CN109472299A - A kind of Impoverished University Students recognition methods based on smart card big data - Google Patents
A kind of Impoverished University Students recognition methods based on smart card big data Download PDFInfo
- Publication number
- CN109472299A CN109472299A CN201811221651.8A CN201811221651A CN109472299A CN 109472299 A CN109472299 A CN 109472299A CN 201811221651 A CN201811221651 A CN 201811221651A CN 109472299 A CN109472299 A CN 109472299A
- Authority
- CN
- China
- Prior art keywords
- impoverished
- data
- smart card
- student
- university students
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention mainly utilizes campus big data to realize accurate poverty alleviation, and in particular to a kind of Impoverished University Students recognition methods based on smart card big data includes: to establish cloud campus data centre;Establish feature extraction model;The campus smart card consumption feature data of university student are extracted from the cloud campus data centre according to the feature extraction model;Establish Impoverished University Students identification model based on support vector machines, using quartic polynomial as smooth function;According to the Impoverished University Students characteristic data set training Impoverished University Students identification model obtained in advance: identifying poor student according to the Impoverished University Students identification model after the campus smart card consumption feature data and the training.The present invention can provide aid decision to the judge of Impoverished University Students for major colleges and universities and regulatory authorities, and the selected fairness of Impoverished University Students can be improved, promote the validity of Impoverished University Students management work.
Description
Technical field
The present invention mainly utilizes campus big data to realize accurate poverty alleviation, and in particular to a kind of based on the poor of smart card big data
Tired university student's recognition methods.
Background technique
According to the higher education statistical data that the Ministry of Education announces, about 28,930,000 people of national institution of higher learning student at school's quantity in 2016
(not including adult and Web education), wherein 20% student is poor student, 8% student is extremely poor student.Poor student's goes to school
With problem concerning life, concerning social equity and harmonious, and the test to state education resource reasonable distribution.Although education department is
It has been formulated a series of system and method goes identification poor student, but these systems and method also can in the actual operation process
The problem of being faced with the validity of identification, that is, be identified as student that whether student of poor student is not identified than those with greater need for
The help of state and society.How more efficiently to identify poor student, has become each colleges and universities and learn urgently to be resolved one of Ministry of worker's door
A problem.
With the determination of the first batch of Experiment site school of Ministry of Education's " Intelligent campus ", large data center construction has been included in colleges and universities basis and has set
Construction plan is applied, and smart card big data is always the most direct and important resource of campus big data.Gradually with data volume
Increase, using historical data, Impoverished University Students are identified using machine learning method, become the common recognition of students managing worker.
Wherein, campus big data how is effectively utilized, innovative identification Impoverished University Students accomplish accurately poverty alleviation, mitigate its life
Living and study trouble and worry, is the major tasks that colleges and universities' big data utilizes.
In practice, since a few years ago, data research project verification is less in the school to research for colleges and universities, cause theoretical research deficient.
Although existing certain methods still can be used for the identification of the poor student based on campus big data, specific data feelings are considered
Border, there are still larger problems for the validity of these methods.It is main reason is that the data volume in database is huge and data
Dimension is complicated, and existing research fails to solve following two critical issues under such data characteristics: (1) from data center
Which type of data is extracted as input feature vector, which type of model (2) construct to complete identification process.
Summary of the invention
To solve the above problems, the present invention provides a kind of Impoverished University Students recognition methods based on smart card big data,
Include:
Establish cloud campus data centre B;
Establish feature extraction model;
The campus smart card consumption of university student is extracted from the cloud campus data centre B according to the feature extraction model
Characteristic;
Establish Impoverished University Students identification model based on support vector machines, using quartic polynomial as smooth function;
According to the Impoverished University Students characteristic data set training Impoverished University Students identification model obtained in advance:
It is poor according to the Impoverished University Students identification model identification after the campus smart card consumption feature data and the training
Tired life.
Optionally, the feature after the extraction includes: that the consumption in the morning, afternoon and evening monthly average of smart card is flat according to, the single moon in water
Equal data, Campus Shopping summation, smart card consume moon summation.
Optionally, the feature after the extraction further includes that class poor student assesses data.
Optionally, the Feature Selection Model of establishing includes:
1) obtains Impoverished University Students characteristic data set by samples selection:
Wherein m indicates the sum of database university student, xjIndicate the feature of j-th of university student, zj∈ { 0,1 } is indicated j-th
The poor classification of university student.
During modeling, training set is denoted as D1D is denoted as with test set2, i.e. D=D1∪D2。
2) it is to find an optimal model f that, which establishes the process of poor student's identification model,*∈ H, H be some to
Fixed abstract model space.
It is as follows to define identification model:
f(xi) indicate to use training dataset xiThe identification model of foundation, f*It indicates so that f (xi) classification results and reality
The smallest optimal models of border classification results error.
If it is as follows to define risk function
Risk function ε (f) is used to metric averaging meaning drag f (xi) the fine or not degree predicted in test data set.
The identification model is defined as:
Given training set D1, then the supporting vector machine model Jing Guo kernel function φ coring is defined as:
ω indicates that the normal vector of segmentation hyperplane, γ indicate the intercept of segmentation hyperplane, Rk+1Indicate the European sky of value
Between.(ω*,γ*) indicate the value so that when supporting vector machine model least risk.
It is as follows to define decision function:
Sign (f (x)) indicates that jump function, decision function d (x) indicate different classifications corresponding to each example, work as mould
Type ω*φ(x)T+γ*The example is indicated when >=0 above support hyperplane, decision function d (x) value is 1;As model ω*φ
(x)T+γ*The example is indicated when < 0 below support hyperplane, decision function d (x) value is -1.
The learning model of use is as follows:
Wherein, I=(1,1 ..., 1) ∈ Rk, φ: Rn→Rk, φ (A)T=(φ (x1)T,Learning model is the amendment to standard supporting vector machine model, can
The strong convexity of objective function is exported, and obtains optimal ω with this*And γ*Value.
The learning model is abbreviated as
Wherein,
The objective function of unconstrained optimization in the i.e. above-mentioned learning model of F (ω, γ).
Optionally, using quadrinomial smooth functionTo the objective function F of Non-smooth surface (ω,
Approximate substitution γ) is carried out, wherein quadrinomial smooth function
Wherein, coring function phi is defined as:
Wherein,
Indicate the mean value of each example in input consumption feature data, L1For the number of example.
Optionally, according to the Impoverished University Students identification model after the campus smart card consumption feature data and the training
Identification poor student includes: that the campus smart card consumption feature data are inputted identification model, is identified according to decision function d (x)
Poor student ,+1 is expressed as non-poor student, and -1 is expressed as poor student.
The beneficial effects of the present invention are: the present invention can comment Impoverished University Students for major colleges and universities and regulatory authorities
Offer aid decision is provided, the selected fairness of Impoverished University Students can be improved, promote the validity of Impoverished University Students management work;
In addition the Impoverished University Students status early warning that the present invention can be online according to consumption dynamic constitution and implementation, improves Impoverished University Students
Process trace.
Detailed description of the invention
Fig. 1 is the flow diagram of the embodiment of the present invention;
Fig. 2 is the Technology Roadmap of the embodiment of the present invention;
Fig. 3 is the smartcard features data sample table of 9 university students.
Specific embodiment
The present invention is described further below with reference to embodiment.
As shown in Figure 1, a kind of Impoverished University Students recognition methods based on smart card big data of the embodiment of the present invention includes
Following steps:
SO1 establishes cloud campus data centre B;
SO3 establishes feature extraction model;
SO5 extracts the campus smart card of university student according to the feature extraction model from the cloud campus data centre B
Consumption feature data;
SO7, establish based on support vector machines, using quartic polynomial as the Impoverished University Students of smooth function identification mould
Type;
SO9, according to the Impoverished University Students characteristic data set training Impoverished University Students identification model obtained in advance;
S11 knows according to the Impoverished University Students identification model after the campus smart card consumption feature data and the training
Other poor student.
Fig. 2 is the Technology Roadmap of the embodiment of the present invention, and wherein F1 (x) indicates the recognition function of Joe college, F2 (x) table
Show that the recognition function of collegegirl, PSSVM algorithm are recognizer proposed by the present invention.
In conjunction with whole technical route figure as shown in Fig. 2, one kind of the embodiment of the present invention is based on smart card big data
Impoverished University Students recognition methods be accomplished by
Step 1, cloud campus data centre B is established.
Cloud campus large data center is established after data improvement according to the actual conditions of oneself first in campus.
Step 2, on large data center basis, several feature extraction models are established, extract the campus intelligence of university student
Card consumption feature data obtain the characteristic data set of all students as input data source;
Extracted feature includes: the monthly average of consumption in the morning, afternoon and evening evidence, the single moon in water average data, campus of smart card
6 dimensions such as summation, smart card consumption moon summation of doing shopping also extract class poor student and assess number to promote recognition accuracy
According to as feature, add up to 7 dimensions.
The feature extraction that the present invention defines is as follows:
1) consumption statistic c (t), statistical time t ∈ [t1,t2],
WhereinFor reference standard, k (t) is the consumption frequency in statistical time section, cj(t) it indicates to disappear in the t period
The number taken,Indicate that student's same day consumes number cusum.Reference standardIt provides there are two types of modes, a kind of foundation
The average data of normal students consumption, is given by student-directed expert.Rule of judgment usesAs threshold value, it is
Because there is abnormal behavior of swiping the card in some students, for example help band meal etc., it may appear that spending amount is excessive to be more thanAt this time
Data are calculated according to the average consumption of student.
2) with the presence or absence of consumption n (t), daily statistical time t ∈ [t in the .t period1,t2],
K (t) is the consumption frequency in statistical time section.K (t) >=1 indicates that student had consumption within the period on same day t
Behavior, then n (t)=1;K (t)=0 indicates that consumer behavior was not present in student within the period on same day t, then n (t)=0.
3) monthly average consumption statistics x (t):
Wherein cj(t) it is counted according to (1) formula, nj(t) it is counted according to (2) formula, N is the number of days monthly counted, monthly average consumption x
(t) indicate that monthly t period overall consumption number consumes accumulative total degree divided by monthly.
4) campus smart card consumption feature data are constituted as follows:
Wherein,
xi1For i-th of monthly early dinner cost: time 6:00~8:00;
xi2Take for i-th of monthly lunch: time 11:00~13:00;
xi3For i-th of monthly dinner expense: time 16:30~19:30;
xi4For water rate average outgo in i-th month campus;
xi5For i-th month total cost of doing shopping in campus;
xi6For i-th month class's assessment data, data were by 0 or 1;
xi7For effectively consumption integrates in i-th month campus:
I=1,2 ..., 9 indicate the statistics month in school;It is three months total according to summer vacation and winter vacation in principle, it is remaining
Month.xi7Indicate i-th of monthly morning, the noon, dinner, water rate average outgo and shopping total cost summation.
Illustratively, Fig. 3 is the smartcard features data sample table of 9 university students.
Step 3, establish based on support vector machines, using quartic polynomial as the Impoverished University Students of smooth function identification mould
Type separates characteristic data set according to men and women, later, training data is selected to establish recognition methods;
Since there are significant differences in the consumer behavior of school by boy student and schoolgirl, so needing characteristic data set according to male
Female separates.Later, selection training data establishes identification model.
1) obtains Impoverished University Students characteristic data set by samples selection:
Wherein m indicates the sum of database university student, xjIndicate the feature of j-th of university student, zj∈ { 0,1 } is indicated j-th
The poor classification of university student.
During modeling, training set is denoted as D1D is denoted as with test set2, i.e. D=D1∪D2。
2) it is to find an optimal model f that, which establishes the process of poor student's identification model,*∈ H, H be some to
Fixed abstract model space.
It is as follows to define identification model:
f(xi) indicate to use training dataset xiThe identification model of foundation, f*It indicates so that f (xi) classification results and reality
The smallest optimal models of border classification results error.
If it is as follows to define risk function
Risk function ε (f) is used to metric averaging meaning drag f (xi) the fine or not degree predicted in test data set.
The identification model is defined as:
Given training set D1, then the supporting vector machine model Jing Guo kernel function φ coring is defined as:
ω indicates that the normal vector of segmentation hyperplane, γ indicate the intercept of segmentation hyperplane, Rk+1Indicate the European sky of value
Between.(ω*,γ*) indicate the value so that when supporting vector machine model least risk.
It is as follows to define decision function:
Sign (f (x)) indicates that jump function, decision function d (x) indicate different classifications corresponding to each example, work as mould
Type ω*φ(x)T+γ*The example is indicated when >=0 above support hyperplane, decision function d (x) value is 1;As model ω*φ
(x)T+γ*The example is indicated when < 0 below support hyperplane, decision function d (x) value is -1.
The learning model of use is as follows:
Wherein, I=(1,1 ..., 1) ∈ Rk, φ: Rn→Rk, φ (A)T=(φ (x1)T,Learning model is the amendment to standard supporting vector machine model, can
The strong convexity of objective function is exported, and obtains optimal ω with this*And γ*Value.
The learning model is abbreviated as
Wherein,
The objective function of unconstrained optimization in the i.e. above-mentioned learning model of F (ω, γ).
In identification model of the present invention, using quadrinomial smooth functionTo the target of Non-smooth surface
Function F (ω, γ) carries out approximate substitution, wherein quadrinomial smooth function
Is defined as:
Wherein coring function phi is selected as
Wherein,
Indicate the mean value of each example in input consumption feature data, L1For the number of example.
Step 4, identification model according to the present invention determines whether university student belongs to poor student.
The campus smart card consumption feature data are inputted into identification model, poor student is identified according to decision function d (x) ,+
1 is expressed as non-poor student, and -1 is expressed as poor student.
Described in the present invention specific embodiments are merely illustrative of the spirit of the present invention, technology belonging to the present invention
The technical staff in field can make various modifications or additions to the described embodiments or by a similar method
Substitution, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (7)
1. a kind of Impoverished University Students recognition methods based on smart card big data characterized by comprising
Establish cloud campus data centre B;
Establish feature extraction model;
The campus smart card consumption feature of university student is extracted from the cloud campus data centre B according to the feature extraction model
Data;
Establish Impoverished University Students identification model based on support vector machines, using quartic polynomial as smooth function;
According to the Impoverished University Students characteristic data set training Impoverished University Students identification model obtained in advance:
Poor student is identified according to the Impoverished University Students identification model after the campus smart card consumption feature data and the training.
2. a kind of Impoverished University Students recognition methods based on smart card big data according to claim 1, which is characterized in that
Feature after the extraction includes: the monthly average of consumption in the morning, afternoon and evening evidence, the single moon in water average data, Campus Shopping of smart card
Summation, smart card consume moon summation.
3. a kind of Impoverished University Students recognition methods method based on smart card big data according to claim 2, feature
It is, the feature after the extraction further includes that class poor student assesses data.
4. a kind of Impoverished University Students recognition methods based on smart card big data according to claim 2, which is characterized in that
The Feature Selection Model of establishing includes:
1) consumption statistic c (t), daily statistical time t ∈ [t1,t2],
WhereinFor reference standard, k (t) is the consumption frequency in statistical time section, cj(t) consumption in the t period is indicated
Number,Indicate that student's same day consumes number cusum.Reference standardIt provides there are two types of modes, a kind of foundation is just
The average data of normal college student's consumption, is given by student-directed expert.Rule of judgment usesAs threshold value, be because
Abnormal behavior of swiping the card occur for some students, for example help band meal etc., it may appear that spending amount is excessive to be more thanIt presses at this time
Data are calculated according to the average consumption of student.
2) with the presence or absence of consumption n (t), daily statistical time t ∈ [t in the .t period1,t2],
K (t) is the consumption frequency in statistical time section.K (t) >=1 indicates that student had consumption row within the period on same day t
For then n (t)=1;K (t)=0 indicates that consumer behavior was not present in student within the period on same day t, then n (t)=0.
3) monthly average consumption statistics x (t):
Wherein cj(t) it is counted according to (1) formula, nj(t) it is counted according to (2) formula, N is the number of days monthly counted, monthly average consumption x (t) table
Show that monthly t period overall consumption number consumes accumulative total degree divided by monthly.
4) campus smart card consumption feature data are constituted as follows:
Wherein,
xi1For i-th of monthly early dinner cost: time 6:00~8:00;
xi2Take for i-th of monthly lunch: time 11:00~13:00;
xi3For i-th of monthly dinner expense: time 16:30~19:30;
xi4For water rate average outgo in i-th month campus;
xi5For i-th month total cost of doing shopping in campus;
xi6For i-th month class's assessment data, data were by 0 or 1;
xi7For effectively consumption integrates in i-th month campus:
I=1,2 ..., 9 indicate the statistics month in school;It is three months total according to summer vacation and winter vacation in principle, the remaining moon
Part.xi7Indicate i-th of monthly morning, the noon, dinner, water rate average outgo and shopping total cost summation.
5. a kind of Impoverished University Students recognition methods based on smart card big data according to claim 4, which is characterized in that
Establishing based on support vector machines, the Impoverished University Students identification model using quartic polynomial as smooth function includes:
1) obtains Impoverished University Students characteristic data set by samples selection:
Wherein m indicates the sum of database university student, xjIndicate the feature of j-th of university student, zj∈ { 0,1 } indicates j-th of university
Raw poor classification.
During modeling, training set is denoted as D1D is denoted as with test set2, i.e. D=D1∪D2。
2) it is to find an optimal model f that, which establishes the process of poor student's identification model,*∈ H, H are some given pumpings
As the model space.
It is as follows to define identification model:
f(xi) indicate to use training dataset xiThe identification model of foundation, f*It indicates so that f (xi) classification results and actual classification
The smallest optimal models of resultant error.
If it is as follows to define risk function
Risk function ε (f) is used to metric averaging meaning drag f (xi) the fine or not degree predicted in test data set.
The identification model is defined as:
Given training set D1, then the supporting vector machine model Jing Guo kernel function φ coring is defined as:
ω indicates that the normal vector of segmentation hyperplane, γ indicate the intercept of segmentation hyperplane, Rk+1Indicate the theorem in Euclid space of value.
(ω*,γ*) indicate the value so that when supporting vector machine model least risk.
It is as follows to define decision function:
Sign (f (x)) indicates jump function, and decision function d (x) indicates different classifications corresponding to each example, as model ω*
φ(x)T+γ*The example is indicated when >=0 above support hyperplane, decision function d (x) value is 1;As model ω*φ(x)T+
γ*The example is indicated when < 0 below support hyperplane, decision function d (x) value is -1.
The learning model of use is as follows:
Wherein, I=(1,1 ..., 1) ∈ Rk, φ: Rn→Rk, φ (A)T=(φ (x1)T,Learning model is the amendment to standard supporting vector machine model, can
The strong convexity of objective function is exported, and obtains optimal ω with this*And γ*Value.
The learning model is abbreviated as
Wherein,
The objective function of unconstrained optimization in the i.e. above-mentioned learning model of F (ω, γ).
6. a kind of Impoverished University Students recognition methods based on smart card big data according to claim 5, which is characterized in that
Using quadrinomial smooth functionApproximate substitution is carried out to the objective function F (ω, γ) of Non-smooth surface,
Wherein quadrinomial smooth functionIs defined as:
Wherein, coring function phi is defined as:
Wherein,
Indicate the mean value of each example in input consumption feature data, L1For the number of example.
7. a kind of Impoverished University Students recognition methods based on smart card big data according to claim 6, which is characterized in that
Include: according to the Impoverished University Students identification model identification poor student after the campus smart card consumption feature data and the training
The campus smart card consumption feature data are inputted into identification model, poor student ,+1 table are identified according to decision function d (x)
It is shown as non-poor student, -1 is expressed as poor student.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811221651.8A CN109472299A (en) | 2018-10-19 | 2018-10-19 | A kind of Impoverished University Students recognition methods based on smart card big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811221651.8A CN109472299A (en) | 2018-10-19 | 2018-10-19 | A kind of Impoverished University Students recognition methods based on smart card big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109472299A true CN109472299A (en) | 2019-03-15 |
Family
ID=65663913
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811221651.8A Pending CN109472299A (en) | 2018-10-19 | 2018-10-19 | A kind of Impoverished University Students recognition methods based on smart card big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109472299A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109992592A (en) * | 2019-04-10 | 2019-07-09 | 哈尔滨工业大学 | Impoverished College Studentss recognition methods based on campus consumption card pipelined data |
CN110097142A (en) * | 2019-05-15 | 2019-08-06 | 杭州华网信息技术有限公司 | Poor student's prediction technique of behavior is serialized for student |
CN110135141A (en) * | 2019-04-28 | 2019-08-16 | 佛山科学技术学院 | The check method and device of a kind of student's identity card based on block chain according to the true and false |
CN112416914A (en) * | 2020-10-15 | 2021-02-26 | 三峡大学 | Difficult student identification and early warning method and system based on big data analysis |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106991187A (en) * | 2017-04-10 | 2017-07-28 | 武汉朱雀闻天科技有限公司 | The analysis method and device of a kind of campus data |
CN108460475A (en) * | 2017-12-20 | 2018-08-28 | 卓智网络科技有限公司 | Poor student's prediction technique and device based on network playing by students behavior |
CN108564117A (en) * | 2018-03-30 | 2018-09-21 | 华南理工大学 | A kind of poor student's auxiliary identification based on SVM |
-
2018
- 2018-10-19 CN CN201811221651.8A patent/CN109472299A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106991187A (en) * | 2017-04-10 | 2017-07-28 | 武汉朱雀闻天科技有限公司 | The analysis method and device of a kind of campus data |
CN108460475A (en) * | 2017-12-20 | 2018-08-28 | 卓智网络科技有限公司 | Poor student's prediction technique and device based on network playing by students behavior |
CN108564117A (en) * | 2018-03-30 | 2018-09-21 | 华南理工大学 | A kind of poor student's auxiliary identification based on SVM |
Non-Patent Citations (2)
Title |
---|
孙梦: "大数据时代精准识别高校贫困生研究", 《北京劳动保障职业学院学报》 * |
李春忠: "支撑向量机数据分类方", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109992592A (en) * | 2019-04-10 | 2019-07-09 | 哈尔滨工业大学 | Impoverished College Studentss recognition methods based on campus consumption card pipelined data |
CN109992592B (en) * | 2019-04-10 | 2020-12-08 | 哈尔滨工业大学 | College poverty and poverty identification method based on flow data of campus consumption card |
CN110135141A (en) * | 2019-04-28 | 2019-08-16 | 佛山科学技术学院 | The check method and device of a kind of student's identity card based on block chain according to the true and false |
CN110135141B (en) * | 2019-04-28 | 2022-11-01 | 佛山科学技术学院 | Block chain-based student certificate authenticity checking method and device |
CN110097142A (en) * | 2019-05-15 | 2019-08-06 | 杭州华网信息技术有限公司 | Poor student's prediction technique of behavior is serialized for student |
CN112416914A (en) * | 2020-10-15 | 2021-02-26 | 三峡大学 | Difficult student identification and early warning method and system based on big data analysis |
CN112416914B (en) * | 2020-10-15 | 2023-07-11 | 三峡大学 | Difficult student identification and early warning method and system based on big data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109472299A (en) | A kind of Impoverished University Students recognition methods based on smart card big data | |
CN107633265A (en) | For optimizing the data processing method and device of credit evaluation model | |
CN110532357A (en) | Generation method, device, equipment and the readable storage medium storing program for executing of ESG score-system | |
CN108256724B (en) | Power distribution network open capacity planning method based on dynamic industry coefficient | |
Xu et al. | A novel mobile personalized recommended method based on money flow model for stock exchange | |
CN109858761A (en) | Business risk predictor method and device | |
CN103177114A (en) | Cross-data-field shift learning sorting method based on differential manifolds | |
CN110751416A (en) | Method, device and equipment for predicting water consumption | |
Kameneva et al. | Distance learning for developing knowledge and skills in English language teaching | |
Wang et al. | Adaptive budget-portfolio investment optimization under risk tolerance ambiguity | |
Reisch et al. | Digitizing a sustainable future | |
CN109992592B (en) | College poverty and poverty identification method based on flow data of campus consumption card | |
CN107316081A (en) | A kind of uncertain data sorting technique based on extreme learning machine | |
Bolouri et al. | New approach for ranking efficient DMUs based on Euclidean norm in data envelopment analysis | |
Marginson | Productivity and efficiency in education | |
CN110084428A (en) | The Water Resources Allocation method and system calculated based on decisionmaker's preference scheme | |
Arroyo et al. | A Hybrid Intelligent Modeling approach for predicting the solar thermal panel energy production | |
Wang et al. | Research on energy consumption in household sector: a comprehensive review based on bibliometric analysis | |
Matintu | Mathematical model of Ethiopia's population growth | |
Si et al. | Construction and management method of university information platform based on big data technology | |
Wang et al. | A Poor College Students identified model based on decision tree | |
Wang et al. | Research on Daily Tourist Flow Prediction of Scenic Spots Based on Similar Day Clustering and LSSVM Model | |
Zhang et al. | [Retracted] Quantitative Evaluation and Empirical Analysis of Educational Policies for Ethnic Minorities in Border Areas Based on the PMC Index Model | |
CN109784632B (en) | Mining method for interruption response characteristics of industrial and commercial users | |
Qamariah | Analysis of financial performance at the Regional Financial and Asset Agency: Evidence from Regional Government Majene |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190315 |