CN107704995A - Student's evaluation system - Google Patents
Student's evaluation system Download PDFInfo
- Publication number
- CN107704995A CN107704995A CN201710810604.6A CN201710810604A CN107704995A CN 107704995 A CN107704995 A CN 107704995A CN 201710810604 A CN201710810604 A CN 201710810604A CN 107704995 A CN107704995 A CN 107704995A
- Authority
- CN
- China
- Prior art keywords
- student
- degree
- fuzzy
- model
- index
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 49
- 238000000205 computational method Methods 0.000 claims abstract description 25
- 230000006399 behavior Effects 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 19
- 230000005484 gravity Effects 0.000 claims description 12
- 238000013461 design Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000008447 perception Effects 0.000 claims description 5
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 claims description 2
- 238000011158 quantitative evaluation Methods 0.000 abstract description 3
- 239000010410 layer Substances 0.000 description 12
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000008450 motivation Effects 0.000 description 2
- 230000008092 positive effect Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000012847 principal component analysis method Methods 0.000 description 2
- 238000003556 assay Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000012792 core layer Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Educational Technology (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses a kind of student's evaluation system, including six models:Wherein, expectational model and life stress model after attitude towards study enthusiasm model, graduation, for receiving the corresponding index parameter of predefined student, the index parameter is calculated using computational methods are perceived, obtain the student attitude towards study enthusiasm, graduation after expectational model and life stress evaluation result;Degree of studying in order to practise model and diploma driving degree model, for receiving the corresponding index parameter of predefined student, the index parameter is calculated using fuzzy logic system, obtain the degree of studying in order to practise and diploma driving degree evaluation result of the student;Crowd belongs to crowd's ownership index parameter that model is used to receive predefined student, and crowd's home type of the student is obtained using principal component analytical method.Implement the present invention more preferably can realize quantitative evaluation learning behavior by each model from understanding student's background, and then all kinds of different students are efficiently identified, and preferably promote personalized service.
Description
Technical field
The present invention relates to Machine self-learning field, more particularly to a kind of student's evaluation system.
Background technology
The evaluation method of traditional education is all relatively simple, scattered, such as by learning to obtain diploma, or it is existing under the pressure of some
Real pressure etc..Now with the arriving in big data epoch, some analyses can be carried out based on large-scale student's data, still
The current big data analysis system for being all based on some particular topics, such as:Mentioned in CN104835373A based on micro- class
Point control type training system is related to a kind of point control type training system based on micro- class, and the training system includes server, with servicing
The terminal device of device network connection, the terminal device include smart mobile phone, computer, tablet personal computer, and the training system includes
Log-in module, student interface, teacher interface and the teaching management operator interfaces being stored on the server, the user is by stepping on
Land module enters respective interface;The student interface includes data inputting module, learning and communication module, micro- class resource module, survey
Die trial block;The teacher interface includes data memory module, learning and communication module, micro- class resource uploading module, assay mould
Block.The study situation of student can be directed to by changing the point control type training system of micro- class, carry out individualized training, scarce mending-leakage is looked into for student,
The combined system assessing, learn, testing, instruct four learning processes is formed, so as to effectively improve student's results of learning.
However, there is presently no being analyzed based on big data, the evaluation to the situation entirety various dimensions of trainee, it is difficult to right
All types of students, which provide, targetedly to be instructed and helps.It would therefore be highly desirable to a kind of effective student's evaluation of programme is developed, to overcome
Above-mentioned deficiency.
The content of the invention
In view of this, the present invention is intended to provide a kind of student's evaluation system, to realize to being carried out to all kinds of different students
Efficiently identify, preferably promote personalized service.
Specifically, student's evaluation system of the invention includes:
Attitude towards study enthusiasm model, for receiving the attitude towards study enthusiasm index parameter of predefined student, and profit
The attitude towards study enthusiasm index parameter is calculated with computational methods are perceived, obtains the attitude towards study enthusiasm of the student
Evaluation result;
Expectational model after graduation, counted for it is expected index parameter after receiving the graduation of predefined student, and using perceiving
Calculation method obtains expectational model after the graduation of the student to it is expected that index parameter calculates after the graduation;
Life stress model, for receiving the life stress index parameter of predefined student, and utilize perception calculating side
Method is calculated the life stress index parameter, obtains the life stress evaluation result of the student;
Degree of studying in order to practise model, patrolled for receiving degree of the studying in order to practise index parameter of predefined student, and using fuzzy
The system of collecting is calculated degree of the studying in order to practise index parameter, obtains degree of the studying in order to practise evaluation result of the student;
Diploma driving degree model, patrolled for receiving the diploma driving degree index parameter of predefined student, and using fuzzy
The system of collecting is calculated the diploma driving degree index parameter, obtains the diploma driving degree evaluation result of the student;
Crowd belongs to model, and the crowd for receiving predefined student belongs to index parameter, and utilizes principal component analysis
Method obtains crowd's home type of the student.
Further, the fuzzy logic system is a type fuzzy logic system, described to perceive obscuring in computational methods
Collection uses a type fuzzy set;Or the fuzzy logic system is two type fuzzy logic systems, in the perception computational methods
Fuzzy set uses type-2 fuzzy sets.
Further, the attitude towards study enthusiasm index parameter includes:Network behavior parameter, including:Learning platform
Access times and access duration, the access times and access duration of mobile terminal, the access times of course forum, the visit of other forums
Ask number and access duration;Learning behavior parameter, including:The number of clicks of learning platform courseware, the click time of mobile terminal video
Number, lead the download time of data, the number of clicks of course bulletin;Job eveluation parameter, including:Online assignment number is completed
With the online assignment completeness of online assignment sum ratio, the offline of off-line operation number and off-line operation sum ratio is had been filed on
Task performance;Forum's behavioral parameters, including:Course forum and post number and the number of visits of other forums;
The attitude towards study enthusiasm model includes index parameter weight determination module, is calculated first with analytic hierarchy process (AHP)
The weight of each attitude towards study enthusiasm index parameter, and then the weight for each parameter being calculated is obscured with triangle
Number represents.
Further, the attitude towards study enthusiasm model, graduation after expectational model, life stress model, study in order to practise
The fuzzy interval of index parameter or input variable in model and diploma driving degree model is spent to divide with the following method:
Ratio computing unit, for calculating each index IkFirst non-zero quantile a in (k=1 ..., n)k1Ratio
xk% and right-hand member sparse data starting quantile akmRatio yk%, wherein, n is the number of index parameter;
Deng subdivision, for by section [xk,yk] m deciles, quantile corresponding to its branch is designated as (a respectivelyk1,ak2,…,
akm);
Trapezoidal fuzzy set representations unit, for the quantile after the m deciles to be represented with the section of predetermined quantity, and it is right
Each fuzzy interval is standardized.
Further, the evaluation knot of expectational model and life stress model after the attitude towards study enthusiasm model, graduation
The computational methods of fruit and step are as follows:
A) certain individual student is directed to, calculates the individual being subordinate to for each index
Computational methods:Each desired value of individual student is substituted into each fuzzy set of index Fuzzy division, calculates its person in servitude
Category degree, that maximum fuzzy set of degree of membership is the individual being subordinate to for the index in each index;
B) second and third layer of index Fuzzy collection of individual is calculated
Computational methods:Second and third layer of individual is calculated with fuzzy weighted average or language weighted average calculation formula
The judge fuzzy set of index;
C) the final evaluation result of individual is calculated
Computational methods:
1) by the judge fuzzy set of third layer index with it is ready-portioned it is small in big fuzzy set carry out fuzzy similarity comparison, obtain
Go out the final fuzzy evaluation result of individual;
2) calculate third layer index the center of gravity of judges fuzzy set or the intermediate value position in center of gravity section as finally
Percentage evaluation result.
Further, it is expected that index parameter includes after the graduation:Expectant salary amount of increase, it is expected work city, it is expected public affairs
Department's scale, it is expected industry type, it is expected post type and it is expected title and rank;
Index parameter weight determination module after the graduation in expectational model, using Expectant salary amount of increase as dependent variable,
Index parameter it is expected as independent variable after other 5 graduations in addition to Expectant salary amount of increase, by random forest method to described
It is expected that index does relative importance analysis after other 5 graduations, and then provide the final weight of 6 influence indexs, and by described 6
The final weight of individual influence index is fuzzy to turn to Triangular Fuzzy Number.
Further, the life stress index parameter includes:
Objective circumstances parameter, including:Age, wedding condition, sex, place city;
Parameter is paid, including:Spending on housing, children's education expenditure, medical expense and other predetermined expenditures;
Parameter it is expected after graduation.
Further, degree of the studying in order to practise index parameter includes:Learn specialty with it is expected industry type degree of correlation,
Learn specialty with it is expected post type degree of correlation, it is existing educational background with it is expected title and rank degree of correlation and it is original educational background with
The degree of correlation of existing title and rank.
Further, the diploma driving degree index parameter includes:Learn specialty with it is expected industry type degree of correlation,
It is existing it is academic with the degree of correlation of existing post type, it is existing it is academic with the degree of correlation of existing post type and title and rank,
It is existing it is academic with the degree of correlation in existing wages section, have a mind to the degree be transferred and promoted in former post.
Further, in degree of studying in order to practise model and diploma the driving degree model, the rule base of fuzzy logic system
Establish and the calculating process of system output is as follows:
The l rules established in FLS rule bases:
Wherein:AiIt is first former piece x1I-th of fuzzy set, i=1,2 ..., m;
BjIt is second former piece x2J-th of fuzzy set, j=1,2 ..., n;
CpIt is the 3rd former piece x3P-th of fuzzy set, p=1,2 ..., s;
DqIt is the 4th former piece x4Q-th of fuzzy set, q=1,2 ..., t;
YlIt is consequent fuzzy set, l=1,2 ..., L;
One shared L=mnst rules, if m=n=s=t=3, wherein YlCalculating put down with FUZZY WEIGHTED
Or language weighted average method is calculated;
When system design is fuzzy logic system, using monodrome fuzzy device, product inference machine, the center defuzzifier of collection
Fuzzy logic system is established, obtains FLS input/output relation expression formula:
Wherein:L is regular number, ylFor the center of gravity of consequent fuzzy set, flHorizontal, the l=1 for the igniting of l rules,
2 ..., L, μl(xi) it is x in l rulesiDegree of membership;
When system design is two type fuzzy logic system, using two type monodrome fuzzy devices, product inference machine, the center of collection
Drop type device establishes two type fuzzy logic systems, i.e., in FLS input/output relation expression formula, ylFor consequent fuzzy set
Center of gravity section, flFor the horizontal section of igniting of l rules, then calculated with fuzzy weighted average.
Further, the crowd belongs to index parameter and included:It is expected after attitude towards study enthusiasm index, graduation, life
Pressure, degree of studying in order to practise and diploma driving degree;
The crowd belongs in model, belongs to index based on above-mentioned five crowds, student is entered with PCA
Row classification, i.e., by the way that two principal components are calculated, then using two principal components as transverse and longitudinal coordinate axle, according to demand to whole flat
Make four-quadrant classification in face.
Student's evaluation system of the present invention, quantitative evaluation more preferably can be realized from understanding student's background by each model
Habit behavior, and then all kinds of different students are efficiently identified, consequently facilitating targetedly treating.Specifically, study in order to practise
Degree analysis result can instruct give a course specialty and enrollment direction, it is expected it is expected to comment after with attitude towards study enthusiasm student graduating after graduation
Estimate, can be easy to preferably instruct the learning motivation of excitation student, diploma driving degree can be identified by the student of diploma driving, be easy to have
Pointedly supervised and guided, the analysis result of life stress and attitude towards study enthusiasm can be easy to identification is compeled by pressure
It is raw, it is easy to provide subsidy to it.
Brief description of the drawings
It is incorporated into specification and the accompanying drawing of a part for constitution instruction shows embodiments of the invention, and with
Description is used for the principle for explaining the present invention together.In the drawings, similar reference is used to represent similar key element.Under
Accompanying drawing in the description of face is some embodiments of the present invention, rather than whole embodiments.Come for those of ordinary skill in the art
Say, on the premise of not paying creative work, other accompanying drawings can be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic diagram of student's evaluation system provided in an embodiment of the present invention;
Fig. 2 is the weight distribution schematic diagram of expectation index after graduation;
Fig. 3 is the structure of fuzzy logic system provided in an embodiment of the present invention;
Fig. 4 is the structural representation of two types fuzzy logic system (T2FLS) provided in an embodiment of the present invention;
Fig. 5 is membership function figure provided in an embodiment of the present invention;
Fig. 6 is the load moment system of battle formations provided in an embodiment of the present invention;
Fig. 7 is that variance provided in an embodiment of the present invention explains ratio schematic diagram;
Fig. 8 is load schematic provided in an embodiment of the present invention;
Fig. 9 is every class crowd number of PCA clusters.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.Need
Illustrate, in the case where not conflicting, the feature in embodiment and embodiment in the application can be mutually combined.
The student's evaluation method and system that implementation that the invention will now be described in detail with reference to the accompanying drawings is related to.
Shown in Figure 1, student's evaluation system includes:
Attitude towards study enthusiasm model, for receiving the attitude towards study enthusiasm index parameter of predefined student, and profit
The attitude towards study enthusiasm index parameter is calculated with computational methods are perceived, obtains the attitude towards study enthusiasm of the student
Evaluation result;
Expectational model after graduation, counted for it is expected index parameter after receiving the graduation of predefined student, and using perceiving
Calculation method obtains expectational model after the graduation of the student to it is expected that index parameter calculates after the graduation;
Life stress model, for receiving the life stress index parameter of predefined student, and utilize perception calculating side
Method is calculated the life stress index parameter, obtains the life stress evaluation result of the student;
Degree of studying in order to practise model, patrolled for receiving degree of the studying in order to practise index parameter of predefined student, and using fuzzy
The system of collecting is calculated degree of the studying in order to practise index parameter, obtains degree of the studying in order to practise evaluation result of the student;
Diploma driving degree model, patrolled for receiving the diploma driving degree index parameter of predefined student, and using fuzzy
The system of collecting is calculated the diploma driving degree index parameter, obtains the diploma driving degree evaluation result of the student;
Crowd belongs to model, and the crowd for receiving predefined student belongs to index parameter, and utilizes principal component analysis
Method obtains crowd's home type of the student.
Such as Fig. 3 and Fig. 4, the fuzzy logic system is a type fuzzy logic system, the mould perceived in computational methods
Paste collection uses a type fuzzy set;Or the fuzzy logic system is two type fuzzy logic systems, in the perception computational methods
Fuzzy set use type-2 fuzzy sets.
(1) design of the attitude towards study enthusiasm model is as follows:
(1) selection of index parameter:By analyze data feature, index related analysis is carried out, finally chooses following three
14 variable of layer:(learning platform { access times, accesses duration } to network behavior, and mobile terminal { access times, accesses duration }, class
Journey forum { access times }, avenge fine (other) forum { access times, accessing duration }), learning behavior (learning platform courseware { point
Hit number }, mobile terminal video { number of clicks }, data { download time } is led, course bulletin { number of clicks }, operation is (online
Task performance=completed online assignment number/online assignment sum, off-line operation completeness=have been filed on off-line operation
Number/off-line operation sum), forum's behavior (course forum and Xue Qing forums { number of posting, number of visits }).
(2) determination of each index weights
Analytic hierarchy process (AHP) (Analytical Hierarchy Process, abbreviation AHP method) is used first, calculates each layer
The weight of each index is as follows:
A) provide questionnaire to expert and count every expert for importance degree between two two indexes of multiple indexs
Judgment matrix, and the direct weight distribution of two indexes;
B) weighting collects the weight distribution drawn between two indexes;
Teaching platform access times:Teaching platform accesses duration=4:6;
Learn access times:Learn and access duration=7:3;
Forum's access times:Forum accesses duration=6:4;
Teaching platform courseware number of clicks:Mobile terminal courseware number of clicks=6:4;
Online assignment schedule:Off-line operation schedule=5:5;
Forum posts number:Forum number of visits=3:7.
C) weighting collects to obtain the judgment matrix of three and more than three indexs;
The judgment matrix of each three and more than three index of layer of the learning initiative of table 1
D) the weighting orders of R language are called to calculate the corresponding weight distribution of multi objective
First-level class:
Network behavior:Learning behavior:Forum behavior=1:6:3
Network behavior secondary classification:
Learning platform:Mobile terminal:Course forum:Xue Qing forum=6:1:2:1
Learning behavior secondary classification:
Courseware learns:Lead data:Operation=2:1:7
Secondly, in order to uncertain present in processing data, by the above-mentioned weight blurring of determination, Triangular Fuzzy Number is used
Represent as follows:
It is of course also possible to fuzzy turn to the type Triangular Fuzzy Number of section two.
(3) the fuzzy interval division of each index
In order to make more scientific fuzzy interval division to each index, density profile, the case line of index are drawn first
Figure, analyze the data characteristicses of each index;Then according to the characteristics of Density Distribution, the progress fuzzy interval division of quantile feature, tool
Body fuzzy division algorithm is following (exemplified by index to be divided into 5 grades of sections, the situation for being divided into other grade of section similar can be carried out):
Step1. each index I is calculatedkFirst non-zero quantile a in (k=1 ..., 14)k1Ratio xk% and right-hand member
Sparse data starting quantile ak8Ratio yk%
Step2. by section [xk,yk] eight equal parts, quantile corresponding to its branch is designated as respectively
(ak1,ak2,ak3,ak4,ak5,ak6,ak7,ak8)
Step3. according to above quantile by each index be divided into very little (XS), small (S), in (M), big (B), very big
(XB) Pyatyi, and with trapezoidal fuzzy set representations, wherein
XS=(0,0, ak1,ak2),
S=(ak1,ak2,ak3,ak4),
M=(ak3,ak4,ak5,ak6),
B=(ak5,ak6,ak7,ak8),
XB=(ak7,ak8,max,max)
Step4. each fuzzy interval is normalized into [0,10].
Note:It is similar to carry out two patterns paste interval division.
(4) computational methods and step of model
A) certain individual student is directed to, calculates the individual being subordinate to (judge) for each index
Computational methods:Each desired value of individual student is substituted into each fuzzy set of index Fuzzy division, calculates its person in servitude
Category degree, that maximum fuzzy set of degree of membership is the individual being subordinate to (judge) for the index in each index.
B) second and third layer of index Fuzzy collection of individual is calculated
Computational methods:With fuzzy weighted average (fuzzy weighted average, FWA) or language weighted average
The judge that (linguistic weighted average, LWA) calculation formula calculates second and third layer of index of individual obscures
Collection.
C) the final evaluation result of individual is calculated
Computational methods:
1) by the judge fuzzy set of third layer index with it is ready-portioned it is small in big fuzzy set carry out (two types) fuzzy similarity
Compare, draw the final fuzzy evaluation result of individual;
2) center of gravity (or the intermediate value in center of gravity section) position of the judge fuzzy set of third layer index is calculated as final
Percentage evaluation result.
(2) design of expectational model is as follows after graduating:
(1) it is expected that index parameter includes after the graduation:Expectant salary amount of increase, it is expected work city, it is expected company size,
It is expected industry type, it is expected post type and it is expected title and rank.
(2) it is expected that the determination of index parameter index weights can be using Expectant salary amount of increase as dependent variable after graduating, other
Index does relative importance analysis, and then provide six influences and refer to by random forest method as independent variable to other 5 indexs
The distribution of target final weight is as shown in Figure 2.Secondly, with attitude towards study enthusiasm model, weight is obscured to three turned in 0-10
Angle fuzzy number.
(3) the fuzzy interval division of each index
With attitude towards study enthusiasm model.
(4) computational methods and step of model
With attitude towards study enthusiasm model.
(3) design of the life stress model is as follows:
(1) selection of index parameter:The life stress index parameter includes three layers of 9 index:
Important expenditure parameter:Spending on housing, children's education, medical expense, other expenditures;
Objective circumstances parameter:Age, sex, no, place city of wedding
Parameter it is expected after graduation:It is expected after graduation.
(2) determination of index weights:Still using the analytic hierarchy process (AHP) (AHP) employed in attitude towards study enthusiasm model come
Calculate, result of calculation is as follows:
Secondly, with attitude towards study enthusiasm model, by the fuzzy Triangular Fuzzy Number turned in 0-10 of weight.
(3) the fuzzy interval division of each index
With attitude towards study enthusiasm model.
(4) computational methods and step of model
With attitude towards study enthusiasm model
(4) design of degree of the studying in order to practise model and diploma driving degree model is as follows:
Degree of studying in order to practise and diploma driving degree model are designed using (two types) fuzzy logic system, and their structure chart is such as
Under:The structure of one fuzzy logic system (FLS) is as shown in Figure 3:
(1) determination and calculating of (two types) fuzzy logic system input variable
We determined that four input variables of following four degrees of correlation as degree of studying in order to practise (T2) FLS models:
1) specialty is learned with it is expected the degree of correlation of industry type;
2) specialty is learned with it is expected the degree of correlation of post type;
3) degree of correlation of the existing educational background with it is expected title and rank;
4) the original academic and degree of correlation of existing title and rank,
It is defined below four degrees of correlation and has a mind to the degree in former post promotion as diploma driving degree (T2) FLS models
Five input variables:
1) specialty is learned with it is expected the degree of correlation of industry type;
2) the existing academic and degree of correlation of existing post type;
3) degree of correlation of existing academic and existing post type and title and rank;
4) the existing academic and degree of correlation in existing wages section;
5) degree being transferred and promoted in former post is had a mind to
Wherein,
Learn specialty:The specialty learned at present is represented,
Industry type:Represent the online relatively more generally acknowledged industry such as 15-17 industry, farming, forestry, husbandary and fishing
Existing educational background:The educational background that will be obtained at present is represented,
Original educational background:Educational background before expression
Post type:Including managing class, technology class, administrative class, work duty class
Position level:Including core layer, middle level, basic unit
Then support Support (X-Y)=P (X, Y) in related analysis technology is used:Contain X and Y in item collection simultaneously
Probability, to calculate above-mentioned degree of correlation.
(2) division of input variable fuzzy interval
Because these above-mentioned degrees of correlation are to reclaim result according to the questionnaire of this Project design, by calculating corresponding support
Spend and obtain, these results are relatively stable, so for degree of studying in order to practise model and diploma driving degree model, we tie according to recovery
Their input variable is divided into three fixed fuzzy intervals by fruit:Low (Trapezoid Fuzzy Number is expressed as [1,1,3,4]), in
(Trapezoid Fuzzy Number is expressed as [3,4,5,6]), high Trapezoid Fuzzy Number are expressed as [5,6,8,8]), then normalize to [0,10] area
In.Their membership function is as shown in Figure 5., also can be trapezoidal by the above-mentioned type of Trapezoid Fuzzy Number section two when using T2FLS
Fuzzy number represents.
(3) determination of (two types) fuzzy logic system rule base
Disturbance degree of the regular former piece to consequent is established by survey first.Questionnaire design is as follows:
1) following four variable is considered, you think that the variable is much to the disturbance degree for degree of studying in order to practise
A) learn specialty with it is expected industry type degree of correlation disturbance degree be _ _ _ _ _ _ _
B) learn specialty with it is expected post type degree of correlation disturbance degree be _ _ _ _ _ _ _
C) it is existing educational background with it is expected title and rank degree of correlation disturbance degree be _ _ _ _ _ _ _
D) it is original it is academic with the degree of correlation of existing title and rank disturbance degree be _ _ _ _ _ _ _
2) following five variables are considered, you think that the variable is much to the disturbance degree of diploma driving degree
A) learn specialty with it is expected industry type degree of correlation disturbance degree be _ _ _ _ _ _ _
B) it is existing it is academic with the degree of correlation of existing post type disturbance degree be _ _ _ _ _ _ _
C) it is existing it is academic with the degree of correlation of existing title and rank disturbance degree be _ _ _ _ _ _ _
D) it is existing it is academic with the degree of correlation in existing wages section disturbance degree be _ _ _ _ _ _ _
E) have a mind to former post be transferred and promoted degree disturbance degree be _ _ _ _ _ _ _
(A) bear during big (- 100%~-70%) (B) is born (- 70%~-40%) (C) and bear small (- 30%~0)
(D) it is honest (70%~100%) without (E) just small (0~30%) (F) center (30%~70%) (G) is influenceed
Here the fuzzy set that ABCDFFG is used is as follows with trapezoidal fuzzy set representations respectively:
A=[- 10, -7.5, -7.5, -5], B=[- 7.5, -5, -5, -2.5], C=[- 5, -2.5, -2.5,0]
D=[- 2.5,0,0,2.5]
E=[0,2.5,2.5,5], F=[2.5,5,5,7.5], G=[5,7.5,10,10]
Note:Here ABCDFFG fuzzy set representations and number selection can suitably adjust according to problem.
The foundation of rule base
By taking degree of studying in order to practise model as an example, l rules that we establish in FLS rule bases as follows:
Wherein:AiIt is first former piece x1I-th of fuzzy set, i=1,2 ..., m;
BjIt is second former piece x2 j-th of fuzzy set, j=1,2 ..., n;
CpIt is the 3rd former piece x3 p-th of fuzzy set, p=1,2 ..., s;
DqIt is the 4th former piece x4 q-th of fuzzy set, q=1,2 ..., t;
YlIt is consequent fuzzy set, l=1,2 ..., L.
One shared L=mnst rules.M=n=s=t=3 is set in this project.
FLS inference machine
In this project, when being designed as FLS, using monodrome fuzzy device, product inference machine, center (the center of of collection
Sets, COS) defuzzifier establishes fuzzy logic system, obtain FLS input/output relation expression formula:
Wherein:L is regular number, ylFor the center of gravity of consequent fuzzy set, flHorizontal, the l=1 for the igniting of l rules,
2,…,L。μl(xi) it is x in l rulesiDegree of membership.
When being designed as T2FLS, using two type monodrome fuzzy devices, product inference machine, center (the center of of collection
Sets, COS) drop type device establishes two type fuzzy logic systems, i.e., in above formula, ylFor the center of gravity section of consequent fuzzy set, fl
For the horizontal section of igniting of l rules, then calculated with FWA.
(5) design of crowd's ownership model is as follows:
Student is classified using PCA (Principal component analysis, PCA).It is main into
The thought of analysis is exactly that n observation is present in p dimension spaces, but not all dimension has same value, passes through
Two dimensions of principal component analysis picking display data structure to greatest extent are analyzed.
Initially set up using expectation after attitude towards study enthusiasm, graduation, life stress, degree of studying in order to practise and diploma driving degree as
The quintuple space of component, each student to should be in quintuple space a point (X1,X2,X3,X4,X5)。
Principal component expression formula is as follows:
F1=β1X1+β2X2+β3X3+β4X4+β5X5
Then the prcomp functions in the stats program bags of R language are called, can obtain principal component as shown in Figure 6 and Figure 7
Loading matrix and variance explain that ratio is as shown in Figure 6.
The first two Principal Component Explanation all data more than half information as seen in Figure 7, illustrate the first two principal component
Explanation dynamics be very big.In addition, it can be seen that by observing loading coefficient:
1) studied in order to practise in first principal component and the coefficient of diploma driving be all very big, illustrate this generalized variable mainly by
This two explain.At the same time, it is negative value to study in order to practise with the coefficient of diploma driving and attitude towards study enthusiasm.Explanation
If the F of student1Bigger, then his degree of studying in order to practise and diploma driving degree are smaller, and attitude towards study enthusiasm is also lower.
2) Second principal component, graduation it is expected and the absolute coefficient of life stress, degree of studying in order to practise these three variables all very
Greatly, and coefficient is negative, is expected that by Second principal component, here and is distinguished studying in order to practise with diploma driving.Illustrate second it is main into
Point higher, graduation it is expected, life stress and studies in order to practise lower.
Fig. 8 is the scatter diagram drawn by two principal component scores calculating of five indexs of each student, abscissa
For first principal component, ordinate is Second principal component,.It was found that scatterplot is evenly distributed in whole plane, then tentatively will be whole
Plane is divided into four parts (1~4 group), since the upper right corner, up time needle sort, according to above analyzing, it was therefore concluded that as follows:
First group:Diploma driving degree is low, and degree of studying in order to practise is low, it is expected low after graduation, and life stress is low, and attitude towards study is positive
Property is general.
Second group:Diploma driving degree is high, and degree of studying in order to practise is general, it is expected low after graduation, and life stress is low, attitude towards study product
Polarity is high.
3rd group:Diploma driving degree is high, and degree of studying in order to practise is high, and height it is expected after graduation, and life stress is high, and attitude towards study is positive
Property is general.
4th group:Diploma driving degree is low, and degree of studying in order to practise is general, and high, life stress height, attitude towards study product it is expected after graduation
Polarity is low.
Fig. 9 gives four as above divided class crowd's numbers.
Quantitative evaluation learning behavior more preferably can be realized from understanding student's background by each model, and then to all kinds of differences
Student is efficiently identified, consequently facilitating targetedly treating.Specifically, degree of studying in order to practise analysis result can instruct to give a course specially
Industry and enrollment direction, it is expected after graduation and it is expected to assess after attitude towards study enthusiasm student graduation, can be easy to preferably instruct to swash
The learning motivation of student is encouraged, diploma driving degree can be identified by the student of diploma driving, be easy to targetedly be supervised and guided, life
The analysis result of pressure and attitude towards study enthusiasm can be easy to the student that identification is compeled by pressure, be easy to provide subsidy to it.
It will appreciated by the skilled person that realize all or part of step/units/modules of above-described embodiment
It can be completed by the related hardware of programmed instruction, foregoing routine can be stored in computer read/write memory medium, should
Upon execution, perform includes step corresponding in above-described embodiment each unit to program;And foregoing storage medium includes:ROM、
RAM, magnetic disc or laser disc etc. are various can be with the medium of store program codes.
Particular embodiments described above, the purpose of the present invention, technical scheme and beneficial effect are carried out further in detail
Describe in detail it is bright, should be understood that the foregoing is only the present invention specific embodiment, be not intended to limit the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements done etc., it should be included in the guarantor of the present invention
Within the scope of shield.
Claims (11)
1. a kind of student's evaluation system, it is characterised in that the system includes:
Attitude towards study enthusiasm model, for receiving the attitude towards study enthusiasm index parameter of predefined student, and utilize sense
Know that computational methods are calculated the attitude towards study enthusiasm index parameter, obtain the attitude towards study enthusiasm evaluation of the student
As a result;
Expectational model after graduation, for it is expected index parameter after receiving the graduation of predefined student, and utilize perception calculating side
Method obtains expectational model after the graduation of the student to it is expected that index parameter calculates after the graduation;
Life stress model, for receiving the life stress index parameter of predefined student, and utilize and perceive computational methods pair
The life stress index parameter is calculated, and obtains the life stress evaluation result of the student;
Degree of studying in order to practise model, for receiving degree of the studying in order to practise index parameter of predefined student, and utilize fuzzy logic system
System is calculated degree of the studying in order to practise index parameter, obtains degree of the studying in order to practise evaluation result of the student;
Diploma driving degree model, for receiving the diploma driving degree index parameter of predefined student, and utilize fuzzy logic system
System is calculated the diploma driving degree index parameter, obtains the diploma driving degree evaluation result of the student;
Crowd belongs to model, and the crowd for receiving predefined student belongs to index parameter, and utilizes principal component analytical method
Obtain crowd's home type of the student.
2. student's evaluation system as claimed in claim 1, it is characterised in that the fuzzy logic system is a pattern fuzzy logic
System, the fuzzy set perceived in computational methods use a type fuzzy set;Or the fuzzy logic system is pasted for two patterns
Flogic system, the fuzzy set perceived in computational methods use type-2 fuzzy sets.
3. student's evaluation system as claimed in claim 1, it is characterised in that the attitude towards study enthusiasm index parameter bag
Include:
Network behavior parameter, including:The access times of learning platform and duration is accessed, when the access times of mobile terminal and access
It is long, the access times of course forum, the access times and access duration of other forums;
Learning behavior parameter, including:The number of clicks of learning platform courseware, the number of clicks of mobile terminal video, lead data
Download time, the number of clicks of course bulletin;
Job eveluation parameter, including:The online assignment completeness of online assignment number and online assignment sum ratio is completed,
Submit the off-line operation completeness of off-line operation number and off-line operation sum ratio;
Forum's behavioral parameters, including:Course forum and post number and the number of visits of other forums;
The attitude towards study enthusiasm model includes index parameter weight determination module, is calculated first with analytic hierarchy process (AHP) each
The weight of the attitude towards study enthusiasm index parameter, and then the weight Triangular Fuzzy Number table by each parameter being calculated
Show.
4. student's evaluation system as claimed in claim 1, it is characterised in that after the attitude towards study enthusiasm model, graduation
Index parameter or the mould of input variable in expectational model, life stress model, degree of studying in order to practise model and diploma driving degree model
Paste interval division with the following method:
Ratio computing unit, for calculating each index IkFirst non-zero quantile a in (k=1 ..., n)k1Ratio xk% and
Right-hand member sparse data starting quantile akmRatio yk%, wherein, n is the number of index parameter;
Deng subdivision, for by section [xk,yk] m deciles, quantile corresponding to its branch is designated as (a respectivelyk1,ak2,…,akm);
Trapezoidal fuzzy set representations unit, for the quantile after the m deciles to be represented with the section of predetermined quantity, and to each
Fuzzy interval is standardized.
5. student's evaluation system as claimed in claim 1, it is characterised in that after the attitude towards study enthusiasm model, graduation
The computational methods of expectational model and the evaluation result of life stress model are as follows with step:
A) certain individual student is directed to, calculates the individual being subordinate to for each index
Computational methods:Each desired value of individual student is substituted into each fuzzy set of index Fuzzy division, it is calculated and is subordinate to journey
Spend, that maximum fuzzy set of degree of membership is the individual being subordinate to for the index in each index;
B) second and third layer of index Fuzzy collection of individual is calculated
Computational methods:Second and third layer of index of individual is calculated with fuzzy weighted average or language weighted average calculation formula
Judge fuzzy set;
C) the final evaluation result of individual is calculated
Computational methods:
1) by the judge fuzzy set of third layer index with it is ready-portioned it is small in big fuzzy set carry out fuzzy similarity comparison, must there emerged a
The final fuzzy evaluation result of body;
2) center of gravity of the judge fuzzy set of third layer index or the intermediate value position in center of gravity section are calculated as final percentage
Compare evaluation result.
6. student's evaluation system as claimed in claim 1, it is characterised in that it is expected that index parameter includes after the graduation:Phase
Wages amount of increase is hoped, work city it is expected, it is expected company size, it is expected industry type, it is expected post type and it is expected title and rank;
Index parameter weight determination module after the graduation in expectational model, using Expectant salary amount of increase as dependent variable, except the phase
It is expected index parameter as independent variable after other 5 graduations hoped beyond wages amount of increase, by random forest method to it is described other 5
It is expected that index does relative importance analysis, and then provides the final weight of 6 influence indexs after individual graduation, and by 6 shadows
Snap target final weight is fuzzy to turn to Triangular Fuzzy Number.
7. student's evaluation system as claimed in claim 1, it is characterised in that the life stress index parameter includes:
Objective circumstances parameter, including:Age, wedding condition, sex, place city;
Parameter is paid, including:Spending on housing, children's education expenditure, medical expense and other predetermined expenditures;
Parameter it is expected after graduation.
8. student's evaluation system as claimed in claim 1, it is characterised in that degree of the studying in order to practise index parameter includes:Institute
Learn specialty and it is expected the degree of correlation of industry type, learn professional degree of correlation, existing educational background and the phase with it is expected post type
Hope the degree of correlation of title and rank and the original academic and degree of correlation of existing title and rank.
9. student's evaluation system as claimed in claim 1, it is characterised in that the diploma driving degree index parameter includes:Institute
Learn specialty with it is expected industry type degree of correlation, it is existing it is academic with the degree of correlation of existing post type, existing educational background with it is existing
Have post type and title and rank degree of correlation, it is existing it is academic with the degree of correlation in existing wages section, have a mind in former post
The degree of promotion.
10. student's evaluation system as claimed in claim 1, it is characterised in that degree of studying in order to practise model and the diploma driving
Spend in model, the calculating process of the foundation of the rule base of fuzzy logic system and system output is as follows:
The l rules established in FLS rule bases:
IFx1isAi,x2isBj,x3isCp,x4isDq,
Wherein:AiIt is first former piece x1I-th of fuzzy set, i=1,2 ..., m;
BjIt is second former piece x2J-th of fuzzy set, j=1,2 ..., n;
CpIt is the 3rd former piece x3P-th of fuzzy set, p=1,2 ..., s;
DqIt is the 4th former piece x4Q-th of fuzzy set, q=1,2 ..., t;
YlIt is consequent fuzzy set, l=1,2 ..., L;
One shared L=mnst rules, if m=n=s=t=3, wherein YlCalculating use fuzzy weighted average or language
Speech weighted average method is calculated;
When system design is fuzzy logic system, using monodrome fuzzy device, product inference machine, the center defuzzifier of collection is established
Fuzzy logic system, obtain FLS input/output relation expression formula:
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>y</mi>
<mo>=</mo>
<mfrac>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>l</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>L</mi>
</msubsup>
<msup>
<mi>y</mi>
<mi>l</mi>
</msup>
<msup>
<mi>f</mi>
<mi>l</mi>
</msup>
</mrow>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>l</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>L</mi>
</msubsup>
<msup>
<mi>f</mi>
<mi>l</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</mtd>
<mtd>
<mrow>
<msup>
<mi>f</mi>
<mi>l</mi>
</msup>
<mo>=</mo>
<munderover>
<mo>&Pi;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>4</mn>
</munderover>
<msup>
<mi>&mu;</mi>
<mi>l</mi>
</msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein:L is regular number, ylFor the center of gravity of consequent fuzzy set, flHorizontal, the l=1 for the igniting of l rules, 2 ...,
L, μl(xi) it is x in l rulesiDegree of membership;
When system design is two type fuzzy logic system, using two type monodrome fuzzy devices, product inference machine, the center drop type of collection
Device establishes two type fuzzy logic systems, i.e., in FLS input/output relation expression formula, ylFor the center of gravity of consequent fuzzy set
Section, flFor the horizontal section of igniting of l rules, then calculated with fuzzy weighted average.
11. student's evaluation system as claimed in claim 1, it is characterised in that the crowd belongs to index parameter and included:Study
Expectation, life stress, degree of studying in order to practise and diploma driving degree after attitude enthusiasm index, graduation;
The crowd belongs in model, belongs to index based on above-mentioned five crowds, student is divided with PCA
Class, i.e., by the way that two principal components are calculated, then using two principal components as transverse and longitudinal coordinate axle, whole plane is done according to demand
Go out four-quadrant classification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710810604.6A CN107704995A (en) | 2017-09-11 | 2017-09-11 | Student's evaluation system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710810604.6A CN107704995A (en) | 2017-09-11 | 2017-09-11 | Student's evaluation system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107704995A true CN107704995A (en) | 2018-02-16 |
Family
ID=61172455
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710810604.6A Pending CN107704995A (en) | 2017-09-11 | 2017-09-11 | Student's evaluation system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107704995A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109615264A (en) * | 2018-12-26 | 2019-04-12 | 中国科学院软件研究所 | A kind of student towards on-line study actively spends the system of determination |
CN109741219A (en) * | 2018-12-12 | 2019-05-10 | 中国联合网络通信集团有限公司 | A kind of Learning behavior analyzing method and device |
CN109948934A (en) * | 2019-03-21 | 2019-06-28 | 南京林业大学 | Course integration evaluation system and its method |
CN110477932A (en) * | 2019-07-31 | 2019-11-22 | 商丘师范学院 | A kind of students psychology Stress appraisal method and system based on internet and cloud computing |
CN110796382A (en) * | 2019-11-01 | 2020-02-14 | 浙江省人民医院 | Assessment analysis method and system applied to nursing subject |
CN111145059A (en) * | 2019-12-31 | 2020-05-12 | 安徽爱学堂教育科技有限公司 | Student learning attitude assessment method and system |
CN112037100A (en) * | 2020-09-28 | 2020-12-04 | 上海松鼠课堂人工智能科技有限公司 | State parameter updating method for adaptive learning system |
-
2017
- 2017-09-11 CN CN201710810604.6A patent/CN107704995A/en active Pending
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109741219A (en) * | 2018-12-12 | 2019-05-10 | 中国联合网络通信集团有限公司 | A kind of Learning behavior analyzing method and device |
CN109615264A (en) * | 2018-12-26 | 2019-04-12 | 中国科学院软件研究所 | A kind of student towards on-line study actively spends the system of determination |
CN109948934A (en) * | 2019-03-21 | 2019-06-28 | 南京林业大学 | Course integration evaluation system and its method |
CN110477932A (en) * | 2019-07-31 | 2019-11-22 | 商丘师范学院 | A kind of students psychology Stress appraisal method and system based on internet and cloud computing |
CN110796382A (en) * | 2019-11-01 | 2020-02-14 | 浙江省人民医院 | Assessment analysis method and system applied to nursing subject |
CN111145059A (en) * | 2019-12-31 | 2020-05-12 | 安徽爱学堂教育科技有限公司 | Student learning attitude assessment method and system |
CN112037100A (en) * | 2020-09-28 | 2020-12-04 | 上海松鼠课堂人工智能科技有限公司 | State parameter updating method for adaptive learning system |
CN112037100B (en) * | 2020-09-28 | 2021-06-22 | 上海松鼠课堂人工智能科技有限公司 | State parameter updating method for adaptive learning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Nieto et al. | Supporting academic decision making at higher educational institutions using machine learning-based algorithms | |
Ang et al. | Big educational data & analytics: Survey, architecture and challenges | |
CN107704995A (en) | Student's evaluation system | |
Feng et al. | Mapping artificial intelligence in education research: A network‐based keyword analysis | |
Dutt et al. | Clustering algorithms applied in educational data mining | |
Liu et al. | Evaluation model of multimedia-aided teaching effect of physical education course based on random forest algorithm | |
Bydžovská | Course Enrolment Recommender System | |
CN109740861A (en) | A kind of learning data analysis method and device | |
CN106373057A (en) | Network education-orientated poor learner identification method | |
da SILVA et al. | Learning analytics and collaborative groups of learners in distance education: a systematic mapping study | |
Kazanidis et al. | Proposed S-Algo+ data mining algorithm for web platforms course content and usage evaluation | |
Peng | Research on online learning behavior analysis model in big data environment | |
Peng et al. | A pattern recognition method of personalized adaptive learning in online education | |
Yun et al. | Affective domain studies of K-12 computing education: A systematic review from a perspective on affective objectives | |
Tong et al. | An evaluation model based on procedural behaviors for predicting MOOC learning performance: students’ online learning behavior analytics and algorithms construction | |
OROZOVA et al. | Generalized net model for dynamic decision making and prognoses | |
Zhang et al. | Enterprise innovation evaluation method based on swarm optimization algorithm and artificial neural network | |
Groth | Applying design-based research findings to improve the Common Core State Standards for Data and Statistics in Grades 4–6 | |
Patil et al. | Big data mining—analysis and prediction of data, based on student performance | |
Han et al. | Latent Dirichlet Allocation-Based Topic Mining Analysis of Educational Scientific Research Projects Based on 2360 NSF Education Projects. | |
Qin et al. | Prediction of in-class performance based on mfo-attention-lstm | |
Marks et al. | Learning systems' learning analytics | |
Jayaratna | Understanding university students’ journey using advanced data analytics | |
Huang et al. | Empirical Research of Classroom Behavior Based on Online Education: A Systematic Review | |
Zheng et al. | Predictive Analytics and Its Uses in Higher Education |
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: 20180216 |