CN105550502B - A kind of data processing method based on health monitoring - Google Patents
A kind of data processing method based on health monitoring Download PDFInfo
- Publication number
- CN105550502B CN105550502B CN201510897273.5A CN201510897273A CN105550502B CN 105550502 B CN105550502 B CN 105550502B CN 201510897273 A CN201510897273 A CN 201510897273A CN 105550502 B CN105550502 B CN 105550502B
- Authority
- CN
- China
- Prior art keywords
- mrow
- msubsup
- data
- mover
- value
- 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.)
- Active
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
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Abstract
A kind of data processing method based on health monitoring proposed by the present invention, the collecting method that this method senses more first with multiconductor, ensure that the accuracy of measurement.Secondly, to the multigroup physiological data collected, screened according to Grobus criterion, to remove the rough error data collected.Finally, the data collected are merged by the way that algorithm for estimating and least-squares algorithm in batches is used in combination, reduces different sensors because measurement accuracy is different, the influence to caused by result.The inventive method is advantageous to accurately obtain the physiologic information of user, and for health monitoring system, detection provides effective foundation in real time.
Description
Technical field
The invention belongs to portable medical technical field, more particularly to a kind of data processing method based on health monitoring.
Background technology
Wearable technology is the brand new ideas to grow up recent years, and it is widely used in clinical monitoring, family
Health care, emergent rescue, special population monitoring, Psychological Assessment, athletic training etc..And wearable technology answering in medical domain
With being exactly to blend clothing, the ornaments of daily physiologic information detection technique and the daily wearing of people, so as to not influence user
Under the premise of daily life and guarantee are comfortable, the characteristic parameter of user is detected.But in the physiological parameter detected, by
In various environmental factors, many rough error parameters can be mixed.And during gathered data, the angle of measurement is single, it is impossible to protects
Demonstrate,prove the accuracy of data.
In addition, using single data fusion method in some wearable devices, the physiologic information of collection is handled,
When sensor breaks down, it is impossible to find that gathered data have error in time, user can not be accurately reflected by ultimately resulting in
Physiologic information.
The content of the invention
In order to overcome the above-mentioned deficiencies of the prior art, the present invention proposes a kind of data processing method based on health monitoring.
The method that this method senses more first with multiconductor ensure that the accuracy of measurement, and then the physiological data of collection is sieved
Choosing, fusion, finally obtain one group of data that can accurately reflect user's physiologic information.On the one hand, the multiconductor in this method passes more
There is good theoretical performance to ensure for sensed quantity mode, learning process, and accuracy of measurement is high；On the other hand, it is wearable prison
Control equipment provides a kind of reference scheme of data processing, has good application prospect.
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention is：
A kind of data processing method based on health monitoring, comprises the following steps：
Step 1：The M class physiological datas of person under test are gathered by sensor, use LmIndividual m+1 classes physiological data sensing
Device, gathers the m+1 class physiological datas of person under test, and its detailed process is：
Step 1-1, the 1st collection of physiological data, each sensor measure respectively at different moments in the N number of of same contact,
N group physiological datas are obtained, every group of data are expressed as：
Step 1-2, the 2nd collection of physiological data, each sensor is respectively in LmThe N number of of individual contact measures at different moments,
N group physiological datas are obtained, every group of data are expressed as：
Wherein, M is natural number, according to actual conditions value；M be physiology data type label, 0≤m≤M-1；LmTable
Show the quantity of m+1 class physiological data sensors；N is the group number of each gathered data, and N is LmIntegral multiple；K is every group of data
Label, 0≤k≤N-1；Q is the measured value total number of every group of data；J represents the label of data acquisition order, j ∈ { 1,2 }；i
ForThe label of middle element, 0≤i≤Q-1,ForMiddle i+1 element；
Step 2, to m+1 class physiological datasElement, utilize Grobus criterion carry out first time screening, tool
Body step is as follows：
Step 2-1, calculateMiddle elementArithmetic mean of instantaneous value
And then calculate its standard deviation
Step 2-2, by Ge Luobusi tables of critical values, a critical value d (Q, θ) is chosen, d (Q, θ) size by Q and shows
Work degree θ value determines；Wherein significance θ takes 0.05；
Step 2-3, Ge Luobusi is distributed g (i) and d (Q, θ) and carries out Q times relatively, wherein,If g
(i) >=d (Q, θ),AsIn gross error, give and reject；Result after rejecting is designated asWherein, Q'
ForAfter middle element is screened, the total number of remaining element, Q'≤Q；
Step 3, the data after being screened to first timeElement, first time data fusion is carried out, using estimating in batches
The method of meter, calculate the fusion value of every group of dataSpecific formula is as follows：
Wherein,ForMiddle element superscriptThe average value of element setForAngle on middle element
MarkThe average value of element set,ForMiddle element superscriptThe variance of element set,ForMiddle element superscriptThe variance of element set；Expression is not more thanMaximum integer；
Step 4, for different j, k, each group of data fusion valueDifference, all fusion values are represented with set ψ：Wherein, v be the set ψ in element label, 0≤v≤2N-1；It is sharp again
With Grobus criterion, programmed screening is carried out to element in set ψ, wherein gross error, the result after screening is rejected and is designated as
SetFor the setThe total number of middle element, 0≤Sm≤2N；For the setMiddle element numerals,The setInIndividual element withRepresent；
Step 5, using least square method of weighting, to the setElement carry out second of data fusion, specifically
For：
By the setElement according to formula：
Merged, wherein,For last fusion value,ForWeight coefficient,Calculation formula be：
And weight coefficient meets：Wherein,ForThe standard deviation of element in corresponding array；Last melts
Conjunction valueAs the end value after the processing of m+1 classes physiological data.
Beneficial effect：A kind of data processing method based on health monitoring proposed by the present invention, this method is first with more
The collecting method that contact senses more, ensure that the accuracy of measurement.Secondly, to the multigroup physiological data collected, according to
Grobus criterion is screened, to remove the rough error data collected.Finally, by the way that algorithm for estimating and most in batches is used in combination
Young waiter in a wineshop or an inn's multiplication algorithm merges to the data collected, different sensors is reduced because measurement accuracy is different, to caused by result
Influence.This method be advantageous to accurately obtain user physiologic information, for health monitoring system in real time detect provide effectively according to
According to.
Brief description of the drawings
Fig. 1 is that a kind of data processing method based on health monitoring performs schematic flow sheet.
Fig. 2 is the partial crit value table of Grobus criterion.
Fig. 3 is LS weighted fusion algorithm algorithm model figure.
Embodiment
For a kind of more detailed description data processing method based on health monitoring proposed by the present invention, with reference to attached
Figure, is illustrated below：
Fig. 1 shows that a kind of data processing method based on health monitoring performs schematic flow sheet.This method mainly includes
Three contents：First, the collecting method sensed more using multiconductor, is acquired to user's physiologic information；Second, to collection
The multigroup physiological data arrived, screened twice before and after carrying out；Third, algorithm for estimating in batches and least-squares algorithm is used in combination to sieve
Data after choosing are merged.
1. gathering the M class physiological datas of person under test by sensor, M takes 2, and physiological data can be specially temperature data and blood
Press data.Using infrared sensor and the temperature data of thermistor (temperature) sensor collection person under test, sensed using resistive pressure
Device and the blood pressure data of capacitance pressure transducer, collection person under test, its detailed process are：
1st step：First time single contact gathers, and each sensor measures respectively at different moments in four of same contact, obtains 4
Group physiological data, every group of data are expressed as：
2nd step：Second of multi-contact data collection, each sensor measure at different moments at the four of four contacts respectively,
4 groups of physiological datas are obtained, every group of data are expressed as：
M is the label of physiology data type, because only measuring body temperature and blood pressure parameter, 0≤m≤1；I.e. the first kind is
Temperature data, the second class are blood pressure data.K is the label of every group of data, 0≤k≤3；J represents the label of data acquisition order, j
∈{1,2}；I isThe label of middle element, 0≤i≤3,Middle i+1 element.
It should be noted that collection only gathers 4 groups of data every time for this implementation, every group of data contain 4 measured values, can also
More multi-group data is gathered according to actual conditions, the physiological data of user is acquired from more angles, is because collection
Data are more, and the accuracy of data will be higher, and the health monitoring of user could be accurate.
2. pair multigroup physiological data collected, carry out first time screening：
1st step：The data that collect are carried out with the differentiation and rejecting of gross error using " Grobus criterion "；Specific side
Method is：
CalculateMiddle elementArithmetic mean of instantaneous valueAnd then calculate mark
It is accurate poor：
2nd step：By the tables of critical values of Fig. 2 Grobus criterions, a critical value d (Q, α) is chosen, its size is by Q and α
Value determine；Wherein significance α takes 0.05；Table look-up and understand d (4,0.05)=1.46, g (i) is distributed according to Ge Luobusi：
G (i) and d (4,0.05) is subjected to 4 comparisons, if g (i) >=d (4,0.05),AsIn thick mistake
Difference, give and reject；Result after screening is designated asWherein, Q' isAfter middle element is screened, remaining element
Total number.
3. carrying out first time fusion to each group of data using algorithm for estimating in batches, detailed process is as follows：
Using the method estimated in batches, to every group of dataRespectively according to formula：
The fusion value of data is calculated, wherein,For fusion value,ForMiddle element superscriptElement set
Average value,ForMiddle element superscriptThe average value of element set,ForMiddle element superscriptThe variance of element set,ForMiddle element superscriptThe variance of element set；
4：For different j, k, each group of data fusion valueDifference, all fusion values are represented with set ψ：Wherein, v be the set ψ in element label, 0≤v≤7；Reuse lattice sieve
Buss criterion, programmed screening is carried out to element in set ψ, reject wherein gross error, the result after screening and be designated as gatheringSmFor the setThe total number of middle element, 0≤Sm≤8；To be described
SetMiddle element numerals,The setInIndividual element withRepresent；
It should be noted that the differentiation and rejecting of gross error twice why are carried out, because the processing of first time is
Carried out for single sensor, if one or several sensor degradation therein, the data obtained is to sensor itself without institute
Gross error is called, and fusion results can be drawn, secondary data processing is rejected with regard to that can would detract from bad sensing data
Fall.
5：On the basis of previous step, using least square method of weighting, to setMiddle element carries out second number
According to fusion, detailed process is：
By the setElement according to formula：
Merged, wherein,For last fusion value,ForWeight coefficient,Calculation formula be：：
And weight coefficient meets：ForThe standard deviation of element in corresponding array；Last fusion valueAs the end value after the processing of m+1 classes physiological data, this example is the last processing costs of body temperature, blood pressure.
It is because estimate in batches it should be noted that carrying out secondary fusion to data using LS weighted fusion algorithm algorithm
Meter between the sensor measurement data of equally accurate suitable for being merged, due to using more sensing measurement data, the essence of sensor
Degree is not exclusively the same, in order that the result of fusion is more excellent, so being carried out using minimum weight blending algorithm to data secondary
Fusion.Finally, the data for representing user's physiological parameter are drawn.
Comprehensive foregoing teachings, the execution flow that can obtain this method are：
The first step, the collecting method sensed more using multiconductor, is acquired to user's physiologic information.
Second step, the multigroup physiological data collected, first time data screening is carried out according to Grobus criterion.
3rd step, to every group of data after screening, first time data fusion is carried out using algorithm for estimating in batches.
4th step, to the result after fusion, it is grouped according to measurement parameter classification, organizes the interior secondary data screening of progress.
5th step, to the data after postsearch screening, the secondary fusion of data, last result are carried out using least square method
Represent the final measured value of user's physiological parameter.
Claims (1)
1. a kind of data processing method based on health monitoring, it is characterised in that comprise the following steps：
Step 1：The M class physiological datas of person under test are gathered by sensor, use LmIndividual m+1 class physiological data sensors, collection
The m+1 class physiological datas of person under test, its detailed process are：
Step 1-1, the 1st collection of physiological data, each sensor measure respectively at different moments in the N number of of same contact, obtain N
Group physiological data, every group of data are expressed as：
<mrow>
<msubsup>
<mi>A</mi>
<mrow>
<mn>1</mn>
<mi>k</mi>
</mrow>
<mi>m</mi>
</msubsup>
<mo>&lsqb;</mo>
<mi>Q</mi>
<mo>&rsqb;</mo>
<mo>=</mo>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msubsup>
<mi>a</mi>
<mrow>
<mn>1</mn>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mn>0</mn>
</mrow>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>a</mi>
<mrow>
<mn>1</mn>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mn>1</mn>
</mrow>
</msubsup>
<mo>,</mo>
<mn>....</mn>
<mo>,</mo>
<msubsup>
<mi>a</mi>
<mrow>
<mn>1</mn>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mi>i</mi>
</mrow>
</msubsup>
<mo>,</mo>
<mn>....</mn>
<msubsup>
<mi>a</mi>
<mrow>
<mn>1</mn>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>Q</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</msubsup>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mo>;</mo>
</mrow>
Step 1-2, the 2nd collection of physiological data, each sensor is respectively in LmThe N number of of individual contact measures at different moments, obtains N
Group physiological data, every group of data are expressed as：
<mrow>
<msubsup>
<mi>A</mi>
<mrow>
<mn>2</mn>
<mi>k</mi>
</mrow>
<mi>m</mi>
</msubsup>
<mo>&lsqb;</mo>
<mi>Q</mi>
<mo>&rsqb;</mo>
<mo>=</mo>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msubsup>
<mi>a</mi>
<mrow>
<mn>2</mn>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mn>0</mn>
</mrow>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>a</mi>
<mrow>
<mn>2</mn>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mn>1</mn>
</mrow>
</msubsup>
<mo>,</mo>
<mn>....</mn>
<mo>,</mo>
<msubsup>
<mi>a</mi>
<mrow>
<mn>2</mn>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mi>i</mi>
</mrow>
</msubsup>
<mo>,</mo>
<mn>....</mn>
<msubsup>
<mi>a</mi>
<mrow>
<mn>2</mn>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>Q</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</msubsup>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mo>;</mo>
</mrow>
Wherein, M is natural number, according to actual conditions value；M be physiology data type label, 0≤m≤M-1；LmRepresent m+
The quantity of 1 class physiological data sensor；N is the group number of each gathered data, and N is LmIntegral multiple；K is the mark of every group of data
Number, 0≤k≤N-1；Q is the measured value total number of every group of data；J represents the label of data acquisition order, j ∈ { 1,2 }；I isThe label of middle element, 0≤i≤Q-1,ForMiddle i+1 element；
Step 2, to m+1 class physiological datasElement, utilize Grobus criterion to carry out first time screening, specific step
It is rapid as follows：
Step 2-1, calculateMiddle elementArithmetic mean of instantaneous value
And then calculate its standard deviation
<mrow>
<msubsup>
<mi>&sigma;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mi>m</mi>
</msubsup>
<mo>=</mo>
<msqrt>
<mfrac>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>Q</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>a</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mi>i</mi>
</mrow>
</msubsup>
<mo>-</mo>
<mover>
<msubsup>
<mi>a</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mi>m</mi>
</msubsup>
<mo>&OverBar;</mo>
</mover>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mrow>
<mi>Q</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mfrac>
</msqrt>
<mo>;</mo>
</mrow>
Step 2-2, by Ge Luobusi tables of critical values, a critical value d (Q, θ) is chosen, d (Q, θ) size is by Q and significance
θ value determines；Wherein significance θ takes 0.05；
Step 2-3, Ge Luobusi is distributed g (i) and d (Q, θ) and carries out Q times relatively, wherein,If g (i) >=
D (Q, θ),AsIn gross error, give and reject；Result after rejecting is designated asWherein, Q' isAfter middle element is screened, the total number of remaining element, Q'≤Q；
Step 3, the data after being screened to first timeElement, carry out first time data fusion, using what is estimated in batches
Method, calculate the fusion value of every group of dataSpecific formula is as follows：
<mrow>
<msubsup>
<mi>R</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mi>m</mi>
</msubsup>
<mo>=</mo>
<mfrac>
<mrow>
<msubsup>
<mi>&sigma;</mi>
<mi>e</mi>
<mn>2</mn>
</msubsup>
<mover>
<mi>f</mi>
<mo>&OverBar;</mo>
</mover>
<mo>+</mo>
<msubsup>
<mi>&sigma;</mi>
<mi>f</mi>
<mn>2</mn>
</msubsup>
<mover>
<mi>e</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
<mrow>
<msubsup>
<mi>&sigma;</mi>
<mi>e</mi>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<msubsup>
<mi>&sigma;</mi>
<mi>f</mi>
<mn>2</mn>
</msubsup>
</mrow>
</mfrac>
</mrow>
Wherein,ForMiddle element superscriptThe average value of element set,ForMiddle element superscriptThe average value of element set,ForMiddle element superscriptThe variance of element set,For
Middle element superscriptThe variance of element set；Expression is not more thanMaximum integer；
Step 4, for different j, k, each group of data fusion value is different, and all fusion values are represented with set ψ：
<mrow>
<mi>&psi;</mi>
<mo>=</mo>
<mo>{</mo>
<msubsup>
<mi>R</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mn>0</mn>
</mrow>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>R</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mn>1</mn>
</mrow>
</msubsup>
<mo>,</mo>
<mn>....</mn>
<mo>,</mo>
<msubsup>
<mi>R</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mi>v</mi>
</mrow>
</msubsup>
<mo>,</mo>
<mn>....</mn>
<msubsup>
<mi>R</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
<mrow>
<mi>m</mi>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</msubsup>
<mo>}</mo>
<mo>;</mo>
</mrow>
Wherein, v be the set ψ in element label, 0≤v≤2N-1；It is sharp again
With Grobus criterion, programmed screening is carried out to element in set ψ, wherein gross error, the result after screening is rejected and is designated as
Set SmFor the total number of element in the set, 0≤Sm≤2N；
For element numerals in the set,；The element is to represent in the set；
Step 5, using least square method of weighting, to the setElement carry out second of data fusion, be specially：
By the setElement according to formula：
<mrow>
<msup>
<mover>
<mi>R</mi>
<mo>~</mo>
</mover>
<mi>m</mi>
</msup>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<msup>
<mi>S</mi>
<mi>m</mi>
</msup>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<mrow>
<msub>
<mi>w</mi>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
</msub>
<msub>
<mi>r</mi>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
</msub>
</mrow>
</mrow>
Merged, wherein,For last fusion value,ForWeight coefficient,Calculation formula be：
<mrow>
<msub>
<mi>w</mi>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
</msub>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<msub>
<mi>&sigma;</mi>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
</msub>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<msup>
<mi>S</mi>
<mi>m</mi>
</msup>
<mo>-</mo>
<mn>1</mn>
</mrow>
</munderover>
<mfrac>
<mn>1</mn>
<msub>
<mi>&sigma;</mi>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
</msub>
</mfrac>
</mrow>
</mfrac>
</mrow>
And weight coefficient meets：Wherein,ForThe standard deviation of element in corresponding array；Last fusion valueAs the end value after the processing of m+1 classes physiological data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510897273.5A CN105550502B (en) | 2015-12-08 | 2015-12-08 | A kind of data processing method based on health monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510897273.5A CN105550502B (en) | 2015-12-08 | 2015-12-08 | A kind of data processing method based on health monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105550502A CN105550502A (en) | 2016-05-04 |
| CN105550502B true CN105550502B (en) | 2018-04-03 |
Family
ID=55829690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510897273.5A Active CN105550502B (en) | 2015-12-08 | 2015-12-08 | A kind of data processing method based on health monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105550502B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202860B (en) * | 2016-06-23 | 2018-08-14 | 南京邮电大学 | A kind of mood regulation service push method |
| CN107436997A (en) * | 2017-07-03 | 2017-12-05 | 上海百纬健康科技有限公司 | The analysis system and method for a kind of physiological data |
| CN113806934A (en) * | 2021-09-16 | 2021-12-17 | 浙江衡玖医疗器械有限责任公司 | Hemispherical temperature sensor prediction model construction method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477143A (en) * | 2009-01-13 | 2009-07-08 | 国网电力科学研究院 | Electronic current mutual inductor data processing method based on multi-sensor data amalgamation technology |
| CN101923789A (en) * | 2010-03-24 | 2010-12-22 | 北京航空航天大学 | Safe airplane approach method based on multisensor information fusion |
| CN102567640A (en) * | 2011-12-29 | 2012-07-11 | 上海电机学院 | Method for monitoring mine gas |
| WO2013134845A1 (en) * | 2012-03-13 | 2013-09-19 | Hongyue Luo | Wearable miniature health monitoring system and method |
-
2015
- 2015-12-08 CN CN201510897273.5A patent/CN105550502B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477143A (en) * | 2009-01-13 | 2009-07-08 | 国网电力科学研究院 | Electronic current mutual inductor data processing method based on multi-sensor data amalgamation technology |
| CN101923789A (en) * | 2010-03-24 | 2010-12-22 | 北京航空航天大学 | Safe airplane approach method based on multisensor information fusion |
| CN102567640A (en) * | 2011-12-29 | 2012-07-11 | 上海电机学院 | Method for monitoring mine gas |
| WO2013134845A1 (en) * | 2012-03-13 | 2013-09-19 | Hongyue Luo | Wearable miniature health monitoring system and method |
Non-Patent Citations (2)
| Title |
|---|
| 《基于多传感器数据融合的温湿度监测系统》;范满红 等；;《压电与声光》;20120630;第34卷(第3期);第459-465页； * |
| 《基于虚拟仪器的温室监测系统的研究》;吴杰;《中国优秀硕士学位论文全文数据库信息科技辑》;20070215(第2期);第I140-263页； * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105550502A (en) | 2016-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105550502B (en) | A kind of data processing method based on health monitoring | |
| TWI393579B (en) | The state of the muscle movement state analysis system, methods and computer program products | |
| CN104188639B (en) | Ambulatory blood pressure continuous monitoring and real-time analysis system | |
| CN206026334U (en) | Motion amount detection device and intelligent wearable equipment comprising same | |
| CN106937808A (en) | A kind of data collecting system of intelligent mattress | |
| CN105118236A (en) | Paralysis falling detection and prevention device and processing method thereof | |
| CN103927851B (en) | A kind of individualized multi thresholds fall detection method and system | |
| CN104983434B (en) | Multi-parameter psychological pressure appraisal procedure and device based on analytic hierarchy process (AHP) | |
| CN107961001A (en) | Appraisal procedure, device and the atherosclerosis detector of Degree of arteriosclerosis | |
| CN102670190A (en) | Heart rate variability nonlinear characteristic-based automatic diagnosis method for congestive heart failure | |
| CN206007231U (en) | A kind of telemedicine monitoring system based on cloud platform | |
| CN106970189A (en) | The testing and analysis system and method for a kind of fruit freshness | |
| CN103637784A (en) | ZigBee technology based physiological parameter acquisition system | |
| CN206499449U (en) | A kind of pulse wave gathers bracelet | |
| TWM478203U (en) | Fitness system with physical ability diagnosis function | |
| CN105982643A (en) | Sleep event detection method and system | |
| CN208781436U (en) | Combat training, which is assassinated, for army examines assessment system | |
| CN106971361A (en) | A kind of professional ability remote test system and professional ability remote test method | |
| CN105528857B (en) | A kind of intelligent remote sign data harvester | |
| CN113825253B (en) | Intelligent electronic scale monitoring system and method based on big data | |
| US10779748B2 (en) | Biometric electromyography sensor device for fatigue monitoring and injury prevention and methods for using same | |
| CN206950149U (en) | A kind of knee strained detection device based on machine learning | |
| CN208970186U (en) | Health detecting system for wearable device | |
| CN113876316A (en) | System, method, device, equipment and medium for detecting abnormal flexion and extension activities of lower limbs | |
| CN106175735A (en) | Non-invasive blood pressure detection device, method and Wearable electronic installation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20181102 Address after: 100071 6 floor 612, 1 building, 9 Guang'an Road, Fengtai District, Beijing. Patentee after: Beijing Qi Huang clinical research center Address before: 210003 new model road 66, Gulou District, Nanjing, Jiangsu Patentee before: Nanjing Post & Telecommunication Univ. |
|
| TR01 | Transfer of patent right |