CN109712715A - A kind of scoring processing method and processing device of physiological data - Google Patents
A kind of scoring processing method and processing device of physiological data Download PDFInfo
- Publication number
- CN109712715A CN109712715A CN201711009941.1A CN201711009941A CN109712715A CN 109712715 A CN109712715 A CN 109712715A CN 201711009941 A CN201711009941 A CN 201711009941A CN 109712715 A CN109712715 A CN 109712715A
- Authority
- CN
- China
- Prior art keywords
- physiological data
- drift
- value
- fluctuation
- temporal aspect
- 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
Abstract
The embodiment of the invention discloses a kind of scoring processing method and processing device of physiological data, method includes: to carry out feature extraction to the physiological data of acquisition, and the fluctuation that extraction obtains the physiological data is acutely spent, mean value shakes index and drift diversity factor；According to the fluctuation, acutely degree, mean value concussion index and the drift diversity factor obtain several temporal aspects of the physiological data；According to the weighted value of described several temporal aspects and each temporal aspect, the score value of the physiological data is calculated.After the embodiment of the present invention is acutely spent by the fluctuation that extraction obtains physiological data, mean value shakes index and drift diversity factor, obtain multiple temporal aspects, the score value of physiological data is calculated according to temporal aspect and its different weighted values, not only make full use of physiological data temporal aspect information, and statistical analysis technique is combined with machine learning algorithm, it simply and efficiently realizes the scoring to physiological data, reduces false alarm rate when health status judge or early warning.
Description
Technical field
The present embodiments relate to field of computer technology, and in particular to a kind of the scoring processing method and dress of physiological data
It sets.
Background technique
In recent years, with the continuous development of all kinds of portable medical health equipments, to the heart of user (especially elderly patients)
The feature extraction and analysis of the physical signs such as rate, blood oxygen saturation, respiratory rate, blood pressure are preventing body emergency case, the state of an illness from disliking
Change even death etc. to be of great significance.
When existing monitor system analyzes physiological data, it is primarily present two problems: firstly, usually only simple analysis
The Change in Mean of the time series datas such as heart rate, respiratory rate, blood pressure, and ignore other feature, these are detected limited
Physical signs information is not utilized adequately；Secondly, using a kind of important physiology sign, in conjunction with simple threshold value method into
Row health status is judged or early warning, false alarm rate are higher.
Summary of the invention
Since existing method is there are the above problem, the embodiment of the present invention propose a kind of physiological data scoring processing method and
Device.
In a first aspect, the embodiment of the present invention proposes a kind of scoring processing method of physiological data, comprising:
Feature extraction is carried out to the physiological data of acquisition, the fluctuation that extraction obtains the physiological data is acutely spent, mean value is shaken
Swing index and drift diversity factor；
According to the fluctuation, acutely degree, mean value concussion index and the drift diversity factor obtain the physiological data
Several temporal aspects；
According to the weighted value of described several temporal aspects and each temporal aspect, the scoring of the physiological data is calculated
Value.
Optionally, several described timing indicators include the sliding average of momentary fluctuation, change rate sliding average line
Deviation value, sliding average line deviation value, drift situation sliding average, the equal line deviation value of drift situation, mean value difference shake number
With drift difference shake number.
Optionally, several described timing indicators are the single order and second differnce temporal aspect extracted in the physiological data
Afterwards, it is obtained according to discrete-time series.
Optionally, the weighted value of each temporal aspect is according to machine learning random forest feature selecting algorithm and the history number
According to each temporal aspect carry out importance ranking after obtain.
Second aspect, the embodiment of the present invention also propose a kind of scoring processing unit of physiological data, comprising:
Characteristic extracting module, for carrying out feature extraction to the physiological data of acquisition, extraction obtains the physiological data
Acutely degree, mean value shake index and drift diversity factor for fluctuation；
Feature processing block, for acutely degree, the mean value to shake index and the drift diversity factor according to the fluctuation
Obtain several temporal aspects of the physiological data；
Score computing module, for the weighted value according to described several temporal aspects and each temporal aspect, is calculated
The score value of the physiological data.
Optionally, several described timing indicators include the sliding average of momentary fluctuation, change rate sliding average line
Deviation value, sliding average line deviation value, drift situation sliding average, the equal line deviation value of drift situation, mean value difference shake number
With drift difference shake number.
Optionally, several described timing indicators are the single order and second differnce temporal aspect extracted in the physiological data
Afterwards, it is obtained according to discrete-time series.
Optionally, the weighted value of each temporal aspect is according to machine learning random forest feature selecting algorithm and the history number
According to each temporal aspect carry out importance ranking after obtain.
The third aspect, the embodiment of the present invention also propose a kind of electronic equipment, comprising:
At least one processor；And
At least one processor being connect with the processor communication, in which:
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to refer to
Order is able to carry out the above method.
Fourth aspect, the embodiment of the present invention also propose a kind of non-transient computer readable storage medium, the non-transient meter
Calculation machine readable storage medium storing program for executing stores computer program, and the computer program makes the computer execute the above method.
As shown from the above technical solution, the embodiment of the present invention by extract obtain physiological data fluctuation acutely spend, mean value
After shaking index and drift diversity factor, multiple temporal aspects are obtained, physiology is calculated according to temporal aspect and its different weighted values
The score value of data not only makes full use of physiological data temporal aspect information, but also statistical analysis technique and machine learning is calculated
Method combines, and simply and efficiently realizes the scoring to physiological data, reduces false alarm when health status judge or early warning
Rate.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these figures.
Fig. 1 is a kind of flow diagram of the scoring processing method for physiological data that one embodiment of the invention provides；
Fig. 2 be another embodiment of the present invention provides a kind of physiological data scoring processing method flow diagram；
Fig. 3 is a kind of structural schematic diagram of the scoring processing unit for physiological data that one embodiment of the invention provides；
Fig. 4 is the logic diagram for the electronic equipment that one embodiment of the invention provides.
Specific embodiment
With reference to the accompanying drawing, further description of the specific embodiments of the present invention.Following embodiment is only used for more
Technical solution of the present invention is clearly demonstrated, and not intended to limit the protection scope of the present invention.
Fig. 1 shows a kind of flow diagram of the scoring processing method of physiological data provided in this embodiment, comprising:
S101, feature extraction is carried out to the physiological data of acquisition, the fluctuation that extraction obtains the physiological data is acutely spent,
Value concussion index and drift diversity factor.
Wherein, acutely it is raw in different times to measure data mainly by single order, second differnce temporal aspect for degree for the fluctuation
The bonding or separation situation for managing the sliding average curve of index change rate, can reflect different times physiological parameter change rate
Otherness.
The mean value concussion index can measure out the bonding or separation of the sliding average curve of different times physical signs
The oscillatory condition of situation and different times data mean value difference.
The drift diversity factor reaction different times physical signs corresponds to the departure degree of normal medical guidelines range.
S102, according to the fluctuation, acutely degree, mean value concussion index and the drift diversity factor obtain the physiology
Several temporal aspects of data.
The weighted value of S103, several temporal aspects and each temporal aspect according to, are calculated the physiological data
Score value.
The present embodiment makes full use of physiological data temporal aspect information, improves the judge accuracy to health status, is old
The body lesion of people or patient, sb.'s illness took a turn for the worse provide early stage early warning reference.In practical applications, mainly acquired including data,
Feature extraction, evaluation method establish and judge several steps in real time, as shown in Figure 2.
Mainly by portable medical health care settings in data acquisition, acquisition normally with the life under all kinds of abnormal conditions
Sign data, including heart rate, respiratory rate, blood oxygen saturation, blood pressure etc., and by medical practitioner to the normal and abnormal conditions of data
It is demarcated.After carrying out the pretreatment such as exceptional value screening to data, data and corresponding state are stored in database, building life
Order sign information database.
Feature extraction is based on above-mentioned constructed vital sign information database, physiological data feature extraction is carried out, if obtaining
Dry temporal aspect.
Evaluation method is established as taking temporal aspect based on mentioned above, assigns different weighted values to every kind of feature, passes through power
The mode beaten again point, judges the health status of current period, and mid-score is higher, and to represent health status poorer.
It is judged as after the completion of above-mentioned evaluation method foundation in real time, that is, completes to comment based on the health of statistical analysis and machine learning
The building of valence method.In practical application, by real-time detection to physiological data pre-processed, feature extraction, and utilize institute's structure
The judge that evaluation method carries out real time health situation is built, that is, completes the judge to user health situation.
After the present embodiment is acutely spent by the fluctuation that extraction obtains physiological data, mean value shakes index and drift diversity factor,
Multiple temporal aspects are obtained, the score value of physiological data is calculated according to temporal aspect and its different weighted values, it is not only sufficiently sharp
With physiological data temporal aspect information, and statistical analysis technique is combined with machine learning algorithm, is simply and efficiently realized
Scoring to physiological data reduces false alarm rate when health status judge or early warning.
Further, on the basis of above method embodiment, several described timing indicators include the cunning of momentary fluctuation
Dynamic average value, the deviation value of change rate sliding average line, sliding average line deviation value, drift situation sliding average, drift feelings
The equal line deviation value of condition, mean value difference shake number and drift difference shake number.
After several described timing indicators are the single order and second differnce temporal aspect extracted in the physiological data, according to
Discrete-time series obtain.
Specifically, when carrying out feature extraction, for certain physiological parameter, taking its discrete-time series is { x (i) }, institute
Studying corresponding data sequence length in time slip-window is N, with n1Indicate that body is in a certain period of history of health status, n2
Indicate current period, extracted characteristic information are as follows:
Fluctuation is acutely spent: this feature mainly passes through single order, second differnce temporal aspect, measures data in different times, life
The bonding or separation situation for managing the sliding average curve of index change rate, can reflect different times physiological parameter change rate
Otherness, circular are as follows:
Data momentary fluctuation value: TR (x (i))=| x (i)-x (i-1) |.
n1The sliding average of period momentary fluctuation:
n2The sliding average of period momentary fluctuation:
The deviation value of change rate sliding average line:
Mean value oscillatior: the index measures out different times, the bonding or separation of the sliding average curve of physical signs
The oscillatory condition of situation and different times data mean value difference, circular are as follows:
n1Period data sliding average:
n2Period data sliding average:
Sliding average line deviation value:
The sliding average of diff (MA (x (i))):
Mean value difference shake number: the index can react the variation acceleration index of different times mean value difference:
OSMA (diff (MA (x (i))), DEA (diff (MA (x (i)))))=
diff(MA(x(i)))-DEA(diff(MA(x(i))))
Drift diversity factor: the index reacts the deviation journey that different times physical signs corresponds to normal medical guidelines range
Degree, withWithThe normality threshold bound respectively indicated, circular are as follows:
Physical signs instantaneous drift:
n1Period drift situation sliding average:
n2Period drift situation sliding average:
The drift equal line deviation value of situation:
The sliding average line of diff (MA (dist (x (i)))):
Drift difference shake number: the index can react the variation acceleration index of different times drift difference:
OSMA (diff (MA (dist (x (i)))), DEA (diff (MA (dist (x (i))))))=
diff(MA(dist(x(i))))-DEA(diff(MA(dist(x(i)))))
The circular that weight marking is judged are as follows:
With hjIndicate weight shared by different characteristic, wherein the corresponding different characteristic amount of j ∈ { 1,2,3..., 7 }.featuejThen root
According to different times characteristic value ATR (TR (x (i))), diff (ATR (x (i))), diff (MA (x (i))), MA (dist (x (i))),
diff(MA(dist(x(i))))、OSMA(diff(MA(x(i))),DEA(diff(MA(x(i)))))、OSMA(diff(MA
(dist (x (i)))), DEA (diff (MA (dist (x (i)))))) significance difference analysis result obtain.
Further, on the basis of above method embodiment, the weighted value of each temporal aspect is random according to machine learning
Forest characteristics selection algorithm and the historical data obtain after carrying out importance ranking to each temporal aspect.
Specifically, weighted value h is being determinedjWhen value, using machine learning random forest feature selecting algorithm, in conjunction with being adopted
Collect historical data, importance ranking is carried out to all features, corresponding h is determined according to feature importance resultjValue.For decision
The random forest that quantity is Ntree is set, to feature featurejThe outer data error errOOB1 of bag of each tree is calculated separately, and
To featurejThe outer data error errOOB2 of bag, the feature importance based on random forest are calculated again after random noise is added
Calculation method are as follows:
Also, in weight marking calculating process, by current period characteristic value and history health status individual features value into
Row significance difference analysis indicates significance difference analysis as a result, if p > 0.05 with common statistics index probability P value
For two groups of characteristic differences without significant meaning, two groups of 0.01≤p≤0.05 item characteristic difference has a conspicuousness, p < 0.01 then two groups it is special
It is extremely significant to levy otherness.According to significance difference analysis result to featurejIt is determined, specifically:
The present embodiment is calculated by single order, second order temporal aspect, sufficiently excavates the temporal aspect information in data；Together
When, statistical analysis technique is combined with machine learning algorithm, the physiological characteristic information of comprehensive a variety of different weights carries out health
Situation is judged, and false alarm rate is reduced.The present invention can prevent old man or the patients clinical state of an illness by the judge to health status
Deterioration, the death condition to be likely to occur the early warning of early stage is provided, have important practical application meaning.
Fig. 3 shows a kind of structural schematic diagram of the scoring processing unit of physiological data provided in this embodiment, the dress
Set includes: characteristic extracting module 301, feature processing block 302 and scoring computing module 303, in which:
The characteristic extracting module 301 is used to carry out feature extraction to the physiological data of acquisition, and extraction obtains the physiology
The fluctuation of data is acutely spent, mean value shakes index and drift diversity factor；
The feature processing block 302 is used for according to the fluctuation acutely degree, mean value concussion index and the drift
Diversity factor obtains several temporal aspects of the physiological data；
The scoring computing module 303 is used for the weighted value according to described several temporal aspects and each temporal aspect, meter
Calculation obtains the score value of the physiological data.
Specifically, the physiological data of 301 pairs of characteristic extracting module acquisitions carries out feature extraction, and extraction obtains the life
The fluctuation of reason data is acutely spent, mean value shakes index and drift diversity factor；The feature processing block 302 is acute according to the fluctuation
Earthquake intensity, mean value concussion index and the drift diversity factor obtain several temporal aspects of the physiological data；Institute's commentary
Divide computing module 303 according to the weighted value of described several temporal aspects and each temporal aspect, the physiological data is calculated
Score value.
After the present embodiment is acutely spent by the fluctuation that extraction obtains physiological data, mean value shakes index and drift diversity factor,
Multiple temporal aspects are obtained, the score value of physiological data is calculated according to temporal aspect and its different weighted values, it is not only sufficiently sharp
With physiological data temporal aspect information, and statistical analysis technique is combined with machine learning algorithm, is simply and efficiently realized
Scoring to physiological data reduces false alarm rate when health status judge or early warning.
Further, on the basis of above-mentioned apparatus embodiment, several described timing indicators include the cunning of momentary fluctuation
Dynamic average value, the deviation value of change rate sliding average line, sliding average line deviation value, drift situation sliding average, drift feelings
The equal line deviation value of condition, mean value difference shake number and drift difference shake number.
Further, on the basis of above-mentioned apparatus embodiment, several described timing indicators are to extract the physiology number
After single order and second differnce temporal aspect in, obtained according to discrete-time series.
Further, on the basis of above-mentioned apparatus embodiment, the weighted value of each temporal aspect is random according to machine learning
Forest characteristics selection algorithm and the historical data obtain after carrying out importance ranking to each temporal aspect.
The scoring processing unit of physiological data described in the present embodiment can be used for executing above method embodiment, principle
Similar with technical effect, details are not described herein again.
Referring to Fig. 4, the electronic equipment, comprising: processor (processor) 401, memory (memory) 402 and total
Line 403；
Wherein,
The processor 401 and memory 402 complete mutual communication by the bus 403；
The processor 401 is used to call the program instruction in the memory 402, to execute above-mentioned each method embodiment
Provided method.
The present embodiment discloses a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program include program instruction, when described program instruction is calculated
When machine executes, computer is able to carry out method provided by above-mentioned each method embodiment.
The present embodiment provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Computer instruction is stored, the computer instruction makes the computer execute method provided by above-mentioned each method embodiment.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
It is noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although reference
Invention is explained in detail for previous embodiment, those skilled in the art should understand that: it still can be right
Technical solution documented by foregoing embodiments is modified or equivalent replacement of some of the technical features；And this
It modifies or replaces, the spirit and model of technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (10)
1. a kind of scoring processing method of physiological data characterized by comprising
Feature extraction is carried out to the physiological data of acquisition, the fluctuation that extraction obtains the physiological data is acutely spent, mean value concussion refers to
Mark and drift diversity factor；
According to the fluctuation, acutely degree, mean value concussion index and the drift diversity factor obtain the several of the physiological data
A temporal aspect；
According to the weighted value of described several temporal aspects and each temporal aspect, the score value of the physiological data is calculated.
2. the method according to claim 1, wherein several described timing indicators include the sliding of momentary fluctuation
Average value, the deviation value of change rate sliding average line, sliding average line deviation value, drift situation sliding average, drift situation
Equal line deviation value, mean value difference shake number and drift difference shake number.
3. the method according to claim 1, wherein several described timing indicators are to extract the physiological data
In single order and second differnce temporal aspect after, obtained according to discrete-time series.
4. the method according to claim 1, wherein the weighted value of each temporal aspect is gloomy at random according to machine learning
Woods feature selecting algorithm and the historical data obtain after carrying out importance ranking to each temporal aspect.
5. a kind of scoring processing unit of physiological data characterized by comprising
Characteristic extracting module, for carrying out feature extraction to the physiological data of acquisition, extraction obtains the fluctuation of the physiological data
Acutely degree, mean value concussion index and drift diversity factor；
Feature processing block, for acutely degree, mean value concussion index and the drift diversity factor to obtain according to the fluctuation
Several temporal aspects of the physiological data；
Score computing module, for the weighted value according to described several temporal aspects and each temporal aspect, is calculated described
The score value of physiological data.
6. device according to claim 5, which is characterized in that several described timing indicators include the sliding of momentary fluctuation
Average value, the deviation value of change rate sliding average line, sliding average line deviation value, drift situation sliding average, drift situation
Equal line deviation value, mean value difference shake number and drift difference shake number.
7. device according to claim 5, which is characterized in that several described timing indicators are to extract the physiological data
In single order and second differnce temporal aspect after, obtained according to discrete-time series.
8. device according to claim 5, which is characterized in that the weighted value of each temporal aspect is gloomy at random according to machine learning
Woods feature selecting algorithm and the historical data obtain after carrying out importance ranking to each temporal aspect.
9. a kind of electronic equipment characterized by comprising
At least one processor；And
At least one processor being connect with the processor communication, in which:
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough methods executed as described in Claims 1-4 is any.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer program is stored up, the computer program makes the computer execute the method as described in Claims 1-4 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711009941.1A CN109712715A (en) | 2017-10-25 | 2017-10-25 | A kind of scoring processing method and processing device of physiological data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711009941.1A CN109712715A (en) | 2017-10-25 | 2017-10-25 | A kind of scoring processing method and processing device of physiological data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109712715A true CN109712715A (en) | 2019-05-03 |
Family
ID=66252126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711009941.1A Pending CN109712715A (en) | 2017-10-25 | 2017-10-25 | A kind of scoring processing method and processing device of physiological data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109712715A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111982299A (en) * | 2020-08-14 | 2020-11-24 | 国家卫星气象中心(国家空间天气监测预警中心) | Dynamic data quality scoring method and system for satellite-borne microwave radiometer |
| CN113066589A (en) * | 2021-03-24 | 2021-07-02 | 联仁健康医疗大数据科技股份有限公司 | Collected data analysis method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101986678A (en) * | 2010-11-18 | 2011-03-16 | 浙江大学 | Smart mobile phone for monitoring multiple physiological parameters in real time |
| CN103020472A (en) * | 2012-12-27 | 2013-04-03 | 中国科学院深圳先进技术研究院 | Physiological signal quality evaluation method and system based on constrained estimation |
| CN103189883A (en) * | 2010-09-07 | 2013-07-03 | 里兰斯坦福初级大学理事会 | Medical scoring systems and methods |
| CN103815966A (en) * | 2012-11-19 | 2014-05-28 | 深圳迈瑞生物医疗电子股份有限公司 | Physiological parameter processing device and method |
| CN104166530A (en) * | 2013-05-16 | 2014-11-26 | 中兴通讯股份有限公司 | Display parameter adjustment method and device and terminal |
| CN105266772A (en) * | 2014-06-20 | 2016-01-27 | 赵海 | Measuring method for physiological parameter |
| CN106980746A (en) * | 2016-12-16 | 2017-07-25 | 清华大学 | A kind of general Woundless blood sugar Forecasting Methodology based on Time-Series analysis |
-
2017
- 2017-10-25 CN CN201711009941.1A patent/CN109712715A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103189883A (en) * | 2010-09-07 | 2013-07-03 | 里兰斯坦福初级大学理事会 | Medical scoring systems and methods |
| CN101986678A (en) * | 2010-11-18 | 2011-03-16 | 浙江大学 | Smart mobile phone for monitoring multiple physiological parameters in real time |
| CN103815966A (en) * | 2012-11-19 | 2014-05-28 | 深圳迈瑞生物医疗电子股份有限公司 | Physiological parameter processing device and method |
| CN103020472A (en) * | 2012-12-27 | 2013-04-03 | 中国科学院深圳先进技术研究院 | Physiological signal quality evaluation method and system based on constrained estimation |
| CN104166530A (en) * | 2013-05-16 | 2014-11-26 | 中兴通讯股份有限公司 | Display parameter adjustment method and device and terminal |
| CN105266772A (en) * | 2014-06-20 | 2016-01-27 | 赵海 | Measuring method for physiological parameter |
| CN106980746A (en) * | 2016-12-16 | 2017-07-25 | 清华大学 | A kind of general Woundless blood sugar Forecasting Methodology based on Time-Series analysis |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111982299A (en) * | 2020-08-14 | 2020-11-24 | 国家卫星气象中心(国家空间天气监测预警中心) | Dynamic data quality scoring method and system for satellite-borne microwave radiometer |
| CN111982299B (en) * | 2020-08-14 | 2021-08-17 | 国家卫星气象中心(国家空间天气监测预警中心) | Dynamic data quality scoring method and system for satellite-borne microwave radiometer |
| CN113066589A (en) * | 2021-03-24 | 2021-07-02 | 联仁健康医疗大数据科技股份有限公司 | Collected data analysis method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Lifelogging data validation model for internet of things enabled personalized healthcare | |
| JP6909078B2 (en) | Disease onset prediction device, disease onset prediction method and program | |
| CN109363659B (en) | Heart rate monitoring method and device based on deep learning and storage medium | |
| Zhang et al. | A context-aware mhealth system for online physiological monitoring in remote healthcare | |
| CN103800001B (en) | Bio signal transmitter, bio signal receiver and the method for sending bio signal | |
| CN103201743A (en) | Method of continuous prediction of patient severity of illness, mortality, and length of stay | |
| AU2019237860A1 (en) | Systems and methods for personalized medication therapy management | |
| CN106599553A (en) | Disease early-warning method and device | |
| CN108510099A (en) | A kind of method and wearable device of path planning | |
| Meina et al. | Tagging Firefighter Activities at the emergency scene: Summary of AAIA'15 data mining competition at knowledge pit | |
| CN110432876A (en) | A kind of health monitoring alarm method and device | |
| KR102424629B1 (en) | System and method for improving development disorder using deep learning module | |
| CN108091391A (en) | Illness appraisal procedure, terminal device and computer-readable medium | |
| KR20190063954A (en) | Method for predicting change of nutrient metabolism by artificial intelligence cloud and method for measuring nutrient metabolism by artificial intelligence cloud and method managing diease by using it | |
| CN106572803A (en) | Generation of medical monitor alarm settings | |
| CN109712715A (en) | A kind of scoring processing method and processing device of physiological data | |
| CN111329459A (en) | Improved patient vital sign monitoring, early warning and scoring method | |
| CN114334175A (en) | Hospital epidemic situation monitoring method and device, computer equipment and storage medium | |
| CN107661092A (en) | Vital sign state monitoring method and computer-readable recording medium | |
| CN114241270A (en) | Intelligent monitoring method, system and device for home care | |
| Garcia-Valverde et al. | Heart health risk assessment system: a nonintrusive proposal using ontologies and expert rules | |
| CN109674474A (en) | Sleep apnea recognition methods, equipment and computer-readable medium | |
| CN114864094A (en) | Intensive care unit intelligent control method, equipment and medium | |
| Li et al. | Design and partial implementation of health care system for disease detection and behavior analysis by using DM techniques | |
| CN116504362A (en) | Sleep adjustment scheme generation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190503 |
|
| RJ01 | Rejection of invention patent application after publication |