CN108288505A - A kind of Mental health evaluation method of visual analysis - Google Patents
A kind of Mental health evaluation method of visual analysis Download PDFInfo
- Publication number
- CN108288505A CN108288505A CN201810085738.0A CN201810085738A CN108288505A CN 108288505 A CN108288505 A CN 108288505A CN 201810085738 A CN201810085738 A CN 201810085738A CN 108288505 A CN108288505 A CN 108288505A
- Authority
- CN
- China
- Prior art keywords
- mental health
- user
- data
- visual analysis
- feature
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Psychiatry (AREA)
- Engineering & Computer Science (AREA)
- Educational Technology (AREA)
- Biomedical Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Physics & Mathematics (AREA)
- Child & Adolescent Psychology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Developmental Disabilities (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention relates to a kind of Mental health evaluation methods of visual analysis, belong to data visualization application technical field.This method includes four parts：The data inputting of 90 Mental health evaluation scales of SCL is completed at data inputting interface；Visual analysis is carried out to the data of current typing, and corresponding Improving advice is provided according to evaluation result combination historical data analysis result using binding block diagram, line chart；The historical data of user is analyzed using feature selecting algorithm, result is presented using scatterplot tree graph；Different regions, age, industry, the whole of the mental health state of gender are presented.A kind of method being applied to visual analysis technology in Mental health evaluation of the present invention, it is theoretical based on data visualization and Mental health evaluation, visual analysis is carried out to the Mental health evaluation data of user, as a result, accurately, it is feasible, especially it is convenient for user that can find the Psychological Health Problem of oneself in time, adjusts the mental health state of oneself.
Description
Technical field
The invention belongs to data visualizations and Mental health evaluation technical field, are related to a kind of mental health of visual analysis
Appraisal procedure.
Background technology
With economic and society development, the basic living of people is met, starts to put forward higher requirements health
With standard.Other than the stable physiological health of prevention of disease, holding, mental health increasingly becomes nowadays of people's attention
Focus, it runs neck and neck with physiological health, becomes one of the key index for weighing level of human health.Mental health visualizes energy
Enough by graphic form intuitively to we reflect there are the problem of, excavate potential information.But with the diversified production of data
Raw, the demand it is impossible to meet people to information, visual analysis (Visual Analytics) are used as new simple chart
Emerging analysis method is come into being.A kind of important method of the visual analysis as big data analysis, can effectively make up calculating
The disadvantage of machine automated analysis method and deficiency.It allows to detect expected information, and offer is quick, is amenable to and is conducive to
The assessment of understanding can explore unknown content with providing and significantly more efficient exchange evaluation measures.
Achievement in research of the visual analysis on psychology shows：Visualization is in the side such as experimental psychology, mental measurement, cognition
Face has certain achievement in research.Current existing mental health visual research is concentrated mainly on psychological health education teaching can
In establishment depending on changing system, the space-time limitation that tradition is given lessons has been broken in the establishment of this system, can be connected to and be taught by internet
Scene and distal end classroom are learned, realizes strange land interaction.Mental health is visually studied, and is removed and is visualized system to psychological health education
It is to be detected in mental health to visual analysis technology and assess the exploration applied there are one important directions outside the research of system.
Although having there is researcher that visual analysis technology is applied in mental health at present, grinding in this respect
Study carefully and is still in the starting stage.With visualization technique in other field compared with, mental health is more close to people’s lives,
It is closely bound up with people's health.Already present Mental health evaluation system is logging data in table form, then will knot
Fruit is provided in a manner of word, number, cannot intuitively describe the Psychological Health Problem of user.
Invention content
In view of this, the purpose of the present invention is to provide a kind of Mental health evaluation methods of visual analysis, for existing
Mental health evaluation system the Psychological Health Problem of user, the psychology of visual analysis proposed by the present invention cannot be described intuitively
Health evaluating method carries out visual analysis to the assessment result of user, user is helped to understand the mental health state of oneself in time,
And analyze oneself existing potential Psychological Health Problem.
In order to achieve the above objectives, the present invention provides the following technical solutions：
A kind of Mental health evaluation method of visual analysis, this method comprise the following steps：
S1：User's typing essential information；
S2：The data inputting of Mental health evaluation scale is completed at data inputting interface；
S3：Visual analysis is carried out to the data of current typing using binding block diagram, line chart, helps user to rigid typing
Mental health data analyzed, and corresponding improve is provided according to evaluation result combination historical data analysis result and is built
View；
S4：The historical data of user is analyzed using feature selecting algorithm, is in result using scatterplot tree graph
It is existing, it helps user to find most susceptible and is constantly in the factor and problem of sub-health state；
S5：Whole presentation is carried out to the mental health state of different regions, age, industry, gender, user is allow to check
The mental health state of different crowd.
Further, typing is carried out as data using SCL-90 Mental health evaluations scale in the step S2.
Further, the step S4 includes specifically：
S41：It is changed with time progress to the total score of user's history data and ten factors using area-graph and line chart
Visual analysis helps user to understand the total ripple situation of the mental health of oneself；
S42：All historical datas of user are analyzed using feature selecting algorithm, user is helped to find most susceptible
With the factor and problem for being constantly in sub-health state.
Further, feature selecting algorithm described in step S42 is the correlation whether dissipated from feature with feature with target
Two aspects to carry out feature selecting to the factor and problem；
It is selected using variance back-and-forth method and fluctuates the big factor and problem, as user is most susceptible to the factor of influence and asks
Topic；
Using the Logic Regression Models with L1 penalty terms filter out with the higher factor of target correlation and problem, as use
Family is always at the factor and problem of sub-health state.
Further, the variance back-and-forth method is specially：
S421：The variance of each feature is calculated, then according to the threshold value of setting, variance is selected to be more than the feature of threshold value；
S422：Feature is selected using the VarianceThreshold classes in the libraries feature_selection, will not met
All features of threshold value are deleted.
Further, the Logic Regression Models with L1 penalty terms are specially：
Use the logistic regression mould of the SelectFromModel class junction belt L1 penalty terms in the libraries feature_selection
Type, to select feature；
When user is when historical data quantity is less than given threshold, passes through the section fallen within per subfactor to user and carry out
The result for counting to filter out the Logic Regression Models with L1 penalty terms is corrected.
Further, essential information described in step S1 includes：Gender, age, occupation, place provinces and cities.
Further, the problem includes：Do not have, is very light, moderate, weighting, serious；
The factor include somzatization, obsessive symptoms, interpersonal relation sensitivity, depression and anxiety, it is hostile, terrified, bigoted,
Psychotic disease and other.
The beneficial effects of the present invention are：The Mental health evaluation method of a kind of visual analysis provided by the invention, in base
On the basis of data visualization, using the thinking of visual analysis, disclosed not in abstract data using visualization is possessed
Know pattern, find the advantage of neodoxy to solve subjectivity and abstractness feature possessed by mental health data, psychology is good for
Health assessment data are analyzed, final that user is helped to understand the mental health state of oneself, find oneself existing mental health
Problem, and fed back in time.The method of the invention overcomes previous Mental health evaluation system and cannot intuitively describe to use
The Psychological Health Problem at family can get information about the mental health state of oneself in time, while also obtain the tune that system provides
The system of the suggestion of whole mental health, this method exploitation can be deployed on the net, and user is easy to use, greatly improves user's
Usage experience.
Description of the drawings
In order to keep the purpose of the present invention, technical solution and advantageous effect clearer, the present invention provides following attached drawing and carries out
Explanation：
Fig. 1 is the flow chart of the Mental health evaluation method of visual analysis of the present invention；
Fig. 2 is the data flow diagram of the Mental health evaluation method of visual analysis of the present invention；
Fig. 3 is the binding block diagram of SCL-90 scale data of certain user；
Fig. 4 is the scatterplot tree graph of certain user's history data.
Specific implementation mode
Below in conjunction with attached drawing, the preferred embodiment of the present invention is described in detail.
As shown in Figure 1, a kind of Mental health evaluation method of visual analysis, includes the following steps：
New user's registration account and typing essential information, essential information include：Gender, age, occupation, place provinces and cities.
Have account user can direct login system, analyze the data of oneself.
1, the Mental health evaluation scale studied using SCL-90 scales as this, in data inputting interface typing scale
Data.
2, visual analysis is carried out to the data of rigid typing, using binding block diagram to SCL-90 Mental health evaluation scales
90 problems are analyzed, it can be found which the problem of user's each degree has, emphasis is carried out to serious and the problem of laying particular stress on
Concern, and can check seriously and which factor respectively belonged to the problem of weighting.It is each in SCL-90 Mental health evaluation scales to ask
There are five degree for topic, respectively：Do not have, is very light, moderate, weighting, serious.
3, statistical classification is carried out to the data of rigid typing, 90 problems is attributed to ten factors, then use line chart pair
Factor outcomes are presented, and are compared with SCL-90 standard norms, and the degree at each factor outcomes of user is provided.
SCL-90 Mental health evaluations scale includes ten factors altogether, respectively：Somzatization, obsessive symptoms, interpersonal relation sensitivity, suppression
Strongly fragrant, anxiety, hostile, terrified, bigoted, psychotic disease and other；There are four degree for factor outcomes in SCL-90 standard norms, divide
It is not：Normally, slightly, moderate, severe.
4, pass through the analysis knot of the visual analysis result combination historical data to current SCL-90 Mental health evaluations data
Fruit provides corresponding Improving advice for user.The Improving advice of proposition should discuss with professional psychological consultation expert and provide, and need
There is certain generality, it is also desirable to which there is certain particularity.
5, the historical data of user is analyzed, usable floor area figure and line chart to the total score of user and each factor with
The trend of time change is presented, and the mental health of customer analysis oneself is helped to change with time situation, and psychology is strong
The fluctuation period of health situation.
6, feature selecting is carried out using the libraries feature_selection in sklearn.Use feature selecting algorithm pair
The historical data of user is analyzed, and user is helped to find most susceptible and be constantly in the factor of sub-health state and ask
Topic.Come to carry out feature selecting to the factor and problem in terms of whether feature dissipates the correlation two with feature and target.
Fluctuate the larger factor and problem using variance back-and-forth method to select, i.e., user be most susceptible to influence the factor and
Problem.
The use of variance back-and-forth method：The variance of each feature is calculated first, then according to the threshold value of setting, selects variance
More than the feature of threshold value.Feature is selected using the VarianceThreshold classes in the libraries feature_selection.
VarianceThreshold is the simple Baseline Methods of feature selecting, it deletes all features that variance does not meet some threshold value.
Under default situations, it can delete all zero difference characteristics, i.e., have the feature of identical value in all samples.
Using the Logic Regression Models with L1 penalty terms come filter out with the higher factor of target correlation and problem, that is, use
Family is always at the factor and problem of sub-health state.
The use of Logic Regression Models with L1 penalty terms：Use the libraries feature_selection
The Logic Regression Models of SelectFromModel class junction belt L1 penalty terms, to select feature.SelectFromModel is one
The first transformer of kind, can be together with any estimator after fitting with coef_ or feature_importances_ attributes
It uses.If corresponding coef_ or feature_importances_ values are less than the threshold parameters provided, these are special
Sign is considered inessential and is removed.Other than numerically specified threshold, also built-in heuristic is used for
Threshold value is searched using string argument.It is available it is heuristic be " average value ", " median " and floating-point multiple.It is punished with L1 norms
The linear model penalized has sparse solution：Their many estimation coefficients are zero.When target is reduced together with another grader
When the dimension of the data used, they can select nonzero coefficient one with feature_selection.SelectFromModel
It rises and uses.It is that linear_model.Lasso is used to return linear_ especially for the useful sparse estimation of this purpose
Model.LogisticRegression and svm.LinearSVC sorts out and classification.The history data store of user needs one
Process, when the historical data quantity of user is less than some threshold value, obtained result is inaccurate, so needing by repeatedly real
It tests and carrys out threshold value.When historical data quantity is less than some threshold value, by user is divided equally per subfactor the section that falls within into
Row counts to be corrected the result for using the Logic Regression Models with L1 penalty terms to filter out, and the accurate of result is improved with this
Degree.
7, the mental health data from Chinese 34 province different sexes, age, occupation, urban human are analyzed,
Understand the mental health state of the entirety and each factor of different crowd.User can select different conditions to check different crowd
Whole mental health state or some factor mental health state, can help user understand different crowd present in master
Want Psychological Health Problem, convenient for oneself present in Psychological Health Problem compare and analyze.
Specific embodiment：
The present invention provides a kind of Mental health evaluation method of visual analysis, is managed based on visual analysis and Mental health evaluation
By, it is necessary first to typing is carried out to the data of SCL-90 Mental health evaluation scales, to the number of rigid typing after logging data
According to analysis assessment is carried out, Psychological Health Problem existing for user is analyzed, it is normal to the assessment result and SCL-90 standards of each factor
Mould is compared, and result is obtained；The data of each typing of user are stored, the historical data of user is analyzed, helped
User has found most susceptible and the factor and problem that are constantly in sub-health state；Then according to evaluation result and history
Data results are that user proposes Improving advice；To from Chinese 34 province different sexes, age, occupation, urban human
Mental health data are analyzed, and the mental health state of the entirety and each factor of different crowd is understood.As shown in Figure 1, this hair
Bright the method specifically includes following steps：
Step 1：Register account number.
In view of ratee individual privacy and conveniently the data of user are stored, so each user is first
Need to create the account of oneself when secondary logging data, and typing some basic informations, essential information includes：Gender, age, duty
Industry, place provinces and cities.The user for having account can directly log in typing and analysis data that existing account carries out data.
Step 2：Typing SCL-90 Mental health evaluation scale data, as shown in Figure 2.
SCL-90 is suitable for 16 years old or more adult as one of foremost Mental health test scale in the world,
It is widely used in each mental disease outpatient service.SCL-90 reflects the psychologic situation of 10 aspects using 10 factors respectively,
It can assist in individual from emotion, thinking, living habit etc. to understand the mental health degree of oneself.
SCL-90 scales include 90 entries, totally 9 subscales, i.e. somzatization, obsessive symptoms, interpersonal relation sensitivity, suppression
Strongly fragrant, anxiety, hostile, terrified, bigoted and psychotic disease.
Somzatization：Including Isosorbide-5-Nitrae, 12,27,40,42,48,49,52,53,56 and 58, totally 12, the subjective body of main reflection
Body sense of discomfort.
Obsessive symptoms：3,9,10,28,38,45,46,51,55 and 65, totally 10, reflect obsessive symptoms group clinically.
Interpersonal relation sensitivity：Including 6,21,34,36,37,41,61,69 and 73, totally 9, certain individuals are referred mainly to not certainly
It is especially more prominent when compared with other people in sense and inferiority complex.
Depression：It is main to reflect and clinic including 5,14,15,20,22,26,29,30,31,32,54,71 and 79, totally 13
The symptom of upper depressive symptom faciation contact.
Anxiety：Including 2,17,23,33,39,57,72,78,80 and 86, totally 10 projects, reflection clinically obviously with
The mental symptom and experience that Anxietysyndrome is associated.
It is hostile：Including 11,24,63,67,74 and 81, totally 6, mainly reflect disease from thinking, emotion and three aspect of behavior
The hostile performance of people.
It is terrified：Including 13,25,47,50,70,75 and 82, totally 7, it is anti-with traditional phobism or agoraphobia institute
The content reflected is almost the same.
It is bigoted：Including 8,18,43,68,76 and 83, totally 6, main reflection is suspected with beziehungswahn etc..
Psychotic disease：Including 7,16,35,62,77,84,85,87,88 and 90, totally 10, reflect phonism, thought broadcasting,
The schizophrenias sample symptom project such as feeling of being revealed.
Remaining 19,44,59,60,64,66 and 89 totally 7 projects, fail to be included into the above-mentioned factor, they, which mainly reflect, sleeps
Dormancy and diet situation.In some analyses, it is classified as the factor 10：" other ".
Step 3：Visual analysis is carried out to the SCL-90 Mental health evaluation scale data of rigid typing.
Step 301：90 problems of SCL-90 Mental health evaluation scales are presented using binding block diagram, column
Figure can check the scoring event of each problem of user.The identical problems link of degree together, is used color by binding block diagram
The factor is distinguished, columnar height is used to indicate the score of each problem, is said to the color represented by each factor
It is bright.It can check that each degree (do not have, slightly, moderate, weighting, serious) is specific comprising which by moving to mouse in column
The problem of, the binding block diagram of each degree of certain user is as shown in Figure 3.
Step 302：The result of SCL-90 Mental health evaluation scales is compared with the standard norm of SCL-90 scales,
The total evaluation result of each factor is presented using line chart, factor line chart helps customer analysis to show that oneself is needed most
The factor of concern.
SCL-90 standard norms：
| Because of sub-project | Norm | Because of sub-project | Norm |
| Somzatization | 1.37±0.48 | It is terrified | 1.23±0.41 |
| Obsessive symptoms | 1.62±0.58 | It is bigoted | 1.43±0.57 |
| Interpersonal relation sensitivity | 1.65±0.51 | Psychotic disease | 1.29±0.42 |
| Depression | 1.50±0.59 | Total score | 129.96±38.76 |
| Anxiety | 1.39±0.43 | It is total to divide equally | 1.44±0.43 |
| It is hostile | 1.48±0.56 | Symptom is divided equally | 2.60±0.59 |
Step 303：In conjunction with current SCL-90 Mental health evaluations scale result and historical data analysis result to
Family proposes Improving advice.Improving advice obtains after should being discussed with psychologist, for more serious assessment result, it should adopt
The mode taken is to give user's prompt, it is proposed that user goes the Psychological Counseling Room of profession to treat.
Step 4：The historical data of user is analyzed using feature selecting algorithm, user is helped to find most susceptible
With the factor and problem for being constantly in sub-health state.
Step 401：Total score and each factor trend of changing with time are presented using area-graph and line chart, used
Family can check the total score or factor variations situation of specific certain day or certain time.
Step 402：Each problem of historical data is presented using scatterplot tree graph, as shown in figure 4, making between the factor
It is distinguished with color, the belonging relation of problem and the factor indicates that the size of the degree point at problem is indicated using line.
When analyzing user's history data, in terms of whether feature dissipates the correlation two with feature and target
To carry out feature selecting to the factor and problem.Using variance back-and-forth method the larger factor and problem, i.e. user are fluctuated to select most
It is easy the affected factor and problem.It is filtered out using the Logic Regression Models with L1 penalty terms higher with target correlation
The factor and problem, i.e. user is always at the factor and problem of sub-health state.When the historical data of user is more, use
With L1 penalty terms Logic Regression Models analysis data generate result and the actual goodness of fit it is higher, as a result with data record item
Number is in a linear relationship.When user's history data record item number is smaller, the Logic Regression Models analysis data production with L1 penalty terms
Raw result will appear larger deviation, so needing when the record strip number of user is less than some threshold value, by every to user
Subfactor is divided equally the section fallen within and is counted, and to be corrected to the result of feature selecting algorithm, improves the accuracy rate of result.
Step 5：According to multiple view theory, using the visualization views such as map and block diagram, stack diagram, word cloud to coming from
Chinese 34 province different sexes, the age, occupation, urban human mental health data analyzed, understand the whole of different crowd
The mental health state of body and each factor.
Finally, in order to facilitate the use of the user, the visualization scheme of Chinese and English two versions should be increased.
Finally illustrate, preferred embodiment above is only to illustrate the technical solution of invention and unrestricted, although passing through
Above preferred embodiment is described in detail the present invention, however, those skilled in the art should understand that, can be in shape
Various changes are made in formula and to it in details, without departing from claims of the present invention limited range.
Claims (8)
1. a kind of Mental health evaluation method of visual analysis, it is characterised in that：This method comprises the following steps：
S1：User's typing essential information；
S2：The data inputting of Mental health evaluation scale is completed at data inputting interface；
S3：Visual analysis is carried out to the data of current typing using binding block diagram, line chart, helps the heart of the user to rigid typing
Reason health data is analyzed, and provides corresponding Improving advice according to evaluation result combination historical data analysis result；
S4：The historical data of user is analyzed using feature selecting algorithm, result is presented using scatterplot tree graph, is helped
It helps user to find most susceptible and is constantly in the factor and problem of sub-health state；
S5：Whole presentation is carried out to the mental health state of different regions, age, industry, gender, user is allow to check difference
The mental health state of crowd.
2. a kind of Mental health evaluation method of visual analysis according to claim 1, it is characterised in that：The step S2
It is middle that typing is carried out as data using SCL-90 Mental health evaluations scale.
3. a kind of Mental health evaluation method of visual analysis according to claim 2, it is characterised in that：The step S4
Include specifically：
S41：Progress is changed with time visually to the total score of user's history data and ten factors using area-graph and line chart
Analysis helps user to understand the total ripple situation of the mental health of oneself；
S42：All historical datas of user are analyzed using feature selecting algorithm, user is helped to find most susceptible and one
The straight factor and problem for being in sub-health state.
4. a kind of Mental health evaluation method of visual analysis according to claim 3, it is characterised in that：In step S42
The feature selecting algorithm be come in terms of whether feature dissipates the correlation two with feature and target to the factor and problem into
Row feature selecting；
It is selected using variance back-and-forth method and fluctuates the big factor and problem, as user is most susceptible to the factor and problem of influence；
Using the Logic Regression Models with L1 penalty terms filter out with the higher factor of target correlation and problem, as user is total
It is the factor and problem in sub-health state.
5. a kind of Mental health evaluation method of visual analysis according to claim 4, it is characterised in that：The variance choosing
The method of selecting is specially：
S421：The variance of each feature is calculated, then according to the threshold value of setting, variance is selected to be more than the feature of threshold value；
S422：Feature is selected using the VarianceThreshold classes in the libraries feature_selection, threshold value will not met
All features deleted.
6. a kind of Mental health evaluation method of visual analysis according to claim 5, it is characterised in that：Band L1 penalty terms
Logic Regression Models be specially：
Using the Logic Regression Models of the SelectFromModel class junction belt L1 penalty terms in the libraries feature_selection, come
Select feature；
When user is when historical data quantity is less than given threshold, counted by the section fallen within per subfactor to user
Result to be filtered out to the Logic Regression Models with L1 penalty terms is corrected.
7. a kind of Mental health evaluation method of visual analysis according to claim 1, it is characterised in that：Institute in step S1
Stating essential information includes：Gender, age, occupation, place provinces and cities.
8. a kind of Mental health evaluation method of visual analysis according to claim 4, it is characterised in that：The problem
Including：Do not have, is very light, moderate, weighting, serious；
The factor includes somzatization, obsessive symptoms, interpersonal relation sensitivity, depression and anxiety, hostile, terrified, bigoted, spiritual
Characteristic of disease and other.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810085738.0A CN108288505A (en) | 2018-01-29 | 2018-01-29 | A kind of Mental health evaluation method of visual analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810085738.0A CN108288505A (en) | 2018-01-29 | 2018-01-29 | A kind of Mental health evaluation method of visual analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108288505A true CN108288505A (en) | 2018-07-17 |
Family
ID=62835935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810085738.0A Pending CN108288505A (en) | 2018-01-29 | 2018-01-29 | A kind of Mental health evaluation method of visual analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108288505A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110393539A (en) * | 2019-06-21 | 2019-11-01 | 合肥工业大学 | Psychological abnormality detection method, device, storage medium and electronic equipment |
| CN112599245A (en) * | 2020-12-16 | 2021-04-02 | 中国人民解放军总医院第八医学中心 | Mental health index evaluation method and system |
| CN114203283A (en) * | 2021-12-31 | 2022-03-18 | 中国科学院自动化研究所 | Sand table game quantitative analysis system, method and equipment |
| CN115035974A (en) * | 2022-08-11 | 2022-09-09 | 北京科技大学 | Psychological assessment data management system and method |
-
2018
- 2018-01-29 CN CN201810085738.0A patent/CN108288505A/en active Pending
Non-Patent Citations (5)
| Title |
|---|
| ROLIN-刘瑞: "特征选择（feature_selection）", 《CSDN：HTTPS://BLOG.CSDN.NET/U010670689/ARTICLE/DETAILS/73196546》 * |
| 余江: "民航飞行学生心理应激状况评估系统的开发研究", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
| 田伟翠: "高职新生SCL－90常模的建立———以福建卫生职业技术学院为例", 《贵阳学院学报（自然科学版）》 * |
| 钱亮亮等: "改进星形图和超维树在健康信息系统中的应用", 《北京工商大学学报（自然科学版）》 * |
| 陈谊等: "多维数据的信息可视化方法及应用研究", 《系统仿真学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110393539A (en) * | 2019-06-21 | 2019-11-01 | 合肥工业大学 | Psychological abnormality detection method, device, storage medium and electronic equipment |
| CN110393539B (en) * | 2019-06-21 | 2021-11-23 | 合肥工业大学 | Psychological anomaly detection method and device, storage medium and electronic equipment |
| CN112599245A (en) * | 2020-12-16 | 2021-04-02 | 中国人民解放军总医院第八医学中心 | Mental health index evaluation method and system |
| CN114203283A (en) * | 2021-12-31 | 2022-03-18 | 中国科学院自动化研究所 | Sand table game quantitative analysis system, method and equipment |
| CN115035974A (en) * | 2022-08-11 | 2022-09-09 | 北京科技大学 | Psychological assessment data management system and method |
| CN115035974B (en) * | 2022-08-11 | 2022-11-15 | 北京科技大学 | Psychological assessment data management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Goldsmith | The status of health status indicators. | |
| Raykov et al. | Basic statistics: An introduction with R | |
| Au et al. | A critical review of end-user information system satisfaction research and a new research framework | |
| Ruiz-Castillo et al. | The skewness of scientific productivity | |
| CN108288505A (en) | A kind of Mental health evaluation method of visual analysis | |
| Bernard et al. | Using dashboard networks to visualize multiple patient histories: a design study on post-operative prostate cancer | |
| Walter et al. | Development and evaluation of a computer adaptive test for ‘Anxiety’(Anxiety-CAT) | |
| Harrison et al. | Personal construct theory in the measurement of environmental images | |
| Howley | Less money or better health? Evaluating individual’s willingness to make trade-offs using life satisfaction data | |
| Jacso | The pros and cons of computing the h‐index using Web of Science | |
| Wiggins et al. | Types of judges and cue utilization in judgments of intelligence. | |
| US8684741B2 (en) | Method and apparatus for analyzing pattern colorings and evaluating psychological status or disorders in art therapy | |
| CN112927782B (en) | Heart health state early warning system based on text emotion analysis | |
| Huang | Dimensions of Taiwanese/Chinese identity and national identity in Taiwan: a latent class analysis | |
| Riffe et al. | Time-to-death patterns in markers of age and dependency | |
| US9990469B2 (en) | Inferring a state of a system over time | |
| Kreisman | Evaluating academic outcomes of Head Start: An application of general growth mixture modeling | |
| CN105893748A (en) | Happy index evaluation method and system based on rough set theory | |
| Colledani et al. | Rasch models in the analysis of repgrid data | |
| Douven et al. | Spatial analysis in health research | |
| Meuschke et al. | GUCCI-guided cardiac cohort investigation of blood flow data | |
| Al’Abri et al. | Association between motivation to leave the teaching profession profiles and job satisfaction among Omani teachers: a latent profile analysis | |
| Mulyanto et al. | The accuracy of self-report versus objective assessment for estimating socioeconomic inequalities in disease prevalence in Indonesia | |
| Selvin et al. | Breast cancer detection: maps of 2 San Francisco Bay area counties. | |
| Jackson | Analysing data |
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: 20180717 |
|
| RJ01 | Rejection of invention patent application after publication |