CN113842127A - Pulse rate detection device, system and storage medium - Google Patents
Pulse rate detection device, system and storage medium Download PDFInfo
- Publication number
- CN113842127A CN113842127A CN202111126494.4A CN202111126494A CN113842127A CN 113842127 A CN113842127 A CN 113842127A CN 202111126494 A CN202111126494 A CN 202111126494A CN 113842127 A CN113842127 A CN 113842127A
- Authority
- CN
- China
- Prior art keywords
- pulse rate
- target
- determining
- peak interval
- sequence
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 239000006185 dispersion Substances 0.000 claims description 160
- 238000005070 sampling Methods 0.000 claims description 30
- 230000011218 segmentation Effects 0.000 claims description 16
- 238000003062 neural network model Methods 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000001174 ascending effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical group [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000126 substance Substances 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
- A61B5/02—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
- A61B5/72—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
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Cardiology (AREA)
- Physiology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a pulse rate detection device, a pulse rate detection system and a storage medium. The method comprises the steps of preprocessing acquired physiological signals to obtain target signals; segmenting the target signal according to the initial segment length to obtain a segment sub-signal; determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence; determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate; and determining the final pulse rate according to the candidate pulse rate sequence. The invention obtains the subsection sub-signal by segmenting the target signal; determining a candidate pulse rate according to the segmented sub-signals, and updating a candidate pulse rate sequence according to the candidate pulse rate; the final pulse rate is determined according to the candidate pulse rate sequence, and compared with the existing mode of obtaining the pulse rate through a trained neural network model, the method provided by the invention does not need to train the model, can directly detect the pulse rate, improves the pulse rate detection efficiency and saves the detection cost.
Description
Technical Field
The present invention relates to the field of pulse rate detection technologies, and in particular, to a pulse rate detection device, a pulse rate detection system, and a storage medium.
Background
Pulse rate refers to the frequency of the beating of the arteries. There are many diseases in the clinic, especially heart disease, which can cause pulse rate changes. Therefore, measuring the pulse rate is an indispensable examination item for the patient. In the existing scheme, a heart rate value is obtained by using a heart rate detection model, and the heart rate value is output, wherein the heart rate detection model is obtained by training a PPG signal and an ECG signal corresponding to the PPG signal. In the prior art, when the pulse rate is calculated by adopting a neural network method, the pulse rate has strong dependence on training data, and the generalization of a neural network model is difficult to ensure. And the training time cost of the model is high.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a pulse rate detection device, a pulse rate detection system and a storage medium, and aims to solve the technical problems of low pulse rate detection efficiency and high cost in the prior art.
In order to achieve the above object, the present invention provides a pulse rate detection device, including: a memory, a processor, and a pulse rate detection program stored on the memory and executable on the processor, the pulse rate detection program configured to implement the steps of:
acquiring a physiological signal, and preprocessing the physiological signal to obtain a target signal;
segmenting the target signal according to the initial segment length to obtain a segment sub-signal;
determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence;
determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate;
and determining the final pulse rate according to the candidate pulse rate sequence.
Optionally, the pulse rate detection program is configured to implement the following steps:
determining a peak interval time sequence from the segmented sub-signals;
determining a peak interval time dispersion according to the peak interval time sequence;
judging whether the time dispersion of the peak interval is smaller than a preset dispersion threshold value or not;
and when the dispersion of the peak interval time is smaller than a preset dispersion threshold value, determining a peak interval mean value according to the peak interval time sequence.
Optionally, the pulse rate detection program is configured to implement the following steps:
determining a segmentation sub-signal peak value according to the segmentation sub-signal;
determining a peak position sequence according to the segmented sub-signal peak value;
differentiating the peak position sequence to obtain a peak position interval sequence;
and determining a peak interval time sequence according to the peak position interval sequence and the sampling rate.
Optionally, the pulse rate detection program is configured to implement the following steps:
determining a target step length according to the time dispersion of the peak interval and the sampling rate;
determining a target segment length according to the target step length and the historical segment length;
judging whether the target segment length is larger than a preset maximum segment length or not;
when the target segment length is smaller than or equal to a preset maximum segment length, the target segment length is taken as the initial segment length, and the step of segmenting the target signal according to the initial segment length to obtain segment sub-signals is executed.
Optionally, the pulse rate detection program is configured to implement the following steps:
judging whether the dispersion of the peak interval time is greater than a preset dispersion threshold value or not;
when the time dispersion of the peak interval is greater than a preset dispersion threshold, determining a target step length according to the following formula:
μ=fs*VarThreshold
wherein μ is a target step length, fs is a sampling rate, and VarThreshold is a preset dispersion threshold.
Optionally, the pulse rate detection program is configured to implement the following steps:
judging whether the candidate pulse rate number in the candidate pulse rate sequence is larger than a preset pulse rate number threshold value or not;
when the candidate pulse rate number in the candidate pulse rate sequence is smaller than or equal to a preset pulse rate number threshold value, acquiring target dispersion;
determining a target dispersion threshold value according to the target dispersion and the preset dispersion threshold value;
and taking the target dispersion threshold value as the preset dispersion threshold value, and executing the step of judging whether the peak interval time dispersion is smaller than the preset dispersion threshold value.
Optionally, the pulse rate detection program is configured to implement the following steps:
calculating a target dispersion threshold value according to the target dispersion and the preset dispersion threshold value through the following formula:
NewVarThreshold=VarThreshold+MaxVar*0.5
wherein, NewVarThreshold is the target dispersion threshold, VarThreshold is the preset dispersion threshold, and MaxVar is the target dispersion.
Optionally, the pulse rate detection program is configured to implement the following steps:
the candidate pulse rate sequence determines a reference pulse rate;
selecting a target pulse rate from the candidate pulse rate sequence according to a preset selection strategy and the reference pulse rate;
and determining a final pulse rate according to the reference pulse rate and the target pulse rate.
In addition, to achieve the above object, the present invention also provides a pulse rate detection system, including: the pulse rate measuring device comprises an acquisition module, a segmentation module, a peak interval mean value determination module, an updating module and a final pulse rate determination module;
the acquisition module is used for acquiring physiological signals and preprocessing the physiological signals to obtain target signals;
the segmentation module is used for segmenting the target signal according to an initial segmentation length to obtain a segmentation sub-signal;
the peak interval mean value determining module is used for determining a peak interval time sequence according to the segmented sub-signals and determining a peak interval mean value according to the peak interval time sequence;
the updating module is used for determining a candidate pulse rate according to the peak interval mean value and updating a candidate pulse rate sequence according to the candidate pulse rate;
and the final pulse rate determining module is used for determining a final pulse rate according to the candidate pulse rate sequence.
In addition, to achieve the above object, the present invention further provides a storage medium, in which a pulse rate detection program is stored, and the pulse rate detection program, when executed by a processor, implements the following steps:
acquiring a physiological signal, and preprocessing the physiological signal to obtain a target signal;
segmenting the target signal according to the initial segment length to obtain a segment sub-signal;
determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence;
determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate;
and determining the final pulse rate according to the candidate pulse rate sequence.
The method comprises the steps of collecting physiological signals, preprocessing the physiological signals and obtaining target signals; segmenting the target signal according to the initial segment length to obtain a segment sub-signal; determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence; determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate; and determining the final pulse rate according to the candidate pulse rate sequence. The invention obtains the subsection sub-signal by segmenting the target signal; determining a peak interval mean value according to the segmented sub-signals; determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate; the final pulse rate is determined according to the candidate pulse rate sequence, and compared with the existing mode of obtaining the pulse rate through a trained neural network model, the method provided by the invention does not need to train the model, can directly detect the pulse rate, improves the pulse rate detection efficiency and saves the detection cost.
Drawings
Fig. 1 is a schematic structural diagram of a pulse rate detection device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a pulse rate detection device according to a first embodiment of the present invention;
FIG. 3 is a schematic flow chart of a pulse rate detection device according to a second embodiment of the present invention;
fig. 4 is a block diagram of a pulse rate detection system according to a first embodiment of the invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a pulse rate detection device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the pulse rate detection apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the pulse rate detection device and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a pulse rate detection program.
In the pulse rate detection device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the pulse rate detection device calls a pulse rate detection program stored in the memory 1005 by the processor 1001.
Referring to fig. 2, fig. 2 is a schematic flow chart of a pulse rate detection device according to a first embodiment of the invention.
The embodiment of the invention provides a pulse rate detection device, which comprises: a memory, a processor, and a pulse rate detection program stored on the memory and executable on the processor, the pulse rate detection program configured to implement the steps of: in this embodiment, the pulse rate detection apparatus includes the following steps:
step S10: and acquiring a physiological signal, and preprocessing the physiological signal to obtain a target signal.
It should be noted that the physiological signal may be a blood oxygen signal or a respiration signal. The target signal may be a signal pre-processed from the blood oxygen signal or the respiration signal. The pre-processing may be a high frequency noise removal processing of the physiological signal using a low pass filter. The pulse rate range is generally 30/min to 300/min, and the corresponding frequency is 0.5Hz to 5Hz, in order to retain the detail information of the signal, the embodiment retains the information of 3 harmonics of the fundamental frequency, that is, low-pass filtering is performed according to the 3 harmonics of the fundamental frequency, and the cut-off frequency of the physiological signal is set to 15Hz for low-pass filtering, and similarly, other physiological signals need to be set to cut off the frequency according to the corresponding pulse rate range, which is not limited herein.
Step S20: and segmenting the target signal according to the initial segment length to obtain a segment sub-signal.
Note that the initial segment length may be a division length for dividing the target signal. The segment sub-signal may be a plurality of sub-signals having a length equal to the initial segment length obtained by segmenting the target information according to the initial segment length.
It should be understood that, in the present embodiment, the final pulse rate is determined by the candidate pulse rate sequence, and therefore, different segment lengths need to be adopted to segment the target signal, so as to obtain a plurality of candidate pulse rates, so as to construct the candidate pulse rate sequence according to the plurality of candidate pulse rates. When the target signal is divided for the first time, the minimum segment length is taken as the initial segment length, that is, the target information is divided by using the minimum segment length, when the target signal is divided in the subsequent time, the target signal is divided by using the initial segment length calculated each time, but it is required to ensure that the initial segment length for dividing is not more than the maximum segment length, and the maximum segment length and the minimum segment length are calculated by the following formulas:
SegmentMin=fs*60/MaxHr/3
SegmentMax=fs*60/MinHr/3
wherein fs represents the sampling rate of the physiological signal, SegmentMin represents the minimum segment length, and MaxHr represents the maximum pulse rate of the physiological signal. In this embodiment, 300 times/minute, SegmentMax represents the maximum segment length, and MinHr represents the minimum pulse rate of the physiological signal, which in this embodiment is 30 times/minute. The values of MinHr and MaxHr can be adaptively adjusted according to different physiological signals, and the embodiment is not limited herein.
Step S30: and determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence.
It should be noted that the peak interval time sequence may be obtained by differentiating the peak position sequence, and the peak interval time sequence is determined according to the peak position interval sequence and the sampling rate. For example, the sampling point of the target signal is 4096 points, the detected peak point is located at 1500 th, 2100 th and 2500 th, the peak position sequence is [1500, 2100, 2500], the peak position sequence is differentiated to obtain the peak position interval sequence [600, 400], and then the peak interval time sequence is determined according to the peak position interval sequence and the sampling rate by the following formula:
RrInterval=DfIndexArray/fs
wherein, the RrInterval is a peak interval time sequence, the DfIndexArray is a peak position interval sequence, and the fs is a sampling rate.
It should be understood that determining a peak interval mean from the sequence of peak interval times may be calculating an average of the individual peak interval times in the sequence of peak interval times, with the average being the peak interval mean.
Further, in order to reduce the pulse rate detection cost and improve the pulse rate detection efficiency, the step S30 may include: determining a peak interval time sequence from the segmented sub-signals; determining a peak interval time dispersion according to the peak interval time sequence; judging whether the time dispersion of the peak interval is smaller than a preset dispersion threshold value or not; and when the dispersion of the peak interval time is smaller than a preset dispersion threshold value, determining a peak interval mean value according to the peak interval time sequence.
It should be noted that the preset dispersion threshold may be a dispersion threshold determined in advance according to an empirical value. The determining of the peak interval time dispersion from the peak interval time series may be calculating the peak interval time dispersion from the peak interval time series by the following formula:
where Var is the time dispersion of the peak intervals, and n is the peak interval in the time sequence of the peak intervals
Quantity of time, RrIntervaliFor the ith peak interval time, RrInterval is the peak interval mean.
In a specific implementation, for example, if the peak interval time sequence is [10,15,12,14], the number n of peak interval times is 4, the 1 st peak interval time is 10, the 2 nd peak interval time is 15, and so on, the peak interval mean value is (10+15+12+14)/4 is 12.75.
It should be understood that, only when the peak interval time dispersion is smaller than a preset dispersion threshold, a peak interval mean value is determined according to the peak interval time sequence, and then a candidate pulse rate is determined according to the peak interval mean value, when the peak interval time dispersion is greater than or equal to the preset dispersion threshold, it is indicated that an error may occur in the currently obtained peak interval time sequence, the candidate pulse rate is not determined according to the peak interval mean value at this time, and the step of determining the target step size according to the peak interval time dispersion and the sampling rate is returned, and the initial segment length is determined again for calculation.
Further, in order to reduce the detection cost of the pulse rate and improve the efficiency of the pulse rate detection, the step of determining the peak interval time sequence according to the segmented sub-signals may include: determining a segmentation sub-signal peak value according to the segmentation sub-signal; determining a peak position sequence according to the segmented sub-signal peak value; differentiating the peak position sequence to obtain a peak position interval sequence; and determining a peak interval time sequence according to the peak position interval sequence and the sampling rate.
It should be understood that a point with the maximum amplitude may be found in each segmented sub-signal, and whether the sub-signal is in an ascending trend or a descending trend is determined according to the maximum amplitude of the current sub-signal and the maximum amplitude of the next sub-signal, and if the maximum amplitude of the current sub-signal is smaller than the maximum amplitude of the next sub-signal, it is indicated that the current sub-signal is in the ascending trend, otherwise, it is in the descending trend. And detecting the trend of the sub-signals, if the sub-signals in the current section are in an ascending trend, and the signals in the later section are in a descending trend, the maximum amplitude of the current sub-signals is the peak value of the section of signals, wherein if sampling points with the same amplitude appear, the front sampling point is taken as the maximum value, therefore, according to the step of determining the peak value, the detection of the peak value at least needs three sub-signals to determine one peak value, and the determination of the peak value point position is carried out on all the sub-signals which are divided according to the target signal through the steps, namely the peak value position is determined according to the ascending or descending trend and the amplitude of the sub-signals. For example, whether the sub-signal is in an upward trend or a downward trend may be determined according to the maximum amplitude of each segmented sub-signal, and the peak value of a segment of the signal may be determined according to the trend of the sub-signal. For example, the segment length is 10, the length of the current sub-signal a is 10 th to 20 th points, the length of the next adjacent sub-signal B is 20 th to 30 th points, the length of the next sub-signal C adjacent to B is 30 th to 40 th points, and the maximum amplitudes of points a, B, and C are 8,11, and 9, respectively. And sequentially acquiring the positions of all peak points in the target signal according to the rule, namely the peak values of the segmented sub-signals. And forming a sequence of the segmented sub-signal peaks according to the sequence in the target signal, namely a peak position sequence. The sequence of peak positions may be differentiated, for example, the sequence of peak positions is [150,200,300,450], and the sequence of peak position intervals obtained by differentiating the sequence of peak positions may be [50,100,150], and the determining the sequence of peak interval times according to the sequence of peak position intervals and the sampling rate may be dividing each item in the sequence of peak position intervals by the sampling rate, respectively. The peak interval time sequence may be determined by the following equation:
RrInterval=DfIndexArray/fs
wherein, RrInterval is a peak interval time sequence, DfIndexArray is a peak position interval sequence, and fs is a sampling rate.
Step S40: and determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate.
It should be noted that the candidate pulse rate sequence may be a sequence formed by segmenting the target information according to different initial segment lengths and then calculating candidate pulse rates. Determining the candidate pulse rate from the peak interval mean may be calculated by the following formula:
wherein the content of the first and second substances,is the peak interval mean value, and f is the candidate pulse rate.
In a specific implementation, after the candidate pulse rate is calculated, in order to facilitate subsequent calculation, the candidate pulse rate needs to be rounded, and in different scenarios, the calculation accuracy may also be maintained without being rounded, and this embodiment is not limited herein.
Further, in order to make the final pulse rate more accurate, after the step S40, the method further includes: judging whether the candidate pulse rate number in the candidate pulse rate sequence is larger than a preset pulse rate number threshold value or not; when the candidate pulse rate number in the candidate pulse rate sequence is smaller than or equal to a preset pulse rate number threshold value, acquiring target dispersion; determining a target dispersion threshold value according to the target dispersion and the preset dispersion threshold value; and taking the target dispersion threshold value as the preset dispersion threshold value, and executing the step of judging whether the peak interval time dispersion is smaller than the preset dispersion threshold value.
It should be noted that the preset pulse rate number threshold may be a preset candidate pulse rate number in a candidate pulse rate sequence. Before determining the candidate pulse rate according to the peak interval mean value, it is necessary to determine whether the peak interval time dispersion is smaller than a preset dispersion threshold, at this time, if the preset dispersion threshold is set too large, the step of determining the candidate pulse rate according to the peak interval mean value may not be performed because the calculated peak interval time dispersion is greater than the preset dispersion threshold, and at this time, the number of pulse rates in the candidate pulse rate sequence may be small or inaccurate. Therefore, when the candidate pulse rate number in the candidate pulse rate sequence is less than or equal to the preset pulse rate number threshold, it may be caused by inaccuracy of setting the preset dispersion threshold, and at this time, the preset dispersion threshold needs to be adaptively adjusted. The target dispersion may be the dispersion with the maximum dispersion value determined according to the dispersion calculated in each cycle in performing the dispersion calculation, for example, when the pulse rate is calculated, when the dispersion is calculated according to the minimum segment length for the first time, the dispersion value is 1.2, after the candidate pulse rate is calculated, the initial segment length is updated and then the target signal is segmented, the dispersion value calculated at this time is 1.4, the dispersion calculated in each cycle is counted in sequence, the dispersion with the maximum dispersion value is taken as the target dispersion, or the target dispersion value is set to 0 in advance, and compared with the dispersion value calculated each time, and when the dispersion value calculated at present is greater than the target dispersion value, the dispersion value at present is taken as the target dispersion value. Determining the target dispersion threshold value according to the target dispersion and the preset dispersion threshold value may be calculating the target dispersion threshold value by the following formula:
NewVarThreshold=VarThreshold+MaxVar*0.5
wherein, NewVarThreshold is the target dispersion threshold, VarThreshold is the preset dispersion threshold, and MaxVar is the target dispersion.
In specific implementation, when the candidate pulse rate number in the candidate pulse rate sequence is less than or equal to a preset pulse rate number threshold, obtaining target dispersion; determining a target dispersion threshold value according to the target dispersion and the preset dispersion threshold value; and taking the target dispersion threshold value as the preset dispersion threshold value, returning to the step of dividing a target signal according to the minimum segment length and calculating the peak interval time dispersion, wherein the step of judging whether the peak interval time dispersion is smaller than the preset dispersion threshold value is to judge whether the peak interval time dispersion is smaller than the target dispersion threshold value, when the peak interval time dispersion is smaller than the target dispersion threshold value, determining a peak interval mean value according to the peak interval time sequence, determining a candidate pulse rate according to the peak interval mean value, updating the candidate pulse rate sequence according to the candidate pulse rate, and returning to the step of determining a target step length according to the peak interval time dispersion and the sampling rate.
Step S50: and determining the final pulse rate according to the candidate pulse rate sequence.
It should be noted that, the determining the final pulse rate according to the candidate pulse rate sequence may be to take a part of the pulse rate adjacent to the reference pulse rate and the reference pulse rate to jointly calculate the final pulse rate according to the pulse rate with the largest occurrence frequency in the candidate pulse rate sequence as the reference pulse rate. The goal is to discard partially inaccurate pulse rate candidates.
Further, in order to make the calculated final pulse rate more accurate, the step S50 may include: determining a reference pulse rate according to the candidate pulse rate sequence; selecting a target pulse rate from the candidate pulse rate sequence according to a preset selection strategy and the reference pulse rate; and determining a final pulse rate according to the reference pulse rate and the target pulse rate.
The reference pulse rate may be a pulse rate with the largest frequency of occurrence in the candidate pulse rate sequence, and if pulse rates with the same frequency of occurrence are present, a smaller pulse rate is selected as the reference pulse rate, for example, if the pulse rates with the largest frequency of occurrence are 60,70,80,80, and 70, the pulse rates with the largest frequency of occurrence are 70 and 80, and the smaller pulse rate is 70 as the reference pulse rate. The selecting the target pulse rate from the candidate pulse rate sequence according to the reference pulse rate according to a preset selection strategy may be selecting a pulse rate having a difference from the reference pulse rate within a preset range. For example, pulse rates that differ by 1% or 2% from the baseline pulse rate, or by a difference in the range of 0-4, are selected. Determining the final pulse rate from the reference pulse rate and the target pulse rate may be calculating the final pulse rate from the reference pulse rate and the target pulse rate by:
HR=HR0*N0/N+HR1*N1/N+...HRn*Nn/N
wherein HR is the final pulse rate value, HR0Is a reference pulse rate value, N0Is the number of the reference pulse rate, N is the total number of the reference pulse rate and the target pulse rate, HR1Is the first target pulse rate, HRnN is the nth target pulse rate, N is the number of pulse rates with different pulse rate values in the target pulse rate, N1The number of pulse rates corresponding to the first target pulse rate, NnThe number of pulse rates corresponding to the nth target pulse rate.
In a specific implementation, for example, the pulse rates in the candidate pulse rates are 59, 60, 65, 60, 61, 60, 61. The pulse rate with the largest occurrence frequency is 60, the reference pulse rate is 60, the selection strategy is to select a pulse rate which is different from the reference pulse rate by 2%, namely the selected range is 58.8-61.2, and the selected target pulse rates are 59 and 61. From the above values, it can be seen that: the reference pulse rate value is 60, the number of the reference pulse rates is 3, the total number of the reference pulse rate and the target pulse rate is 3 of the reference pulse rate and 3 of the target pulse rate, the total number of the reference pulse rate and the target pulse rate is 6, the target pulse rate values are 59 and 61, the target pulse rate 59 is used as a first target pulse rate, the target pulse rate 61 is used as a second target pulse rate, the number of the pulse rates corresponding to the first target pulse rate 59 is 1, the number of the pulse rates corresponding to the second target pulse rate 61 is 2, and the data are taken into the final pulse rate to calculate the final pulse rate HR as:
HR=60*3/6+59*1/6+61*2/6
the embodiment collects physiological signals, and preprocesses the physiological signals to obtain target signals; segmenting the target signal according to the initial segment length to obtain a segment sub-signal; determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence; determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate; and determining the final pulse rate according to the candidate pulse rate sequence. The present embodiment obtains a segmented sub-signal by segmenting a target signal; determining a peak interval mean value according to the segmented sub-signals; determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate; and determining the final pulse rate according to the candidate pulse rate sequence, wherein compared with the existing mode of obtaining the pulse rate through the trained neural network model, the mode of the embodiment does not need to train the model, can directly detect the pulse rate, improves the pulse rate detection efficiency and saves the detection cost.
Referring to fig. 3, fig. 3 is a schematic flow chart of a pulse rate detection apparatus according to a second embodiment of the invention.
Based on the first embodiment, in this embodiment, after step S40, the method further includes:
step S401: and determining a target step length according to the time dispersion of the peak interval and the sampling rate.
It should be noted that the target step size may be a step size for updating the initial segment length, for example, if the initial segment length is a, the target step size is B, and then the updated initial segment length is a + B. The determining the target step size according to the peak interval time dispersion and the sampling rate may be calculating the target step size by the following algorithm:
wherein mu is a target step length, Var is a time dispersion of a peak interval, VarThreshold is a preset dispersion threshold, and fs is a sampling rate.
In specific implementation, when calculating the target step length, the peak interval time dispersion is compared with a preset dispersion threshold and 0.01, a corresponding formula for calculating the target step length is selected according to a comparison result, and the target step length is calculated according to the corresponding formula for calculating the target step length, wherein the 0.01 and the preset dispersion threshold are both thresholds set according to experience, and can be adjusted according to an actual scene, which is not limited in this embodiment.
Further, in order to make the detected pulse rate more accurate, the step S401 may include: judging whether the dispersion of the peak interval time is greater than a preset dispersion threshold value or not;
when the time dispersion of the peak interval is greater than a preset dispersion threshold, determining a target step length according to the following formula:
μ=fs*VarThreshold
wherein μ is a target step length, fs is a sampling rate, and VarThreshold is a preset dispersion threshold.
It should be understood that, when the peak interval time dispersion is greater than the preset dispersion threshold, it indicates that when the target signal is segmented by the current initial segment length, there may be a certain error in the obtained peak interval time, and at this time, the initial segment length needs to be re-determined to perform the candidate pulse rate calculation.
Step S402: and determining the target segment length according to the target step length and the historical segment length.
It should be noted that the historical segment length may be an initial segment length used in the last time the candidate pulse rate is calculated. Determining a target segment length from the target step size and historical segment lengths may be determining a target segment length by:
NewSegment=Segment+μ
wherein NewSegment is the target Segment length, Segment is the history Segment length, and μ is the target step size.
In a specific implementation, since the target step size corresponds to the length of the sampling point of the sub-signal, when determining the target segment length according to the target step size and the historical segment length, it is necessary to perform rounding processing on the target step size first, specifically, rounding may be performed by rounding, or decimal place may be directly discarded. The target segment length is the initial segment length used for segmenting the target signal when the candidate pulse rate is calculated at this time.
Step S403: and judging whether the target segment length is larger than a preset maximum segment length or not.
It should be noted that the preset maximum segment length may be a segment length calculated by the following formula:
SegmentMax=fs*60/MinHr/3
wherein fs represents the sampling rate of the physiological signal, SegmentMax represents the preset maximum segment length, and MinHr represents the minimum pulse rate of the physiological signal, which can be 30 times/minute in this embodiment. The value of MinHr can be adaptively adjusted according to different physiological signals, and the embodiment is not limited herein.
In a specific implementation, it is determined whether the target segment length is greater than a preset maximum segment length, and when the target segment length is greater than the preset maximum segment length, it is not suitable for the target signal to be segmented by the target segment length, and at this time, the step of determining the final pulse rate according to the candidate pulse rate sequence may be returned to.
Step S404: when the target segment length is smaller than or equal to a preset maximum segment length, the target segment length is taken as the initial segment length, and the step of segmenting the target signal according to the initial segment length to obtain segment sub-signals is executed.
It should be understood that, when the target segment length is less than or equal to the preset maximum segment length, the target signal may be segmented according to the target segment length to obtain a candidate pulse rate, so as to obtain a more comprehensive candidate pulse rate sequence, and further make the final pulse rate calculated according to the candidate pulse rate sequence more accurate. Therefore, when the target segment length is smaller than or equal to the preset maximum segment length, the target segment length is taken as the initial segment length, and the step of segmenting the target signal according to the initial segment length to obtain the segment sub-signals is returned, so that the candidate pulse rate is obtained and the candidate pulse rate sequence is updated.
The embodiment determines a target step length according to the time dispersion of the peak interval and the sampling rate; determining a target segment length according to the target step length and the historical segment length; judging whether the target segment length is larger than a preset maximum segment length or not; when the target segment length is smaller than or equal to a preset maximum segment length, the target segment length is taken as the initial segment length, and the step of segmenting the target signal according to the initial segment length to obtain segment sub-signals is executed. The embodiment determines the target step length through the time dispersion of the peak interval and the sampling rate; and determining the target segment length according to the target step length and the historical segment length, further segmenting the target signal by adopting the target segment length, determining the candidate pulse rate again, and updating the candidate pulse rate sequence, so that the pulse rate in the obtained candidate pulse rate sequence is more comprehensive and accurate. Thereby making the calculated final pulse rate more accurate.
Referring to fig. 4, fig. 4 is a block diagram of a pulse rate detection system according to a first embodiment of the present invention.
As shown in fig. 4, the pulse rate detection system according to the embodiment of the present invention includes: the pulse rate measuring method comprises an acquisition module 10, a segmentation module 20, a peak interval mean value determination module 30, an updating module 40 and a final pulse rate determination module 50;
the acquisition module 10 is configured to acquire a physiological signal and preprocess the physiological signal to obtain a target signal;
the segmentation module 20 is configured to segment the target signal according to an initial segment length to obtain a segment sub-signal;
the peak interval mean value determining module 30 is configured to determine a peak interval time sequence according to the segmented sub-signals, and determine a peak interval mean value according to the peak interval time sequence;
the updating module 40 is configured to determine a candidate pulse rate according to the peak interval mean, and update a candidate pulse rate sequence according to the candidate pulse rate;
the final pulse rate determining module 50 is configured to determine a final pulse rate according to the candidate pulse rate sequence.
The embodiment collects physiological signals, and preprocesses the physiological signals to obtain target signals; segmenting the target signal according to the initial segment length to obtain a segment sub-signal; determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence; determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate; and determining the final pulse rate according to the candidate pulse rate sequence. The present embodiment obtains a segmented sub-signal by segmenting a target signal; determining a peak interval mean value according to the segmented sub-signals; determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate; and determining the final pulse rate according to the candidate pulse rate sequence, wherein compared with the existing mode of obtaining the pulse rate through the trained neural network model, the mode of the embodiment does not need to train the model, can directly detect the pulse rate, improves the pulse rate detection efficiency and saves the detection cost.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may refer to the parameter operation method provided in any embodiment of the present invention, and are not described herein again.
Based on the first embodiment of the pulse rate detection system of the present invention, a second embodiment of the pulse rate detection system of the present invention is provided.
In this embodiment, the peak interval mean value determining module 30 is further configured to determine a peak interval time sequence according to the segmented sub-signal; determining a peak interval time dispersion according to the peak interval time sequence; judging whether the time dispersion of the peak interval is smaller than a preset dispersion threshold value or not; and when the dispersion of the peak interval time is smaller than a preset dispersion threshold value, determining a peak interval mean value according to the peak interval time sequence.
Further, the peak interval mean value determining module 30 is further configured to determine a peak value of the segment sub-signal according to the segment sub-signal; determining a peak position sequence according to the segmented sub-signal peak value; differentiating the peak position sequence to obtain a peak position interval sequence; and determining a peak interval time sequence according to the peak position interval sequence and the sampling rate.
Further, the updating module 40 is further configured to determine a target step length according to the time dispersion of the peak interval and the sampling rate; determining a target segment length according to the target step length and the historical segment length; judging whether the target segment length is larger than a preset maximum segment length or not; when the target segment length is smaller than or equal to a preset maximum segment length, the target segment length is taken as the initial segment length, and the step of segmenting the target signal according to the initial segment length to obtain segment sub-signals is executed.
Further, the updating module 40 is further configured to determine whether the time dispersion of the peak interval is greater than a preset dispersion threshold; when the time dispersion of the peak interval is greater than a preset dispersion threshold, determining a target step length according to the following formula:
μ=fs*VarThreshold
wherein μ is a target step length, fs is a sampling rate, and VarThreshold is a preset dispersion threshold.
Further, the updating module 40 is further configured to determine whether a candidate pulse rate number in the candidate pulse rate sequence is greater than a preset pulse rate number threshold; when the candidate pulse rate number in the candidate pulse rate sequence is smaller than or equal to a preset pulse rate number threshold value, acquiring target dispersion; determining a target dispersion threshold value according to the target dispersion and the preset dispersion threshold value; and taking the target dispersion threshold value as the preset dispersion threshold value, and executing the step of judging whether the peak interval time dispersion is smaller than the preset dispersion threshold value.
Further, the updating module 40 is further configured to calculate a target dispersion threshold according to the target dispersion and the preset dispersion threshold by using the following formula:
NewVarThreshold=VarThreshold+MaxVar*0.5
wherein, NewVarThreshold is the target dispersion threshold, VarThreshold is the preset dispersion threshold, and MaxVar is the target dispersion.
Further, the final pulse rate determining module 50 is further configured to determine a reference pulse rate according to the candidate pulse rate sequence; selecting a target pulse rate from the candidate pulse rate sequence according to a preset selection strategy and the reference pulse rate; and determining a final pulse rate according to the reference pulse rate and the target pulse rate.
Other embodiments or specific implementations of the pulse rate detection system of the present invention may refer to the above method embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A pulse rate detection device, comprising: a memory, a processor, and a pulse rate detection program stored on the memory and executable on the processor, the pulse rate detection program configured to implement the steps of:
acquiring a physiological signal, and preprocessing the physiological signal to obtain a target signal;
segmenting the target signal according to the initial segment length to obtain a segment sub-signal;
determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence;
determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate;
and determining the final pulse rate according to the candidate pulse rate sequence.
2. The pulse rate detection device of claim 1, wherein the pulse rate detection procedure is configured to implement the steps of:
determining a peak interval time sequence from the segmented sub-signals;
determining a peak interval time dispersion according to the peak interval time sequence;
judging whether the time dispersion of the peak interval is smaller than a preset dispersion threshold value or not;
and when the dispersion of the peak interval time is smaller than a preset dispersion threshold value, determining a peak interval mean value according to the peak interval time sequence.
3. The pulse rate detection device of claim 2, wherein the pulse rate detection procedure is configured to implement the steps of:
determining a segmentation sub-signal peak value according to the segmentation sub-signal;
determining a peak position sequence according to the segmented sub-signal peak value;
differentiating the peak position sequence to obtain a peak position interval sequence;
and determining a peak interval time sequence according to the peak position interval sequence and the sampling rate.
4. The pulse rate detection device of claim 1, wherein the pulse rate detection procedure is configured to implement the steps of:
determining a target step length according to the time dispersion of the peak interval and the sampling rate;
determining a target segment length according to the target step length and the historical segment length;
judging whether the target segment length is larger than a preset maximum segment length or not;
when the target segment length is smaller than or equal to a preset maximum segment length, the target segment length is taken as the initial segment length, and the step of segmenting the target signal according to the initial segment length to obtain segment sub-signals is executed.
5. The pulse rate detection device of claim 4, wherein the pulse rate detection procedure is configured to implement the steps of:
judging whether the dispersion of the peak interval time is greater than a preset dispersion threshold value or not;
when the time dispersion of the peak interval is greater than a preset dispersion threshold, determining a target step length according to the following formula:
μ=fs*VarThreshold
wherein μ is a target step length, fs is a sampling rate, and VarThreshold is a preset dispersion threshold.
6. The pulse rate detection device of claim 1, wherein the pulse rate detection procedure is configured to implement the steps of:
judging whether the candidate pulse rate number in the candidate pulse rate sequence is larger than a preset pulse rate number threshold value or not;
when the candidate pulse rate number in the candidate pulse rate sequence is smaller than or equal to a preset pulse rate number threshold value, acquiring target dispersion;
determining a target dispersion threshold value according to the target dispersion and the preset dispersion threshold value;
and taking the target dispersion threshold value as the preset dispersion threshold value, and executing the step of judging whether the peak interval time dispersion is smaller than the preset dispersion threshold value.
7. The pulse rate detection device of claim 6, wherein the pulse rate detection procedure is configured to implement the steps of:
calculating a target dispersion threshold value according to the target dispersion and the preset dispersion threshold value through the following formula:
NewVarThreshold=VarThreshold+MaxVar*0.5
wherein, NewVarThreshold is the target dispersion threshold, VarThreshold is the preset dispersion threshold, and MaxVar is the target dispersion.
8. The pulse rate detection device of claim 1, wherein the pulse rate detection procedure is configured to implement the steps of:
determining a reference pulse rate according to the candidate pulse rate sequence;
selecting a target pulse rate from the candidate pulse rate sequence according to a preset selection strategy and the reference pulse rate;
and determining a final pulse rate according to the reference pulse rate and the target pulse rate.
9. A pulse rate detection system, comprising: the pulse rate measuring device comprises an acquisition module, a segmentation module, a peak interval mean value determination module, an updating module and a final pulse rate determination module;
the acquisition module is used for acquiring physiological signals and preprocessing the physiological signals to obtain target signals;
the segmentation module is used for segmenting the target signal according to an initial segmentation length to obtain a segmentation sub-signal;
the peak interval mean value determining module is used for determining a peak interval time sequence according to the segmented sub-signals and determining a peak interval mean value according to the peak interval time sequence;
the updating module is used for determining a candidate pulse rate according to the peak interval mean value and updating a candidate pulse rate sequence according to the candidate pulse rate;
and the final pulse rate determining module is used for determining a final pulse rate according to the candidate pulse rate sequence.
10. A storage medium having a pulse rate detection program stored thereon, the pulse rate detection program when executed by a processor implementing the steps of:
acquiring a physiological signal, and preprocessing the physiological signal to obtain a target signal;
segmenting the target signal according to the initial segment length to obtain a segment sub-signal;
determining a peak interval time sequence according to the segmented sub-signals, and determining a peak interval mean value according to the peak interval time sequence;
determining a candidate pulse rate according to the peak interval mean value, and updating a candidate pulse rate sequence according to the candidate pulse rate;
and determining the final pulse rate according to the candidate pulse rate sequence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111126494.4A CN113842127B (en) | 2021-09-26 | 2021-09-26 | Pulse rate detection device, pulse rate detection system, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111126494.4A CN113842127B (en) | 2021-09-26 | 2021-09-26 | Pulse rate detection device, pulse rate detection system, and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113842127A true CN113842127A (en) | 2021-12-28 |
CN113842127B CN113842127B (en) | 2023-11-03 |
Family
ID=78980099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111126494.4A Active CN113842127B (en) | 2021-09-26 | 2021-09-26 | Pulse rate detection device, pulse rate detection system, and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113842127B (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150005654A1 (en) * | 2013-06-28 | 2015-01-01 | Bruce Hopenfeld | Heart Beat Detection Based on Permissible Sequence Searching |
-
2021
- 2021-09-26 CN CN202111126494.4A patent/CN113842127B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150005654A1 (en) * | 2013-06-28 | 2015-01-01 | Bruce Hopenfeld | Heart Beat Detection Based on Permissible Sequence Searching |
Also Published As
Publication number | Publication date |
---|---|
CN113842127B (en) | 2023-11-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108186011B (en) | Atrial fibrillation detection method, atrial fibrillation detection device and readable storage medium | |
KR20160094265A (en) | Computing device and method for analyzing biophysiological rate features thereof | |
CN107837082A (en) | Electrocardiogram automatic analysis method and device based on artificial intelligence self study | |
US20130338519A1 (en) | Apparatus and Method for Measuring Physiological Signal Quality | |
CN109117730A (en) | Electrocardiogram auricular fibrillation real-time judge method, apparatus, system and storage medium | |
CN103549948A (en) | Cardiac activation time detection | |
CN108158578A (en) | Noise segments recognition methods, ECG signal processing method and processing device | |
CN111345816A (en) | Multi-lead QRS complex detection method, device, equipment and storage medium | |
US11610073B2 (en) | Device and method for analyzing the state of a system in a noisy context | |
CN115349865A (en) | Driver electrocardiosignal analysis method and device and storage medium | |
CN111684540A (en) | Statistical display method of physiological parameters in monitoring equipment and monitoring equipment | |
CN113842127A (en) | Pulse rate detection device, system and storage medium | |
JP6468635B2 (en) | Sleepiness estimation apparatus and sleepiness estimation program | |
CN109712708B (en) | Health condition prediction method and device based on data mining | |
CN106778561B (en) | Identity recognition method and device of wearable equipment | |
CN111345815B (en) | Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal | |
JP2015217060A (en) | Heartbeat detection method and heartbeat detector | |
CN111493856B (en) | Correction method and device for heart beat classification, electrocardiogram checking system and storage medium | |
CN114403889B (en) | NN interval signal acquisition device, NN interval signal acquisition system and storage medium | |
CN111887836A (en) | Electrocardiosignal processing method, device and equipment | |
CN114530246A (en) | Physiological characteristic signal processing method, electronic device, chip and readable storage medium | |
EP3815604A1 (en) | Blood flow analysis device, blood flow analysis program, and blood flow analysis system | |
CN116229521B (en) | Method, device and equipment for detecting heart information based on multi-scale features | |
CN111134656A (en) | Method and device for detecting electrocardiogram data and computer readable storage medium | |
CN114219028B (en) | Electrocardiogram ST elevation recognition model training and ST elevation recognition method and device |
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 |