removing the static targets in the area of vital signs to be detected, and the range-phase mapping relationship of the moving target. The parameter determination module is used to determine at least one specified parameter corresponding to a distance based on the distance-energy mapping relationship and the distance-phase mapping relationship; wherein, the specified parameter includes at least the proportion of high-frequency signals greater than 2Hz; The detection result module is used to input the specified parameters corresponding to the at least one distance into a pre-built support vector machine model to obtain the vital sign detection results output by the support vector machine model. The support vector machine model is used to determine whether the subject is experiencing respiratory arrest in the area of the vital signs to be detected or whether the subject is not in the area of the vital signs to be detected.
2. The apparatus according to claim 1, characterized in that, The specified parameter may also include one or more of the following parameters: Energy intensity of respiratory frequency band, energy intensity of heart rate frequency band, maximum energy intensity of heart rate frequency band, variance of energy intensity of heart rate frequency band, and variance of maximum energy intensity of heart rate frequency band.
3. The apparatus according to claim 1, characterized in that, The support vector machine model is constructed in the following way: Obtain specified parameters for at least one distance sample and corresponding labels for the at least one distance sample, wherein the labels include that the subject to be detected is not within the area of the vital signs to be detected; The specified parameters of the at least one distance sample are input into the support vector machine model so that the support vector machine model outputs the predicted label of the at least one distance sample; The support vector machine model is trained based on the loss between the predicted label and the labeled label.
4. The apparatus according to claim 1, characterized in that, The radar sensor collects data from the area of vital signs to be detected in the following ways: multi-antenna transmission and multi-antenna reception. The device further includes: Beamforming is performed on the data received by multiple receivers of the radar sensor.
5. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the function of the vital signs detection device as described in any one of claims 1 to 4.
6. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is enabled to perform the functions of the vital signs detection device as described in any one of claims 1 to 4.
7. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they perform the functions of the vital signs detection device as described in any one of claims 1 to 4.