CN114052692A - Heart rate analysis method and equipment based on millimeter wave radar - Google Patents
Heart rate analysis method and equipment based on millimeter wave radar Download PDFInfo
- Publication number
- CN114052692A CN114052692A CN202111248081.3A CN202111248081A CN114052692A CN 114052692 A CN114052692 A CN 114052692A CN 202111248081 A CN202111248081 A CN 202111248081A CN 114052692 A CN114052692 A CN 114052692A
- Authority
- CN
- China
- Prior art keywords
- millimeter wave
- wave radar
- heart rate
- waveform data
- analysis method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 32
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 24
- 238000005070 sampling Methods 0.000 claims abstract description 20
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 23
- 230000009466 transformation Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000033001 locomotion Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000000241 respiratory effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 238000013526 transfer learning Methods 0.000 description 3
- 230000008602 contraction Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 210000000876 intercostal muscle Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004165 myocardium Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02438—Detecting, measuring or recording pulse rate or heart rate with portable devices, e.g. worn by the patient
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention relates to a heart rate analysis method and a technical scheme of equipment based on a millimeter wave radar, wherein the heart rate analysis method comprises the following steps: collecting heartbeat waveform data of a front living body including noise through a millimeter wave radar device; sampling the heartbeat waveform data and performing filtering processing; sampling the heartbeat waveform data subjected to filtering processing, and calculating time-frequency characteristics; creating a convolutional neural network, taking the time-frequency characteristics as the input of the convolutional neural network, and outputting the sample entropy of the heart rate and heartbeat waveform data; and determining the optimal heart rate monitoring position of the millimeter wave radar device through the sample entropy. The invention has the beneficial effects that: measuring the heart rate is accurate, which can guide the user to use the device correctly.
Description
Technical Field
The invention relates to the field of computers, in particular to a heart rate analysis method and equipment based on a millimeter wave radar.
Background
Millimeter wave (mmWave) is a special radar technology that uses short wavelength electromagnetic waves, which can emit signals with wavelengths on the order of millimeters. In the electromagnetic spectrum, this wavelength is considered to be a short wavelength, which is also one of the advantages of this technology. Indeed, the size of the system components (e.g., antennas) required to process millimeter-wave signals is really small. Another advantage of short wavelengths is high accuracy. A millimeter wave system with an operating frequency of 76-81 GHz (corresponding to a wavelength of about 4mm) will be able to detect movements as small as a few tenths of a millimeter.
The breathing and heartbeat of a human body are macroscopically mechanical movement, the breathing movement is periodic movement generated by the contraction and the relaxation of diaphragm muscles and intercostal muscles, the abdomen has 1 to 12mm fluctuation and the back has 0.1 to 0.5mm fluctuation. The heartbeat is a periodic motion generated by the contraction and relaxation of the heart muscle, with 0.1 to 0.5mm fluctuation in the chest around the heart and 0.01 to 0.2mm fluctuation in the back around the heart. It is clear that these minor changes can be detected by millimeter wave radar. At present, the applications of the millimeter wave radar in monitoring the respiratory heart rate include monitoring the respiratory heart rate in sleep, monitoring the respiratory heart rate of a driver and the like.
Four difficulties exist in monitoring the respiratory heart rate by the millimeter wave radar:
(1) the sensitivity is not sufficient, the millimeter wave radar can detect the movement of a few tenths of a millimeter and the movement generated by the heartbeat is 0.1 to 0.5mm (chest) and 0.01 to 0.2mm (back).
(2) The interference is large, the interference is strong, the movement of the trunk and limbs of the human body is strong interference for the detection of the breathing heart rate, the talking blinking of eyes is also strong interference, the wriggling of the intestinal tract, the shaking of muscles and the like.
(3) The non-contact measurement has the defects, the non-contact measurement is originally the advantages of the millimeter wave radar, but the non-contact measurement has the defects, the radar wave is emitted from the transmitting antenna, reaches a measured object through a section of space, then is reflected, and then reaches the receiving antenna through a section of space, various interferences are introduced in the whole transmission process, and the influences such as reflectivity, reflection area and the like are also caused.
(4) Software and hardware technology is not yet mature.
The four difficulties of monitoring the respiratory heart rate by the millimeter wave radar are solved, and the method is difficult to achieve by only depending on software or hardware.
Disclosure of Invention
The invention aims to at least solve one of the technical problems in the prior art, provides a heart rate analysis method and equipment based on a millimeter wave radar, and solves the defects in the prior art.
The technical scheme of the invention comprises a heart rate analysis method based on a millimeter wave radar, which is characterized by comprising the following procedures: collecting heartbeat waveform data of a front living body including noise through a millimeter wave radar device; performing first sampling on the heartbeat waveform data and filtering; performing second sampling on the heartbeat waveform data subjected to filtering processing, and calculating time-frequency characteristics; creating a convolutional neural network, taking the time-frequency characteristics as the input of the convolutional neural network, and outputting sample entropies of heart rate and heart beat waveform data; and determining the optimal heart rate monitoring position of the millimeter wave radar device according to the sample entropy.
According to the heart rate analysis method based on the millimeter wave radar, the step of collecting the heart beat waveform data of the front living body including noise through the millimeter wave radar device comprises the following steps: and (3) constraining radar waves emitted by the millimeter wave radar device, and calling an interface to analyze the acquired data to obtain the distance, the position and the heartbeat waveform data of the front living body.
According to the heart rate analysis method based on the millimeter wave radar, the step of performing first sampling and filtering on the heartbeat waveform data comprises the following steps: sampling the heartbeat waveform data for the first time to obtain a time sequence S, and then filtering the S, wherein the filter is a finite-length single-bit impulse response filter, and the mathematical expression of the filter is
According to the heart rate analysis method based on the millimeter wave radar, the filter is configured to be of an equal ripple design, the order of the filter is 200, the cut-off frequency of the band-pass filter is 0.6HZ, the pass frequency is 1HZ, the pass frequency is 5.4HZ, the cut-off frequency is 5.8HZ, and the maximum attenuation in the stop band is 40 dB.
The method for heart rate analysis based on millimeter wave radar, wherein the filtering is performedPerforming a second sampling of the processed heartbeat waveform data and calculating time-frequency characteristics includes: continuously sampling the filtered time sequence data to obtain a time sequence S1, and performing continuous wavelet transform on the time sequence S1, wherein the transform formula is
Where φ is the fundamental wavelet and a is the scale parameter a>0 and b are position parameters, a wavelet function cluster is obtained by continuously changing the values of the scale parameter a and the position parameter b, and the wavelet function cluster and the time sequence S1 are subjected to similarity operation to obtain continuous wavelet transformation coefficients
For continuous wavelet transform coefficient
And calculating the absolute value to obtain the time-frequency characteristics of the time sequence S1.
The millimeter wave radar-based heart rate analysis method, wherein a convolutional neural network is created, the time-frequency features are used as input of the convolutional neural network, and outputting sample entropy of heart rate and heart beat waveform data comprises the following steps: acquiring a pre-trained GoogleLeNet convolutional neural network, and converting time-frequency features obtained by continuous wavelet transformation into RGB images of 224 × 3 as input; setting the random discarding probability of pool5-drop _7x7_ s1 layer to 0.6; replacing loss3-classifier by a new full connection layer, and resetting the learning rate of the full connection layer; setting the output of the GoogLeNet convolutional neural network into 135 classes, wherein the 135 classes comprise sample entropies of 27 classes of heart rates and 5 classes of heartbeat waveform data; wherein the google lenet convolutional neural network is a pre-trained deep neural network.
The millimeter wave radar-based heart rate analysis method, wherein determining the optimal heart rate monitoring position of the millimeter wave radar device through the sample entropy, comprises: a plurality of heart rate measuring positions are generated through horizontal and vertical rotation of two stepping motors, sample entropies are calculated at each measuring position through a convolution network, the calculated sample entropies are sorted from small to large, and when the minimum sample entropies are smaller than a set threshold value, the optimal searching position is determined.
According to the heart rate analysis method based on the millimeter wave radar, the method further comprises the following steps: the heart rate is continuously monitored by staying at the optimal search position, and the search is restarted when the sample entropy of the position exceeds the set threshold.
The technical scheme of the invention also comprises analysis equipment based on the millimeter wave radar, which comprises an operation processor, a millimeter wave radar sensing device, a power supply circuit, a motor driving circuit and a stepping motor; the millimeter wave radar sensing device is provided with a receiving and transmitting antenna; the millimeter wave radar sensing device is connected with the operation processor through an SPI bus; the power supply circuit is used for respectively supplying power to the operation processor and the millimeter wave radar sensing device; the motor driving circuit is used for driving the stepping motor; the operation processor executes any one of the millimeter wave radar-based heart rate analysis methods.
The millimeter-wave radar-based analysis device of claim, wherein the transceiver antenna is configured to constrain the emitted millimeter-radar waves, the transceiver antenna comprising a horn antenna or a lens.
The invention has the beneficial effects that: (1) the millimeter wave radar integrated chip is used on hardware, and the advantages of high integration are that the circuit design is simplified, the consistency is good, the anti-interference performance is high, and the like; (2) a lens or a horn antenna is additionally arranged, and one of the two enhancing signals and the other enhancing the directivity of the millimeter wave radar are used; (3) the two stepping motors are used for driving a circuit board provided with the radar chip to rotate in the horizontal and vertical directions to find an optimal heart rate measuring position; (4) extracting characteristics, namely converting the one-dimensional heartbeat waveform obtained after filtering into time-frequency characteristics through Continuous Wavelet Transform (CWT), wherein the time-frequency characteristics can better describe the essence of data; (5) and constructing a convolutional neural network, wherein the input of the convolutional neural network is a time-frequency characteristic, the sample entropy of the two-heart-beat waveform data of one heart rate with two dimensions is output, and the circuit board provided with the radar chip is driven by the sample entropy adjusting stepping motor to rotate in the horizontal and vertical directions to find the optimal heart rate measuring position.
Drawings
The invention is further described below with reference to the accompanying drawings and examples;
fig. 1 is a flow chart illustrating a heart rate analysis of a millimeter wave radar according to an embodiment of the present invention.
Fig. 2 is a diagram showing the device connection relationship of the millimeter wave radar apparatus according to the embodiment of the present invention.
Fig. 3 is a schematic diagram illustrating millimeter wave radar sensing according to an embodiment of the present invention.
Fig. 4 is a schematic diagram showing the acquisition of heart rate at different constraint angles of the millimeter wave radar according to the embodiment of the invention.
Fig. 5 is a schematic view illustrating the operation of a stepping motor according to an embodiment of the present invention.
FIG. 6 is a schematic diagram of a convolutional neural network according to an embodiment of the present invention.
FIG. 7 is a graph showing a comparison of heart rate waveforms for different signal-to-noise ratios according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number.
In the description of the present invention, the consecutive reference numbers of the method steps are for convenience of examination and understanding, and the implementation order between the steps is adjusted without affecting the technical effect achieved by the technical solution of the present invention by combining the whole technical solution of the present invention and the logical relationship between the steps.
In the description of the present invention, unless otherwise explicitly defined, terms such as set, etc. should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
Fig. 1 is a flow chart illustrating a heart rate analysis of a millimeter wave radar according to an embodiment of the present invention. The process comprises the following steps: collecting heartbeat waveform data of a front living body including noise through a millimeter wave radar device; performing first sampling on the heartbeat waveform data and performing filtering processing; performing second sampling on the heartbeat waveform data subjected to filtering processing, and calculating time-frequency characteristics; creating a convolutional neural network, taking the time-frequency characteristics as the input of the convolutional neural network, and outputting the sample entropy of the heart rate and heartbeat waveform data; and determining the optimal heart rate monitoring position of the millimeter wave radar device through the sample entropy.
In one embodiment, for filter design, a FIR filter is adopted, the service provided by the millimeter wave radar chip library is called to obtain data (heartbeat waveform data containing noise) of a front living body, then the data is continuously sampled at a sampling rate of 50HZ to obtain a time sequence S, then the S is filtered, the filter is a finite-length single-bit impulse response (FIR) filter, and the mathematical expression of the FIR filter is that
Specific parameters of the filter include: the order of the design of the equal ripple is 200, the band-pass filter (the cut-off frequency is 0.6HZ, the passing frequency is 1HZ, the passing frequency is 5.4HZ, and the cut-off frequency is 5.8HZ) has maximum attenuation of 40dB in the stop band.
In one embodiment, the extracting of the time-frequency characteristics comprises continuously sampling the filtered time-series data at a sampling rate of 50HZ to obtain a time series S1, and performing a Continuous Wavelet Transform (CWT) on S1, wherein the transform is performed according to the following formula
Phi is a basic wavelet, a is a scale parameter a >0, b is a position parameter, a wavelet function cluster is obtained by continuously changing the values of the scale parameter a and the position parameter b, similarity operation is carried out on the wavelet function cluster and a time sequence S1 to obtain continuous wavelet transform coefficients (W phi f) (a, b), and the absolute value of the continuous wavelet transform coefficients (W phi f) (a, b) is obtained to obtain the time-frequency characteristic of a time sequence S1.
And extracting time-frequency characteristics, wherein the time-frequency analysis comprises short-time Fourier transform and wavelet transform. The short-time Fourier transform time-frequency analysis window has a fixed size, and the short window has higher time resolution but poor frequency resolution. The use of long windows provides higher frequency resolution but poor time resolution. In practice, a compromise must be made between the time window and the frequency window width, and any compromise becomes meaningless when the signal being analyzed is of a type where slow transitions and transients coexist. Wavelet transform is essentially the correlation of the original signal with a family of warped wavelet functions. By adjusting the scale, wavelets with different time-frequency widths can be obtained to match different positions of an original signal, so that the local analysis of the signal is achieved, the window of wavelet transformation is an adjustable time-frequency window, a short window is used at high frequency, a wide window is used at low frequency, the wavelet transformation is different from short-time Fourier transformation, and the contradiction of time and frequency resolution can be better solved by the wavelet transformation.
The filtered time series data are continuously sampled at a sampling rate of 50HZ to obtain a time series S1, S1 of length 1000, and a matlab implementation code is as follows:
fig. 2 is a diagram showing the connection relationship of the devices of the millimeter wave radar apparatus according to the embodiment of the present invention, and describes the positional relationship between the millimeter wave radar chip and the horn antenna on the circuit board. The method comprises the following steps: an arithmetic processor, a millimeter wave radar sensing chip (device), a power supply circuit, a motor driving circuit and a stepping motor (not shown); the millimeter wave radar sensing chip is provided with a receiving and transmitting antenna; the millimeter wave radar sensing chip is connected with the operation processor through an SPI bus; the power supply circuit is used for respectively supplying power to the operation processor and the millimeter wave radar sensing chip; the motor driving circuit is used for driving the stepping motor.
In a specific implementation mode, a millimeter wave radar integrated chip (also integrated with a transmitting and receiving antenna) is used on hardware, so that the design of the whole circuit is simplified, the millimeter wave radar chip adopts a pulse coherent radar sensor, all circuits used by the millimeter wave radar are integrated and comprise the transmitting and receiving antenna, a library running on an operation processor is provided besides the millimeter wave radar chip, the library is provided in a service mode, and a developer can obtain information such as the distance and the speed of an object in front of the radar by directly calling the service. The motor drive circuit is a drive circuit for two stepping motors. The arithmetic processor is a platform for running the radar chip library and is also a platform for running all the following algorithms.
Referring to the embodiment of fig. 3, a horn antenna is additionally provided, the echo energy received by the millimeter wave radar chip is affected by various factors such as the transmitting power, the reflectivity, the reflection area, and the like, the horn antenna is a method for optimizing these factors, and the horn antenna has two functions:
1. the signal is enhanced.
2. The directivity of the millimeter wave is enhanced, the millimeter wave radar has stronger directivity, and the directivity is further enhanced through the horn antenna. The horn antenna may also be replaced with a lens.
FIG. 4 is a schematic diagram showing the narrowing of the millimeter wave energy detection range after the horn antenna is added, and the more directional, for heart rate detection, the best position is in the chest around the heart, which is a smaller area, and if the millimeter wave radar can be pointed to the area accurately, the signal-to-noise ratio can be improved well
Fig. 5 is a schematic view illustrating the operation of a stepping motor according to an embodiment of the present invention. Two stepping motors are added for horizontal and vertical rotation, so that the optimal monitoring position of the heart can be changed continuously in a scene of monitoring the heart rate by the millimeter wave radar, and the circuit board provided with the millimeter wave radar chip is driven by the two stepping motors to rotate in two horizontal and vertical directions so as to enable the optimal position of the millimeter wave to be accurately directed to heart rate detection.
The working process comprises the steps that a plurality of heart rate measuring positions are generated through horizontal and vertical rotation of two stepping motors, sample entropies are calculated at each measuring position through a convolution network, the calculated sample entropies are sorted from small to large, and when the minimum sample entropies are smaller than a set threshold value, the optimal searching position is determined.
FIG. 6 is a schematic diagram of a convolutional neural network according to an embodiment of the present invention. The time-frequency characteristics are constructed to be used as sample entropies of input heart rate and heartbeat waveform data to be used as an output convolution neural network, the framework of the network is obtained by modifying GoogLeNet, and the GoogLeNet is shown in figure 6, and the specific modification is as follows:
1. the input 224 × 3 of the google lenet network, so it is necessary to convert the time-frequency features obtained by the continuous wavelet transform into RGB images 224 × 3.
2. Dropout Layer is to prevent overfitting, and when it propagates forward, let the activation value of a certain neuron stop working with a certain probability p, so that the model generalization can be stronger, and pool5-drop _7x7_ s1 in google lenet network has a default probability of 0.5, and is replaced by a Dropout Layer with a probability of 0.6.
3. The convolutional layers of the network extract image features, and the two layers of 'loss3-classifier' and 'output' in google net contain information about how to merge the network extracted features into class probabilities and prediction labels. To retrain google net to classify RGB images, the two layers are replaced with new layers that fit the data.
4. The google lenet network outputs 1000 classes, modified to 135 classes, and the calculation of heart rate is inherently a regression problem, here considered as a classification problem with the advantage that the data is easy to label, because human heart rate varies from moment to moment, the classification method is 45 to 50 times per minute for one class, 50 to 55 times per minute for the second class, and so on, and the last class is 175 to 180 times per minute for a total of 27 classes. The sample entropies of the heartbeat waveform data represented by the time-frequency features are classified into 5 categories, and the final network output is 135 categories.
And performing and training the convolutional neural network, wherein the convolutional neural network constructed by the invention takes the time-frequency characteristics of the filtered heartbeat time sequence waveform as input, and takes the sample entropy of the heartbeat and heartbeat time sequence waveform as output. The calculation of the heart rate is inherently a regression problem, and here it is seen as an advantage of the classification problem in that the data is easy to label, since the human heart rate varies from moment to moment, by 45 to 50 per minute for one class, 50 to 55 per minute for the second class, and so on, and 175 to 180 per minute for the last class, for a total of 27 classes. The sample entropy is a quantity for describing the chaos degree of time series data, the lower the value of the sample entropy is, the higher the sequence self-similarity is, the larger the value of the sample entropy is, the higher the probability of the generation of a new mode is, the greater the complexity of the sequence is, the sample entropy also reflects the signal-to-noise ratio of the data in the system for detecting the heart rate by the millimeter wave radar, and the lower the sample entropy is, the higher the signal-to-noise ratio is, and the lower the signal-to-noise ratio is. According to different degrees of the positions pointed by the millimeter waves and close to the heart, the obtained heartbeat waveforms are roughly divided into three types shown in fig. 7, wherein the waveform 1 is closest to the heart and is characterized in that the waveform of the heartbeat cycle is clear and has lower signal-to-noise ratio than the entropy of a sample. The waveform 2 is slightly far away from the heart and is characterized in that the waveform of the heartbeat cycle is obviously slightly larger in signal-to-noise ratio and slightly larger in sample entropy. The waveform 3 is far away from the heart and is characterized in that the signal-to-noise ratio of the waveform of the heartbeat cycle is low due to noise inundation and the sample entropy is large. The training data is (train _ x, train _ y), where train _ x is a time-frequency representation of the heartbeat cycle waveform, a heart rate value corresponding to the train _ y waveform, and a sample entropy of the heartbeat timing waveform. The training data collection procedure is as follows: the method comprises the steps of acquiring needed heartbeat cycle waveforms by utilizing hardware designed by the invention, synchronously recording heart rate values by an oximeter, converting the acquired heartbeat cycle waveforms into time-frequency representation train _ x by continuous wavelet transformation, wherein the recorded heart rate values are heart rate values in train _ y, the sample entropy of train _ y is obtained by calculation, the calculation step is to intercept two adjacent heartbeat cycle waveforms, respectively perform Fourier transformation to obtain amplitude-frequency characteristics, and then calculate the Pearson correlation coefficient of the amplitude-frequency characteristics. This coefficient is inversely related to the sample entropy. The calculated sample entropy is divided into five levels, i.e., 5 classes, by setting a threshold.
Transfer Learning (Transfer Learning) is a machine Learning method, which transfers knowledge in one field (i.e., a source field) to another field (i.e., a target field) to enable the target field to obtain a better Learning effect. The source domain data volume is sufficient, the target domain data volume is small, the scene is very suitable for transfer learning, and the GoogLeNet network convolution layer training weight is utilized.
One matlab code is as follows:
it should be recognized that the method steps in embodiments of the present invention may be embodied or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The method may use standard programming techniques. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein.
A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as consumers. In a preferred embodiment of the present invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on the consumer.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. A heart rate analysis method based on a millimeter wave radar is characterized by comprising the following procedures:
collecting heartbeat waveform data of a front living body including noise through a millimeter wave radar device;
performing first sampling on the heartbeat waveform data and filtering;
performing second sampling on the heartbeat waveform data subjected to filtering processing, and calculating time-frequency characteristics;
creating a convolutional neural network, taking the time-frequency characteristics as the input of the convolutional neural network, and outputting sample entropies of heart rate and heart beat waveform data;
and determining the optimal heart rate monitoring position of the millimeter wave radar device according to the sample entropy.
2. The millimeter wave radar-based heart rate analysis method according to claim 1, wherein the acquiring, by the millimeter wave radar device, the heart beat waveform data of the front living body including noise comprises:
and (3) constraining radar waves emitted by the millimeter wave radar device, and calling an interface to analyze the acquired data to obtain the distance, the position and the heartbeat waveform data of the front living body.
3. The millimeter wave radar-based heart rate analysis method according to claim 1, wherein the performing of the first sampling and the filtering on the heartbeat waveform data comprises:
sampling the heartbeat waveform data for the first time to obtain a time sequence S, and then filtering the S, wherein the filter is a finite-length single-bit impulse response filter, and the mathematical expression of the filter is
4. The millimeter wave radar-based heart rate analysis method of claim 3, wherein the filter is configured as an equal ripple design, with a 200 order bandpass filter having a cutoff frequency of 0.6Hz, a pass frequency of 1Hz, a pass frequency of 5.4Hz, a cut frequency of 5.8Hz, and a maximum attenuation of 40dB within the stop band.
5. The millimeter wave radar-based heart rate analysis method according to claim 1, wherein the performing second sampling on the filtered heartbeat waveform data and calculating time-frequency characteristics comprises:
continuously sampling the filtered time sequence data to obtain a time sequence S1, and performing continuous wavelet transform on the time sequence S1, wherein the transform formula is
Where φ is the fundamental wavelet and a is the scale parameter a>0 and b are position parameters, a wavelet function cluster is obtained by continuously changing the values of the scale parameter a and the position parameter b, and the wavelet function cluster and the time sequence S1 are subjected to similarity operation to obtain continuous wavelet transformation coefficients
(a, b) for continuous wavelet transform coefficients
And (a, b) calculating absolute values to obtain time-frequency characteristics of the time series S1.
6. The millimeter wave radar-based heart rate analysis method according to claim 1, wherein the creating a convolutional neural network, the time-frequency feature being an input of the convolutional neural network, and the outputting the sample entropies of the heart rate and the heart beat waveform data comprises:
acquiring a pre-trained GoogleLeNet convolutional neural network, and converting time-frequency features obtained by continuous wavelet transformation into RGB images of 224 × 3 as input;
setting the random discarding probability of pool5-drop _7x7_ s1 layer to 0.6;
replacing loss3-classifier by a new full connection layer, and resetting the learning rate of the full connection layer;
setting the output of the GoogLeNet convolutional neural network into 135 classes, wherein the 135 classes comprise sample entropies of 27 classes of heart rates and 5 classes of heartbeat waveform data;
wherein the google lenet convolutional neural network is a pre-trained deep neural network.
7. The millimeter wave radar-based heart rate analysis method of claim 1, wherein the determining an optimal heart rate monitoring location for the millimeter wave radar device from the sample entropy comprises:
a plurality of heart rate measuring positions are generated through horizontal and vertical rotation of two stepping motors, sample entropies are calculated at each measuring position through a convolution network, the calculated sample entropies are sorted from small to large, and when the minimum sample entropies are smaller than a set threshold value, the optimal searching position is determined.
8. The millimeter wave radar-based heart rate analysis method of claim 7, further comprising:
the heart rate is continuously monitored by staying at the optimal search position, and the search is restarted when the sample entropy of the position exceeds the set threshold.
9. An analytical equipment based on a millimeter wave radar is characterized by comprising an arithmetic processor, a millimeter wave radar sensing device, a power supply circuit, a motor driving circuit and a stepping motor;
the millimeter wave radar sensing device is provided with a receiving and transmitting antenna;
the millimeter wave radar sensing device is connected with the operation processor through an SPI bus;
the power supply circuit is used for respectively supplying power to the operation processor and the millimeter wave radar sensing device;
the motor driving circuit is used for driving the stepping motor;
the arithmetic processor executes the millimeter wave radar-based heart rate analysis method of any one of claims 1 to 8.
10. A millimeter-wave radar-based analysis apparatus according to claim 9, wherein the transceiver antenna is configured to confine the emitted millimeter-radar waves, and the transceiver antenna comprises a horn antenna or a lens.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111248081.3A CN114052692B (en) | 2021-10-26 | 2021-10-26 | Heart rate analysis method and equipment based on millimeter wave radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111248081.3A CN114052692B (en) | 2021-10-26 | 2021-10-26 | Heart rate analysis method and equipment based on millimeter wave radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114052692A true CN114052692A (en) | 2022-02-18 |
| CN114052692B CN114052692B (en) | 2024-01-16 |
Family
ID=80235569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111248081.3A Active CN114052692B (en) | 2021-10-26 | 2021-10-26 | Heart rate analysis method and equipment based on millimeter wave radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114052692B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2125899A (en) * | 1994-10-07 | 1999-05-13 | Masimo Corporation | Physiological monitor and method of minimizing noise |
| US20180240235A1 (en) * | 2017-02-23 | 2018-08-23 | Zebra Medical Vision Ltd. | Convolutional neural network for segmentation of medical anatomical images |
| CN110325929A (en) * | 2016-12-07 | 2019-10-11 | 阿瑞路资讯安全科技股份有限公司 | System and method for detecting the waveform analysis of cable network variation |
| CN110598549A (en) * | 2019-08-07 | 2019-12-20 | 王满 | Convolutional neural network information processing system based on cardiac function monitoring and training method |
| KR20200006447A (en) * | 2018-07-10 | 2020-01-20 | 재단법인 아산사회복지재단 | Method and program for stroke volume acquisition using arterial pressure waveform |
| CN111329455A (en) * | 2020-03-18 | 2020-06-26 | 南京润楠医疗电子研究院有限公司 | Non-contact cardiovascular health assessment method |
| CN111358435A (en) * | 2020-03-13 | 2020-07-03 | 珠海向量科技有限公司 | Data enhancement method for improving precision of deep neural network |
| US20200405148A1 (en) * | 2019-06-27 | 2020-12-31 | Bao Tran | Medical analysis system |
| WO2021026400A1 (en) * | 2019-08-06 | 2021-02-11 | Neuroenhancement Lab, LLC | System and method for communicating brain activity to an imaging device |
| CN112716468A (en) * | 2020-12-14 | 2021-04-30 | 首都医科大学 | Non-contact heart rate measuring method and device based on three-dimensional convolution network |
| CN112716462A (en) * | 2020-12-09 | 2021-04-30 | 北京航空航天大学 | Narrow-beam millimeter wave human body heartbeat/respiration sign monitoring device capable of controlling irradiation direction |
| WO2021171091A2 (en) * | 2020-02-27 | 2021-09-02 | Takuya Sakamoto | Vital information acquisition apparatus and method |
| CN113420624A (en) * | 2021-06-11 | 2021-09-21 | 华中师范大学 | Non-contact fatigue detection method and system |
-
2021
- 2021-10-26 CN CN202111248081.3A patent/CN114052692B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2125899A (en) * | 1994-10-07 | 1999-05-13 | Masimo Corporation | Physiological monitor and method of minimizing noise |
| CN110325929A (en) * | 2016-12-07 | 2019-10-11 | 阿瑞路资讯安全科技股份有限公司 | System and method for detecting the waveform analysis of cable network variation |
| US20180240235A1 (en) * | 2017-02-23 | 2018-08-23 | Zebra Medical Vision Ltd. | Convolutional neural network for segmentation of medical anatomical images |
| KR20200006447A (en) * | 2018-07-10 | 2020-01-20 | 재단법인 아산사회복지재단 | Method and program for stroke volume acquisition using arterial pressure waveform |
| US20200405148A1 (en) * | 2019-06-27 | 2020-12-31 | Bao Tran | Medical analysis system |
| WO2021026400A1 (en) * | 2019-08-06 | 2021-02-11 | Neuroenhancement Lab, LLC | System and method for communicating brain activity to an imaging device |
| CN110598549A (en) * | 2019-08-07 | 2019-12-20 | 王满 | Convolutional neural network information processing system based on cardiac function monitoring and training method |
| WO2021171091A2 (en) * | 2020-02-27 | 2021-09-02 | Takuya Sakamoto | Vital information acquisition apparatus and method |
| CN111358435A (en) * | 2020-03-13 | 2020-07-03 | 珠海向量科技有限公司 | Data enhancement method for improving precision of deep neural network |
| CN111329455A (en) * | 2020-03-18 | 2020-06-26 | 南京润楠医疗电子研究院有限公司 | Non-contact cardiovascular health assessment method |
| CN112716462A (en) * | 2020-12-09 | 2021-04-30 | 北京航空航天大学 | Narrow-beam millimeter wave human body heartbeat/respiration sign monitoring device capable of controlling irradiation direction |
| CN112716468A (en) * | 2020-12-14 | 2021-04-30 | 首都医科大学 | Non-contact heart rate measuring method and device based on three-dimensional convolution network |
| CN113420624A (en) * | 2021-06-11 | 2021-09-21 | 华中师范大学 | Non-contact fatigue detection method and system |
Non-Patent Citations (5)
| Title |
|---|
| WANG, LD AND ZHOU, XG: "Detection of Congestive Heart Failure Based on LSTM-Based Deep Network via Short-Term RR Intervals", SENSORS, vol. 19, no. 7 * |
| 胡玉舟: "基于CNN与心跳信号的胚蛋成活性检测方法研究", 《中国优秀硕士学位论文全文数据库》, no. 7 * |
| 赵莉娜: "基于模糊思想的熵方法及在心血管信号分析中的应用", 《中国优秀硕士学位论文全文数据库》, no. 9 * |
| 金宝财, 张强, 耿金繁等: "中西医结合治疗黄牛大叶性肺炎", 畜牧兽医科技信息, no. 9, pages 46 * |
| 黄如强, 苏卫华, 张世月: "救援机器人的非接触式人体体征视觉测量方法研究", 医疗卫生装备, vol. 41, no. 6, pages 26 - 31 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114052692B (en) | 2024-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021066918A1 (en) | Systems and methods of determining heart-rate and respiratory rate from a radar signal using machine learning methods | |
| Liu et al. | Deep learning and recognition of radar jamming based on CNN | |
| CN112998701A (en) | Vital sign detection and identity recognition system and method based on millimeter wave radar | |
| CN110755076A (en) | Image acquisition method, apparatus, device and medium for magnetic resonance scanner | |
| CN112130118B (en) | Ultra-wideband radar signal processing system and method based on SNN | |
| CN110007366A (en) | A kind of life searching method and system based on Multi-sensor Fusion | |
| Zhu et al. | TagCare: Using RFIDs to monitor the status of the elderly living alone | |
| Li et al. | Real-time fall detection using mmWave radar | |
| CN113447905A (en) | Double-millimeter-wave radar human body falling detection device and detection method | |
| CN114305355B (en) | Breathing heartbeat detection method, system and device based on millimeter wave radar | |
| CN115343704A (en) | Gesture recognition method of FMCW millimeter wave radar based on multi-task learning | |
| CN113762130A (en) | Millimeter wave radar gesture detection and recognition method | |
| CN114052693B (en) | Heart rate analysis method, device and equipment | |
| Qian et al. | Parallel lstm-cnn network with radar multispectrogram for human activity recognition | |
| CN116879910B (en) | Laser scanning distance measuring device and method thereof | |
| CN106419884B (en) | A kind of rate calculation method and system based on wavelet analysis | |
| Yang et al. | Extraction and denoising of human signature on radio frequency spectrums | |
| CN115469303A (en) | Cognitive biological radar method and device for detecting human body posture and vital signs | |
| CN114052692A (en) | Heart rate analysis method and equipment based on millimeter wave radar | |
| CN108398183A (en) | The multi-thread spectrum Duffing oscillators detection of unknown parameters and frequency discrimination methods under a kind of strong noise background | |
| Park et al. | Increasing accuracy of hand gesture recognition using convolutional neural network | |
| CN113572546B (en) | Method for identifying human body activities by utilizing DenseNet network based on CSI signals | |
| CN113827216A (en) | Method and system for sensorless heart rate monitoring based on micro-motion algorithm | |
| CN114052694B (en) | Radar-based heart rate analysis method and device | |
| CN114847931A (en) | Human motion tracking method, device and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |