CN110313902A - A kind of blood volume change pulse signal processing method and relevant apparatus - Google Patents
A kind of blood volume change pulse signal processing method and relevant apparatus Download PDFInfo
- Publication number
- CN110313902A CN110313902A CN201910621119.3A CN201910621119A CN110313902A CN 110313902 A CN110313902 A CN 110313902A CN 201910621119 A CN201910621119 A CN 201910621119A CN 110313902 A CN110313902 A CN 110313902A
- Authority
- CN
- China
- Prior art keywords
- blood volume
- pulse signal
- volume change
- value
- change pulse
- 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
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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Cardiology (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The embodiment provides a kind of blood volume change pulse signal processing method and relevant apparatus, are related to computer field.Above-mentioned blood volume change pulse signal processing method is by obtaining blood volume change pulse signal；Wherein, the blood volume change pulse signal, which is corresponded in the period by contactless devices in current time window, acquires；Examine whether the blood volume change pulse signal meets preset standard；Wherein, the preset standard be for determine signal fluctuation whether Gui Ze condition；When the blood volume change pulse signal does not meet preset standard, frequency spectrum tracking is carried out to the blood volume change pulse signal, to obtain corresponding estimating physiological parameters.Namely, this programme enhances wherein cardiopulmonary frequency content by corresponding to the irregular part of waveform in identification BVP signal, slackens motion artifacts in BVP signal, influence so as to improve motion artifacts to physiological parameter assessment accuracy, obtains the physiological parameter estimated value of more reasonably stability.
Description
Technical field
The present invention relates to computer fields, in particular to a kind of blood volume change pulse signal processing method and phase
Close device.
Background technique
Blood volume change pulse (Blood Volume Pulse, BVP) signal is that one kind can react human body physiological state
Important physiological data.It can analyze out the physiological parameters such as heart rate, the breathing of detected person based on BVP signal.In daily life
In, the real-time collecting of the physiological parameters such as heart rate, breathing may be implemented to be monitored the diseases such as angiocarpy, prevent and prognosis is commented
Estimate.
Currently, BVP signal can be acquired with non-intrusion type, for example, being acquired using photoplethaysmography, can also use
Contactless acquisition, for example, being acquired using imaging type photoplethaysmography (iPPG).However, in daily life, no matter
Which kind of mode BVP signal is acquired by, can all be influenced by motion artifacts.Motion artifacts not can avoid, but it
The accuracy of the physiological parameter directly affected.
Summary of the invention
The purpose of the present invention includes, for example, a kind of blood volume change pulse signal processing method and relevant apparatus are provided,
It can eliminate influence of the motion artifacts to physiological parameter assessment accuracy in BVP signal, to obtain the life of more reasonably stability
Manage estimates of parameters.
The embodiment of the present invention this can be implemented so that
In a first aspect, the embodiment of the present invention provides a kind of blood volume change pulse signal processing method, the blood volume becomes
Changing pulse signal processing method includes: to obtain blood volume change pulse signal；Wherein, the blood volume change pulse signal is by non-
Contact arrangement is corresponded in the period in current time window and is acquired；Examine whether the blood volume change pulse signal meets pre- bidding
It is quasi-；Wherein, the preset standard be for determine signal fluctuation whether Gui Ze condition；When the blood volume change pulse signal
When not meeting preset standard, frequency spectrum tracking is carried out to the blood volume change pulse signal, to obtain corresponding estimation physiology ginseng
Number.
Second aspect, the embodiment of the present invention provide a kind of blood volume change pulse signal processing apparatus, and the blood volume becomes
Changing pulse signal processing unit includes: acquisition module, for obtaining blood volume change pulse signal；Wherein, the blood volume becomes
Change pulse signal, which is corresponded in the period by contactless devices in current time window, to be acquired；Inspection module, for examining the blood volume
Whether change pulse signal meets preset standard；Wherein, the preset standard be for determine signal fluctuation whether Gui Ze item
Part；Processing module, for when the blood volume change pulse signal does not meet preset standard, to the blood volume change pulse
Signal carries out frequency spectrum tracking, to obtain corresponding estimating physiological parameters.
The third aspect, the embodiment of the present invention provide a kind of computer-readable storage medium, are stored thereon with computer journey
Sequence realizes the blood volume change pulse signal processing as described in aforementioned embodiments when the computer program is executed by processor
Method.
Fourth aspect, the embodiment of the present invention provide a kind of electronic equipment, comprising: processor, storage medium and bus, it is described
Storage medium is stored with the executable machine readable instructions of the processor, when electronic equipment operation, the processor and institute
It states by bus communication between storage medium, the processor executes the machine readable instructions, to execute such as aforementioned embodiment party
Described in formula the step of blood volume change pulse signal processing method.
The embodiment of the present invention the utility model has the advantages that the embodiment of the invention provides a kind of blood volume change pulse signal processing sides
Method, the blood volume change pulse signal processing method is by obtaining using contactless collected blood volume change pulse letter
Number, then examine whether blood volume change pulse signal meets preset standard, to judge the corresponding wave of blood volume change pulse signal
Whether shape is regular.When blood volume change pulse signal does not meet preset standard, the blood volume change pulse letter at this time is determined
Number there is larger fluctuation, that is, motion artifacts are big, should not be directly used in the corresponding estimating physiological parameters value of analysis.At this point, logical
Cross to blood volume change pulse signal carry out frequency spectrum tracking processing, reinforce blood volume change pulse signal in cardiopulmonary frequency at
Point, to weaken the influence of noise bring, obtain the physiological parameter estimated value of reasonably stability.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention；
Fig. 2 is a kind of step flow chart of blood volume change pulse signal processing method provided in an embodiment of the present invention；
Fig. 3 is the sub-step flow chart of step S102 in Fig. 2；
Fig. 4 is the sub-step flow chart of step S103 in Fig. 2；
Fig. 5 is the step flow chart of an application example of the embodiment of the present invention；
Fig. 6 is a kind of structural schematic diagram of blood volume change pulse signal processing apparatus provided in an embodiment of the present invention.
Icon: 100- electronic equipment；101- storage medium；102- communication interface；103- processor；104- bus；200-
Blood volume change pulse signal processing apparatus；201- obtains module；202- inspection module；203- processing module.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.In addition, if there is term
" first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.It should be noted that
In the absence of conflict, the feature in the embodiment of the present invention can be combined with each other.
Referring to FIG. 1, present embodiments providing a kind of electronic equipment 100.Above-mentioned electronic equipment 100 can be, but unlimited
In PC (personal computer, PC), server, the computer of distributed deployment etc..It is understood that
Electronic equipment 100 is also not necessarily limited to physical server, can also be the virtual machine on physical server, based on what is constructed in cloud platform
Virtual machine etc. can provide the computer for having identical function with the server or virtual machine.
The operating system of electronic equipment 100 may be, but not limited to, Windows system, linux system etc..Above-mentioned electronics
Equipment 100 includes storage medium 101, communication interface 102, processor 103 and bus 104, and the storage medium 101, communication connect
Mouth 102 and processor 103 are connected by bus 104, and processor 103 is for executing the executable mould stored in storage medium 101
Block, such as computer program.Wherein, storage medium 101 may include high-speed random access memory (RAM:Random
Access Memory), it is also possible to it further include non-labile memory (non-volatile memory), for example, at least one
Magnetic disk storage.The electronic equipment 100 and outside are realized by least one communication interface 102 (can be wired or wireless)
Communication connection between equipment.
Bus 104 can be isa bus, pci bus or eisa bus etc..It is only indicated with a four-headed arrow in Fig. 1, but
It is not offered as only a bus 104 or a type of bus 104.
Wherein, storage medium 101 is for storing program, such as blood volume change pulse signal processing apparatus shown in fig. 6
200.The blood volume change pulse signal processing apparatus 200 includes at least one can be in the form of software or firmware (firmware)
It is stored in the storage medium 101 or is solidificated in the operating system (operating system, OS) of the electronic equipment 100
In software function module.The processor 103 executes described program after receiving and executing instruction to realize implementation of the present invention
The blood volume change pulse signal processing method that example discloses.
Processor 103 may be a kind of IC chip, the processing capacity with signal.It is above-mentioned during realization
Each step of method can be completed by the integrated logic circuit of the hardware in processor 103 or the instruction of software form.On
The processor 103 stated can be general processor, including central processing unit (Central Processing Unit, abbreviation
CPU), network processing unit (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (DSP), dedicated
Integrated circuit (ASIC), ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor
Logical device, discrete hardware components.
First embodiment
Referring to FIG. 2, Fig. 2 shows blood volume change pulse signal processing methods provided in an embodiment of the present invention.It can be with
Understand that ground, above-mentioned blood volume change pulse signal processing method are applied to electronic equipment 100 shown in FIG. 1.Optionally, above-mentioned blood
Volume change pulse signal processing method the following steps are included:
Step S101 obtains blood volume change pulse signal.
In embodiments of the present invention, above-mentioned BVP signal can be is collected by contactless devices.It is above-mentioned non-contact to adopt
Collection equipment can be image capture device.Preferably, after contactless devices collect the image data with the personnel of being detected, from
The area-of-interest for extracting BVP signal is determined in image data.Again by all pixels point R, G, B tri- in the area-of-interest
Channel components are averaged, and obtain an one-dimensional source signal changed over time, and be filtered to obtain BVP under time domain
Signal.It is to be understood that the acquisition of BVP signal is a lasting process, the BVP largely continued to increase is handled for convenience
Data can be slided, successively acquisition time window is right after sliding each time in favor of the time window of preset length along acquisition time axis
BVP signal in the period answered.It is, the BVP signal obtained, which can be acquisition acquisition time, belongs to current time window pair
Answer multiple BVP signals of period.Above-mentioned BVP signal arranges on a timeline according to corresponding acquisition time, forms waveform, currently
Each BVP signal in time window has corresponding index value according to acquisition time sequence, for example, first in current time window
The index value of collected BVP signal is 1, and the index value of second collected BVP signal is 2, and so on.
Step S102, examines whether the blood volume change pulse signal meets preset standard.
In embodiments of the present invention, above-mentioned preset standard can be for determine signal fluctuation whether Gui Ze condition.It is logical
It crosses whether inspection BVP signal meets preset standard, judges whether the waveform of BVP signal is regular, to judge that BVP signal is corresponding
Whether fluctuate widely.It is to be appreciated that fluctuating widely caused by usually motion artifacts etc. in BVP signal, adopts
With the mode of the relevant technologies, physiological parameter extraction directly is carried out to the BVP signal to fluctuate widely, not only will increase computational efficiency
With runing time, and obtained physiological parameter is inaccurate.Therefore, in the embodiment of the present invention, appearance significantly wave need to be recognized
Dynamic BVP signal, and handled.
As an implementation, as shown in figure 3, above-mentioned steps S102 may include following sub-step:
Sub-step S1021 calculates the first variance characteristic sequence and second variance feature sequence of blood volume change pulse signal
Column.
In embodiments of the present invention, the BVP signal under current time window may include multiple crest values and multiple valley values.
Above-mentioned crest value is the local maximum in BVP signal, is greater than two BVP signals adjacent thereto.Above-mentioned valley value is
For the local minimum in BVP signal, it is less than two BVP signals adjacent thereto.It is to be appreciated that above-mentioned multiple crest values
It is sequentially arranged on a timeline according to acquisition time；Above-mentioned multiple valley values sequentially arrange on a timeline according to acquisition time.
Above-mentioned first variance characteristic sequence includes the Variance feature of crest value.Above-mentioned second variance characteristic sequence includes the variance of valley value
Feature.Optionally, the mode of the first variance characteristic sequence and second variance characteristic sequence that calculate above-mentioned BVP signal can be as
Under:
(1) corresponding signal successively is calculated according to each crest value and other crest values after the crest value
Variance yields, the crest value described in the penultimate, to generate first variance sequence.
As an implementation, there is also specified quantity (for example, specified quantity can be 7) after a crest value
Crest value when, according to the crest value of the specified quantity after the crest value and the crest value, calculate the corresponding letter of the crest value
Number variance yields.When crest value quantity after a crest value is less than specified quantity, will according to the crest value and the crest value it
All crest values afterwards calculate the corresponding signal variance value of the crest value.It should be understood that without it after the last one crest value
Therefore he does not calculate its corresponding signal variance value by crest value.It is, there is x crest value, then x-1 signal variance is corresponded to
Value.The signal variance value being calculated is arranged according to the sequence of its corresponding crest value, obtains first variance sequence.
(2) other valley values being successively located at according to each valley value and acquisition time after the valley value calculate institute
The corresponding signal variance value of valley value is stated, the valley value described in the penultimate, to generate second variance sequence.
As an implementation, there is also specified quantity (for example, specified quantity can be 7) after a valley value
Valley value when, according to the valley value of the specified quantity after the valley value and the valley value, calculate the corresponding letter of the valley value
Number variance yields.When valley value quantity after a valley value is less than specified quantity, after the valley value and the valley value
All valley values, calculate the corresponding signal variance value of the valley value.It should be understood that without other after the last one valley value
Therefore valley value does not calculate its corresponding signal variance value.It is, there is y valley value, then y-1 signal variance is corresponded to
Value.The signal variance value being calculated is arranged according to the sequence of its corresponding valley value, obtains second variance sequence.
(3) according to first variance sequence, second variance sequence, change arteries and veins in the blood volume in conjunction with crest value and valley value
Corresponding index value in signal is rushed, formula is utilized:
And
Generate the first variance characteristic sequence and second variance characteristic sequence.
In embodiments of the present invention,The corresponding Variance feature of i-th of crest value is represented,Described in representative
The corresponding signal variance value of i-th of crest value in first variance sequence；location(Mi) represent i-th of crest value
The corresponding index value；location(Mi+1) represent the corresponding index value of the i+1 crest value；I successively takes 1 to x-1
Between value；X represents the total number of the crest value.Obtained Variance feature is arranged according to the sequence of corresponding crest value
Column generate first variance characteristic sequence.
In embodiments of the present invention,The corresponding Variance feature of n-th of valley value is represented,Represent described second
The corresponding signal variance value of n-th of valley value in variance sequence；location(mn) represent the corresponding rope of n-th of valley value
Draw value；location(mn+1) represent the corresponding index value of (n+1)th valley value；N successively takes 1 to the value between y-1；Y represents institute
State the total number of valley value.Obtained Variance feature is arranged according to the sequence of corresponding valley value, generates second variance
Characteristic sequence.
Sub-step S1022, according to first variance characteristic sequence and second variance characteristic sequence, in conjunction with crest value and trough
Value, judges whether the blood volume change pulse signal meets preset standard.
In embodiments of the present invention, above-mentioned first variance characteristic sequence and second variance characteristic sequence, combination ripple be can be
When peak value and valley value meet following any one, determine that above-mentioned BVP signal does not meet preset standard:
1) there are at least one Variance features to be much larger than empirical value in first variance characteristic sequence.In the embodiment of the present invention
In, above-mentioned empirical value can be fitted to obtain an empirical according to historical data.It is to be appreciated that when Variance feature is greater than
When the empirical value of default first multiple, it can determine whether it much larger than empirical value.Above-mentioned default first multiple can be one big
In 1 number, for example, 3 times of empirical value.
2) there are at least one Variance features to be much larger than empirical value in second variance characteristic sequence.In the embodiment of the present invention
In, above-mentioned empirical value can be fitted to obtain an empirical according to historical data.It is to be appreciated that when Variance feature is greater than
When the empirical value of default first multiple, it can determine whether it much larger than empirical value.Above-mentioned default first multiple can be one big
In 1 number, for example, 3 times of empirical value.
3) there are crest values to meet location (Mi+4)-location(Mi) it is much smaller than distFAR.Wherein, location
(Mi) represent the corresponding index value of i-th of crest value；location(Mi+4) to represent the i-th+4 crest values corresponding
Index value.It should be understood that location (Mi+4)-location(Mi) it is much smaller than distFAR, can be location (Mi+4)-
location(Mi) it is less than the dist of default second multipleFAR, above-mentioned default second multiple can be a number less than 1, than
Such as, 1/2 times of distFAR。
4) there are crest values to meet location (Mi+2)-location(Mi) it is much larger than distNEAR.Wherein, location
(Mi) represent the corresponding index value of i-th of crest value；location(Mi+2) represent the i-th+2 crest values pair
The index value answered.It should be understood that location (Mi+2)-location(Mi) it is much larger than distNEAR, can be location
(Mi+2)-location(Mi) it is greater than the dist of default first multipleNEAR。
5) there are valley values to meet location (mn+4)-location(mn) it is much smaller than distFAR.Wherein, location
(mn) represent the corresponding index value of n-th of valley value；location(mn+4) represent the n-th+4 valley values pair
The index value answered.It should be understood that location (mn+4)-location(mn) it is much smaller than distFAR, can be location
(mn+4)-location(mn) it is less than the dist of default second multipleFAR。
6) there are valley values to meet location (mn+2)-location(mn) it is much larger than distNEAR.Wherein, location
(mn) represent the corresponding index value of n-th of valley value；location(mn+2) represent the n-th+2 valley values pair
The index value answered.It should be understood that location (mn+2)-location(mn) it is much larger than distNEAR, can be location
(mn+2)-location(mn) it is greater than the dist of default first multipleNEAR。
In embodiments of the present invention, above-mentioned distFAR=ρ × 180/Epre, distNEAR=ρ × 60/Epre.ρ generation acquisition BVP
The sample frequency of signal.EpreRepresent adjacent estimating physiological parameters.It is to be appreciated that above-mentioned neighbour's estimating physiological parameters are according to phase
The estimating physiological parameters that BVP signal under an adjacent upper time window obtains.
It is to be appreciated that determining that BVP signal does not meet preset standard, then it can be determined that the BVP signal under current time window
Corresponding waveform is irregular, for example, fluctuating widely.
Step S103, when blood volume change pulse signal does not meet preset standard, to blood volume change pulse signal into
Line frequency spectrum tracking, to obtain corresponding estimating physiological parameters.
It in embodiments of the present invention, can be with after identifying that the corresponding waveform of BVP signal under current time frame is irregular
It is eliminated by following steps as shown in Figure 4 and is fluctuated widely caused by motion artifacts:
Sub-step S1031, the spline interpolation for carrying out predetermined number of times to blood volume change pulse signal are handled.
It is to be appreciated that although motion artifacts will cause fluctuating widely for BVP signal, but the influence of its bring is usually
Of short duration.Therefore, the frequency of the cardiopulmonary in BVP signal can be reinforced by being handled using spline interpolation facture BVP signal
Ingredient, to weaken the influence of noise bring.To obtain stable BVP signal.It preferably, can be to BVP signal sample three times
Interpolation processing.
Sub-step S1032, the blood volume change pulse signal obtained after spline interpolation is handled are transformed into frequency domain, obtain more
A frequency content.
In embodiments of the present invention, the blood volume obtained after being handled spline interpolation using Fast Fourier Transform (FFT) (FFT)
Change pulse signal is transformed into frequency domain, therefrom to obtain multiple frequency contents.
Sub-step S1033 selects the frequency content to be processed of preset quantity from multiple frequency contents.That selects is to be processed
Frequency content is all larger than other frequency contents in the multiple frequency content.
As an implementation, BVP signal can be transformed into all frequency values obtained after frequency domain according to its value
Size is arranged in descending order.Will sequence in the pervious frequency content of default ranking, be determined as frequency to be processed at
Point.For example, the frequency content of front three will be arranged in as frequency content to be processed.
Sub-step S1034 assesses a corresponding physiological parameter to be selected according to each frequency content to be processed respectively.
In the embodiment of the present invention, it is heart rate and respiratory rate etc. that above-mentioned physiological parameter to be selected, which may be, but not limited to,.For
Facilitate description, even if being only illustrated by taking heart rate and respiratory rate as an example below, does not also represent the restriction to its range.
Further, to treated, BVP signal presses preset model progress spectrum analysis, to obtain physiological parameter.It can
Selection of land, above-mentioned preset model can be ARIMA (p, d, q) (Autoregressive Integrated Moving
Average Model, autoregression integrate moving average model).Specifically, using autoregression integral moving average model at this
BVP signal in the frequency domain obtained after reason carries out spectrum analysis, and calculating the corresponding physiological parameter of each frequency content, (heart rate is exhaled
Suction rate), wherein AR is autoregression, and p is autoregression item；MA is rolling average, and q is rolling average item number, d be time series at
By it is steady when the difference number that does.It is put down it should be understood that above-mentioned physiological parameter to be selected can be using autoregression integral sliding
Equal model treats the parameter obtained after processing frequency ingredient is analyzed.
Sub-step S1035 successively calculates the absolute difference between each physiological parameter to be selected and adjacent estimating physiological parameters
Value.
In embodiments of the present invention, above-mentioned adjacent estimating physiological parameters can be according to the blood under an adjacent upper time window
The final physiological parameter that volume change pulse signal determines.Above-mentioned absolute difference refers to physiological parameter to be selected and adjacent estimation physiology
The absolute value of difference namely the distance between physiological parameter to be selected and adjacent estimating physiological parameters between parameter.
Minimum and no more than preset threshold the corresponding physiological parameter to be selected of absolute difference is determined as by sub-step S1036
Estimating physiological parameters corresponding to blood volume change pulse signal under current time window.
In embodiments of the present invention, above-mentioned preset threshold can be a preset constant value.Preferably, above-mentioned pre-
If threshold value can be 15bmp.The corresponding absolute difference of each physiological parameter to be selected, corresponding absolute difference is minimum, and
The physiological parameter to be selected that corresponding absolute difference is no more than preset threshold is determined as the blood volume change pulse under current time window
Estimating physiological parameters corresponding to signal.
It is to be appreciated that in some cases, it can be possible to there are two minimums simultaneously and being no more than the absolute difference of preset threshold
Value can represent current time then just needing the variation tendency of the further corresponding physiological parameter of assessment BVP signal to determine
The accurate estimating physiological parameters of blood volume change pulse signal under window.It specifically, can be by first by current time window
Time span shortens, and obtains determining time window.For example, the initial time of current time window can be remained unchanged, by time window
Length shorten one third, obtain a new time window, i.e., judgement time window.Obtaining the blood appearance for belonging to judgement time window again
The corresponding multiple frequency contents of amount variation pulse signal.Then, multiple lifes are obtained according to the corresponding frequency content of judgement time window
Manage parameter.If it is determined that the corresponding multiple physiological parameters of time window then will be greater than adjacent estimating physiological parameters and corresponding in being incremented by
The smallest physiological parameter to be selected of absolute difference is determined as described corresponding to the blood volume change pulse signal under current time window
Estimating physiological parameters.If the corresponding multiple physiological parameters of the judgement time window taper off, adjacent estimation physiology ginseng will be less than
The several and corresponding the smallest physiological parameter to be selected of absolute difference is determined as the blood volume change pulse signal institute under current time window
The corresponding estimating physiological parameters.
Adjacent estimating physiological parameters are determined as working as by sub-step S1037 when the smallest absolute difference is more than preset threshold
Estimating physiological parameters corresponding to blood volume change pulse signal under preceding time window.
In embodiments of the present invention, if all select the corresponding absolute difference of physiological parameter to be above preset threshold,
Illustrate that this section of BVP signal fluctuation is still big, poor signal quality then selects adjacent estimating physiological parameters as under preceding time window at this time
Blood volume change pulse signal corresponding to estimating physiological parameters.
Step S104 changes blood volume using preset model when blood volume change pulse signal meets preset standard
Pulse signal carries out spectrum analysis, to obtain corresponding estimating physiological parameters.
In embodiments of the present invention, above-mentioned preset model can be ARIMA (p, d, q) (Autoregressive
Integrated Moving Average Model, autoregression integrate moving average model).
It in order to be further explained to the present invention, is described below with an example, as shown in figure 5, the present invention provides
Blood volume change pulse signal processing method include:
S1 obtains the BVP signal for passing through time-domain filtering under current time window.
S2 obtains crest value and valley value all in BVP signal.
S3 successively examines whether each crest value is the last one crest value.If it is not, process enters step S4.If
It is that process enters step S7.
S4 calculates the corresponding signal variance value of the crest value.Optionally, if there are also 7 crest values after the crest value,
Then 7 crest values based on the crest value and thereafter, calculate corresponding signal variance value；If the crest value after the crest value
Less than 7, then all crest values based on the crest value and thereafter, calculate corresponding signal variance value.Further, process is returned
To step S3.
S5 successively examines whether each valley value is the last one valley value.If it is not, process enters step S6.If
It is that process enters S7.
S6 calculates the corresponding signal variance value of the valley value.Optionally, if there are also 7 valley values after the valley value,
Then 7 valley values based on the valley value and thereafter, calculate corresponding signal variance value；If the valley value after the valley value
Less than 7, then all valley values based on the valley value and thereafter, calculate corresponding signal variance value.Further, process is returned
To step S5.
It is to be appreciated that absolute sequencing is not present between above-mentioned steps S3 and step S5, it is preferable that can be parallel
Processing.
S7, according to the corresponding signal variance value of each crest value and the corresponding signal variance value of each valley value, combination ripple
Peak value and the valley value corresponding index value in BVP signal calculate the corresponding first variance characteristic sequence of BVP signal and second party
Poor characteristic sequence.First variance characteristic sequence includes the corresponding Variance feature of multiple crest values, and second variance characteristic sequence includes
The corresponding Variance feature of multiple valley values.
S8 judges to be greater than 3*TH with the presence or absence of at least one Variance feature in first variance characteristic sequenceAM.Above-mentioned THAMFor
Empirical value.If so, process enters step S15；If it is not, process enters step S9.
S9 judges to be greater than 3*TH with the presence or absence of at least one Variance feature in second variance characteristic sequenceAM.If so, stream
Journey enters step S15；If it is not, process enters step S10.
S10 judges whether there is the distance between i-th of crest value and the i-th+4 crest values much smaller than distFAR.It is above-mentioned
distFAR=ρ × 180/Epre, the sample frequency of ρ generation acquisition BVP signal.EpreRepresent adjacent estimating physiological parameters.Above-mentioned i's takes
Value range is 1 to x, and x represents the total number of the crest value.Further, if so, process enters step S15；If no
It is that process enters step S11.
S11 judges whether there is the distance between the i-th crest value and the i-th+2 crest values much larger than distNEAR.Into one
Step ground, if so, process enters step S15；If it is not, process enters step S12.
S12 judges whether there is the distance between n-th of valley value and the n-th+4 valley values much smaller than distFAR.Into one
Step ground, if so, process enters step S15；If it is not, process enters step S13.The value range of above-mentioned n is 1 to y, y
Represent the total number of the valley value.
S13 judges whether there is the distance between the n-th valley value and the n-th+2 valley values much larger than distNEAR.Into one
Step ground, if so, process enters step S15；If it is not, process enters step S14.
S14 carries out spectrum analysis to blood volume change pulse signal using preset model, to obtain corresponding estimation physiology
Parameter terminates process.
S15 carries out cubic spline interpolation processing to BVP signal.
S16, the blood volume change pulse signal obtained after spline interpolation is handled are transformed into frequency domain, obtain multiple frequencies at
Point.
S17 therefrom selects three frequency contents, respectively f1、f2And f3.Above-mentioned f1、f2And f3Be all larger than other frequencies at
Point.
S18 determines f using autoregression integral moving average model respectively1、f2And f3Corresponding heart rate value E1、E2And E3。
S19 calculates separately E1、E2And E3With neighbor evaluation heart rate value EpreBetween absolute difference.That is absolute difference Δ E1
=| Epre-E1|, absolute difference Δ E2=| Epre-E2|, absolute difference Δ E3=| Epre-E3|。
S20, from Δ E1、ΔE2With Δ E3In determine minimum value Δ Emin.It is to be appreciated that Δ EminIt can be Δ E1、Δ
E2With Δ E3In one.
S21, if 60* Δ EminNo more than 15bmp, then by Δ EminCorresponding heart rate value is as estimating under current time window
Count heart rate value.
S22, if 60* Δ EminMore than 15bmp, then by EpreAs the estimation heart rate value under current time window.
To sum up, the above method is respectively adopted and directlys adopt autoregression integral moving average model in the prior art to same
Group BVP signal is handled, and every Comparative result is as follows:
Second embodiment
Fig. 6 is please referred to, Fig. 6 shows a kind of blood volume change pulse signal processing apparatus provided in an embodiment of the present invention
200 structural block diagram.Above-mentioned blood volume change pulse signal processing apparatus 200 include: obtain module 201, inspection module 202 and
Processing module 203.
Above-mentioned acquisition module 201, for obtaining blood volume change pulse signal；Wherein, the blood volume change pulse letter
It number is corresponded in the period and to be acquired in current time window by contactless devices.
In embodiments of the present invention, above-mentioned steps S101 can be executed by acquisition module 201.
Above-mentioned inspection module 202, for examining whether the blood volume change pulse signal meets preset standard；Wherein,
The preset standard be for determine signal fluctuation whether Gui Ze condition.
In embodiments of the present invention, above-mentioned steps S102 can be executed by inspection module 202.
Above-mentioned processing module 203, for when the blood volume change pulse signal does not meet preset standard, to the blood
Volume change pulse signal carries out frequency spectrum tracking, to obtain corresponding estimating physiological parameters.
In embodiments of the present invention, above-mentioned steps S103 and step S104 can be executed by processing module 203.
It is apparent to those skilled in the art that for convenience and simplicity of description, the device of foregoing description
Specific work process, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
The embodiment of the present invention further discloses a kind of computer-readable storage medium, is stored thereon with computer program, institute
State the method for realizing that present invention discloses when computer program is executed by processor 103.
In conclusion the embodiment of the invention provides a kind of blood volume change pulse signal processing method and relevant apparatus,
Above-mentioned blood volume change pulse signal processing method is by obtaining blood volume change pulse signal；Wherein, the blood volume variation
Pulse signal is corresponded in the period in current time window by contactless devices and is acquired；Whether examine the blood volume change pulse signal
Meet preset standard；Wherein, the preset standard be for determine signal fluctuation whether Gui Ze condition；When the blood volume becomes
When change pulse signal does not meet preset standard, frequency spectrum tracking is carried out to the blood volume change pulse signal, it is corresponding to obtain
Estimating physiological parameters.By the cardiopulmonary frequency content in enhancing BVP signal, motion artifacts in BVP signal are effectively eliminated.It eliminates
Influence of the motion artifacts to physiological parameter assessment accuracy, to obtain the physiological parameter estimated value of more reasonably stability.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.It needs
Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship or sequence on border.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those familiar with the art, all answers
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be with the scope of protection of the claims
It is quasi-.
Claims (10)
1. a kind of blood volume change pulse signal processing method, which is characterized in that blood volume change pulse signal processing side
Method includes:
Obtain blood volume change pulse signal；Wherein, the blood volume change pulse signal is by contactless devices in current time
Window corresponds to acquisition in the period；
Examine whether the blood volume change pulse signal meets preset standard；Wherein, the preset standard is for determining to believe
Number fluctuation whether Gui Ze condition；
When the blood volume change pulse signal does not meet preset standard, frequency spectrum is carried out to the blood volume change pulse signal
Tracking, to obtain corresponding estimating physiological parameters.
2. blood volume change pulse signal processing method as described in claim 1, which is characterized in that described that the blood is examined to hold
Measure that the step of whether variation pulse signal meets preset standard includes:
Calculate the first variance characteristic sequence and second variance characteristic sequence of the blood volume change pulse signal；Wherein, described
Blood volume change pulse signal includes multiple crest values and multiple valley values；The first variance characteristic sequence includes the wave crest
The Variance feature of value；The second variance characteristic sequence includes the Variance feature of the valley value；
Institute is judged in conjunction with the crest value and valley value according to the first variance characteristic sequence and second variance characteristic sequence
State whether blood volume change pulse signal meets preset standard.
3. blood volume change pulse signal processing method as claimed in claim 2, which is characterized in that described to calculate the blood appearance
Amount variation pulse signal first variance characteristic sequence and second variance characteristic sequence the step of include:
Other crest values being successively located at according to crest value described in each and acquisition time after the crest value calculate corresponding
Signal variance value, the crest value described in the penultimate, to generate first variance sequence；
Other valley values being successively located at according to valley value described in each and acquisition time after the valley value, calculate the wave
The corresponding signal variance value of valley, the valley value described in the penultimate, to generate second variance sequence；
According to the first variance sequence, second variance sequence, change in conjunction with the crest value and valley value in the blood volume
Corresponding index value in pulse signal, utilizes formula:
And
Generate the first variance characteristic sequence and second variance characteristic sequence；
Wherein,The corresponding Variance feature of i-th of crest value is represented,It represents in the first variance sequence
The corresponding signal variance value of the described crest value of i；location(Mi) represent the corresponding index of i-th of crest value
Value；location(Mi+1) represent the corresponding index value of the i+1 crest value；I successively takes 1 to the value between x-1；X is represented
The total number of the crest value；
The corresponding Variance feature of n-th of valley value is represented,Represent n-th of institute in the second variance sequence
State the corresponding signal variance value of valley value；location(mn) represent the corresponding index value of n-th of valley value；
location(mn+1) represent the corresponding index value of (n+1)th valley value；N successively takes 1 to the value between y-1；Y represents institute
State the total number of valley value.
4. blood volume change pulse signal processing method as claimed in claim 2, which is characterized in that described according to described first
Variance feature sequence and second variance characteristic sequence judge the blood volume change pulse in conjunction with the crest value and valley value
The step of whether signal meets preset standard include:
When being much larger than empirical value there are Variance feature described at least one in the first variance characteristic sequence, described in judgement
Blood volume change pulse signal does not meet preset standard；
When being much larger than empirical value there are Variance feature described at least one in the second variance characteristic sequence, described in judgement
Blood volume change pulse signal does not meet preset standard；
Meet location (M when existingi+4)-location(Mi) it is much smaller than distFARThe crest value when, judge the blood
Volume change pulse signal does not meet preset standard；Wherein, location (Mi) represent the corresponding index of i-th of crest value
Value；location(Mi+4) represent the corresponding index value of the i-th+4 crest values；
Meet location (M when existingi+2)-location(Mi) it is much larger than distNEARThe crest value when, judge the blood
Volume change pulse signal does not meet preset standard；Wherein, location (Mi) to represent i-th of crest value corresponding described
Index value；location(Mi+2) represent the corresponding index value of the i-th+2 crest values；
Meet location (m when existingn+4)-location(mn) it is much smaller than distFARThe valley value when, judge the blood
Volume change pulse signal does not meet preset standard；Wherein, location (mn) to represent n-th of valley value corresponding described
Index value；location(mn+4) represent the corresponding index value of the n-th+4 valley values；
Meet location (m when existingn+2)-location(mn) it is much larger than distNEARThe valley value when, judge the blood
Volume change pulse signal does not meet preset standard；Wherein, location (mn) to represent n-th of valley value corresponding described
Index value；location(mn+2) represent the corresponding index value of the n-th+2 valley values；
Wherein, distFAR=ρ × 180/Epre, distNEAR=ρ × 60/Epre；It is corresponding that ρ represents the blood volume change pulse signal
Sample frequency；EpreAdjacent estimating physiological parameters are represented, neighbour's estimating physiological parameters are according under an adjacent upper time window
The obtained estimating physiological parameters of the blood volume change pulse signal.
5. blood volume change pulse signal processing method as described in claim 1, which is characterized in that described to the blood volume
Change pulse signal carry out frequency spectrum tracking the step of include:
The spline interpolation processing of predetermined number of times is carried out to the blood volume change pulse signal；
The blood volume change pulse signal obtained after spline interpolation is handled is transformed into frequency domain, obtains multiple frequency contents；
The frequency content to be processed of preset quantity is determined from the multiple frequency content；Wherein, the frequency to be processed at
Divide bigger than other frequency contents in the multiple frequency content；
A corresponding physiological parameter to be selected is assessed according to each frequency content to be processed respectively；
Successively calculate the absolute difference between each physiological parameter to be selected and adjacent estimating physiological parameters；Wherein, described
Adjacent estimating physiological parameters are the institute that obtains according to the blood volume change pulse signal under an adjacent upper time window
State estimating physiological parameters；
It is determined as by minimum and no more than the corresponding physiological parameter to be selected of the absolute difference of preset threshold described current
The estimating physiological parameters corresponding to blood volume change pulse signal under time window.
6. blood volume change pulse signal processing method as claimed in claim 5, which is characterized in that described to the blood volume
Change pulse signal carries out the step of frequency spectrum tracking further include:
When the smallest absolute difference is more than the preset threshold, the adjacent estimating physiological parameters are determined as described work as
The estimating physiological parameters corresponding to blood volume change pulse signal under preceding time window.
7. blood volume change pulse signal processing method as claimed in claim 5, which is characterized in that when there are two minimums and
No more than preset threshold the absolute difference when, it is described to the blood volume change pulse signal carry out frequency spectrum tracking the step of
Further include:
The time span of the current time window is shortened, obtains determining time window；
It obtains and belongs to the corresponding multiple frequency contents of blood volume change pulse signal for determining time window；
Multiple physiological parameters are obtained according to the corresponding frequency content of the judgement time window；
If the corresponding the multiple physiological parameter of the judgement time window will be greater than the adjacent estimating physiological parameters in being incremented by
And the corresponding the smallest physiological parameter to be selected of absolute difference is determined as the blood volume change pulse under the current time window
The estimating physiological parameters corresponding to signal；
If the corresponding the multiple physiological parameter of the judgement time window tapers off, the adjacent estimating physiological parameters will be less than
And the corresponding the smallest physiological parameter to be selected of absolute difference is determined as the blood volume change pulse under the current time window
The estimating physiological parameters corresponding to signal.
8. a kind of blood volume change pulse signal processing apparatus, which is characterized in that the blood volume change pulse signal processing device
It sets and includes:
Module is obtained, for obtaining blood volume change pulse signal；Wherein, the blood volume change pulse signal is set by non-contact
Standby correspond in the period in current time window acquires；
Inspection module, for examining whether the blood volume change pulse signal meets preset standard；Wherein, the preset standard
For for determine signal fluctuation whether Gui Ze condition；
Processing module, for changing arteries and veins to the blood volume when the blood volume change pulse signal does not meet preset standard
It rushes signal and carries out frequency spectrum tracking, to obtain corresponding estimating physiological parameters.
9. a kind of computer-readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
Such as method of any of claims 1-7 is realized when processor executes.
10. a kind of electronic equipment characterized by comprising processor, storage medium and bus, the storage medium are stored with
The executable machine readable instructions of the processor, when electronic equipment operation, between the processor and the storage medium
By bus communication, the processor executes the machine readable instructions, to execute the blood as described in claim 1 to 7 is any
The step of volume change pulse signal processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910621119.3A CN110313902B (en) | 2019-07-10 | 2019-07-10 | Blood volume change pulse signal processing method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910621119.3A CN110313902B (en) | 2019-07-10 | 2019-07-10 | Blood volume change pulse signal processing method and related device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110313902A true CN110313902A (en) | 2019-10-11 |
| CN110313902B CN110313902B (en) | 2021-03-12 |
Family
ID=68123342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910621119.3A Active CN110313902B (en) | 2019-07-10 | 2019-07-10 | Blood volume change pulse signal processing method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110313902B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822329A (en) * | 2021-08-10 | 2021-12-21 | 国网新源控股有限公司 | Hydro-power generating unit main shaft throw signal processing method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030212336A1 (en) * | 2002-04-15 | 2003-11-13 | Samsung Electronics Co., Ltd. | Apparatus and method for detecting heartbeat using PPG |
| US20090326349A1 (en) * | 2008-06-30 | 2009-12-31 | Nellcor Puritan Bennett Ireland | Consistent Signal Selection By Signal Segment Selection Techniques |
| US20160367198A1 (en) * | 2014-02-26 | 2016-12-22 | Ki H. Chon | Apparatus and method for detecting and removing artifacts in optically acquired biological signals |
-
2019
- 2019-07-10 CN CN201910621119.3A patent/CN110313902B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030212336A1 (en) * | 2002-04-15 | 2003-11-13 | Samsung Electronics Co., Ltd. | Apparatus and method for detecting heartbeat using PPG |
| US20090326349A1 (en) * | 2008-06-30 | 2009-12-31 | Nellcor Puritan Bennett Ireland | Consistent Signal Selection By Signal Segment Selection Techniques |
| US20160367198A1 (en) * | 2014-02-26 | 2016-12-22 | Ki H. Chon | Apparatus and method for detecting and removing artifacts in optically acquired biological signals |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822329A (en) * | 2021-08-10 | 2021-12-21 | 国网新源控股有限公司 | Hydro-power generating unit main shaft throw signal processing method and device |
| CN113822329B (en) * | 2021-08-10 | 2023-11-03 | 国网新源控股有限公司 | Method and device for processing main shaft swing degree signal of hydroelectric generating set |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110313902B (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106073743B (en) | Method and system for noise cleaning of photoplethysmograph signals | |
| CN105578960B (en) | For handling processing unit, the processing method and system of physiological signal | |
| CN101732050B (en) | Photoelectric volume wave-based breathing rate monitoring method | |
| CN110664390B (en) | Heart rate monitoring system and method based on wrist strap type PPG and deep learning | |
| CN109247923A (en) | Contactless pulse real-time estimation method and equipment based on video | |
| CN104305992B (en) | A kind of interactive fast automatic extracting method of Fetal ECG | |
| CN108056770A (en) | A kind of heart rate detection method based on artificial intelligence | |
| CN110461215A (en) | Health mark is determined using portable device | |
| US20140200460A1 (en) | Real-time physiological characteristic detection based on reflected components of light | |
| CN107595247A (en) | A kind of monitoring method and system of the depth of anesthesia based on EEG signals | |
| CN109864741A (en) | Cyclical action appraisal procedure and device, terminal device based on electromyography signal | |
| CN110313902A (en) | A kind of blood volume change pulse signal processing method and relevant apparatus | |
| CN114707563A (en) | Human body action recognition method based on Wi-Fi channel state information | |
| CN114999643A (en) | WiFi-based intelligent monitoring method for old people | |
| CN106236041B (en) | A kind of algorithm and system measuring heart rate and respiratory rate in real time and accurately | |
| CN108694355B (en) | Signal processing method and device | |
| CN109542021A (en) | A kind of sensor weak signal data acquisition method and device | |
| US20230000376A1 (en) | System and method for physiological measurements from optical data | |
| US20130211273A1 (en) | Method and apparatus for heart rate measurement | |
| Temko | PPG-based heart rate estimation using Wiener filter, phase vocoder and Viterbi decoding | |
| CN116502124A (en) | Pulse wave signal quality evaluation method and device and computer readable storage medium | |
| CN108652604A (en) | It is a kind of based on electrocardiosignal without air bag blood pressure detecting method and system | |
| CN114488841A (en) | Data collection processing method of intelligent wearable device | |
| Kang et al. | Accurately counting steps of the pedestrian with varying walking speeds | |
| CN112006665A (en) | Scenic spot intelligent integrated service wearable system based on Internet of things |
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 |