CN106778575A - A kind of recognition methods of Students ' Learning state based on wearable device and system - Google Patents
A kind of recognition methods of Students ' Learning state based on wearable device and system Download PDFInfo
- Publication number
- CN106778575A CN106778575A CN201611110218.8A CN201611110218A CN106778575A CN 106778575 A CN106778575 A CN 106778575A CN 201611110218 A CN201611110218 A CN 201611110218A CN 106778575 A CN106778575 A CN 106778575A
- Authority
- CN
- China
- Prior art keywords
- wearable device
- axis acceleration
- physical signs
- behavior
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/168—Evaluating attention deficit, hyperactivity
Abstract
Recognition methods and system the invention discloses a kind of Students ' Learning state based on wearable device, by the existing mood classification of the mankind, the physical signs corresponding with each classification is set, typing mood data storehouse, by behavior state classification when learning, set and all kinds of corresponding human body 3-axis acceleration semaphores, typing behavior database；Physical signs and individual 3-axis acceleration semaphore are gathered using wearable device, collection signal is filtered, then carry out the extraction of temporal signatures, frequency domain character；Using linear discriminant method to extract temporal signatures, frequency domain character carry out dimensionality reduction, determine the physical signs after dimensionality reduction and 3-axis acceleration semaphore, the physical signs and 3-axis acceleration semaphore that dimensionality reduction is gone out are compared with the data in mood data storehouse and behavior database respectively, and identification obtains affiliated mood and behavior state in each period.The present invention can be enable parent or teacher timely to pinpoint the problems and make and targetedly instructed correction with the learning state of objective and accurate acquisition student.
Description
Technical field
Recognition methods and system the present invention relates to a kind of Students ' Learning state based on wearable device.
Background technology
Intelligent spire lamella is a kind of function wrist strap with scientific and technological content for being different from conventional wristband, there is pedometer, and alarm clock is slept
The various functions such as dormancy monitoring, health control, anti-lost positioning.A bracelet band is only needed on hand, the number of needs can be detected
According to.
For most of students in middle and primary schools, the consciousness of study and enthusiasm or relatively low.Most middle and primary schools
Life is required for for a long time keeping learning state in the case of supervision, but due to current social environment, not only family
It is long be for the study time of supervision of student it is extremely limited, in school teacher covered for the supervision of individual student nor
Very comprehensively, and students in middle and primary schools are not yet ripe due to mostly intelligence, always constantly look for supervising that leak and being difficult to restrains oneself is engaged in
Activity outside habit, such as can not timely find and supervise guidance, it is easy to allow student to go astray, neglect one's studies.
With the arrival of the Internet of things era, various wearable devices rise therewith, wherein also including for medium and small
Anti-lost bracelet, motion detection wrist strap of student etc., but due to being currently based on Emotion identification of the wearable device for wearer
And the technical bottleneck of Activity recognition, it is impossible to obtain wearer's behavioral data and carry out science by wearable device and accurately divide
Analysis, therefore, wearable device is urgently improved in terms of students in middle and primary schools' study supervision.
The content of the invention
The present invention is in order to solve the above problems, it is proposed that a kind of identification side of the Students ' Learning state based on wearable device
Method and system, the present invention carry out data acquisition and go forward side by side market thread, Activity recognition using wearable device, finally by intersecting judgement
The Students ' Learning state of state recognition is carried out, mood and Activity recognition is effectively carried out.
To achieve these goals, the present invention is adopted the following technical scheme that：
A kind of recognition methods of the Students ' Learning state based on wearable device, comprises the following steps：
(1) by the existing mood classification of the mankind, the setting physical signs corresponding with each classification, typing mood data storehouse,
By behavior state classification when learning, set and all kinds of corresponding human body 3-axis acceleration semaphores, typing behavior database；
(2) physical signs and individual 3-axis acceleration semaphore are gathered using wearable device, collection signal is carried out
Filtering, then the extraction for carrying out temporal signatures, frequency domain character；
(3) using linear discriminant method to extract temporal signatures, frequency domain character carry out dimensionality reduction, determine the physiology after dimensionality reduction
Index and 3-axis acceleration semaphore；
(4) physical signs and 3-axis acceleration semaphore for going out dimensionality reduction respectively with mood data storehouse and behavior database in
Data be compared, affiliated mood and behavior state that identification obtains in each period.
In the step (1), according to the existing categories of emotions of the mankind, input database, mood includes but is not limited to happy, height
It is emerging, excited, exciting, happy, pleasantly surprised, surprised, angry, nervous, anxiety, animosity, indignation, melancholy, sad, sad, frightened, harmful
Be afraid of, it is shy, ashamed, feel ashamed or abashed, regret, compunction, be crazy about, it is tranquil, irritable, bored, painful, pessimistic, dejected, slack, leisurely and carefree,
Meaning, it is comfortable, happy, peaceful, feel oneself inferior, it is self-satisfied, uneven and/or discontented.
In the step (1), every kind of mood is correspondingly arranged corresponding physical signs scope, and physical signs includes：Heart rate, blood
Flow velocity degree, body temperature, brain wave frequency, brain wave power, brain wave power spectral density and/or brain wave energy are extremely asymmetric
Property.
In the step (1), according to people's behavior produced when daily life learns, behavior database is set up, specifically
Including：Write, sit quietly, reading, standing, walking about, running, desk of lying prone, lying low or sleep, and the axle of human body three of every kind of behavior is set
Acceleration signal amount.
Preferably, to physical signs such as indivedual hardly possible identification behavior typing hearts rate, VPVs, difficult identification behavior includes quiet
Sit, lie low, sleep.
In the step (2), the physical signs and 3-axis acceleration semaphore of human body are gathered, specifically include time, class
Mesh and numerical value.
In the step (2), it is to the difference equation that 3-axis acceleration semaphore is filtered：
In formula, N is the forms length of wave filter, and h (m) is specific pulse bandwidth filtering system, and x (n) is input signal to be filtered,
Y (n) is output signal after filtering, and filtering system is obtained by following formula
H (n)=WN(n)hd(n) (2)
In formula, hdN () is ideal filter, fNN () is window procedure, N is forms length, and wherein window procedure is：
In the step (2), frequency domain character extracting method is：
Wherein,
Wherein X (n) represents the discrete physiological signal sequence of input, WNIt is twiddle factor, X (k) is that list entries X (n) is right
The relative amplitude of the N number of discrete point in frequency answered, X (k+N)=X (k) arbitrarily takes continuous N number of point and represents calculating effect, and n, k are
It is that natural number value is 0 to N-1.
In the step (3), the linear discriminant method based on LDS carries out dimensionality reduction to the feature extracted, by the pattern of higher-dimension
Sample projects to best discriminant technique vector space, the effect of classification information and compressive features space dimensionality is extracted to reach, after projection
Assured Mode sample has most preferably within this space in the between class distance and minimum inter- object distance, i.e. pattern that there is maximum new subspace
Separability.
In the step (3), multi-class problem is then needed to constitute a projection matrix by multiple projection vectors, sample is thrown
Shadow on projection matrix, so as to extract low one-dimensional characteristic vector.
In the step (4), non-learning state in individual identification result and abnormal emotion are marked, it is suitable according to the time
Sequence, forms learning state report.
A kind of identifying system of the Students ' Learning state based on wearable device, including：
Database server, is configured as, by the existing mood classification of the mankind, setting the physiology corresponding with each classification and referring to
Mark, typing mood data storehouse, by behavior state classification when learning, is set and all kinds of corresponding human body 3-axis acceleration signals
Amount, typing behavior database；
Wearable device, is configured as collection physical signs and individual 3-axis acceleration semaphore；
Characteristic extracting module, is configured as receiving the information of wearable device collection, and it is filtered, and extracts time domain special
Levy, frequency domain character；
Dimension-reduction treatment module, be configured as using linear discriminant method to extract temporal signatures, frequency domain character drops
Dimension, determines the physical signs after dimensionality reduction and 3-axis acceleration semaphore；
Comparator, be configured as the physical signs that dimensionality reduction and 3-axis acceleration semaphore respectively with mood data storehouse and
Data in behavior database are compared, and identification obtains affiliated mood and behavior state in each period.
Beneficial effects of the present invention are：
(1) present invention can enable parent or teacher timely to find with the learning state of objective and accurate acquisition student
Problem simultaneously makes targetedly guidance correction, and such as notice concentration problem and learning time is adjusted；
(2) contribute to form learning state report, interior for a period of time of student can be rapidly understood in a short time
Habit state so that parent or teacher need not take a significant amount of time and supervise Students ' Learning constantly, and make teacher to the pipe of a large amount of students
Reason education is more accurate, efficient, is conducive to the lifting of school eduaction level.
Brief description of the drawings
Fig. 1 is the schematic flow sheet for setting up pervasive database model of the invention；
Fig. 2 is the schematic flow sheet of analysis of information collection of the invention；
Fig. 3 is state recognition of the invention and process of feedback schematic diagram.
Specific embodiment：
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
The measure of supervision and system of the Students ' Learning state based on wearable device, comprise the following steps：
As shown in figure 1, the first stage：Pervasive database model is set up
Step 1：According to the existing categories of emotions of the mankind, input database.Main mood is divided into happy, glad, excited, sharp
Dynamic, happy, pleasantly surprised, surprised, angry, nervous, anxiety, animosity, indignation, melancholy, it is sad, sad, frightened, fear, it is shy, shy
Shame, feel ashamed or abashed, regret, compunction, be crazy about, it is tranquil, irritable, bored, painful, pessimistic, dejected, slack, leisurely and carefree, proud, comfortable, fast
It is happy, peaceful, feel oneself inferior, it is self-satisfied, uneven, discontented etc..
Step 2：The physical signs scope of every kind of mood is set.Physical signs mainly includes：Heart rate, VPV, body temperature,
Brain wave frequency, brain wave power, brain wave power spectral density, brain wave energy extremely asymmetry.
Step 3：According to people's behavior produced when daily life learns, behavior database is set up.Main behavior includes：
Write, sit quietly, reading, standing, walking about, running, desk of lying prone, lie low, sleep.
Step 4：The data target of every kind of behavior is set.Data target refers to human body 3-axis acceleration semaphore.And to indivedual
The physical signs such as difficult identification behavior typing heart rate, VPV, difficult identification behavior includes sitting quietly, lying low, sleeping.
As shown in Fig. 2 second stage：Analysis of information collection
Step 1：
Individual heart rate, VPV, body temperature, brain wave frequency, brain wave power, brain wave are gathered by wearable device
The physical signs such as power spectral density, brain wave energy extremely asymmetry and individual 3-axis acceleration semaphore.Form is：【When
Between, classification, numerical value】
Step 2：
Individual behavior (3-axis acceleration semaphore) is filtered.
Filter difference equation is
In formula, N is the forms length of wave filter, and h (m) is specific pulse bandwidth filtering system, and x (n) is input signal to be filtered,
Y (n) is output signal after filtering.Filtering system is obtained by following formula
H (n)=WN(n)hd(n) (2)
In formula, hdN () is ideal filter, fNN () is window procedure, N is forms length, and wherein window procedure is：
Step 3：
Feature extraction is carried out to gathered data, mainly including temporal signatures, frequency domain character.
Wherein frequency domain character is extracted：
Wherein, k=0,1 ..., N-1；
Wherein X (n) represents the discrete physiological signal sequence of input, WNIt is twiddle factor, X (k) is that list entries X (n) is right
The relative amplitude of the N number of discrete point in frequency answered, because one group of discrete frequency range value that LKS is calculated is actually in frequency
In mechanical periodicity on axle, i.e. X (k+N)=X (k), therefore any continuously N number of point that takes can represent the calculating effect of LKS.
Step 4：
Feature to extracting carries out dimensionality reduction, and the present invention uses the linear discriminant method dimensionality reduction based on LDS.
Comprise the following steps that：
ChooseReach any n n dimensional vector ns of maximumAs projecting direction so that the sample after projection has maximum
Like members dispersion and minimum within-cluster variance.
The pattern sample of higher-dimension is projected into best discriminant technique vector space, classification information and compressive features sky are extracted to reach
Between dimension effect, after projection Assured Mode sample new subspace have maximum between class distance SAWith minimum inter- object distance SW,
I.e. pattern has optimal separability within this space, and to reach optimal classification effect, this algorithm is introduced and differentiates criterion table in addition
Up to formula (5)
For lower dimensional space is projected, multi-class problem is then needed to constitute a projection matrix by multiple projection vectors, by sample
Originally project on projection matrix, so as to extract low one-dimensional characteristic vector.
As shown in figure 3, the phase III：State recognition and feedback
Step 1：Data after treatment are compared with each state parameter scope in database, individual each period is drawn
Mood, behavior state.
Step 2：Non- learning state in individual identification result and abnormal emotion are marked.
Step 3：Sequentially in time, reported with written form output learning state.
Although above-mentioned be described with reference to accompanying drawing to specific embodiment of the invention, not to present invention protection model
The limitation enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not
Need the various modifications made by paying creative work or deformation still within protection scope of the present invention.
Claims (10)
1. a kind of recognition methods of the Students ' Learning state based on wearable device, it is characterized in that：Comprise the following steps：
(1) by the existing mood classification of the mankind, the physical signs corresponding with each classification is set, typing mood data storehouse will be learned
Behavior state classification during habit, is set and all kinds of corresponding human body 3-axis acceleration semaphores, typing behavior database；
(2) physical signs and individual 3-axis acceleration semaphore are gathered using wearable device, collection signal are filtered,
The extraction of temporal signatures, frequency domain character is carried out again；
(3) using linear discriminant method to extract temporal signatures, frequency domain character carry out dimensionality reduction, determine the physical signs after dimensionality reduction
And 3-axis acceleration semaphore；
(4) physical signs and 3-axis acceleration semaphore for going out dimensionality reduction respectively with mood data storehouse and behavior database in number
According to being compared, identification obtains affiliated mood and behavior state in each period.
2. a kind of recognition methods of the Students ' Learning state based on wearable device as claimed in claim 1, it is characterized in that：Institute
State in step (1), every kind of mood is correspondingly arranged corresponding physical signs scope, physical signs includes：Heart rate, VPV, body
Temperature, brain wave frequency, brain wave power, brain wave power spectral density and/or brain wave energy extremely asymmetry.
3. a kind of recognition methods of the Students ' Learning state based on wearable device as claimed in claim 1, it is characterized in that：Institute
State in step (1), according to people's behavior produced when daily life learns, set up behavior database, and every kind of behavior is set
Human body 3-axis acceleration semaphore.
4. a kind of recognition methods of the Students ' Learning state based on wearable device as claimed in claim 1, it is characterized in that：Institute
State in step (2), gather the physical signs and 3-axis acceleration semaphore of human body, specifically include time, classification and numerical value.
5. a kind of recognition methods of the Students ' Learning state based on wearable device as claimed in claim 1, it is characterized in that：Institute
State in step (2), be to the difference equation that 3-axis acceleration semaphore is filtered：
In formula, N is the forms length of wave filter, and h (m) is specific pulse bandwidth filtering system, and x (n) is input signal to be filtered, y (n)
It is output signal after filtering, filtering system is obtained by following formula
H (n)=WN(n)hd(n) (2)
In formula, hdN () is ideal filter, fNN () is window procedure, N is forms length, and wherein window procedure is：
6. a kind of recognition methods of the Students ' Learning state based on wearable device as claimed in claim 1, it is characterized in that：Institute
State in step (2), frequency domain character extracting method is：
Wherein,
Wherein X (n) represents the discrete physiological signal sequence of input, WNIt is twiddle factor, X (k) is the corresponding N of list entries X (n)
The relative amplitude of individual discrete point in frequency, X (k+N)=X (k) arbitrarily takes continuous N number of point and represents calculating effect, and n, k are natures
Number value is 0 to N-1.
7. a kind of recognition methods of the Students ' Learning state based on wearable device as claimed in claim 1, it is characterized in that：Institute
State in step (3), the linear discriminant method based on LDS carries out dimensionality reduction to the feature extracted, and the pattern sample of higher-dimension is projected to
Best discriminant technique vector space, the effect of classification information and compressive features space dimensionality, Assured Mode sample after projection are extracted to reach
This has optimal can be separated within this space in the between class distance and minimum inter- object distance, i.e. pattern that there is maximum new subspace
Property.
8. a kind of recognition methods of the Students ' Learning state based on wearable device as claimed in claim 1, it is characterized in that：Institute
State in step (3), multi-class problem is then needed to constitute a projection matrix by multiple projection vectors, sample is projected into projection square
In battle array, so as to extract low one-dimensional characteristic vector.
9. a kind of recognition methods of the Students ' Learning state based on wearable device as claimed in claim 1, it is characterized in that：Institute
State in step (4), non-learning state in individual identification result and abnormal emotion are marked, sequentially in time, formed and learned
Practise state report.
10. a kind of identifying system of the Students ' Learning state based on wearable device, it is characterized in that：Including：
Database server, is configured as, by the existing mood classification of the mankind, setting the physical signs corresponding with each classification, record
Enter mood data storehouse, behavior state classification when learning is set and all kinds of corresponding human body 3-axis acceleration semaphores, record
Enter behavior database；
Wearable device, is configured as collection physical signs and individual 3-axis acceleration semaphore；
Characteristic extracting module, is configured as receiving the information of wearable device collection, and it is filtered, extraction temporal signatures,
Frequency domain character；
Dimension-reduction treatment module, be configured as using linear discriminant method to extract temporal signatures, frequency domain character carry out dimensionality reduction, really
Determine the physical signs after dimensionality reduction and 3-axis acceleration semaphore；
Comparator, be configured as the physical signs that dimensionality reduction and 3-axis acceleration semaphore respectively with mood data storehouse and behavior
Data in database are compared, and identification obtains affiliated mood and behavior state in each period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611110218.8A CN106778575A (en) | 2016-12-06 | 2016-12-06 | A kind of recognition methods of Students ' Learning state based on wearable device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611110218.8A CN106778575A (en) | 2016-12-06 | 2016-12-06 | A kind of recognition methods of Students ' Learning state based on wearable device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106778575A true CN106778575A (en) | 2017-05-31 |
Family
ID=58879142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611110218.8A Pending CN106778575A (en) | 2016-12-06 | 2016-12-06 | A kind of recognition methods of Students ' Learning state based on wearable device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778575A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107582076A (en) * | 2017-08-15 | 2018-01-16 | 浙江大学 | A kind of attention force checking device and detection method based on wireless action acquisition module |
| CN108009954A (en) * | 2017-12-12 | 2018-05-08 | 联想(北京)有限公司 | A kind of Formulating Teaching Program method, apparatus, system and electronic equipment |
| CN109215791A (en) * | 2018-10-31 | 2019-01-15 | 深圳市儿童医院 | Health control method, system, equipment and storage medium based on multi information decision |
| CN109300350A (en) * | 2018-12-08 | 2019-02-01 | 廖洪来 | A kind of method and apparatus of instruction after class |
| CN111248928A (en) * | 2020-01-20 | 2020-06-09 | 北京津发科技股份有限公司 | Pressure identification method and device |
| CN111767367A (en) * | 2020-05-13 | 2020-10-13 | 上海光数信息科技有限公司 | Method and system for tracking student moods and extracting emotional features |
| WO2021068783A1 (en) * | 2019-10-12 | 2021-04-15 | 广东电网有限责任公司电力科学研究院 | Emotion recognition method, device and apparatus |
| CN114098692A (en) * | 2021-10-28 | 2022-03-01 | 北京心世纪医疗科技有限公司 | Left ventricle auxiliary device implantation method based on blood flow distribution optimization |
| CN116725538A (en) * | 2023-08-11 | 2023-09-12 | 深圳市昊岳科技有限公司 | Bracelet emotion recognition method based on deep learning |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542849A (en) * | 2012-01-20 | 2012-07-04 | 东南大学 | Formative evaluation system |
| CN102663347A (en) * | 2012-03-21 | 2012-09-12 | 陕西师范大学 | Student learning behavior acquisition and analysis system and method thereof |
| CN104056445A (en) * | 2014-07-01 | 2014-09-24 | 杭州攻壳科技有限公司 | Human motion analytical method based on heart rate and acceleration sensor and device based on method |
| CN104545951A (en) * | 2015-01-09 | 2015-04-29 | 天津大学 | Body state monitoring platform based on functional near-infrared spectroscopy and motion detection |
| CN105082150A (en) * | 2015-08-25 | 2015-11-25 | 国家康复辅具研究中心 | Robot man-machine interaction method based on user mood and intension recognition |
| CN105136156A (en) * | 2014-05-29 | 2015-12-09 | 通用汽车环球科技运作有限责任公司 | Adaptive navigation and location-based services based on user behavior patterns |
| CN105260745A (en) * | 2015-09-30 | 2016-01-20 | 西安沧海网络科技有限公司 | Information push service system capable of carrying out emotion recognition and prediction based on big data |
| CN105395192A (en) * | 2015-12-09 | 2016-03-16 | 恒爱高科(北京)科技有限公司 | Wearable emotion recognition method and system based on electroencephalogram |
| CN105536118A (en) * | 2016-02-19 | 2016-05-04 | 京东方光科技有限公司 | Emotion regulation device, wearable equipment and cap with function of relieving emotion |
| CN105844101A (en) * | 2016-03-25 | 2016-08-10 | 惠州Tcl移动通信有限公司 | Emotion data processing method and system based smart watch and the smart watch |
-
2016
- 2016-12-06 CN CN201611110218.8A patent/CN106778575A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102542849A (en) * | 2012-01-20 | 2012-07-04 | 东南大学 | Formative evaluation system |
| CN102663347A (en) * | 2012-03-21 | 2012-09-12 | 陕西师范大学 | Student learning behavior acquisition and analysis system and method thereof |
| CN105136156A (en) * | 2014-05-29 | 2015-12-09 | 通用汽车环球科技运作有限责任公司 | Adaptive navigation and location-based services based on user behavior patterns |
| CN104056445A (en) * | 2014-07-01 | 2014-09-24 | 杭州攻壳科技有限公司 | Human motion analytical method based on heart rate and acceleration sensor and device based on method |
| CN104545951A (en) * | 2015-01-09 | 2015-04-29 | 天津大学 | Body state monitoring platform based on functional near-infrared spectroscopy and motion detection |
| CN105082150A (en) * | 2015-08-25 | 2015-11-25 | 国家康复辅具研究中心 | Robot man-machine interaction method based on user mood and intension recognition |
| CN105260745A (en) * | 2015-09-30 | 2016-01-20 | 西安沧海网络科技有限公司 | Information push service system capable of carrying out emotion recognition and prediction based on big data |
| CN105395192A (en) * | 2015-12-09 | 2016-03-16 | 恒爱高科(北京)科技有限公司 | Wearable emotion recognition method and system based on electroencephalogram |
| CN105536118A (en) * | 2016-02-19 | 2016-05-04 | 京东方光科技有限公司 | Emotion regulation device, wearable equipment and cap with function of relieving emotion |
| CN105844101A (en) * | 2016-03-25 | 2016-08-10 | 惠州Tcl移动通信有限公司 | Emotion data processing method and system based smart watch and the smart watch |
Non-Patent Citations (6)
| Title |
|---|
| 付小宁: "《数据处理及模型化方法》", 30 June 2016, 西北农林科技大学出版社 * |
| 成娟: "基于表面肌电和加速度信号融合的动作识别和人体行为分析研究", 《万方学位论文全文数据库》 * |
| 温万慧: "基于生理信号的情感识别方法研究", 《中国博士学位论文全文数据库》 * |
| 范长军: "融合加速度和生理信号的人体活动识别", 《万方学位论文全文数据库》 * |
| 金靖: "《实时数字信号处理实践方法 从理论到现实》", 31 August 2016, 北京航空航天大学出版社 * |
| 陈玉东: "《数字信号处理》", 30 September 2014, 地质出版社 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107582076A (en) * | 2017-08-15 | 2018-01-16 | 浙江大学 | A kind of attention force checking device and detection method based on wireless action acquisition module |
| CN107582076B (en) * | 2017-08-15 | 2020-05-19 | 浙江大学 | Attention detection device and detection method based on wireless action acquisition module |
| CN108009954A (en) * | 2017-12-12 | 2018-05-08 | 联想(北京)有限公司 | A kind of Formulating Teaching Program method, apparatus, system and electronic equipment |
| CN108009954B (en) * | 2017-12-12 | 2021-10-22 | 联想(北京)有限公司 | Teaching plan making method, device and system and electronic equipment |
| CN109215791A (en) * | 2018-10-31 | 2019-01-15 | 深圳市儿童医院 | Health control method, system, equipment and storage medium based on multi information decision |
| CN109300350A (en) * | 2018-12-08 | 2019-02-01 | 廖洪来 | A kind of method and apparatus of instruction after class |
| WO2021068783A1 (en) * | 2019-10-12 | 2021-04-15 | 广东电网有限责任公司电力科学研究院 | Emotion recognition method, device and apparatus |
| CN111248928A (en) * | 2020-01-20 | 2020-06-09 | 北京津发科技股份有限公司 | Pressure identification method and device |
| CN111767367A (en) * | 2020-05-13 | 2020-10-13 | 上海光数信息科技有限公司 | Method and system for tracking student moods and extracting emotional features |
| CN114098692A (en) * | 2021-10-28 | 2022-03-01 | 北京心世纪医疗科技有限公司 | Left ventricle auxiliary device implantation method based on blood flow distribution optimization |
| CN116725538A (en) * | 2023-08-11 | 2023-09-12 | 深圳市昊岳科技有限公司 | Bracelet emotion recognition method based on deep learning |
| CN116725538B (en) * | 2023-08-11 | 2023-10-27 | 深圳市昊岳科技有限公司 | Bracelet emotion recognition method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778575A (en) | A kind of recognition methods of Students ' Learning state based on wearable device and system | |
| Zhang et al. | Emotion recognition using multi-modal data and machine learning techniques: A tutorial and review | |
| Smith et al. | A developmental approach to machine learning? | |
| Vézard et al. | EEG classification for the detection of mental states | |
| CN108577865A (en) | A kind of psychological condition determines method and device | |
| CN110070105A (en) | Brain electricity Emotion identification method, the system quickly screened based on meta learning example | |
| CN107205652A (en) | The sleep analysis system with automatic mapping is generated with feature | |
| CN104571533B (en) | A kind of apparatus and method based on brain-computer interface technology | |
| CN108122004A (en) | The brain electricity sorting technique of the sparse learning machine that transfinites is differentiated based on Fisher | |
| CN106991409A (en) | A kind of Mental imagery EEG feature extraction and categorizing system and method | |
| Liu et al. | A novel stress state assessment method for college students based on EEG | |
| Nigam et al. | An improved approach for stress detection using physiological signals | |
| CN104679249A (en) | Method for implementing Chinese BCI (brain and computer interface) based on a DIVA (directional into velocities of articulators) model | |
| Liu et al. | A data-driven adaptive emotion recognition model for college students using an improved multifeature deep neural network technology | |
| CN105854147A (en) | Intelligent home environment regulation system and method | |
| Azcarraga et al. | Predicting academic emotions based on brainwaves, mouse behaviour and personality profile | |
| CN109044351A (en) | Logical thinking training system and method based on EEG feedback | |
| Singh et al. | Architectural review of co-adaptive brain computer interface | |
| Zhang et al. | Decoding analysis of alpha oscillation networks on maintaining driver alertness | |
| Chai et al. | Application of EEG signal recognition method based on duffing equation in psychological stress analysis | |
| Fu et al. | Detecting drowsiness in driving simulation based on EEG | |
| Huynh et al. | An investigation of ensemble methods to classify electroencephalogram signaling modes | |
| Sun et al. | Vigilance analysis based on EEG band power using support vector machine | |
| Fordson et al. | A feature learning approach based on multimodal human body data for emotion recognition | |
| Liang | A Method of Extracting and Identifying College Students’ Music Psychological Features Based on EEG Signals |
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: 20170531 |
|
| RJ01 | Rejection of invention patent application after publication |