CN108523868A - Self-calibration system and method for blood pressure measurement - Google Patents
Self-calibration system and method for blood pressure measurement Download PDFInfo
- Publication number
- CN108523868A CN108523868A CN201810616479.XA CN201810616479A CN108523868A CN 108523868 A CN108523868 A CN 108523868A CN 201810616479 A CN201810616479 A CN 201810616479A CN 108523868 A CN108523868 A CN 108523868A
- Authority
- CN
- China
- Prior art keywords
- blood pressure
- human body
- human
- blood
- model
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000009530 blood pressure measurement Methods 0.000 title claims abstract description 32
- 230000036772 blood pressure Effects 0.000 claims abstract description 121
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 230000001133 acceleration Effects 0.000 claims description 38
- 230000010349 pulsation Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 239000008280 blood Substances 0.000 claims description 3
- 210000004369 blood Anatomy 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 238000004422 calculation algorithm Methods 0.000 description 24
- 238000010586 diagram Methods 0.000 description 20
- 230000007704 transition Effects 0.000 description 16
- 238000005259 measurement Methods 0.000 description 15
- 238000007781 pre-processing Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 8
- 230000004927 fusion Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 230000000295 complement effect Effects 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 5
- 230000005389 magnetism Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000000386 athletic effect Effects 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000035487 diastolic blood pressure Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000035488 systolic blood pressure Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- A61B5/021—Measuring pressure in heart or blood vessels
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
Abstract
The present invention relates to blood pressure detecting technical fields, specifically, being related to a kind of self-calibration system and method for blood pressure measurement.The system includes blood pressure collecting unit, human body attitude collecting unit and processing unit, blood pressure collecting unit is for acquiring human blood-pressure detection signal, human body attitude collecting unit is equipped with blood pressure detecting model, human body attitude identification model and the list of feature values for describing blood pressure detecting model coefficient under human body difference behavior pattern for acquiring human motion signal at processing unit；Processing unit is used to identify the behavior pattern of current human by human body attitude identification model according to human motion signal, and blood pressure detecting model into is brought corresponding coefficient according to the list of feature values, and then signal is detected according to human blood-pressure, human blood-pressure detected value is obtained by blood pressure detecting model.This method is realized based on the system.The present invention can preferably realize the automatic calibration to blood pressure detecting model in the continuous monitoring process of blood pressure.
Description
Technical field
The present invention relates to blood pressure detecting technical fields, specifically, being related to a kind of self-calibration system for blood pressure measurement
And method.
Background technology
Important physiological health index of the blood pressure (Blood Pressure, BP) as human body can be such as cardiovascular disease
The Clinics and Practices of disease etc. provide important parameter foundation.
Existing blood pressure measurement can be divided into invasive blood pressure measurement and non-invasive blood pressure measures two major classes, wherein：Invasive blood pressure
It measures and needs the main artery of the conduit insertion measurement object of pressure sensor or heart to detect blood pressure signal, measurement result
Precisely, but time is long, requires high to testee and easily causes complication；Non-invasive blood pressure measures generally by contacting human body table
Layer obtains characteristic signal progress analyzing processing and obtains blood pressure, wound will not be brought to testee, therefore non-invasive measurement method is more suitable for
The demand of conventional blood pressure measurement.
Blood pressure it is automatic continuous measurement medically have great practical significance, such as on clinical medicine to urgent patient with
Patient with severe symptoms in operation is required for carrying out the continuous monitoring of blood pressure, once so that the unexpected medical staff of patient's appearance can
Effective rescue measure is taken in time.Existing such as Ke Shi auditions method, oscillographic method, angiosthenia method, volume-compensation method are noninvasive
Blood pressure measuring method is limited due to the factors such as being restored by blood vessel elasticity, cannot all be carried out blood pressure and continuously be monitored.
It is commonly based on volume pulsation wave at present, noninvasive continuous monitoring is carried out to the blood pressure of measurement object, this kind of method is main
It is to be realized by establishing volume pulsation wave conduction time and the model of blood pressure correlation.However, this blood pressure measurement model tool
Have certain limitation, can be only applied to it is consistent with modeling environment under conditions of.Because only that in feelings similar with modeling environment
Under condition, characterization will not just change with relevant coefficients of characteristics such as blood vessel viscosity, elasticity in blood pressure measurement model.But in reality
In the application of border, the behavior pattern and intensity of performance of testee constantly change, measuring environment and having differences property of modeling environment, blood vessel
The vessel properties parameter such as viscosity and elasticity morphs, and blood pressure measurement model is caused with validity, not need continuous school
Positive model coefficient could carry out subsequent blood pressure and effectively measure, and cannot be satisfied the need of health control and the monitoring of blood pressure continuous measurement
It asks.
Invention content
The present invention provides a kind of self-calibration system for blood pressure measurement, certain or certain of the prior art can be overcome
A little defects.
Self-calibration system according to the present invention for blood pressure measurement comprising blood pressure collecting unit, human body attitude acquisition
Unit and processing unit, blood pressure collecting unit is for acquiring human blood-pressure detection signal, and human body attitude collecting unit is for acquiring
Human motion signal is equipped with blood pressure detecting model, human body attitude identification model at processing unit and describes human body difference behavior
The list of feature values of blood pressure detecting model coefficient under pattern；Processing unit according to human motion signal by human body attitude for being identified
Model Identification goes out the behavior pattern of current human, and brings corresponding coefficient into blood pressure detecting model according to the list of feature values, in turn
Signal is detected according to human blood-pressure, and human blood-pressure detected value is obtained by blood pressure detecting model.
In the present invention, detection can be synchronized to the behavior pattern of human body at this time when carrying out blood pressure detecting to human body,
It is enable to be brought different coefficients in blood pressure detecting model into according to the different behavior patterns of human body, so as to have
Effect ground reduces the otherness between measuring environment and modeling environment, realizes to the automatic calibration in blood pressure measurement, and then can
Preferably realize the continuous measurement to blood pressure.
Preferably, blood pressure collecting unit includes the photoelectric sensor for acquiring human body volume pulsation wave.With reference to bulletin
Number be CN107157461A Chinese invention patent, the present invention in pressure value it is continuous measurement can only need acquisition single-point light
Power Capacity pulse wave signal, you can preferably obtain systolic pressure SBP and diastolic pressure, thus greatly reduce signal acquisition difficulty,
Measurement comfort level is preferably improved, and prediction model result precision is higher, to realize continuous blood pressure monitoring well.
Preferably, human body attitude collecting unit includes 3-axis acceleration sensor, three axis geomagnetic sensors and three axis tops
Spiral shell instrument sensor, 3-axis acceleration sensor are used to acquire the acceleration information generated during human motion, and three axis earth magnetism pass
Sensor is used to acquire the magnetic field data generated during human motion, and three-axis gyroscope sensor is for acquiring human motion process
The angular velocity data of middle generation.So as to which preferably the current behavior pattern of human body is identified.
Preferably, connecting an output unit at control unit, output unit is used to carry out the pressure value of current detection
Output.So as to be convenient for data to export.
Preferably, control unit is attached with a cloud server, human body attitude identification model and the list of feature values are equal
It is stored at cloud server.So as to preferably facilitate the storage and processing of data.
Based on above-mentioned any self-calibration system for blood pressure measurement, the present invention also provides one kind to survey for blood pressure
The method for self-calibrating of amount comprising following steps：
Step 1 acquires human blood-pressure by a blood pressure collecting unit and detects signal, and according to blood pressure measured value, establishes people
Blood pressure detecting model between body blood pressure detecting signal and pressure value；
Step 2 acquires human motion signal by a human body attitude collecting unit, and according to human body agenda pattern,
Establish the human body attitude identification model between human motion signal and human body behavior pattern；
Step 3, the coefficient of correspondence value of blood pressure detecting model when acquisition human body is in different behavior patterns, to establish
The list of feature values；
Step 4, after the completion of blood pressure detecting model, human body attitude identification model and the list of feature values are established, to human body blood
When pressure is detected, while human blood-pressure detection signal is acquired by blood pressure collecting unit and passes through human body attitude collecting unit
Human motion signal is acquired, later by a control unit according to human motion signal identification human body current behavior pattern, in turn
By the list of feature values by corresponding coefficient update to blood pressure detecting model, signal and update are detected according to human blood-pressure later
Blood pressure detecting model after coefficient obtains human blood-pressure measured value.
Method through the invention can to human body carry out blood pressure detecting when behavior pattern synchronize detection, thus
Make it possible to be brought different coefficients in blood pressure detecting model into according to the different behavior patterns of human body, so as to effectively
The otherness between measuring environment and modeling environment is reduced, is realized to the automatic calibration in blood pressure measurement, and then can be preferable
Realize the continuous measurement to blood pressure in ground.
Preferably, blood pressure collecting unit acquires human body volume pulsation wave by photoelectric sensor is used as human blood-pressure detection
Signal.So as to realize continuous blood pressure monitoring well.
Preferably, human body attitude collecting unit passes through 3-axis acceleration sensor, three axis geomagnetic sensors and three axis tops
Spiral shell instrument sensor acquires the magnetic field number generated during the acceleration information generated during human motion, human motion respectively
According to the angular velocity data with generation during human motion as human motion signal.
Preferably, control unit exports the pressure value of current detection by an output unit.So as to just
It is exported in data.
Preferably, control unit and a cloud server carry out data interaction, and by human body attitude identification model and spy
Value indicative table is stored at cloud server.So as to preferably facilitate the storage and processing of data.
Description of the drawings
Fig. 1 is the system block diagram schematic diagram of the self-calibration system for blood pressure measurement in embodiment 1；
Fig. 2 is the foundation of the human body attitude identification model in embodiment 1 and the system block diagram schematic diagram of identifying system；
Fig. 3 is the system block diagram schematic diagram of the attitude algorithm unit in embodiment 1；
Fig. 4 is a kind of flow diagram of method for self-calibrating for blood pressure measurement in embodiment 1；
Fig. 5 is foundation and the recognition methods flow diagram of the human body attitude identification model in embodiment 1.
Specific implementation mode
To further appreciate that present disclosure, the present invention is described in detail in conjunction with the accompanying drawings and embodiments.It should be understood that
, embodiment be only to the present invention explain and and it is non-limiting.
Embodiment 1
As shown in Figure 1, present embodiments providing a kind of self-calibration system for blood pressure measurement comprising blood pressure acquisition is single
Member, human body attitude collecting unit and processing unit, blood pressure collecting unit are adopted for acquiring human blood-pressure detection signal, human body attitude
Collection unit is equipped with blood pressure detecting model, human body attitude identification model and record for acquiring human motion signal at processing unit
The list of feature values of blood pressure detecting model coefficient under human body difference behavior pattern；Processing unit is used for logical according to human motion signal
The behavior pattern that human body gesture recognition Model Identification goes out current human is crossed, and blood pressure into is brought corresponding coefficient according to the list of feature values
Detection model, and then signal is detected according to human blood-pressure, human blood-pressure detected value is obtained by blood pressure detecting model.
In the present embodiment, inspection can be synchronized to the behavior pattern of human body at this time when carrying out blood pressure detecting to human body
It surveys, is enable to be brought different coefficients in blood pressure detecting model into according to the different behavior patterns of human body, so as to
The otherness being enough effectively reduced between measuring environment and modeling environment is realized to the automatic calibration in blood pressure measurement, in turn
It can preferably realize the continuous measurement to blood pressure.
In the present embodiment, blood pressure collecting unit includes the photoelectric sensor for acquiring human body volume pulsation wave.
With reference to the Chinese invention patent that notification number is CN107157461A, to the continuous measurement energy of pressure value in the present embodiment
It is enough only to need to acquire single-point photoplethysmographic signal, you can systolic pressure SBP and diastolic pressure preferably to be obtained, to drop significantly
Low signal acquisition difficulty preferably improves measurement comfort level, and prediction model result precision is higher, to real well
Continuous blood pressure monitoring is showed.
In the present embodiment, human body attitude collecting unit includes 3-axis acceleration sensor, three axis geomagnetic sensors and three axis
Gyro sensor, 3-axis acceleration sensor are used to acquire the acceleration information generated during human motion, three axis earth magnetism
Sensor is used to acquire the magnetic field data generated during human motion, and three-axis gyroscope sensor is for acquiring human motion
The angular velocity data generated in journey.
In the present embodiment, human body attitude collecting unit can be used in incuding the limb action of human body, such as waves, bounces, goes
It walks, jump, by can preferably identify that user is current ongoing dynamic to the rule action of human body difference limbs
Make.
In conjunction with Fig. 2,3-axis acceleration sensor, three axis geomagnetic sensors and three-axis gyroscope sensor in the present embodiment
It is all made of MEMS sensor, so as to preferably carry out real-time capture record to human motion.And since 3-axis acceleration passes
Sensor, three axis geomagnetic sensors and three-axis gyroscope sensor can be integrated in simultaneously at a human body wearable device, by by people
Body wearable device is set to the different location of user, you can it preferably realizes to the athletic posture detection at human body corresponding site,
The detection to human body behavior pattern can be preferably realized by dressing multiple human body wearable devices.
Wherein, a number for carrying out data processing to human body attitude collecting unit can also be equipped at human body wearable device
According to processing module, certain data processing module can be also set at control unit.
In the present embodiment, data processing module includes that data pre-processing unit, state transition diagram establish unit, attitude algorithm
Unit, the first weight calculation unit, integrated classification unit and the second weight calculation unit；Data pre-processing unit is used for three axis
The signal that acceleration transducer, three axis geomagnetic sensors and three-axis gyroscope sensor are acquired is pre-processed, and is extracted
Multiple characteristic points；State transition diagram establishes unit for shifting graph model according to the foundation of the multiple characteristic point or matching status；
Attitude algorithm unit is used for carrying out attitude algorithm through data pre-processing unit treated data, to obtain human body three-dimensional posture
Information；First weight calculation unit is used to carry out one or more of the multiple characteristic point and human body three-dimensional posture information
Weighted calculation, integrated classification unit are used to establish or match according to weighing computation results human body attitude and presort model；Second adds
Power computing unit is used to that the presort matching result of model of state transition diagram model and human body attitude to be weighted, to
Establish or match human body attitude identification model.
In the present embodiment, body motion information can be acquired using human body attitude collecting unit, so as to obtain correlation
It is special can to extract multiple frequency domains, time domain, time-frequency using existing sliding window method from signal waveform later for the waveform of data
Point is levied, while attitude algorithm module can be utilized to obtain human body three-dimensional posture information, that is, human motion three-dimensional attitude angle；It
Can extract the characteristic value of Partial Feature point afterwards and three-dimensional attitude angle be weighted and by integrated classification algorithm into
Row training is simultaneously matched with human body actual motion posture, you can and it preferably obtains human body attitude and presorts model, so as to
Establish preliminary transition states model and steady-state model；Simultaneously, according to the feature vector variation relation for the characteristic point extracted,
State transition diagram model can be established.Later, it is presorted the weight of model and state transition diagram model by the way that human body attitude is arranged
Than, you can preferably obtain human body attitude identification model.
In the present embodiment, weight ratio used by the first weight calculation unit and the second weight calculation unit is according to mould
Type predicted value passes through certain comparative analysis with measured value, is obtained after Mathematical treatment.
After the completion of above-mentioned model foundation, data that human body attitude collecting unit is acquired can be with the model established
It is matched, so as to preferably obtain human motion posture.So as to realize the automatic continuous identification of human motion, and
Human body behavior pattern can be finally inversed by according to recognition result.
In the present embodiment, at integrated classification unit with integrated classification algorithm be combine KNN (k-Nearest
Neighbor) algorithm and SVM (Support Vector Machine) algorithm.The thinking of KNN algorithms is：If a sample exists
Most of in k in feature space most like samples (i.e. closest in feature space) belong to some classification, then this
Sample also belongs to this classification, and SVM is that sample space is mapped to a higher-dimension or even nothing by a Nonlinear Mapping p
In the feature space tieed up thoroughly so that the problem of Nonlinear separability is converted into the line in feature space in original sample space
The problem of property can divide.By the way that the two to be combined, effectively the stable state of human body and transition state action can be identified, and
The diversity of feature vector can be kept simultaneously, so that iteration can all retain the characteristic quantity between sample and update judgement every time
Standard will generate the feature vector of optimal matching degree after successive ignition, and the stability of blending algorithm is stronger.
In the present embodiment, the foundation of steady-state model is the features described above vector (packet first extracted under each steady state of motion
The human body three-dimensional posture information for including the multiple characteristic values extracted and calculating), using integrated classification algorithm to feature vector into
Row training fitting, corrects each steady state of motion and distinguishes matched feature vector, finally obtain the feature of the measurement object
The relational model of vector and steady state of motion.
In the present embodiment, transition states model be by establish features described above vector (including the multiple characteristic values extracted and
The human body three-dimensional posture information calculated) with the non-linear real-time relationship of transition state, pass through large sample and iteratively solve relationship mould
Delay parameter in type and unknowm coefficient.
In the present embodiment, steady state of motion, which refers to, to be repeated within opposite a period of time, continues, identical activity, such as static,
Continuous running etc.；Unsteady motion state refers to existence migration and conversion, such as runs to standing still, and lies down to sitting up.
In the present embodiment, human body current state during the motion can be preferably represented by establishing state transition diagram
With the conversion relations between front and back state.
In the present embodiment, it can preferably handle to obtain the current 3 d pose information of human body i.e. by attitude algorithm unit
Three-dimensional attitude angle can preferably extract 3-axis acceleration sensor by data pre-processing unit, three axis earth magnetism pass
Multiple frequency domains during sensor and three-axis gyroscope sensor are signal collected, time domain, time-frequency characteristics point, by the multiple spy
One or more of sign point is weighted processing with 3 d pose information, can preferably promote the accuracy of recognition result.
In the present embodiment, 3-axis acceleration sensor, three axis geomagnetic sensors and three-axis gyroscope sensor can be real-time
Ground is detected the motion state of human body, and can generate acceleration change waveform, magnetic force change waveform and gyroscope waveform,
Data pre-processing unit can be pre-processed and extracted to acceleration change waveform, magnetic force change waveform and gyroscope waveform
Correlated characteristic point, and then convenient for the subsequent processing of data.
In conjunction with Fig. 3, the attitude algorithm unit in the present embodiment includes complementary filter unit and Quaternion Algorithm unit, complementation
Filter unit includes the median filter unit of the data progress median filter process for being acquired to 3-axis acceleration sensor,
The self calibration unit that data for being acquired to three axis geomagnetic sensors are calibrated, for what is acquired to three-axis gyroscope
Data carry out the mean filter unit of mean filter processing, for the data handled by median filter unit and self calibration unit
The normalized unit being normalized, and for handled by normalized unit and mean filter unit
Data carry out Data Fusion to obtain the data fusion unit of quaternary number；Quaternion Algorithm unit is used for complementary filter list
Quaternary number acquired in member is handled, to obtain human body three-dimensional posture information.
In the present embodiment, 3-axis acceleration sensor, three axis geomagnetic sensors and three-axis gyroscope sensor are into rower
After fixed, 3-axis acceleration sensor can use median filter unit progress medium filtering to add so as to effective filter out three axis
Pulse error during velocity sensor is signal collected, the later letter by being acquired with three axis geomagnetic sensors after self calibration
Number be normalized, and with through mean filter, treated that three-axis gyroscope signal carries out data fusion, can be effectively
Signal collected dynamic property and static accuracy are promoted, to preferably ensure that the real-time and precision of institute's gathered data.
Can include as accelerated to the feature point extraction of the signal collected waveform of 3-axis acceleration sensor in the present embodiment
Mean value, variance, zero-crossing rate are spent, mean square deviation etc. can wrap the feature point extraction of the three signal collected waveforms of axis geomagnetic sensor
It includes such as the angle degree of bias, kurtosis etc., can include such as Fu to the feature point extraction of the signal collected waveform of three-axis gyroscope sensor
In acceleration DC component after leaf transformation, power spectral density, angular speed amplitude, frequency, DC component etc..
In the present embodiment, connect an output unit at control unit, output unit be used for the pressure value of current detection into
Row output.So as to be convenient for data to export.
In the present embodiment, control unit is attached with a cloud server, human body attitude identification model and the list of feature values
It is stored at cloud server.So as to preferably facilitate the storage and processing of data.
As shown in figure 4, a kind of self-calibration system for blood pressure measurement based on the present embodiment, the present embodiment additionally provide
A kind of method for self-calibrating for blood pressure measurement comprising following steps：
Step 1 acquires human blood-pressure by a blood pressure collecting unit and detects signal, and according to blood pressure measured value, establishes people
Blood pressure detecting model between body blood pressure detecting signal and pressure value；
Step 2 acquires human motion signal by a human body attitude collecting unit, and according to human body agenda pattern,
Establish the human body attitude identification model between human motion signal and human body behavior pattern；
Step 3, the coefficient of correspondence value of blood pressure detecting model when acquisition human body is in different behavior patterns, to establish
The list of feature values；
Step 4, after the completion of blood pressure detecting model, human body attitude identification model and the list of feature values are established, to human body blood
When pressure is detected, while human blood-pressure detection signal is acquired by blood pressure collecting unit and passes through human body attitude collecting unit
Human motion signal is acquired, later by a control unit according to human motion signal identification human body current behavior pattern, in turn
By the list of feature values by corresponding coefficient update to blood pressure detecting model, signal and update are detected according to human blood-pressure later
Blood pressure detecting model after coefficient obtains human blood-pressure measured value.
Method through this embodiment can to human body carry out blood pressure detecting when behavior pattern synchronize detection, from
And make it possible to be brought different coefficients in blood pressure detecting model into according to the different behavior patterns of human body, so as to effective
Ground reduces the otherness between measuring environment and modeling environment, realizes to the automatic calibration in blood pressure measurement, and then can be compared with
The continuous measurement to blood pressure is realized goodly.
In the present embodiment, blood pressure collecting unit acquires human body volume pulsation wave by photoelectric sensor and is used as human blood-pressure inspection
Survey signal.It is introduced into notification number herein as the full content in the Chinese invention patent of CN107157461A, in the present embodiment, uses
Method identical with the patent application realizes the continuous detection to blood pressure.Thus greatly reduce signal acquisition difficulty, preferably
Ground improves measurement comfort level, and prediction model result precision is higher, can realize continuous blood pressure monitoring well.
In the present embodiment, human body attitude collecting unit passes through 3-axis acceleration sensor, three axis geomagnetic sensors and three axis
Gyro sensor acquires the magnetic field generated during the acceleration information generated during human motion, human motion respectively
The angular velocity data generated during data and human motion is as human motion signal.
It is foundation and the recognition methods flow diagram of the human body attitude identification model in the present embodiment in conjunction with shown in Fig. 5.
In the present embodiment, the method that human body attitude is identified is included the following steps：
Step 1 acquires body motion information by human body attitude collecting unit；
Step 2, the data acquired to human body attitude collecting unit by data processing module are handled, and will place
Result after reason is matched with human body attitude identification model, to obtain human motion attitude prediction result；
In the step, human body attitude identification model is initially set up, it can be according to people after the foundation of human body attitude identification model
The information that body Posture acquisition unit is acquired is matched with human body attitude identification model to obtain human body current behavior pattern；
In the foundation of human body attitude identification model and when being matched to body motion information, pass through a data prediction list
The signal that member acquires human body attitude collecting unit pre-processes, and extracts multiple characteristic points；It is shifted by a state
Figure establish unit established according to the multiple characteristic point or matching status transfer graph model；By an attitude algorithm unit to through number
Data after Data preprocess cell processing carry out attitude algorithm, to obtain human body three-dimensional posture information；It is counted by one first weighting
It calculates unit one or more of the multiple characteristic point and human body three-dimensional posture information is weighted, passes through a fusion
Taxon is established or is matched human body attitude according to weighing computation results and presorts model；Pass through one second weight calculation unit pair
The presort matching result of model of state transition diagram model and human body attitude is weighted, and then establishes or matching human body appearance
State identification model.
In the present embodiment, in step 1, using the acceleration generated during 3-axis acceleration sensor acquisition human motion
Degrees of data is sensed using the magnetic field data generated during the acquisition human motion of three axis geomagnetic sensors using three-axis gyroscope
Device acquires the angular velocity data and angle-data generated during human motion.
In the present embodiment, in step 2,3-axis acceleration sensor, three axis earth magnetism are passed using a data pre-processing unit
The signal that sensor and three-axis gyroscope sensor are acquired is pre-processed, and is extracted multiple characteristic points and be sent to a processing list
Member；Using an attitude algorithm unit to carrying out attitude algorithm through data pre-processing unit treated data, to obtain human body three
Dimension posture information is simultaneously sent to processing unit；Through the processing unit to one or more of the multiple characteristic point and three-dimensional appearance
State information, which is weighted, to be handled and is matched with human body attitude identification model to obtain human body behavior pattern prediction result.
In the present embodiment, when attitude algorithm unit through data pre-processing unit treated data to carrying out attitude algorithm,
Using a complementary filter unit to the data of 3-axis acceleration sensor, three axis geomagnetic sensors and three-axis gyroscope sensor into
Row handles and obtains quaternary number, is handled the quaternary number acquired in complementary filter unit using a Quaternion Algorithm unit,
To obtain human body three-dimensional posture information.
In the present embodiment, when being handled related data using complementary filter unit, using a median filter unit pair
The data that 3-axis acceleration sensor is acquired carry out median filter process, using three axis geomagnetic sensor of a self calibration unit pair
The data acquired are calibrated, and the data acquired to three-axis gyroscope using a mean filter unit are carried out at mean filter
Reason, is normalized using the data handled by a normalized cell pairs value filtering unit and self calibration unit
, the data handled by normalized unit and mean filter unit are carried out at data fusion using a data fusion unit
Reason is to obtain quaternary number.
Human motion gesture recognition method in through this embodiment so that in human motion, 3-axis acceleration sensing
Device can acquire the acceleration information of human motion, and three axis geomagnetic sensors can acquire the magnetic field number during human motion
According to three-axis gyroscope sensor can acquire the angular speed and angle-data of human motion；Later, 3-axis acceleration can be passed
Sensor, three axis geomagnetic sensors and the signal collected waveform of three-axis gyroscope sensor are pre-processed and extract multiple frequencies
Domain, time domain, time-frequency characteristics point；Later, median filter process can be carried out to the data that 3-axis acceleration sensor acquires, to three
The data of axis geomagnetic sensor acquisition carry out self calibration, and the data acquired to three-axis gyroscope sensor carry out medium filtering；
Later, place is normalized in the data that can be acquired treated 3-axis acceleration sensor and three axis geomagnetic sensors
Reason, and three-axis gyroscope sensor institute gathered data carries out data fusion with treated, so as to obtain quaternary number；It
Afterwards, Quaternion Algorithm can be used to carry out quaternary number calculating to acquired quaternary number, so as to obtain human body three-dimensional posture
Information, i.e. the three-dimensional attitude angle of human motion；It later, can be by acquired three-dimensional attitude angle and adopted characteristic point
One or more of characteristic value be weighted processing, and matched with the human body attitude identification model established, to
It can preferably the athletic posture current to human body be identified.
In the present embodiment, the relevant parameter and human body that human body attitude identification model is acquired when being according to human motion are practical
Athletic posture and establish.Pass through, acquisition and treated data and human body attitude identification model are carried out match can be preferable
The current kinetic posture to human body be identified.
In the present embodiment, 3-axis acceleration sensor, three axis geomagnetic sensors and three-axis gyroscope sensor can be passed through
It realizes the acquisition to human body movement data, the data acquired can be pre-processed simultaneously by data pre-processing unit later
Extract characteristic quantity, after can pass through attitude algorithm unit through data pre-processing unit treated data and carry out posture solution
It calculates.Wherein, when establishing model, can be added according to one or more of extracted characteristic quantity and the result of attitude algorithm
Human body attitude is established after power processing with the practical posture of human body to presort model, variation that can be according to extracted characteristic quantity and human body
Practical attitudes vibration establishes state transition diagram model, and the model that can be presorted according to state transition diagram model and human body attitude
Weighted value is set, human body attitude identification model is established out.It wherein, can be according in extracted characteristic quantity when identifying posture
It is one or more be weighted with the result of attitude algorithm handle after matched with human body attitude model of presorting, being capable of basis
Extracted characteristic quantity is matched with state transition diagram model, and can be according to the matching result and human body of state transition diagram model
The presort matching result of model of posture carries out weight calculation, and then obtains human body by matching human body attitude identification model and works as
Preceding posture.
Method through this embodiment can realize that the movement to human body stable state and transition state identifies.
In the present embodiment, control unit exports the pressure value of current detection by an output unit.So as to
It is exported convenient for data.
In the present embodiment, control unit and a cloud server carry out data interaction, and by human body attitude identification model and
The list of feature values is stored at cloud server.So as to preferably facilitate the storage and processing of data.
Schematically the present invention and embodiments thereof are described above, description is not limiting, institute in attached drawing
What is shown is also one of embodiments of the present invention, and actual structure is not limited to this.So if the common skill of this field
Art personnel are enlightened by it, without departing from the spirit of the invention, are not inventively designed and the technical solution
Similar frame mode and embodiment, are within the scope of protection of the invention.
Claims (10)
1. the self-calibration system for blood pressure measurement, it is characterised in that：Including blood pressure collecting unit, human body attitude collecting unit and
Processing unit, blood pressure collecting unit is for acquiring human blood-pressure detection signal, and human body attitude collecting unit is for acquiring human body fortune
Signal is moved, blood pressure detecting model, human body attitude identification model are equipped at processing unit and is described under human body difference behavior pattern
The list of feature values of blood pressure detecting model coefficient；Processing unit according to human motion signal by human body attitude identification model for being known
Do not go out the behavior pattern of current human, and blood pressure detecting model into is brought corresponding coefficient according to the list of feature values, and then according to people
Body blood pressure detecting signal obtains human blood-pressure detected value by blood pressure detecting model.
2. the self-calibration system according to claim 1 for blood pressure measurement, it is characterised in that：Blood pressure collecting unit includes
Photoelectric sensor for acquiring human body volume pulsation wave.
3. the self-calibration system according to claim 1 for blood pressure measurement, it is characterised in that：Human body attitude collecting unit
Including 3-axis acceleration sensor, three axis geomagnetic sensors and three-axis gyroscope sensor, 3-axis acceleration sensor is for adopting
Collect the acceleration information generated during human motion, three axis geomagnetic sensors are used to acquire the magnetic generated during human motion
Field data, three-axis gyroscope sensor are used to acquire the angular velocity data generated during human motion.
4. the self-calibration system according to claim 1 for blood pressure measurement, it is characterised in that：One is connected at control unit
Output unit, output unit is for exporting the pressure value of current detection.
5. the self-calibration system according to claim 1 for blood pressure measurement, it is characterised in that：Control unit and a high in the clouds
Server is attached, and human body attitude identification model and the list of feature values are stored at cloud server.
6. the method for self-calibrating for blood pressure measurement comprising following steps：
Step 1 acquires human blood-pressure by a blood pressure collecting unit and detects signal, and according to blood pressure measured value, establishes human body blood
Blood pressure detecting model between pressure detection signal and pressure value；
Step 2 acquires human motion signal by a human body attitude collecting unit, and according to human body agenda pattern, establishes
Human body attitude identification model between human motion signal and human body behavior pattern；
Step 3, the coefficient of correspondence value of blood pressure detecting model when acquisition human body is in different behavior patterns, to establish feature
It is worth table；
Step 4, after the completion of blood pressure detecting model, human body attitude identification model and the list of feature values are established, to human blood-pressure into
When row detection, while human blood-pressure detection signal is acquired by blood pressure collecting unit and is acquired by human body attitude collecting unit
Human motion signal later by a control unit according to human motion signal identification human body current behavior pattern, and then passes through
The list of feature values detects signal and update coefficient according to human blood-pressure later by corresponding coefficient update to blood pressure detecting model
Blood pressure detecting model afterwards obtains human blood-pressure measured value.
7. the method for self-calibrating according to claim 6 for blood pressure measurement, it is characterised in that：Blood pressure collecting unit passes through
Photoelectric sensor acquires human body volume pulsation wave and detects signal as human blood-pressure.
8. the method for self-calibrating according to claim 6 for blood pressure measurement, it is characterised in that：Human body attitude collecting unit
By 3-axis acceleration sensor, three axis geomagnetic sensors and three-axis gyroscope sensor, respectively during acquisition human motion
The angular velocity data that the magnetic field data and human motion that the acceleration information of generation, human motion generate in the process generate in the process
As human motion signal.
9. the method for self-calibrating according to claim 6 for blood pressure measurement, it is characterised in that：Control unit is defeated by one
Go out unit to export the pressure value of current detection.
10. the method for self-calibrating according to claim 6 for blood pressure measurement, it is characterised in that：Control unit and a cloud
It holds server to carry out data interaction, and human body attitude identification model and the list of feature values is stored at cloud server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810616479.XA CN108523868A (en) | 2018-06-15 | 2018-06-15 | Self-calibration system and method for blood pressure measurement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810616479.XA CN108523868A (en) | 2018-06-15 | 2018-06-15 | Self-calibration system and method for blood pressure measurement |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108523868A true CN108523868A (en) | 2018-09-14 |
Family
ID=63471061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810616479.XA Pending CN108523868A (en) | 2018-06-15 | 2018-06-15 | Self-calibration system and method for blood pressure measurement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108523868A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109893110A (en) * | 2019-03-06 | 2019-06-18 | 深圳市理邦精密仪器股份有限公司 | A kind of method and device for calibrating ambulatory blood pressure |
| CN109893111A (en) * | 2019-03-06 | 2019-06-18 | 深圳市理邦精密仪器股份有限公司 | A kind of ambulatory blood pressure measurement pattern selection method and device |
| WO2020135725A1 (en) * | 2018-12-29 | 2020-07-02 | 中兴通讯股份有限公司 | Apparatus and electronic device for calculating blood pressure |
| CN113545762A (en) * | 2020-04-23 | 2021-10-26 | 疆域康健创新医疗科技成都有限公司 | Blood pressure measuring method and blood pressure measuring device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09220207A (en) * | 1996-02-19 | 1997-08-26 | Omron Corp | Blood pressure calculation device |
| JP2005261966A (en) * | 2005-05-12 | 2005-09-29 | Colin Medical Technology Corp | Oscillometric automatic blood pressure measuring apparatus |
| WO2014101466A1 (en) * | 2012-12-27 | 2014-07-03 | 深圳迈瑞生物医疗电子股份有限公司 | Blood pressure gauge |
| CN104138253A (en) * | 2013-05-11 | 2014-11-12 | 吴健康 | Noninvasive continuous arterial blood pressure measuring method and equipment |
| CN106725495A (en) * | 2017-01-13 | 2017-05-31 | 深圳先进技术研究院 | A kind of fall detection method, apparatus and system |
| WO2018030380A1 (en) * | 2016-08-10 | 2018-02-15 | 株式会社村田製作所 | Blood pressure state measurement device |
-
2018
- 2018-06-15 CN CN201810616479.XA patent/CN108523868A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09220207A (en) * | 1996-02-19 | 1997-08-26 | Omron Corp | Blood pressure calculation device |
| JP2005261966A (en) * | 2005-05-12 | 2005-09-29 | Colin Medical Technology Corp | Oscillometric automatic blood pressure measuring apparatus |
| WO2014101466A1 (en) * | 2012-12-27 | 2014-07-03 | 深圳迈瑞生物医疗电子股份有限公司 | Blood pressure gauge |
| CN104138253A (en) * | 2013-05-11 | 2014-11-12 | 吴健康 | Noninvasive continuous arterial blood pressure measuring method and equipment |
| WO2018030380A1 (en) * | 2016-08-10 | 2018-02-15 | 株式会社村田製作所 | Blood pressure state measurement device |
| CN106725495A (en) * | 2017-01-13 | 2017-05-31 | 深圳先进技术研究院 | A kind of fall detection method, apparatus and system |
Non-Patent Citations (1)
| Title |
|---|
| 潘婉苏;李晓风;许金林;李皙茹;程龙乐;: "基于MEMS的人体行为特征反演系统设计", 计算机技术与发展, no. 10, pages 13 - 16 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020135725A1 (en) * | 2018-12-29 | 2020-07-02 | 中兴通讯股份有限公司 | Apparatus and electronic device for calculating blood pressure |
| CN109893110A (en) * | 2019-03-06 | 2019-06-18 | 深圳市理邦精密仪器股份有限公司 | A kind of method and device for calibrating ambulatory blood pressure |
| CN109893111A (en) * | 2019-03-06 | 2019-06-18 | 深圳市理邦精密仪器股份有限公司 | A kind of ambulatory blood pressure measurement pattern selection method and device |
| CN109893111B (en) * | 2019-03-06 | 2021-07-23 | 深圳市理邦精密仪器股份有限公司 | Dynamic blood pressure measurement mode selection method and device |
| CN113545762A (en) * | 2020-04-23 | 2021-10-26 | 疆域康健创新医疗科技成都有限公司 | Blood pressure measuring method and blood pressure measuring device |
| CN113545762B (en) * | 2020-04-23 | 2023-12-19 | 疆域康健创新医疗科技成都有限公司 | Blood pressure measuring method and blood pressure measuring device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104127187B (en) | For the wearable system of patient's Parkinson cardinal symptom quantitative determination | |
| US8509886B2 (en) | Cardiac monitoring system | |
| CN103491868B (en) | For cardiac output, stroke output, mental and physical efforts and blood pressure continuously, the body worn formula system of non-invasive measurement | |
| CN105451652B (en) | For determining the processing unit and processing method of the breath signal of object | |
| CN108523868A (en) | Self-calibration system and method for blood pressure measurement | |
| US20090082679A1 (en) | Cardiac monitoring system | |
| Yan et al. | Novel deep convolutional neural network for cuff-less blood pressure measurement using ECG and PPG signals | |
| CN107137071A (en) | It is a kind of to analyze the method that heart impact signal is used for calculating short-term heart beat value | |
| CN108186000A (en) | Real-time blood pressure monitor system and method based on heart impact signal and photosignal | |
| CN103892818A (en) | Non-invasive central aortic blood pressure measuring method and device | |
| CN111631698A (en) | Wearable blood pressure monitoring and correcting method based on motion mode cascade constraint | |
| CN105726000A (en) | Method for calculating heart and vessel functional parameters based on blood pressure and pulses of four limbs | |
| CN107785081A (en) | Calculate method, apparatus, storage medium and the equipment of central hemodynamics index | |
| CN115500800A (en) | Wearable physiological parameter detection system | |
| CN105595983A (en) | Blood pressure measuring device and method for improving blood pressure measuring accuracy | |
| CN106691402A (en) | Fatigue level analysis method and device based on pulse characteristics | |
| CN105534517A (en) | Method for removing vehicle motion noise in three-lead electrocardiosignal | |
| CN107049270A (en) | System and method for measuring pulse wave translation time | |
| CN111419205A (en) | Three-element cuff-free continuous blood pressure detection system based on artificial neural network | |
| CN113907727B (en) | Beat-by-beat blood pressure measurement system and method based on photoplethysmography | |
| CN105796091B (en) | A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise | |
| WO2021184818A1 (en) | Particle filter-based device and method for measuring heart rate of human body beat by beat | |
| KR101744691B1 (en) | Method and Apparatus for Detecting Heartbeat using Ballistocardiogram | |
| JP4882052B2 (en) | Pulse wave diagnosis system using self-organizing map, self-organizing map generating program and generating method | |
| CN209463972U (en) | Self-calibration system for blood pressure measurement |
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 |