CN108281197A - A method of relationship between analysis environmental factor and juvenile shortsightedness - Google Patents
A method of relationship between analysis environmental factor and juvenile shortsightedness Download PDFInfo
- Publication number
- CN108281197A CN108281197A CN201810071276.7A CN201810071276A CN108281197A CN 108281197 A CN108281197 A CN 108281197A CN 201810071276 A CN201810071276 A CN 201810071276A CN 108281197 A CN108281197 A CN 108281197A
- Authority
- CN
- China
- Prior art keywords
- user
- eye
- data
- pixel
- relationship
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Eye Examination Apparatus (AREA)
- Eyeglasses (AREA)
Abstract
The invention discloses the methods of relationship between analysis environmental factor and juvenile shortsightedness, including:Step 1, objective detecting and acquisition are carried out at the same time to the near work of user and outdoor exposure data;Step 2, the eye parameter of user is obtained;Step 3, the eye parameter of the near work of user and outdoor exposure data and user cloud platform is respectively transmitted to store;Step 4, the near work and outdoor exposure data and the eye parameter of user stored to cloud platform database using big data analysis system carries out noise reduction and conversion according to the requirement of big data analysis, then user is extracted with eye behavioural characteristic, and to being associated with the eye parameter of eye behavioural characteristic and user.This method in use can in real time, dynamic, objectively monitoring user really uses eye behavior and visual environment, overcome the problem of can not accurately analyzing relationship between environmental factor and juvenile shortsightedness in the prior art.
Description
Technical field
The present invention relates to myopia and the analysis fields of environmental concerns, and in particular, to a kind of analysis environmental factor and blueness are few
The method of relationship between year myopia.
Background technology
Myopia prevalence growth is very swift and violent, there is no effective preventions at present.It is generally acknowledged that myopia is gene
It is coefficient with environmental factor as a result, and myopia prevalence swift and violent the phenomenon that increasing in over the past several decades, prompts, environment
Factor is leading reason.Environmental factor includes mainly two broad aspect of near work and outdoor exposure.Up to now, environmental factor
It is still unclear for the specific effect of occurrence and devlopment of myopia.To find out its cause, being because of the past research environment factor and myopia
Between relationship be mainly questionnaire by inquiry method.
Have at present some researchs using the wearable device for capableing of objective detecting near work or outdoor exposure come
To assessing in a certain respect for environmental factor, it there is no research application while visitor can be carried out near work and outdoor exposure
See the intelligent wearable device of monitoring.For example, Leung etc. comes objective detecting user's using wear-type near work analyzer
These researchers of near work situation are utilized respectively portable light receptor, Actiwatch and FitSight fitness
Tracker monitors the outdoor exposure situation of user.
There are following two major defects for this method of questionnaire.The first, it requires to fill out writer according to its memory answer
The problem very wide comprising face in questionnaire, content is very specific, can not avoid recall bias, lead to counted data accuracy not
By force.The second, it is only capable of providing the aggregate data of environmental factor, and the high-density line that cannot simultaneously and dynamically record interviewee is
Data are learned, thus it (is the work of duration or the work of discontinuity when such as near work that can not depict its behavior pattern
Deng), zoopery has confirmed that behavior pattern has a major impact the development of diopter.
With the development of information technology, there is the more above-described method for capableing of objective detecting environmental factor, but
They also have the shortcomings that some are main.The first, these methods can only monitoring of environmental factor some aspect, such as wear-type
Proximity analysis instrument is only capable of monitoring near work, and Actiwatch is only capable of the monitoring outdoor exposure time, this is clearly not comprehensive
, environmental factor can not be fully assessed, effect of the environmental factor to occurrence and devlopment of myopia cannot be disclosed completely.The
Two, the illumination that the surrounding enviroment illumination non-ocular that these methods are monitored is received.Third, these methods do not have perfect number
According to storage platform, teen-age myopia corelation behaviour data can not be obtained on a large scale, cannot also generate corresponding behavior
Database is learned, being associated between behaviouristics data and diopter can not be excavated using the means of big data.
Therefore it provides it is a kind of in use can in real time, dynamic, objectively monitoring user really use eye behavior and
Visual environment, the shortcomings that overcoming the past method there are recall bias and environment aggregate data can only be provided;It can monitor simultaneously
Close to two dimensions of real work distance and surrounding enviroment illumination residing for eyes, overcome the past method monitoring dimension it is single and
The shortcomings that institute's measured data non-ocular true local environment data;Cloud platform with storage data, overcoming the past method can not
The shortcomings that Mass storage data;And data are excavated and are analyzed using big data method, be expected to really to determine environment because
The method of relationship is this hair between a kind of analysis environmental factor and juvenile shortsightedness of quantitative relationship between element and myopia
The problem of bright urgent need to resolve.
Invention content
In view of the above technical problems, the object of the present invention is to provide it is a kind of in use can in real time, it is dynamic, objective
Monitoring user really use eye behavior and visual environment, overcome the past method there are recall bias and can only to provide environment total
The shortcomings that measuring data;It can monitor simultaneously close to two dimensions of real work distance and surrounding enviroment illumination residing for eyes, gram
It has taken the monitoring of the past method dimension is single and the shortcomings that institute's measured data non-ocular true local environment data;With storage data
Cloud platform, overcome the past method can not Mass storage data the shortcomings that;And data are excavated using big data method
And analysis, it is expected to really determine that a kind of analysis environmental factor of the quantitative relationship between environmental factor and myopia is close with teenager
Depending on the method for relationship between eye.
To achieve the goals above, the present invention provides the sides of relationship between analysis environmental factor and juvenile shortsightedness
Method, the method includes:
Step 1, objective detecting and acquisition are carried out at the same time to the near work of user and outdoor exposure data;
Step 2, the eye parameter of user is obtained;
Step 3, the eye parameter of the near work of user and outdoor exposure data and user is respectively transmitted to cloud
Platform is stored;
Step 4, the near work and outdoor exposure number cloud platform database stored using big data analysis system
According to this and the eye parameter of user carries out noise reduction and conversion according to the requirement of big data analysis, then special with eye behavior to user
Sign extracts, and to being associated with the eye parameter of eye behavioural characteristic and user, and then illustrates environmental factor to myopia
The influence of morbidity.
Preferably, the eye parameter of the user includes:The objective refraction number of degrees and axis oculi data.
Preferably, big data analysis system includes:CPU processor, data management module, behavior characteristic extraction module are closed
Join model module and optimal models decision module and environment impact index generation module;Wherein, the data management module is used
It is wanted according to big data analysis in the near work and outdoor exposure data of cloud platform storage and the eye parameter of user
It asks and carries out noise reduction and conversion;The behavior characteristic extraction module is used for the near work data using cloud platform storage and open air
Exposure data, user is extracted with eye behavioural characteristic, depicts the behavioural characteristic of different user;The correlation model is built
Formwork erection block is used for after user is completed with the extraction of eye behavioural characteristic, is set up behavioural characteristic using correlation model and is joined with eye
Contact between number is to establish being associated between behavioural characteristic and diopter progress;The optimal models decision module is used for
Selection determines optimal models;The environment impact index generation module, which is used to generate, can reflect that user's is good with eye behavioural habits
Bad environment impact index;The CPU processor is used to coordinate the work and data analysis of modules.
Preferably, the data management module filters the data i.e. noise of high frequency using fast Fourier variation.
Preferably, the user's includes with eye behavioural characteristic:The illumination (EI) of operating distance (VD) and surrounding enviroment,
VD data and EI data after noise reduction are mapped to 2 dimension spaces (spaces VD-EI), and the longitudinal axis is VD, and horizontal axis is log10 (EI),
Just the behavior scatter chart of user is obtained, then the behavior curve of all users is overlapped respectively, just obtains the user group
The behavior of body is distributed thermodynamic chart, and depict the user group at once uses eye behavioural characteristic.
Preferably, the index of diopter progress be at least 2 years equivalent sphere mirror degrees (SER) changing value Δ SER and
The changing value Δ AL of axis oculi (AL);Wherein, the SER=S+1/2C;S and C is to pass through computerized optometry after paralysis cilia-like muscle respectively
The concave-sphere number of degrees and mean of cylindrical diopter that instrument is obtained;The Δ SER=SER lasts-SER baselines, Δ AL=AL last-AL bases
Line;SER lasts and AL lasts respectively represent the refractive diopter and axis oculi data, SER baselines and AL bases that user's last time provides
Line is expressed as the refractive diopter and axis oculi data that user provides for the first time.
Preferably, the critical assumptions for illustrating to establish the model are also needed to before the correlation model establishes module work,
It then needs to consider that the influence of contiguous pixels around it is assumed to obey:As unit of pixel, calculates in each pixel and include
The time of every user behavior accounts for the ratio (PoT) of user group behavior total time, using radial basis function (RBF kernel functions)
Tax power is carried out to the pixel of different distance, then reuses cum rights linear regression (WLR) to analyze the relationship between PoT and SER,
It is smaller that the pixel closer from the pixel influences bigger, remoter pixel influence;For the RBF kernel functions of 2 pixel x and x ',
Given x and x ' is defined as relative to the weights of x:
||xind-x′ind||2Square of Euclidean distance between two pixels, the entire spaces VD-EI are divided into 40*40
A pixel can give each pixel to assign a pair of of index value, to calculate the Euclidean distance between any two pixel, RBF cores
Function can assign small weights to remote pixel, and big weights are assigned to close pixel.
Preferably, it when analyzing some pixel, needs to come using the pixel as the center of circle one a certain size region of restriction true
Determine coverage, wherein defining the size in this region with parameter δ (0≤δ≤20), 2 times of δ is using certain pixel as the circle in the center of circle
Radius, then the pixel in all circles have certain influence to the pixel.
Preferably, each pixel can establish the cum rights linear regression model (LRM) between PoT and diopter progress, the mould
The slope (K) of type represents and is associated with property and intensity between certain behavioural characteristic and diopter progress, if the value is positive value, explanation
Good with eye custom, the bigger behavioural habits of positive value are better, and represent the user has protection to make myopia on the whole with eye behavior
With;The value is negative value, and explanation is bad with eye custom, and the smaller behavioural habits of negative value are more bad, represents the whole with eye behavior of the user
To the dangerous effect of myopia on body.
Preferably, it is worn using intelligent wearable device and visitor is carried out at the same time to the near work and outdoor exposure data of user
Monitoring and acquisition are seen, the frequency of gathered data is 4-6s/ times, and the data of the intelligence wearable device acquisition can pass through bluetooth
It is sent to cell phone application, APP is transferred data to by network on server again.
According to above-mentioned technical proposal, relationship between a kind of analysis environmental factor provided by the invention and juvenile shortsightedness
Method in real time, dynamically, objectively can monitor user in use and really use eye behavior and visual environment, overcome both
Toward method there are recall bias and the shortcomings that environment aggregate data can only be provided;It can monitor simultaneously close to true residing for eyes
It is single and institute's measured data non-ocular is true to overcome the past method monitoring dimension for two dimensions of operating distance and surrounding enviroment illumination
The shortcomings that local environment data;With storage data cloud platform, overcome the past method can not Mass storage data lack
Point;And data are excavated and analyzed using big data method, it is expected to really determine the amount between environmental factor and myopia
Change relationship.
Other features and advantages of the present invention will be described in detail in subsequent specific embodiment part.
Description of the drawings
Attached drawing is to be used to provide further understanding of the present invention, an and part for constitution instruction, with following tool
Body embodiment is used to explain the present invention together, but is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 be the present invention a kind of preferred embodiment under a kind of analysis environmental factor that provides and juvenile shortsightedness
Between relationship method flow diagram;
Fig. 2 be the present invention a kind of preferred embodiment under a kind of analysis environmental factor that provides and juvenile shortsightedness
Between relationship method in the structural schematic diagram worn of intelligent wearable device;
Fig. 3 be the present invention a kind of preferred embodiment under a kind of analysis environmental factor that provides and juvenile shortsightedness
Between relationship method in intelligent wearable device be worn over the installation diagram on glasses.
Reference sign
1 UV sensor, 2 bluetooth
3 three axis angular rate sensor, 4 range sensor
5 intensity of illumination sensors
Specific implementation mode
The specific implementation mode of the present invention is described in detail below in conjunction with attached drawing.It should be understood that this place is retouched
The specific implementation mode stated is merely to illustrate and explain the present invention, and is not intended to restrict the invention.
As shown in Figs. 1-3, the present invention provides relationships between a kind of analysis environmental factor and juvenile shortsightedness
Method, which is characterized in that the method includes:Step 1, visitor is carried out at the same time to the near work of user and outdoor exposure data
See monitoring and acquisition;Step 2, the eye parameter of user is obtained;Step 3, by the near work of user and outdoor exposure data
And the eye parameter of user is respectively transmitted to cloud platform and stores;Step 4, using big data analysis system to cloud platform number
The eye parameter of the near work and outdoor exposure data and user that are stored according to library according to big data analysis requirement into
Then row noise reduction and conversion extract user with eye behavioural characteristic, and to being joined with the eye of eye behavioural characteristic and user
Number is associated, and then illustrates the influence that environmental factor falls ill to myopia.
According to above-mentioned technical proposal, relationship between a kind of analysis environmental factor provided by the invention and juvenile shortsightedness
Method in real time, dynamically, objectively can monitor user in use and really use eye behavior and visual environment, overcome both
Toward method there are recall bias and the shortcomings that environment aggregate data can only be provided;It can monitor simultaneously close to true residing for eyes
It is single and institute's measured data non-ocular is true to overcome the past method monitoring dimension for two dimensions of operating distance and surrounding enviroment illumination
The shortcomings that local environment data;With storage data cloud platform, overcome the past method can not Mass storage data lack
Point;And data are excavated and analyzed using big data method, it is expected to really determine the amount between environmental factor and myopia
Change relationship.
In a kind of preferred embodiment of the present invention, the eye parameter of the user includes:The objective refraction number of degrees and
Axis oculi data, the two parameters are the main eye parameter of user, and the eye parameter of the user of the present invention is not limited to certainly
The two eye parameters.
In a kind of preferred embodiment of the present invention, big data analysis system includes:CPU processor, data management
Module, behavior characteristic extraction module, correlation model module and optimal models decision module and environment impact index generation module;
Wherein, the data management module is used near work and the eye of outdoor exposure data and user to cloud platform storage
Parameter carries out noise reduction and conversion according to the requirement of big data analysis;The behavior characteristic extraction module is used to utilize cloud platform storage
Near work data and outdoor exposure data, user is extracted with eye behavioural characteristic, depicts different user
Behavioural characteristic;After the correlation model establishes module for being completed with the extraction of eye behavioural characteristic in user, association mould is used
Type sets up contacting between behavioural characteristic and eye parameter, is to establish being associated between behavioural characteristic and diopter progress;
The optimal models decision module determines optimal models for selecting;The environment impact index generation module can for generating
Reflect the environment impact index with eye behavioural habits quality of user;The CPU processor is used to coordinate the work of modules
And data analysis.
In a kind of preferred embodiment of the present invention, the data management module is filtered using fast Fourier variation
Data, that is, noise of high frequency.The presentation mode of the behaviouristics data obtained from cloud platform be using the priority of acquisition time as sequence,
A behaviouristics data are shown at interval of 4-6s, the time point for including gathered data per data and the work corresponding to the time point
Make distance and surrounding enviroment illumination, the initial data of this form can not obtain the distribution characteristics of primary data, need to carry out certain place
Reason.By taking a certain position user as an example, its behaviouristics data is subjected to Arabic numerals number in temporal sequence, regard number as horizontal seat
Mark, number corresponding ambient light illumination (EI) or operating distance (VD) are used as ordinate, obtain the operating distance distribution of the user
Figure or surrounding enviroment Illumination Distribution figure.From data profile can primary data noise it is excessive, can not carry out big data analysis, must be right
Data carry out noise reduction process.It is an effective noise-reduction method that fast Fourier, which changes (FFT), and the data that it filters high frequency (are made an uproar
Sound), there are one the distributions for being more appropriate to analysis for data after noise reduction.
In a kind of preferred embodiment of the present invention, the user's includes with eye behavioural characteristic:Operating distance
(VD) and the illumination of surrounding enviroment (EI), after noise reduction VD data and EI data be mapped to 2 dimension spaces (VD-EI be empty
Between), the longitudinal axis is VD, and horizontal axis is log10 (EI), just obtains the behavior scatter chart of user, then the behavior of all users is bent
Line is overlapped respectively, is just obtained the behavior distribution thermodynamic chart of the user group, is depicted being gone with eye for the user group at once
It is characterized.Behaviouristics data are made of 3 features:Continuous time series, corresponding operating distance of each acquisition time or
Person's illumination.The present invention is it is contemplated that user's uses eye behavioural characteristic, so negligible time dimension, analyzes remaining 2 spies
Sign:The illumination (EI) of operating distance (VD) and surrounding enviroment.By taking a certain position user as an example, VD the and EI data after noise reduction are mapped
To 2 dimension space (spaces VD-EI), the longitudinal axis is VD, and horizontal axis is log10 (EI), and the behavior distribution for just obtaining certain user is bent
Line chart, depict the user at once uses eye behavioural characteristic.The behavior curve of all users is overlapped respectively again, is just obtained
The behavior of the user group is distributed thermodynamic chart, and depict the user group at once uses eye behavioural characteristic.
In a kind of preferred embodiment of the present invention, the index of the diopter progress is at least 2 years equivalent spheres
The changing value Δ SER of mirror degree (SER) and the changing value Δ AL of axis oculi (AL);Wherein, the SER=S+1/2C;S and C are respectively
The concave-sphere number of degrees and mean of cylindrical diopter obtained by rafractive after paralysis cilia-like muscle;The Δ SER=SER lasts-SER
Baseline, Δ AL=AL last-AL baselines;SER lasts and AL lasts respectively represent user last time provide refractive diopter and
Axis oculi data, SER baselines and AL baselines are expressed as the refractive diopter and axis oculi data that user provides for the first time.Pass through behavior
After characteristic extracting module obtains the total behavior distribution thermodynamic chart of user group, the entirety that can obtain the user group is gone with eye
It is characterized.Obviously, whole to establish incidence relation between diopter progress with eye behavioural characteristic, therefore, by total row
It is divided into 40x40 grid (pixel) for distribution thermodynamic chart, each pixel represents the behavioural characteristic of a part.Next, needing
Establish being associated between the behavioural characteristic of part and diopter progress.
In a kind of preferred embodiment of the present invention, before correlation model foundation, it need to illustrate the pass for establishing the model
Key means that being covered with eye behavior for people is a piece of it is assumed that it is that space is continuous with eye behavior that crucial hypothesis, which is people,
Continuous pixel.So when being analyzed for each pixel, to consider the influence of contiguous pixels around it and be assumed with obeying.
As unit of pixel, the time for calculating every subject's behavior for including in each pixel accounts for these subject's rows
For the ratio (PoT) of total time, for some subject, PoT is its residing time and in its behavior in one pixel
The ratio of residing time in all pixels that curve passes through reflects the subject and is taken time in this pixel (behavioural characteristic)
Accounting.So far, there has been the independent variable PoT linked up with patients' behavioural characteristic, there has also been reaction subject's diopter into
The dependent variable Δ of exhibitionSERAnd ΔAL, you can establish the pass between the PoT of subject and their diopter progress in per unit pixel
Connection relationship.As previously mentioned, when analyzing some pixel, the influence of surrounding contiguous pixels need to be considered.Obviously, closer from the pixel
Pixel influence is bigger, and the influence of remoter pixel is smaller, therefore the pixel of different distance is given using radial basis function (RBF kernel functions)
Tax power is carried out, then reuses cum rights linear regression (WLR) to analyze the relationship between PoT and SER;
For the RBF kernel functions of 2 pixel x and x ', given x and x ' relative to weights be defined as:
||xind-x′ind||2Square of Euclidean distance between two pixels, the entire spaces VD-EI are divided into 40*40
A pixel can give each pixel to assign a pair of of index value, to calculate the Euclidean distance between any two pixel, RBF cores
Function can assign small weights to remote pixel, and big weights are assigned to close pixel.
In a kind of preferred embodiment of the present invention, when analyzing some pixel, since neighboring pixel exists centainly
Influence, it is therefore desirable to a certain size a region is limited as the center of circle using the pixel and determines coverage, wherein with parameter δ
(0≤δ≤20) define the size in this region, and 2 times of δ is the then picture in all circles using certain pixel as the radius of the circle in the center of circle
Element has certain influence to the pixel;
Wherein, optimal models decision module:The module is mainly used for determining which correlation model is optimal models.Different
δ values, the relational model between obtained PoT and diopter progress be different, it is therefore desirable to verify δ and takes and be established when what value
Relational model is the most accurate.If there is no behavior in a pixel and the pixel for including in the circle of radius by 2 δ of the center of circle using it
Distribution, i.e. PoT are 0, which can not establish the cum rights linear regression model (LRM) between PoT and diopter progress, at this time can be with
Think that the slope (K) of model is 0.In extreme circumstances, if all pixels and wrapped in the circle of radius by 2 δ of the center of circle using it
It is distributed without behavior in the pixel contained, then can not establish the relational model between PoT and diopter progress.So the picture of K=0
Plain number is fewer, more can effecting reaction PoT and diopter progress between relationship.Obviously, the number of the pixel of K=0 how much and δ
Value have much relations, δ values are bigger, and the influence area on certain pixel periphery is bigger, and the pixel for including in region is more, complete
The full probability without behavior distribution with regard to smaller, be more possible to establish PoT and diopter be in progress between relational model (i.e. K=0's
Probability is smaller).Therefore, δ values are bigger theoretically, and the relational model between the PoT established and diopter progress is more accurate.
In a kind of preferred embodiment of the present invention, each pixel can establish PoT and be in progress it with diopter
Between cum rights linear regression model (LRM), the slope (K) of the model represents and is associated with property between certain behavioural characteristic and diopter progress
And intensity, if the value is positive value, explanation eye is accustomed to well, and the bigger behavioural habits of positive value are better, and represent the user uses eye
Behavior has protective effect to myopia on the whole;The value is negative value, and explanation is bad with eye custom, and the smaller behavioural habits of negative value are more not
Good, represent the user uses eye behavior on the whole to the dangerous effect of myopia;Wherein, the big data analysis system includes
The environment impact index generation module be used to generate and can reflect that user with the environment of eye behavioural habits quality influences to refer to
Number:In the present invention by the parameter nomenclature be " environment impact index " be one kind it is self-defined, just as anaemia, according to containing for hemoglobin
Amount it is determined that;Hypertension, be assured that with the value of diastolic pressure according to systolic pressure as;The present invention wants to set up an energy
The parameter of enough reflection eye behavioural habits quality:" environment impact index ".
In a kind of preferred embodiment of the present invention, the near work to user is worn using intelligent wearable device
It is carried out at the same time objective detecting and acquisition with outdoor exposure data, the frequency of gathered data is 4-6s/ times, and the intelligence is wearable
The data of equipment acquisition can be sent to cell phone application by bluetooth, and APP is transferred data to by network on server again.
The preferred embodiment of the present invention is described in detail above in association with attached drawing, still, the present invention is not limited to above-mentioned realities
The detail in mode is applied, within the scope of the technical concept of the present invention, a variety of letters can be carried out to technical scheme of the present invention
Monotropic type, these simple variants all belong to the scope of protection of the present invention.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case of shield, can be combined by any suitable means, in order to avoid unnecessary repetition, the present invention to it is various can
The combination of energy no longer separately illustrates.
In addition, various embodiments of the present invention can be combined randomly, as long as it is without prejudice to originally
The thought of invention, it should also be regarded as the disclosure of the present invention.
Claims (10)
1. a kind of method of relationship between analysis environmental factor and juvenile shortsightedness, which is characterized in that the method includes:
Step 1, objective detecting and acquisition are carried out at the same time to the near work of user and outdoor exposure data;
Step 2, the eye parameter of user is obtained;
Step 3, the eye parameter of the near work of user and outdoor exposure data and user is respectively transmitted to cloud platform
It is stored;
Step 4, the near work that cloud platform database is stored using big data analysis system and outdoor exposure data with
And the eye parameter of user carries out noise reduction and conversion according to the requirement of big data analysis, then to user with eye behavioural characteristic into
Row extraction, and to being associated with the eye parameter of eye behavioural characteristic and user, and then illustrate environmental factor and fall ill to myopia
Influence.
2. the method for relationship between analysis environmental factor according to claim 1 and juvenile shortsightedness, which is characterized in that
The eye parameter of the user includes:The objective refraction number of degrees and axis oculi data.
3. the method for relationship between analysis environmental factor according to claim 1 and juvenile shortsightedness, which is characterized in that
Big data analysis system includes:CPU processor, data management module, behavior characteristic extraction module, correlation model module and optimal
Model decision module and environment impact index generation module;Wherein,
The data management module is used near work and the eye of outdoor exposure data and user to cloud platform storage
Parameter carries out noise reduction and conversion according to the requirement of big data analysis;
The behavior characteristic extraction module be used for using cloud platform storage near work data and outdoor exposure data, to
Being extracted with eye behavioural characteristic for family, depicts the behavioural characteristic of different user;
After the correlation model establishes module for being completed with the extraction of eye behavioural characteristic in user, established using correlation model
Contacting between behavioural characteristic and eye parameter is played, is to establish being associated between behavioural characteristic and diopter progress;
The optimal models decision module determines optimal models for selecting;
The environment impact index generation module, which is used to generate, can reflect that the environment with eye behavioural habits quality of user influences
Index;
The CPU processor is used to coordinate the work and data analysis of modules.
4. the method for relationship between analysis environmental factor according to claim 3 and juvenile shortsightedness, which is characterized in that
The data management module filters the data i.e. noise of high frequency using fast Fourier variation.
5. the method for relationship between analysis environmental factor according to claim 3 and juvenile shortsightedness, which is characterized in that
The user's includes with eye behavioural characteristic:The illumination (EI) of operating distance (VD) and surrounding enviroment, the VD data after noise reduction
2 dimension spaces (spaces VD-EI) are mapped to EI data, the longitudinal axis is VD, and horizontal axis is log10 (EI), just obtains the row of user
For scatter chart, then the behavior curve of all users is overlapped respectively, just obtains the behavior distributed heat of the user group
Try hard to, depict the user group at once uses eye behavioural characteristic.
6. the method for relationship between analysis environmental factor according to claim 3 and juvenile shortsightedness, which is characterized in that
The index of the diopter progress is at least the changing value of the changing value Δ SER and axis oculi (AL) of 2 years equivalent sphere mirror degrees (SER)
ΔAL;Wherein,
The SER=S+1/2C;S and C is the concave-sphere number of degrees and column obtained by rafractive after paralysis cilia-like muscle respectively
Mirror degree number;
The Δ SER=SER lasts-SER baselines, Δ AL=AL last-AL baselines;SER lasts and AL lasts respectively represent
The refractive diopter and axis oculi data that user's last time provides, SER baselines and AL baselines are expressed as user and provide for the first time
Refractive diopter and axis oculi data.
7. the method for relationship between analysis environmental factor according to claim 6 and juvenile shortsightedness, which is characterized in that
The critical assumptions for illustrating to establish the model are also needed to before the correlation model establishes module work, then need to consider around it
The influence of contiguous pixels is assumed with obeying:As unit of pixel, calculate every user behavior for including in each pixel when
Between account for the ratio (PoT) of user group behavior total time, the pixel of different distance is given using radial basis function (RBF kernel functions)
Tax power is carried out, then reuses cum rights linear regression (WLR) to analyze the relationship between PoT and SER, the picture closer from the pixel
It is smaller that element influences bigger, remoter pixel influence;
For the RBF kernel functions of 2 pixel x and x ', given x and x ' is defined as relative to the weights of x:
||xind-x′ind||2Square of Euclidean distance between two pixels, the entire spaces VD-EI are divided into 40*40 picture
Element can give each pixel to assign a pair of of index value, to calculate the Euclidean distance between any two pixel, RBF kernel functions
Small weights can be assigned to remote pixel, big weights are assigned to close pixel.
8. the method for relationship between analysis environmental factor according to claim 7 and juvenile shortsightedness, which is characterized in that
When analyzing some pixel, need to limit a certain size a region using the pixel as the center of circle to determine coverage, wherein
Define the size in this region with parameter δ (0≤δ≤20), 2 times of δ is then all circles using certain pixel as the radius of the circle in the center of circle
In pixel have certain influence to the pixel.
9. the method for relationship between analysis environmental factor according to claim 3 and juvenile shortsightedness, which is characterized in that
Each pixel can establish the cum rights linear regression model (LRM) between PoT and diopter progress, and the slope (K) of the model represents
It is associated with property and intensity between certain behavioural characteristic and diopter progress, if the value is positive value, explanation is accustomed to well, just with eye
Value is bigger, and behavioural habits are better, and represent the user has protective effect to myopia on the whole with eye behavior;The value is negative value, is said
Bright bad with eye custom, the smaller behavioural habits of negative value are more bad, and represent the user has danger to myopia on the whole with eye behavior
Danger effect.
10. the method for relationship, feature exist between analysis environmental factor according to claim 1 and juvenile shortsightedness
In wearing to be carried out at the same time the near work and outdoor exposure data of user using intelligent wearable device and objective detecting and adopt
Collection, the frequency of gathered data is 4-6s/ times, and the data of the intelligence wearable device acquisition can be sent to mobile phone by bluetooth
APP, APP are transferred data to by network on server again.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810071276.7A CN108281197B (en) | 2018-01-25 | 2018-01-25 | Method for analyzing relationship between environmental factors and teenager myopia |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810071276.7A CN108281197B (en) | 2018-01-25 | 2018-01-25 | Method for analyzing relationship between environmental factors and teenager myopia |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108281197A true CN108281197A (en) | 2018-07-13 |
CN108281197B CN108281197B (en) | 2021-09-24 |
Family
ID=62804995
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810071276.7A Active CN108281197B (en) | 2018-01-25 | 2018-01-25 | Method for analyzing relationship between environmental factors and teenager myopia |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108281197B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109682426A (en) * | 2019-01-30 | 2019-04-26 | 苏州中视慧眼电子科技有限公司 | A kind of teenager's eye intelligent monitoring device |
CN109754885A (en) * | 2019-03-18 | 2019-05-14 | 杭州镜之镜科技有限公司 | Near-sighted forecasting system and method |
CN110047590A (en) * | 2019-04-22 | 2019-07-23 | 张卫东 | One kind can be used for myopia prevention and control purpose method and its intelligent terminal system |
CN110135529A (en) * | 2019-06-26 | 2019-08-16 | 重庆康萃医药科技有限公司 | The training time data analysing method and system that eye is adjusted |
CN116109121A (en) * | 2023-04-17 | 2023-05-12 | 西昌学院 | User demand mining method and system based on big data analysis |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1184710A1 (en) * | 1999-05-24 | 2002-03-06 | Shuxiang Xu | A spectacle with lens and prisms |
CN203595868U (en) * | 2013-11-14 | 2014-05-14 | 杨涛 | Eyeball optical view information collection glasses |
CN104905761A (en) * | 2015-06-02 | 2015-09-16 | 杭州镜之镜科技有限公司 | Individual eye use monitoring system |
CN105468147A (en) * | 2015-11-19 | 2016-04-06 | 宁波力芯科信息科技有限公司 | Intelligent device, system and method for preventing myopia |
CN107065224A (en) * | 2017-06-12 | 2017-08-18 | 哈尔滨理工大学 | Kopiopia recognition methods and its intelligent glasses based on big data |
CN107065226A (en) * | 2017-06-23 | 2017-08-18 | 邵建军 | The intelligent mirror holder of one kind preventing and treating myopia |
CN107767965A (en) * | 2017-11-14 | 2018-03-06 | 广东乐心医疗电子股份有限公司 | Health monitoring system and method for multi-factor correlation comparison |
-
2018
- 2018-01-25 CN CN201810071276.7A patent/CN108281197B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1184710A1 (en) * | 1999-05-24 | 2002-03-06 | Shuxiang Xu | A spectacle with lens and prisms |
CN203595868U (en) * | 2013-11-14 | 2014-05-14 | 杨涛 | Eyeball optical view information collection glasses |
CN104905761A (en) * | 2015-06-02 | 2015-09-16 | 杭州镜之镜科技有限公司 | Individual eye use monitoring system |
CN107595239A (en) * | 2015-06-02 | 2018-01-19 | 杭州镜之镜科技有限公司 | Individual uses eye monitoring system |
CN105468147A (en) * | 2015-11-19 | 2016-04-06 | 宁波力芯科信息科技有限公司 | Intelligent device, system and method for preventing myopia |
CN107065224A (en) * | 2017-06-12 | 2017-08-18 | 哈尔滨理工大学 | Kopiopia recognition methods and its intelligent glasses based on big data |
CN107065226A (en) * | 2017-06-23 | 2017-08-18 | 邵建军 | The intelligent mirror holder of one kind preventing and treating myopia |
CN107767965A (en) * | 2017-11-14 | 2018-03-06 | 广东乐心医疗电子股份有限公司 | Health monitoring system and method for multi-factor correlation comparison |
Non-Patent Citations (2)
Title |
---|
杨智宽 等: "杨智宽教授团队全球率先利用大数据技术,为近视眼临床防控开拓潜在新方向", 《HTTPS://WWW.AIERCHINA.COM/JJAE/MTBD/MYFT/4658.HTML》 * |
温龙波 等: "客观监测近视眼相关环境因素的新设备"云夹"的准确性和稳定性研究", 《中华眼视光与视觉科学杂志》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109682426A (en) * | 2019-01-30 | 2019-04-26 | 苏州中视慧眼电子科技有限公司 | A kind of teenager's eye intelligent monitoring device |
CN109754885A (en) * | 2019-03-18 | 2019-05-14 | 杭州镜之镜科技有限公司 | Near-sighted forecasting system and method |
WO2020186480A1 (en) * | 2019-03-18 | 2020-09-24 | 杭州镜之镜科技有限公司 | Myopia prediction system and method |
CN110047590A (en) * | 2019-04-22 | 2019-07-23 | 张卫东 | One kind can be used for myopia prevention and control purpose method and its intelligent terminal system |
CN110135529A (en) * | 2019-06-26 | 2019-08-16 | 重庆康萃医药科技有限公司 | The training time data analysing method and system that eye is adjusted |
CN116109121A (en) * | 2023-04-17 | 2023-05-12 | 西昌学院 | User demand mining method and system based on big data analysis |
CN116109121B (en) * | 2023-04-17 | 2023-06-30 | 西昌学院 | User demand mining method and system based on big data analysis |
Also Published As
Publication number | Publication date |
---|---|
CN108281197B (en) | 2021-09-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108281197A (en) | A method of relationship between analysis environmental factor and juvenile shortsightedness | |
CN106060142A (en) | Mobile phone capable of checking eyesight, and method for checking eyesight by using mobile phone | |
CN106236115A (en) | A kind of psychological test system | |
Chen et al. | Predicting the effect of street environment on residents' mood states in large urban areas using machine learning and street view images | |
CN106469302A (en) | A kind of face skin quality detection method based on artificial neural network | |
CN105224285A (en) | Eyes open and-shut mode pick-up unit and method | |
CN115547497B (en) | Myopia prevention and control system and method based on multi-source data | |
AU2021101742A4 (en) | Method for Analyzing Relationship between Environmental Factors and Juvenile Myopia | |
US20170185909A1 (en) | Systems and methods for performing real-time convolution calculations of matrices indicating amounts of exposure | |
KR20220053544A (en) | How to determine risk indicators for myopia | |
CN110378736A (en) | The method that tourist experiences satisfaction to natural resources is evaluated by facial expression recognition | |
CN112987910B (en) | Testing method, device, equipment and storage medium of eyeball tracking equipment | |
CN110276228A (en) | Multiple features fusion video fire hazard recognizer | |
CN114052654A (en) | Dynamic eye health management system | |
CN103829952B (en) | For finding User's Interface and the method for user auditory sensitivity on intelligent mobile phone | |
TWI554245B (en) | Corrective lens prescription adaptation system for personalized optometry, method and computer program product thereof | |
CN116466823A (en) | Automatic community environment quality identification and evaluation method, system and equipment | |
CN116597946A (en) | Teenager mental health detection method based on house-tree-person | |
US20220395206A1 (en) | Cognitive assessment system based on eye movement | |
CN110147728A (en) | Customer information analysis method, system, equipment and readable storage medium storing program for executing | |
CN110287797B (en) | Refractive screening method based on mobile phone | |
CN109344791B (en) | Identification and identification method based on intelligent face scanning | |
KR102595038B1 (en) | Methods and systems for adapting human visual and/or visual-motor behavior | |
CN106725364B (en) | Controller fatigue detection method and system based on probability statistical method | |
CN111428577A (en) | Face living body judgment method based on deep learning and video amplification technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |