CN112315471A - Brain training evaluation system based on intelligent maze and evaluation method thereof - Google Patents
Brain training evaluation system based on intelligent maze and evaluation method thereof Download PDFInfo
- Publication number
- CN112315471A CN112315471A CN202011136200.1A CN202011136200A CN112315471A CN 112315471 A CN112315471 A CN 112315471A CN 202011136200 A CN202011136200 A CN 202011136200A CN 112315471 A CN112315471 A CN 112315471A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- maze
- brain wave
- module
- walking
- 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 101
- 210000004556 brain Anatomy 0.000 title claims abstract description 57
- 238000012549 training Methods 0.000 title claims description 10
- 238000012360 testing method Methods 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 208000019901 Anxiety disease Diseases 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 16
- 230000036506 anxiety Effects 0.000 claims abstract description 15
- 238000013135 deep learning Methods 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Physiology (AREA)
- Computational Linguistics (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a maze levelness assessment system which comprises a maze, a brain wave testing device, a brain wave analysis module, a levelness assessment module, a control module, a camera for shooting the maze and a display and recording system for displaying and recording maze walking live situations on site. The brain wave analysis module is used for analyzing corresponding four types of brain wave characteristic values of smooth and unsmooth walking, anxiety and excitement of a player in a competition, and after the anxiety is overcome, the scores are calculated through an entropy weight method, and machine evaluation on the maze level of the player is realized. And the maze walking situation co-evaluation personnel shot by the camera judge according to experience, and the final comprehensive evaluation is obtained through geometry and evaluation thereof. The invention also provides a maze level evaluation method based on the evaluation system and a method for improving the maze ability of the picomouse through deep learning by using the brain wave characteristics of excellent testers. The invention utilizes the entropy weight method to recombine machine evaluation to obtain the optimal machine evaluation, and can objectively, accurately and scientifically analyze the maze level of a player by combining manual evaluation.
Description
Technical Field
The invention relates to an evaluation system and an evaluation method for game competition ability, in particular to a maze level evaluation system and an evaluation method thereof, and belongs to the field of intelligent learning evaluation.
Background
Picomice, as racing walking machines, are particularly challenged by designers' chips and the ability to communicate and algorithmically design in maze walking competitions. The prior art improves the anti-interference (CN102841618A), dynamic level (CN103605363A), turning motion (CN103472831A), sprint time (CN103529846A) and motion accuracy (CN206039293U) of the picomouse during the maze type walking by improving the functions of components of the picomouse. Maze walking traditionally has no international competition of artificial walking, but is biased in the direction of game and intelligence test, and the horizontal evaluation is only dependent on the time length. The brain wave control device is used for playing games, controlling game screen objects (CN201949631U) or recognizing feelings in the games (CN110866537A), and is a non-contact control technology for game control.
In summary, the prior art does not pay attention to the development prospects in two aspects, and firstly, does not pay attention to the improvement of the maze ability of the picomouse through learning, particularly through learning of walking skills of excellent artificial players; secondly, the prior art has a single evaluation method for the elite players, and cannot obtain a model of the elite skills through a reasonable model, so as to optimize the artificial intelligence capability of the picomouse walking. Patent CN107468260A uses a single classification model to identify the mental state of an animal, which is obviously not suitable for the state of a human maze match, and CN107538492A only provides a method using brain waves to control the movement of a robot, and does not relate to the evaluation of the match level.
The competition is a comprehensive ability test of comprehensive intelligence and psychology, and the competition not only needs time, but also needs whether a walking route is smooth or not when the competition passes through, and the competition is anxious and excited, overcomes the anxiety and can reflect the selected comprehensive quality. There is therefore a need to detect these game-affecting factors in real time. And single-pass machine evaluation is not always objective to level evaluation easily due to inaccurate algorithm. Therefore, there is a need for a device capable of detecting the walking state and psychological state of a player in real time so as to obtain a machine evaluation method through a reasonable algorithm.
Further, evaluation of human experience is also an indispensable link, and human evaluation can be given to judgment of expert level according to the experience of a game. The prior art does not comprehensively consider the combination of machine evaluation and manual evaluation.
Disclosure of Invention
Based on the defects of the prior art, the invention provides a comprehensive and reasonable machine algorithm and a brain training evaluation system based on an intelligent maze. The method solves the technical problems that in the prior art, single time length evaluation is used, and comprehensive consideration of evaluation and manual evaluation is ignored. A maze level evaluation system according to the present invention includes: the system comprises a maze, a brain wave testing device, a brain wave analysis module, a level evaluation module, a camera for shooting the maze, a display and record system for displaying and recording the walking condition of the maze on site, and a control module. The control module is respectively electrically connected with the brain wave testing device, the brain wave analysis module, the level evaluation module and the camera, the display and recording system and is used for controlling the devices and the modules, and the control module is also provided with input equipment and is used for inputting scores including expert evaluation.
When a tester is in a match, the brain wave testing device continuously detects brain wave signals of the tester, and the signals are denoised and the characteristic signal values are extracted through the brain wave analysis module, so that whether the end is smooth to walk is judged according to the residence time of a certain point in a walking route of the match, the condition that the end is not smooth to walk is stipulated that the end is not smooth to walk when the end is retained for more than 3 seconds at a certain position point in the walking process of the maze, and whether the end is in an anxiety state is judged according to the mean value of the brain wave characteristic signal values reduced variation value as the anxiety characteristic signal if the end is not smooth to walk for more than 2 times (for example, 5-15 seconds), and whether the normal characteristic signal value is recovered or not is detected after the anxiety characteristic signal occurs for more than 2 times, so that whether the anxiety is overcome or not is. And the average value of the rising change values higher than the normal characteristic signal value is used as the excitation characteristic signal
The average value of the change values of the brain wave characteristic signal values decreasing (or increasing) is an arithmetic average value of the sum of differences (defined as positive values) between the values of the anxiety (or excitement) characteristic signal and the normal characteristic signal n times, and the absolute value of the obtained score is increased correspondingly when the difference is larger. Therefore, five brain wave characteristic signals are sampled once every 2-5 seconds by using p1 (which is a positive value) with smooth walking, p2 (which is a negative value) with unsmooth walking, p 39 3 (which is a negative value) with anxiety, p4 (which is a positive value) with overcoming anxiety, p5 (which is a positive value) with racing excitation and p6 as six evaluation indexes, and the values of the five types of brain wave characteristic signals are acquired, and the score of the racing time is acquired when the race is finished. And finally, processing all sampling values and the game time scores (the sampling obtained each time corresponds to the same game time score index, namely the game time scores are unchanged) by an entropy weight method through a horizontal evaluation module to obtain scores F' so as to obtain a machine evaluation result. The entropy weight method comprises index normalization processing, entropy value calculation, information entropy redundancy, index weight and calculation score. And defining the world fastest recording time as a competition time score 1, and correspondingly calculating the competition time score f as 1/(1+ w) according to the percentage w of the competition time exceeding the world fastest recording time. When at least one player is used for average or exceeds the fastest recording time of the world, the fastest one is evaluated as the best show manually without participating in machine evaluation.
When the match is finished, the display and recording system enables a plurality of field watching match experts of the live condition shot by the camera to watch through the display screen in the display and recording system, and therefore a plurality of manual evaluation scores are obtained. When the score is objectified, the score can be reviewed and reevaluated through video recording of the game. The expert inputs the respective final evaluation scores F1, F2... Fn (n is a natural number which is not zero) through an input device of the control module, and the comprehensive evaluation score is calculated through the level evaluation module. The overall evaluation score F ═ aF' + bF1+ cF2+ ·+ xFn, where a, b, c., x are positive real weights, a is not less than 0.5, and a + b + c. + x ═ 1; a, b, c, d.. x is given corresponding weight according to the grade level of the referee, and the weight is larger when the grade is higher.
The invention provides an evaluation method of a brain training evaluation system based on an intelligent maze, which is characterized by comprising the following steps:
the S1 control module controls the opening of the brain wave testing device, the brain wave analysis module, the level evaluation module, the camera and the display and recording system to enable the brain wave testing device, the brain wave analysis module, the level evaluation module and the camera to be in a working state;
s2, connecting the head of the tester with the sensing patch in the electric wave testing device, testing, and sampling five brain wave characteristic signals once every 2-5 seconds; at the moment, the horizontal evaluation module starts to time, the electroencephalogram analysis module receives and denoises the electroencephalogram characteristic signal, and transmits the processed electroencephalogram characteristic signal to the horizontal evaluation module; meanwhile, the camera starts to shoot the maze video, and the judge watches the match through a display screen in the display and record system;
s3, sampling five brain wave characteristic signals once every 3 seconds by taking the measured walking smoothness positive value p1, walking unsmooth negative value p2, anxiety negative value p3, overcome anxiety positive value p4, competition excitation positive value p5 and competition time score positive value p6 as six evaluation indexes, and obtaining five types of brain wave characteristic signal values; calculating the match time score f as 1/(1+ w) according to the percentage w of the match time exceeding the fastest recording time of the world;
s4, when the match is finished, the horizontal evaluation module carries out entropy weight method processing to obtain scores F 'to obtain a machine evaluation result, wherein the score of each index is the arithmetic mean of all sampling scores, and F' is the arithmetic mean of scores of six indexes; inputting a manual evaluation score F1, F2... Fn by a referee through an input device of a display and recording system, wherein n is a natural number which is not zero, and calculating a comprehensive evaluation score F ═ aF' + bF1+ cF2+.. + xFn by a horizontal evaluation module, wherein a, b, c,. once, x is a positive real number weight, 0.5 ≦ a < 0.65, and a + b + c. + x ═ 1; a, b, c, d.. x gives corresponding weight according to the grade level of the judge, the higher the grade is, the higher the weight is, only one special judge is set to give 0.2 weight, one first-grade judge is set to give 0.15 weight, and each of the other judges gives the average number z of the rest weights according to the human head; if a total of y other officials are set, z is (0.65-a)/y;
wherein, the competition time score f is correspondingly calculated to be 1/(1+ w) according to the percentage w of the competition time exceeding the fastest recording time of the world. When at least one player uses the time to average or exceed the fastest recording time of the world, the fastest one is evaluated as the best show manually.
The invention also provides a method for optimizing the maze ability of the mini mouse, which is characterized in that the deep learning of a plurality of different mazes is carried out through six index values of the top one hundred superior world ranks, and the path with the highest score is selected at the position point of the fork in the walking process, so that the skill of the maze walking is continuously accumulated, and the maze walking ability of the mini mouse is optimized. Wherein the deep learning comprises at least one of convolutional neural networks, self-coding, sparse coding, and deep belief networks.
Drawings
FIG. 1 is a schematic diagram of a brain training evaluation system based on the intelligent maze.
The system comprises a competition platform 1, a maze and brain wave testing device 3, a brain wave analysis module 4, a level evaluation module 5, a camera 6 for shooting a maze, a display and recording system 7 for displaying and recording the walking condition of the maze on site, and a control module 8.
Detailed Description
The brain training evaluation system and the evaluation method based on the intelligent maze are described below with reference to fig. 1.
Example 1
Fig. 1 shows a brain training evaluation system based on an intelligent maze, which is arranged on a competition platform 1 and comprises a maze 2, a brain wave testing device 3, a brain wave analysis module 4, a level evaluation module 5, a camera 6 for shooting the maze, a display and record system 7 for displaying and recording the walking condition of the maze on site, and a control module 8. The control module 8 is respectively electrically connected with the brain wave testing device 3, the brain wave analysis module 4, the level evaluation module 5, the camera 6 and the display and recording system 7, and is used for controlling the devices and the modules, and the control module 8 is also provided with input equipment (not shown) for inputting scores including expert evaluation.
Example 2
The evaluation method of the brain training evaluation system based on the intelligent maze in the embodiment 1 is characterized by comprising the following steps:
the S1 control module 8 controls the brain wave testing device 3, the brain wave analysis module 4, the level evaluation module 5, the camera 6 and the display and recording system 7 to be turned on to be in a working state;
s2, connecting the head of the tester with the sensing patch in the electric wave testing device 3, testing, and sampling five brain wave characteristic signals once every 2-5 seconds; at the moment, the level evaluation module 5 starts to time, the electroencephalogram analysis module 4 receives and denoises the electroencephalogram characteristic signal, and transmits the processed electroencephalogram characteristic signal to the level evaluation module 5; at the same time, the camera 6 starts to shoot the video in the maze 2, and the referee watches the match through the display screen in the display and recording system 7;
s3, sampling five brain wave characteristic signals once every 3 seconds by taking the measured walking smoothness positive value p1, walking unsmooth negative value p2, anxiety negative value p3, overcome anxiety positive value p4, competition excitation positive value p5 and competition time score positive value p6 as six evaluation indexes, and obtaining five types of brain wave characteristic signal values; calculating the match time score f as 1/(1+ w) according to the percentage w of the match time exceeding the fastest recording time of the world;
s4, obtaining match time scores when a match is finished, and carrying out entropy weight method processing on all sampling values and the match time scores in a level evaluation module 5 to obtain scores F 'to obtain a machine evaluation result, wherein the score of each index is the arithmetic mean of all sampling scores, and F' is the arithmetic mean of scores of six indexes; the referee inputs the manual evaluation scores F1, F2... Fn, where n is a natural number other than zero, through an input device of the display and recording system 7, and calculates a comprehensive evaluation score F ═ aF' + bF1+ cF2+ dF3, where a ═ 0.6, by the level evaluation module 5; setting b as 0.2 corresponding to one special judge, c as 0.15 corresponding to one first judge, and two other judges, each bit giving the rest weight 0.025; wherein for each obtained sample it corresponds to the same index of the playing time score, i.e. the playing time score is constant.
The entropy weight calculation method is as follows:
(1) supposing that m sampling samples to be evaluated are provided, and n evaluation indexes form an original index data matrix: wherein x isijRepresents the ith
Sampling the value of the jth evaluation index of the sample;
(2) the respective indices were normalized as follows:
p1, p4, p5 and p6 adopt forward indexes:
p2, p3 adopt negative indicators:
(3) calculating weights
Calculating the weight of the ith sample (normalized) in the jth index
(4) Calculating the jth index entropy:
since 0 ≦ ej ≦ 1, then
(5) And (3) weight calculation:
(6) Calculate to obtain the ith
Score value of sample:
example 3
The embodiment provides a method for optimizing the maze ability of a mini-mouse, which is characterized in that the deep learning of a plurality of different mazes is carried out through six index values of the top one hundred excellent world ranks, and the path with the highest score is selected at the position point of the branch path during the walking, so that the skill of the maze walking is continuously accumulated, and the maze walking ability of the mini-mouse is optimized. Wherein the deep learning comprises at least one of convolutional neural networks, self-coding, sparse coding, and deep belief networks.
Claims (6)
1. Brain training evaluation system based on intelligence maze, its characterized in that, maze level evaluation system sets up on the race table, and maze level evaluation system includes: the system comprises a maze, a brain wave testing device, a brain wave analysis module, a level evaluation module, a camera for shooting the maze, a display and record system for displaying and recording the walking live condition of the maze on site and a control module; the control module is respectively electrically connected with the brain wave testing device, the brain wave analysis module, the level evaluation module and the camera, the display and recording system, and the control module is also provided with input equipment for inputting scores including expert evaluation.
2. The evaluation method of the intelligent maze-based brain training evaluation system of claim 1, comprising the steps of:
the S1 control module controls the opening of the brain wave testing device, the brain wave analysis module, the level evaluation module, the camera and the display and recording system to enable the brain wave testing device, the brain wave analysis module, the level evaluation module and the camera to be in a working state;
s2, connecting the head of the tester with the sensing patch in the electric wave testing device, testing, and sampling five brain wave characteristic signals once every 2-5 seconds; at the moment, the horizontal evaluation module starts to time, the electroencephalogram analysis module receives and denoises the electroencephalogram characteristic signal, and transmits the processed electroencephalogram characteristic signal to the horizontal evaluation module; meanwhile, the camera starts to shoot the maze video, and the judge watches the match through a display screen in the display and record system;
s3, taking five measured walking smooth positive values p1, walking unsmooth negative values p2, anxiety negative values p3, overcome anxiety positive values p4, game excitation positive values p5 and game time score positive values p6 as six evaluation indexes, sampling the five brain wave characteristic signals once every 2-5 seconds, and obtaining five brain wave characteristic signal values;
s4, obtaining match time scores when a match is finished, and carrying out entropy weight method processing on all sampling values and the match time scores in a level evaluation module to obtain scores F 'to obtain a machine evaluation result, wherein the score of each index is the arithmetic mean of all sampling scores, and F' is the arithmetic mean of scores of six indexes; inputting a manual evaluation score F1, F2... Fn by a referee through an input device of a display and recording system, wherein n is a natural number which is not zero, and calculating a comprehensive evaluation score F ═ aF' + bF1+ cF2+.. + xFn by a horizontal evaluation module, wherein a, b, c,. once, x are positive real number weights, 0.5 ≦ a < 1, and a + b + c +.. + x ═ 1; a, b, c, d.. x gives corresponding weight according to the grade level of the judge, and the weight is larger when the grade is higher;
the entropy weight calculation method is as follows:
(1) supposing that m sampling samples to be evaluated are provided, and n evaluation indexes form an original index data matrix: wherein x isijRepresents the ith
J-th evaluation finger of sampling sampleA target value;
(2) the respective indices were normalized as follows:
p1, p4, p5 and p6 adopt forward indexes:
，
p2, p3 adopt negative indicators:
(3) calculating weights
Calculating the weight of the ith sample (normalized) in the jth index
(4) Calculating the jth index entropy:
since 0 ≦ ej ≦ 1, then
(5) And (3) weight calculation:
(6) Calculate to obtain the ith
Score value of sample:
3. the evaluation method according to claim 2, characterized in that a super judge is set to weight 0.2, a first judge to weight 0.15, and each of the other judges to the average z by head of the remaining weights; if a total of y other officials is set, z is (0.65-a)/y.
4. An evaluation method according to claim 2 or 3, wherein in step S3, a match time score f is calculated as 1/(1+ w) based on the percentage w of the match time exceeding the fastest recording time of the world; when at least one player uses the time to average or exceed the fastest recording time of the world, the fastest one is evaluated as the best show manually.
5. A method for optimizing the maze ability of a mini-mouse, characterized in that six evaluation index values obtained according to claim 2 of one hundred top world ranking are used to perform deep learning of a plurality of different mazes, and the path with the highest score is selected at the branch point during walking, thereby continuously accumulating the skill of maze walking and optimizing the maze walking ability of the mini-mouse.
6. The method of claim 4, wherein the deep learning comprises at least one of convolutional neural networks, self-coding, sparse coding, and deep belief networks.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011136200.1A CN112315471A (en) | 2020-10-22 | 2020-10-22 | Brain training evaluation system based on intelligent maze and evaluation method thereof |
| PCT/CN2020/124836 WO2022082840A1 (en) | 2020-10-22 | 2020-10-29 | Brain training evaluation system based on smart maze and evaluation method therefor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011136200.1A CN112315471A (en) | 2020-10-22 | 2020-10-22 | Brain training evaluation system based on intelligent maze and evaluation method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112315471A true CN112315471A (en) | 2021-02-05 |
Family
ID=74312131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011136200.1A Pending CN112315471A (en) | 2020-10-22 | 2020-10-22 | Brain training evaluation system based on intelligent maze and evaluation method thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112315471A (en) |
| WO (1) | WO2022082840A1 (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030024482A1 (en) * | 2001-08-06 | 2003-02-06 | Vijay Gondhalekar | Programmable electronic maze for use in the assessment of animal behavior |
| CN208001848U (en) * | 2017-12-21 | 2018-10-26 | 中国科学院深圳先进技术研究院 | A kind of labyrinth experiment device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201995441U (en) * | 2010-10-14 | 2011-10-05 | 复旦大学附属华山医院 | Dementia rat labyrinth type intellectual rehabilitation training device |
| AU2012259507B2 (en) * | 2011-05-20 | 2016-08-25 | Nanyang Technological University | Systems, apparatuses, devices, and processes for synergistic neuro-physiological rehabilitation and/or functional development |
| WO2016080341A1 (en) * | 2014-11-17 | 2016-05-26 | 国立研究開発法人産業技術総合研究所 | Method for evaluating similarity using electroencephalography, evaluation device, evaluation system and program |
| CN105230520A (en) * | 2015-07-25 | 2016-01-13 | 南昌航空大学 | Full-automatic rat maze behavior training system |
| CN107422841B (en) * | 2017-03-03 | 2020-03-20 | 杭州市第一人民医院 | Man-machine interaction method based on non-contact emotion recognition |
| CN111420401A (en) * | 2020-04-13 | 2020-07-17 | 宋宇 | Live-action maze system and control method thereof |
-
2020
- 2020-10-22 CN CN202011136200.1A patent/CN112315471A/en active Pending
- 2020-10-29 WO PCT/CN2020/124836 patent/WO2022082840A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030024482A1 (en) * | 2001-08-06 | 2003-02-06 | Vijay Gondhalekar | Programmable electronic maze for use in the assessment of animal behavior |
| CN208001848U (en) * | 2017-12-21 | 2018-10-26 | 中国科学院深圳先进技术研究院 | A kind of labyrinth experiment device |
Non-Patent Citations (2)
| Title |
|---|
| 宋宇辰等: "《基于系统动力学的能源 经济 环境 人口可持续发展建模研究》", 30 November 2016, 冶金工业出版社 * |
| 赖盛章: "大鼠机器人迷宫实验系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022082840A1 (en) | 2022-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334573B (en) | Human motion state discrimination method based on dense connection convolutional neural network | |
| CN111905350B (en) | Automatic table tennis hitting performance evaluation method and system based on motion data | |
| KR101768729B1 (en) | Sensory testing data analysis by categories | |
| US20140074268A1 (en) | Method for Indexation and Level Classification of Kinesthetic Gifted Infants | |
| Yang et al. | Research on face recognition sports intelligence training platform based on artificial intelligence | |
| CN114469089A (en) | Multi-mode data compression resistance evaluation method and system based on virtual reality technology | |
| CN112315471A (en) | Brain training evaluation system based on intelligent maze and evaluation method thereof | |
| US20210245005A1 (en) | Implementation of machine learning for skill-improvement through cloud computing and method therefor | |
| Yip et al. | Badminton smashing recognition through video performance by using deep learning | |
| CN116246347A (en) | Standard judging method and scoring device for basic motor skills of human body | |
| CN115546886A (en) | Method and device for testing wall paddling by volleyballs based on visual technology | |
| CN115620050A (en) | Improved YOLOv5 aphid identification and counting method based on climate chamber environment | |
| Karunaratne et al. | Objectively measure player performance on Olympic weightlifting | |
| Chua et al. | Activity identification and classification in wheelchair rugby using fractal dimensions | |
| CN112070411A (en) | Method for evaluating adaptation degree of new players and teams in basketball tournament | |
| Abdullah et al. | Computer Vision System For Backflip Motion Recognition in Gymnastics Based On Deep Learning | |
| Huang | The Application of Artificial Intelligence Technology in the On-site Decision System of Sports Competitions | |
| Kerdvibulvech | Real-time augmented reality application using color analysis | |
| CN117390401B (en) | Campus sports digital management system and method based on cloud platform | |
| Li | Sports Effect Evaluation Technology based on Elastic Network | |
| Gonzalez-Artetxe et al. | Effects of free play or artificial rules on young soccer players’ individual tactical behaviour: a one-by-one analysis | |
| CN113713360B (en) | Volleyball hitting counting method and device | |
| Shen | Learn from teachers: A teacher learner yoga pose classification and scoring network | |
| CN115414646B (en) | Basketball auxiliary training method and device | |
| Kamnardsiri et al. | Implementation and validity of the long jump knowledge-based system: Case of the approach run phase |
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 |