CN107992896A - A kind of scientific concept evaluating method that tracer technique is moved based on eye - Google Patents

A kind of scientific concept evaluating method that tracer technique is moved based on eye Download PDF

Info

Publication number
CN107992896A
CN107992896A CN201711331227.4A CN201711331227A CN107992896A CN 107992896 A CN107992896 A CN 107992896A CN 201711331227 A CN201711331227 A CN 201711331227A CN 107992896 A CN107992896 A CN 107992896A
Authority
CN
China
Prior art keywords
eye
concept
scientific concept
data
student
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
Application number
CN201711331227.4A
Other languages
Chinese (zh)
Inventor
禹东川
靳来鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN201711331227.4A priority Critical patent/CN107992896A/en
Publication of CN107992896A publication Critical patent/CN107992896A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
    • A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
    • A61B3/113—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for determining or recording eye movement
    • 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
    • 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
    • G09B19/00—Teaching not covered by other main groups of this subclass

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Business, Economics & Management (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Educational Technology (AREA)
  • Molecular Biology (AREA)
  • Human Computer Interaction (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Biophysics (AREA)
  • Ophthalmology & Optometry (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Educational Administration (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

The invention belongs to educate the technical field of evaluation and test, more particularly to a kind of scientific concept evaluating method that tracer technique is moved based on eye, comprise the following steps, record conceptual change student and concept does not change this two major classes crowd of student eye movement data, behavioral data, question answering button and question answering voice data in the understanding process of core scientific concept；The locus that content according to that need to assess core scientific concept is presented, chooses and divides vision processing district (area-of-interest)；Calculate the fixation time on region of interest and account for the ratio of time used in completion task and to the probability that redirects between each region of interest, obtain feature vector, and and then acquisition training data sample set and test sample collection；According to the feedforward neural network structure-design technique acquisition model grader of standard；Understand that learner the degree of core scientific concept is assessed using the pattern classifier of acquisition；Feedback more objective, more comprehensively, more timely, more efficient that evaluation result can be given.

Description

A kind of scientific concept evaluating method that tracer technique is moved based on eye
Technical field
The invention belongs to educate the technical field of evaluation and test, more particularly to a kind of scientific concept that tracer technique is moved based on eye is commented Survey method.
Background technology
In today that science and technology is grown rapidly, the effect of education of science is all heavy to closing no matter for country or individual Want.Scientific concept is not only the carrier of education of science as the education of science center to be surrounded is carried out, and student wants The target of grasp.But student, when science classroom is entered, their brain is not an empty container, for many years Experience of life allow them the operation to the world to form the theory of oneself, i.e., " preconception ".These preconceptions are general and can not Science, the foundation of the preconception of mistake to correct scientific concept have adverse effect.It is general in the science held before the class to student Thought level carries out evaluation and test it will be seen that the preconception of student, helps to formulate rational instructional strategies, promote student to establish correctly Scientific concept, be the key for realizing Teaching Effectively；The scientific concept level held after class to student is evaluated and tested then can be with Effective Feedback is given to education activities.
However, the evaluating method in Traditional Scientific education sector is in the comprehensive of feedback, promptness and objectivity etc. With limitation.For a certain scientific concept, hold the student of erroneous picture and hold the student of correct concept, they are solving When problem in addition to the answer difference provided, what difference their thinking processes have, the strategy taken have it is why not same, It is difficult reflected to be in traditional pencil-and-paper test, today of mainstream is especially accounted in standardization multiple-choice question, this test is lost Too many information is lost." self-report " or " interview " these forms then have the characteristics that subjectivity and anamnesis, its result exists The memory and consciousness of speaker itself is depended on to a certain extent, lacks objectivity, promptness, and inefficiency.
Although in recent years eye move tracer technique it is educational application it is more and more, it is general how to apply it to science Do not studied also in the evaluation and test of thought level, it is desirable to be able to which the scientific concept evaluation and test that tracer technique is moved based on eye applied to practice is referred to Mark and application.
The content of the invention
The present invention solves above-mentioned technical problem existing in the prior art, there is provided a kind of science that tracer technique is moved based on eye Concept evaluating method.
To solve the above problems, technical scheme is as follows：
A kind of scientific concept evaluating method that tracer technique is moved based on eye, is comprised the following steps,
First step S1：Record conceptual change student and concept do not change student this two major classes crowd in core scientific concept Understanding process in eye movement data, behavioral data, question answering button and question answering voice data；
Second step S2：The locus that content according to that need to assess core scientific concept is presented, chooses and division regards Feel processing district, the vision processing district is area-of-interest；
Third step S3：The fixation time calculated on region of interest accounts for the ratio of time used in completion task and to each sense Probability is redirected between region of interest, obtains feature vector, and and then acquisition training data sample set and test sample collection；
Four steps S4：To S3 obtain training data sample set and test sample collection according to standard feedforward neural network Structure-design technique acquisition model grader；
5th step S5：Understand that learner the degree of core scientific concept is commented using the S4 pattern classifiers obtained Estimate.
Preferably, eye movement data are recorded by distant reading type eye tracker described in S1.
Preferably, behavioral data, question answering voice data are recorded by recording and broadcasting system described in S1.
Preferably, S1 described problems are answered button and are recorded by computer keyboard.
Preferably, the S1 is concretely comprised the following steps：This two major classes crowd of student is not changed to conceptual change student and concept Subject, completes eye to eye tracker first and moves correction tasks, be in then current task instruction to it by computer display, afterwards Presented to subject it is understood that core scientific concept, it is desirable to after thinking, directly say answer, while carried out by lower keyboard Event indicator；With eye movement of the distant reading type eye tracker record subject in test process, the whole record subject of recording and broadcasting system exists The corresponding voice of behavior and answer in test process.
Preferably, the content of the need assessment core scientific concept described in S2 includes word, picture, answer.
Preferably, training data sample set described in S3 and the input vector of test sample collection are by region of interest when watching attentively Between account between the ratio of time used in completion task and each region of interest after rejecting redirect probability composition, output knot Fruit is { 0,1 } data, wherein 0 represents the data that concept does not change student, 1 represents the data of conceptual change student.
Preferably, pattern classifier described in S4 determines hidden layer using the feedforward neural network structure design algorithm of standardization Neuronal quantity, hidden layer weights and threshold values, output layer weights and threshold values structural information.
Preferably, the hidden layer excitation function of the pattern classifier is Sigmoid functionsOutput layer Activation primitive is linear function f (x)=x；The Function Mapping relation of so pattern classifier can be expressed as：Out=W2*f(W1* in+B1)+B2, wherein out is the output of the Function Mapping relation of pattern classifier, in is pattern classifier Function Mapping relation Input, W1For hidden layer weights, W2For output layer weights, B1For hidden layer threshold values, B2For output layer threshold values.
Relative to the prior art, advantages of the present invention is as follows,
(1) evaluation result is more objective, more comprehensively.The scientific concept level of student is evaluated and tested using eye movement technique, is removed Outside can know that simple answer is corrected errors, it can provide the vision attention clue of student to us, show its thinking strategies, Excavate achievement behind deeper, more essential information.
(2) easily it is combined with Modern Education Technology.It is combined with computer Online Judge technology, is expected to realize big rule Mould, in time, objectively scientific concept is evaluated and tested.
In conclusion method proposed by the present invention can effectively meet the education on demand of the horizontal evaluation and test of scientific concept, tool There are preferable market prospects.
Brief description of the drawings
Fig. 1 is technical solution implementing procedure figure proposed by the invention.
Embodiment
Embodiment 1：
As shown in Figure 1, a kind of scientific concept evaluating method that tracer technique is moved based on eye provided by the invention, including：
First step S1：This two major class of student crowd subject is not changed to conceptual change student and concept, it is necessary first to complete Correction tasks are moved into eye, are in then current task instruction to it by computer display, are presented as requested to subject afterwards It is understood that core scientific concept, it is desirable to after thinking, directly say answer, while event indicator carried out by lower keyboard； Distant reading type eye tracker can record eye movement of the subject in test process, and recording and broadcasting system whole can record subject in test process In the corresponding voice of behavior and answer.
Second step S2：Content (including the element such as word, picture, answer) according to that need to assess core scientific concept is in Existing locus, chooses and divides vision processing district (area-of-interest), is follow-up eye dynamic skipped mode and concern area The statistical analysis in domain provides spatial information；
Third step S3：Do not change this two major class of student crowd subject to conceptual change student and concept, emerging is being felt to it Fixation time in interesting area accounts for the ratio of time used in completion task, and the probability that redirects between each region of interest is counted Calculate；Thus obtain feature vector, and and then acquisition training data sample set and test sample collection；
Four steps S4：The training data sample set of this two major classes crowd of student is not changed to conceptual change student and concept Feedforward neural network structure-design technique acquisition model grader with test sample collection according to standard；
5th step S5, is finally realized using the four steps S4 pattern classifiers obtained and understands that student core science is general The degree of thought is assessed.
Training data sample set and the input vector of test sample collection are by watching attentively on region of interest in the third step Time accounts between the ratio of time used in completion task and each region of interest after rejecting and redirects probability composition, output As a result it is { 0,1 } data, wherein 0 represents the data that concept does not change student, 1 represents the data of conceptual change student.
Pattern classifier employs the feedforward neural network structure design algorithm of standardization in the four steps S4, determines The structural information such as hidden neuron quantity, hidden layer weights and threshold values, output layer weights and threshold values.
The hidden layer excitation function of the pattern classifier is Sigmoid functionsOutput layer activation primitive For linear function f (x)=x；The Function Mapping relation of so pattern classifier can be expressed as：Out=W2*f(W1*in+B1)+ B2, wherein out is the output of the Function Mapping relation of pattern classifier, in is pattern classifier Function Mapping relation it is defeated Enter, W1For hidden layer weights, W2For output layer weights, B1For hidden layer threshold values, B2For output layer threshold values.
It should be noted that above-described embodiment is only presently preferred embodiments of the present invention, it is not used for limiting the present invention's Protection domain, the equivalent substitution or replacement made on the basis of the above belong to protection scope of the present invention.

Claims (9)

  1. A kind of 1. scientific concept evaluating method that tracer technique is moved based on eye, it is characterised in that comprise the following steps,
    First step S1：Record conceptual change student and concept do not change reason of this two major classes crowd of student in core scientific concept Eye movement data, behavioral data, question answering button and question answering voice data in solution preocess；
    Second step S2：The locus that content according to that need to assess core scientific concept is presented, chooses and division vision adds Work area, the vision processing district are area-of-interest；
    Third step S3：The fixation time calculated on region of interest accounts for the ratio of time used in completion task and to each interested Probability is redirected between area, obtains feature vector, and and then acquisition training data sample set and test sample collection；
    Four steps S4：To S3 obtain training data sample set and test sample collection according to standard feedforward neural network structure Designing technique acquisition model grader；
    5th step S5：Understand that learner the degree of core scientific concept is assessed using the S4 pattern classifiers obtained.
  2. 2. the scientific concept evaluating method of tracer technique is moved based on eye as claimed in claim 1, it is characterised in that eye described in S1 Dynamic track data is recorded by distant reading type eye tracker.
  3. 3. the scientific concept evaluating method of tracer technique is moved based on eye as claimed in claim 1, it is characterised in that row described in S1 Recorded for data, question answering voice data by recording and broadcasting system.
  4. 4. the scientific concept evaluating method of tracer technique is moved based on eye as claimed in claim 1, it is characterised in that asked described in S1 Topic is answered button and is recorded by computer keyboard.
  5. 5. the scientific concept evaluating method of tracer technique is moved based on eye as claimed in claim 1, it is characterised in that the S1's Concretely comprise the following steps：Do not change this two major class of student crowd subject to conceptual change student and concept, eye is completed to eye tracker first Dynamic correction tasks, be in then current task instruction to it by computer display, backward subject presentation it is understood that core Heart scientific concept, it is desirable to after thinking, directly say answer, while event indicator is carried out by lower keyboard；Moved with distant reading type eye Eye movement of the instrument record subject in test process, behavior and answer of the whole record subject of recording and broadcasting system in test process Corresponding voice.
  6. 6. the scientific concept evaluating method of tracer technique is moved based on eye as claimed in claim 1, it is characterised in that described in S2 The content of core scientific concept, which need to be assessed, includes word, picture, answer.
  7. 7. the scientific concept evaluating method of tracer technique is moved based on eye as claimed in claim 1, it is characterised in that instruction described in S3 The input vector of white silk set of data samples and test sample collection time as used in the fixation time on region of interest accounts for completion task Probability composition is redirected between ratio and each region of interest after rejecting, output result is { 0,1 } data, wherein 0 generation Table concept does not change the data of student, and 1 represents the data of conceptual change student.
  8. 8. the scientific concept evaluating method of tracer technique is moved based on eye as claimed in claim 1, it is characterised in that mould described in S4 Formula grader determines hidden neuron quantity, hidden layer weights and valve using the feedforward neural network structure design algorithm of standardization Value, output layer weights and threshold values structural information.
  9. 9. the scientific concept evaluating method of tracer technique is moved based on eye as claimed in claim 1, it is characterised in that the pattern The hidden layer excitation function of grader is Sigmoid functionsOutput layer activation primitive for linear function f (x)= x；The Function Mapping relation of so pattern classifier can be expressed as：Out=W2*f(W1*in+B1)+B2, wherein out is pattern The output of the Function Mapping relation of grader, the input for the Function Mapping relation that in is pattern classifier, W1For hidden layer weights, W2 For output layer weights, B1For hidden layer threshold values, B2For output layer threshold values.
CN201711331227.4A 2017-12-13 2017-12-13 A kind of scientific concept evaluating method that tracer technique is moved based on eye Pending CN107992896A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711331227.4A CN107992896A (en) 2017-12-13 2017-12-13 A kind of scientific concept evaluating method that tracer technique is moved based on eye

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711331227.4A CN107992896A (en) 2017-12-13 2017-12-13 A kind of scientific concept evaluating method that tracer technique is moved based on eye

Publications (1)

Publication Number Publication Date
CN107992896A true CN107992896A (en) 2018-05-04

Family

ID=62038350

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711331227.4A Pending CN107992896A (en) 2017-12-13 2017-12-13 A kind of scientific concept evaluating method that tracer technique is moved based on eye

Country Status (1)

Country Link
CN (1) CN107992896A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI679558B (en) * 2018-11-25 2019-12-11 國立臺灣師範大學 The method of identifying fixations real-time from the raw eye- tracking data and a real-time identifying fixations system applying this method
CN110634356A (en) * 2019-04-13 2019-12-31 北京一目了然教育科技有限公司 Method for training reading ability based on eye movement tracking technology
CN117649157A (en) * 2024-01-30 2024-03-05 中国人民解放军空军军医大学 Instrument discrimination capability assessment method based on sight tracking

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050071755A1 (en) * 2003-07-30 2005-03-31 Xerox Corporation Multi-versioned documents and method for creation and use thereof
CN104318253A (en) * 2014-11-11 2015-01-28 东南大学 MOOC online learning pattern recognition system and method
CN106407935A (en) * 2016-09-21 2017-02-15 俞大海 Psychological test method based on face images and eye movement fixation information
CN106937531A (en) * 2014-06-14 2017-07-07 奇跃公司 Method and system for producing virtual and augmented reality
JP2017527036A (en) * 2014-05-09 2017-09-14 グーグル インコーポレイテッド System and method for using eye signals in secure mobile communications
CN107438398A (en) * 2015-01-06 2017-12-05 大卫·伯顿 Portable wearable monitoring system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050071755A1 (en) * 2003-07-30 2005-03-31 Xerox Corporation Multi-versioned documents and method for creation and use thereof
JP2017527036A (en) * 2014-05-09 2017-09-14 グーグル インコーポレイテッド System and method for using eye signals in secure mobile communications
CN106937531A (en) * 2014-06-14 2017-07-07 奇跃公司 Method and system for producing virtual and augmented reality
CN104318253A (en) * 2014-11-11 2015-01-28 东南大学 MOOC online learning pattern recognition system and method
CN107438398A (en) * 2015-01-06 2017-12-05 大卫·伯顿 Portable wearable monitoring system
CN106407935A (en) * 2016-09-21 2017-02-15 俞大海 Psychological test method based on face images and eye movement fixation information

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
JING HAN 等: "Eye-tracking of visual attention in web-based assessment using the Force Concept Inventory", 《EYE-TRACKING OF VISUAL ATTENTION IN WEB-BASED ASSESSMENT USING THE FORCE CONCEPT INVENTORY》 *
靳来鹏 等: "眼动技术:个性化评测的新"武器"", 《中小学管理》 *
黄彬瑶: "语境制约汉语反语认知加工的神经心理机制研究", 《中国博士学位论文全文数据库哲学与人文科学辑》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI679558B (en) * 2018-11-25 2019-12-11 國立臺灣師範大學 The method of identifying fixations real-time from the raw eye- tracking data and a real-time identifying fixations system applying this method
CN110634356A (en) * 2019-04-13 2019-12-31 北京一目了然教育科技有限公司 Method for training reading ability based on eye movement tracking technology
CN117649157A (en) * 2024-01-30 2024-03-05 中国人民解放军空军军医大学 Instrument discrimination capability assessment method based on sight tracking
CN117649157B (en) * 2024-01-30 2024-03-29 中国人民解放军空军军医大学 Instrument discrimination capability assessment method based on sight tracking

Similar Documents

Publication Publication Date Title
Limo et al. Personalized tutoring: ChatGPT as a virtual tutor for personalized learning experiences
Borko et al. Teachers’ decision making: From Alan J. Bishop to today
Prabha et al. Educational data mining applications
Asada Mentoring novice teachers in Japanese schools
CN107992896A (en) A kind of scientific concept evaluating method that tracer technique is moved based on eye
Kaewkiriya et al. The design of a rule base for an e-learning recommendation system base on multiple intelligences
Mohammad et al. Clustering of slow learners behavior for discovery of optimal patterns of learning
Odufuwa et al. Assessment of senior secondary students’ perceptions and career interest in science, technology, engineering and mathematics (STEM) in Ijebu-Ode Local Government Area, Ogun State
Wakelam et al. The potential for using artificial intelligence techniques to improve e-learning systems
Hamtini et al. A proposed dynamic technique for detecting learning style using literature based approach
Leka et al. Implementation of Moodle plugins to support student’s learning styles
Falcinelli et al. The use of video in educational research and teacher training in the digital classroom
Pujiyono et al. Interactive learning media based on RPP ICT
Moreno et al. Using virtual classroom cases as thinking tools in teacher education
da Silva et al. Adaptation in educational hypermedia based on the classification of the user profile
Wicks et al. 21st Century Learning Skills and Artificial Intelligence
Rocca et al. Designing an assistance tool for Analyzing and Modeling trainer activity in professional training through simulation
Zullo et al. Characteristics of questions that promote rich mathematical discussions
Cofino et al. Performance Analysis of Agriculture Students in Adapting to Distance Learning During COVID-19 Pandemic through Educational Data Mining (EDM)
Sung Enhancing English learning website content and user interface functions using integrated quality assessment
Štilić et al. Interplay between technology and society: Effects of remote emergency teaching on undergraduate students' performance
Barnett et al. Neural Syntonicity: A Constructionist Approach to the Development of Image Recognition Tools Used to Teach Students about Powerful Ideas in Artificial Intelligence
Chen et al. A Learning Module of the 0/1 Knapsack Problem Using Dynamic Programming KLA Modeling
Chobthamdee et al. Competency of Learning Management through Video on Social Media Platform of Pre-Service Teachers with Collaborative Learning
Naidu et al. A REVIEW OF BIG DATA ANALYTICS IN TEACHING ENGLISH AS A FOREIGN LANGUAGE

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20180504

RJ01 Rejection of invention patent application after publication