CN110334662A - A kind of animal based on automated image identification itches behavior analysis method - Google Patents
A kind of animal based on automated image identification itches behavior analysis method Download PDFInfo
- Publication number
- CN110334662A CN110334662A CN201910615140.2A CN201910615140A CN110334662A CN 110334662 A CN110334662 A CN 110334662A CN 201910615140 A CN201910615140 A CN 201910615140A CN 110334662 A CN110334662 A CN 110334662A
- Authority
- CN
- China
- Prior art keywords
- animal
- behavior
- picture
- scratching
- png
- 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
- 241001465754 Metazoa Species 0.000 title claims abstract description 77
- 208000003251 Pruritus Diseases 0.000 title claims abstract description 61
- 238000004458 analytical method Methods 0.000 title claims abstract description 34
- 230000006399 behavior Effects 0.000 claims abstract description 80
- 238000006748 scratching Methods 0.000 claims abstract description 44
- 230000002393 scratching effect Effects 0.000 claims abstract description 44
- 230000007803 itching Effects 0.000 claims abstract description 12
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 230000003542 behavioural effect Effects 0.000 claims abstract description 11
- 230000001154 acute effect Effects 0.000 claims abstract description 9
- 238000002474 experimental method Methods 0.000 claims abstract description 5
- 230000000694 effects Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 14
- NTYJJOPFIAHURM-UHFFFAOYSA-N Histamine Chemical compound NCCC1=CN=CN1 NTYJJOPFIAHURM-UHFFFAOYSA-N 0.000 claims description 10
- 239000003795 chemical substances by application Substances 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 6
- 229960001340 histamine Drugs 0.000 claims description 5
- 238000010254 subcutaneous injection Methods 0.000 claims description 5
- 239000007929 subcutaneous injection Substances 0.000 claims description 5
- 238000011746 C57BL/6J (JAX™ mouse strain) Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 206010002519 Animal scratch Diseases 0.000 claims description 3
- PIWKPBJCKXDKJR-UHFFFAOYSA-N Isoflurane Chemical compound FC(F)OC(Cl)C(F)(F)F PIWKPBJCKXDKJR-UHFFFAOYSA-N 0.000 claims description 3
- 230000003444 anaesthetic effect Effects 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 229960002725 isoflurane Drugs 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 206010002091 Anaesthesia Diseases 0.000 description 2
- 230000037005 anaesthesia Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000010171 animal model Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000005062 synaptic transmission Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K67/00—Rearing or breeding animals, not otherwise provided for; New or modified breeds of animals
- A01K67/02—Breeding vertebrates
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Animal Husbandry (AREA)
- Health & Medical Sciences (AREA)
- Zoology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of animal based on automated image identification and itches behavior analysis method, includes the following steps: raising early period of (1) animal；(2) building of acute model of itching；(3) with the scratching behavior of video recorder record mouse；(4) video file according to the rate-adaptive pacemaker picture of ten frame per second, and time tag is added for these pictures；(5) manual identified picture is scratched picture corresponding be put in file and non-scratching file；(6) behavior picture identification model is scratched by machine learning program construction animal；(7) Activity recognition of the unknown images based on machine learning model judges whether each particular moment animal behavior performance scratches by program, the behavior so that animal under analyzing specific condition of experiment itches.The present invention is significantly improved animal and itched the efficiency of behavioural analysis, and the relative intensity (duration length) for the scratching caused by behavior that can be itched every time with accurate description, so that behavioural analysis of itching is finer under the premise of ensuring accuracy.
Description
Technical field
The present invention relates to image identification technical fields, and in particular to a kind of animal based on automated image identification itches behavior
Analysis method.
Background technique
Itching is a kind of somatesthesia beastly, can cause the scratching desire of people, seriously affect patients ' life quality.
Currently, the neurotransmission and modulation scheme of feel of itching are unclear.A series of neurobiological studies focus on announcement and participate in feel of itching
The neural circuitry of regulation, in these research process, an essential component part is that experimental animal itches the inspection of behavior
With analysis.For animal itches behavior, scratching is a very special behavioral indicator, can quantitative description animal itch behavior.Mesh
The step of preceding animal itches behavioural analysis, mainly scratches number by artificial recorded video, video playback, artificial counting animal,
Carry out quantitative analysis animal to itch behavior.Main deficiency is to consume a large amount of manpowers and practice, and is difficult to quantitative analysis animal single and grabs
Scratch and (itch) intensity of performance.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of animals based on automated image identification to itch behavioural analysis side
Method realizes that animal itches the automation of behavior, the analysis of high-accuracy by machine learning, image recognition technology.
Itch row in order to solve the above technical problems, the embodiment of the present invention provides a kind of animal based on automated image identification
For analysis method, include the following steps:
(1) raising early period of animal
Adult healthy male C 57 BL/6 J mouse is selected to itch behavioural analysis object for animal, feeding environment are as follows: temperature 22 ± 2
DEG C, humidity is 55RH ± 10%, gives illumination 12 hours daytimes, and the holding of 12 hours nights is dark, and ad lib drinks water；
(2) building of acute model of itching
Before recording, the building of the acute model of itching of decimal is carried out, specific construction method is: mouse is through isoflurane inhalant anesthetic
It after anesthesia, is relied in mouse the nape of the neck subcutaneous injection histamine and causes to itch agent, chmice acute is itched model construction completion；
(3) mouse for causing to itch agent will have been injected in step (2) to be placed in behavior box, with video recorder record mouse at least
Scratching behavior in 45min after video recording, generates a video file, is stored in the SD card of video recorder；
(4) video file that step (3) is obtained according to several png formats of the rate-adaptive pacemaker of ten frame per second picture,
And according to the one-to-one relationship of time in picture name and video, time tag is added for these pictures, as follows:
Out1.png, first second
Out2.png, first second
…
Out10.png, first second
Out11.png, second second
Out12.png, second second
…
Out20.png, second second
And so on；
(5) manual identified picture
Video playback, artificial counting animal scratch number, to each its starting of scratching behavior record and whole story time point, essence
Really to the second；Then, according to the time tag of step (2), if the time tag of a certain picture falls in certain time zone once scratched
In, then it is scratching this picture handmarking；Anyway, then it is labeled as not scratching；
Finally, the animal behavior picture labeled as scratching is put into a unique file folder, as scratching file；It
His picture is put into another unique file folder, as non-scratching file；It is used for subsequent deep learning software training；
(6) behavior picture identification model is scratched by machine learning program construction animal
Using the animal behavior picture in scratching file and non-scratching file as primary data, machine learning mould is inputted
The Python training program (the entitled train_network.py of program) of block carries out deep learning training, establishes animal scratching row
For picture recognition model；
(7) Activity recognition of the unknown images based on machine learning model
Step (1)-(4) are repeated, animal behavior picture to be identified is obtained, in the picture recognition model that step (6) are established
On the basis of, the Python of operation machine learning module compares program, inputs animal behavior picture to be identified, moves according to be identified
The one-to-one time tag of object behavior picture judges whether each particular moment animal behavior performance scratches by program, thus
Animal under analysis specific condition of experiment itches behavior.
Preferably, in step (1), the weight of C57BL/6J mouse is 24 ± 2g.
Preferably, it in step (2), is relied in mouse the nape of the neck subcutaneous injection histamine and causes itch agent C48/80, concentration 2mg/
Ml, 50 μ l of volume.
Preferably, the behavior box in step (3) is blue behavior box, long 16cm, wide 14cm, high 15cm.
Preferably, scratching behavior of the record mouse in 45min in step (3).
Wherein, the format for the video file that step (3) obtains is mp4 format.
Wherein, in step (4), by video file according to the specific side of the picture of the rate-adaptive pacemaker png format of ten frame per second
Method are as follows: realized by ffmpeg tool in the PC platform based on Ubuntu, specific instructions are ffmpeg-i video.mp4-f
Image2-r 10out%d.png, wherein video.mp4 is the animal behavior video for the mp4 format initially recorded, and is finally given birth to
At picture entitled out1.png, out2.png, out3.png ....
Wherein, in step (6), the specifically used method of Python training program are as follows: python train_
network.py--dataset images--model santa_not_santa.model。
Wherein, in step (7), Python compares the specifically used method of program are as follows: python test_
network.py--model santa_not_santa.model--image santa_01.png.Above-mentioned technology of the invention
Scheme has the beneficial effect that: video point from the present invention may be implemented to itch behavior to machine from artificial observation video analysis animal
Analysis animal itches the conversion of behavior, under the premise of ensuring accuracy, can significantly improve animal and itch the efficiency of behavioural analysis, and
Can be itched every time the relative intensity (duration length) of scratching caused by behavior with accurate description, so that behavioural analysis of itching is more smart
Carefully.
Detailed description of the invention
Fig. 1 is work flow diagram of the invention；
Fig. 2 is structural schematic diagram when shooting video in the present invention.
Description of symbols:
1, C57BL/6J mouse；2, behavior box；3, video recorder.
Specific embodiment
To keep the technical problem to be solved in the present invention, technical solution and advantage clearer, below in conjunction with attached drawing and tool
Body embodiment is described in detail.
The present invention provides a kind of animal based on automated image identification and itches behavior analysis method, workflow such as Fig. 1 institute
Show, includes the following steps:
(1) raising early period of animal
Adult healthy male C57BL/J mouse 1 is selected to itch behavioural analysis object for animal, weight is 24 ± 2g, raises ring
Border are as follows: 22 ± 2 DEG C of temperature, humidity is 55RH ± 10%, gives illumination 12 hours daytimes, and the holding of 12 hours nights is dark, freely
It feeds, drink water；
(2) building of acute model of itching
Before recording, the building of the acute model of itching of decimal is carried out, specific construction method is: mouse is through isoflurane inhalant anesthetic
After anesthesia, is relied in mouse the nape of the neck subcutaneous injection histamine and cause itch agent C48/80, concentration 2mg/ml, 50 μ l of volume, mouse is anxious
Property itch model construction completion；
(3) mouse of agent of causing to itch will have been injected in step (2) to be placed in blue behavior box 2, behavior box long 16cm is wide
14cm, high 15cm record scratching behavior of the mouse in 45min with video recorder 3, as shown in Fig. 2, generating one after video recording
The video file of a mp4 format, is stored in the SD card of video recorder；
(4) video file that step (3) is obtained according to several png formats of the rate-adaptive pacemaker of ten frame per second picture,
Such as: the animal behavior video of shooting 1 hour can finally export 36000 pictures.And according to picture name and video
The one-to-one relationship of middle time adds time tag for these pictures, as follows:
Out1.png, first second
Out2.png, first second
…
Out10.png, first second
Out11.png, second second
Out12.png, second second
…
Out20.png, second second
And so on；
Wherein, by video file according to the picture of the rate-adaptive pacemaker png format of ten frame per second method particularly includes: pass through
Ffmpeg tool realizes that specific instructions are ffmpeg-i video.mp4-f image2-r in the PC platform based on Ubuntu
10out%d.png, wherein video.mp4 is the animal behavior video for the mp4 format initially recorded, the picture name ultimately produced
For out1.png, out2.png, out3.png ....
(5) manual identified picture
Video playback, artificial counting animal scratch number, to each its starting of scratching behavior record and whole story time point, essence
Really to the second；Then, according to the time tag of step (2), if the time tag of a certain picture falls in certain time zone once scratched
In, then it is scratching this picture handmarking；Anyway, then it is labeled as not scratching；
Finally, the animal behavior picture labeled as scratching is put into a unique file folder, as scratching file；It
His picture is put into another unique file folder, as non-scratching file；It is used for subsequent deep learning software training；
(6) behavior picture identification model is scratched by machine learning program construction animal
Using the animal behavior picture in scratching file and non-scratching file as primary data, machine learning mould is inputted
The Python training program (the entitled train_network.py of program) of block carries out deep learning training, establishes animal scratching row
For picture recognition model；
Wherein, the specifically used method of Python training program are as follows: python train_network.py--dataset
images--model santa_not_santa.model。
The source code of train_network.py is following (being indicated with underscore):
(7) Activity recognition of the unknown images based on machine learning model
Step (1)-(4) are repeated, animal behavior picture to be identified is obtained, in the picture recognition model that step (6) are established
On the basis of, the Python of operation machine learning module compares program (test_network.py), inputs ethogram to be identified
Piece, according to the one-to-one time tag of animal behavior picture to be identified, each particular moment animal behavior is judged by program
Whether performance scratches, the behavior so that animal under analyzing specific condition of experiment itches；
Wherein, Python compares the specifically used method of program are as follows: python test_network.py--model
santa_not_santa.model--image santa_01.png。
The source code of test_network.py is following (being indicated with underscore):
According to initial video recording total time (by taking 45min as an example), 27000 animal behavior pictures are amounted to, according to above-mentioned figure
As identification model, every picture all is automatically labeled as scratching or not scratching by program, finally counts the number of pictures of total scratching,
Can quantitative description animal in an automated manner behavior of itching.Meanwhile each single is scratched, it can be by counting it
Duration (or scratching number/frequency in the unit time) is itched the intensity of behavior with quantitative mode indirect reaction animal.
Key innovations of the invention are to establish a kind of animal based on automated image identification and itch behavior analysis method,
Realize that image recognition technology based on deep learning introduces Neurobiology field, integration has disclosed at present, freely and opens
The tools such as software, the server in source, video analysis animal from realization itches behavior to machine from artificial observation video analysis animal
Itch the conversion of behavior.This manually arrives the conversion of automation, can significantly improve animal and itch the efficiency of behavioural analysis, save manpower
With the time.
Specifically, the itch difference of the method for behavior of the present invention and current manual analysis animal is two steps: logical
Cross machine learning program construction animal scratching behavior picture identification model and the unknown images identification based on machine learning model.On
Stating two steps is the key that realize that automation (and unartificial) analyzing animal is itched the main of behavior and the method for the invention
Innovative point.According to current test data of experiment, on the basis of handmarking animal scratching behavior early period, as described above
The preferred embodiment of invention, the image generated by Python training program (the entitled train_network.py of program) training
Identification model overall accuracy is more than 95%.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principles of the present invention, it can also make several improvements and retouch, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (9)
- The behavior analysis method 1. a kind of animal based on automated image identification itches, which comprises the steps of:(1) raising early period of animalAdult healthy male C 57 BL/6 J mouse is selected to itch behavioural analysis object for animal, feeding environment are as follows: 22 ± 2 DEG C of temperature, Humidity is 55RH ± 10%, gives illumination 12 hours daytimes, and the holding of 12 hours nights is dark, and ad lib drinks water；(2) building of acute model of itchingBefore recording, carries out chmice acute and itch the building of model, specific construction method is: mouse is anaesthetized through isoflurane inhalant anesthetic Afterwards, mouse the nape of the neck subcutaneous injection histamine rely on cause itch agent (C48/80), chmice acute itch model construction completion；(3) mouse for causing to itch agent will have been injected in step (2) to be placed in behavior box, with video recorder record mouse at least Scratching behavior in 45min after video recording, generates a video file, is stored in the SD card of video recorder；(4) video file that step (3) is obtained and is pressed according to the picture of several png formats of the rate-adaptive pacemaker of ten frame per second The one-to-one relationship of time in photograph and picture name and video adds time tag for these pictures, as follows:Out1.png, first secondOut2.png, first second…Out10.png, first secondOut11.png, second secondOut12.png, second second…Out20.png, second secondAnd so on；(5) manual identified pictureVideo playback, artificial counting animal scratch number, to each its starting of scratching behavior record and whole story time point, are accurate to Second；Then, according to the time tag of step (2), if the time tag of a certain picture is fallen in the time interval that certain is once scratched, It is then scratching this picture handmarking；Anyway, then it is labeled as not scratching；Finally, the animal behavior picture labeled as scratching is put into a unique file folder, as scratching file；Other figures Piece is put into another unique file folder, as non-scratching file；It is used for subsequent deep learning software training；(6) behavior picture identification model is scratched by machine learning program construction animalUsing the animal behavior picture in scratching file and non-scratching file as primary data, machine learning module is inputted Python training program (the entitled train_network.py of program) carries out deep learning training, establishes animal scratching behavior Picture recognition model；(7) Activity recognition of the unknown images based on machine learning modelStep (1)-(4) are repeated, animal behavior picture to be identified is obtained, in the basis for the picture recognition model that step (6) are established On, operation machine learning module Python compare program, input animal behavior picture to be identified, according to animal row to be identified For the one-to-one time tag of picture, judge whether each particular moment animal behavior performance scratches by program, to analyze Animal under specific condition of experiment itches behavior.
- The behavior analysis method 2. animal according to claim 1 based on automated image identification itches, which is characterized in that step Suddenly in (1), the weight of C57BL/J mouse is 24 ± 2g.
- The behavior analysis method 3. animal according to claim 1 based on automated image identification itches, which is characterized in that step Suddenly it in (2), is relied in mouse the nape of the neck subcutaneous injection histamine and causes itch agent C48/80, concentration 2mg/ml, 50 μ l of volume.
- The behavior analysis method 4. animal according to claim 1 based on automated image identification itches, which is characterized in that step Suddenly the behavior box in (3) is blue behavior box, long 16cm, wide 14cm, high 15cm.
- The behavior analysis method 5. animal according to claim 1 based on automated image identification itches, which is characterized in that step Suddenly scratching behavior of the record mouse in 45min in (3).
- 6. according to claim 1, the animal based on automated image identification described in 4 or 5 itches behavior analysis method, feature exists In the format for the video file that step (3) obtains is mp4 format.
- The behavior analysis method 7. animal according to claim 1 based on automated image identification itches, which is characterized in that step Suddenly in (4), by video file according to the picture of the rate-adaptive pacemaker png format of ten frame per second method particularly includes: pass through ffmpeg Tool realizes that specific instructions are ffmpeg-i video.mp4-f image2-r 10out% in the PC platform based on Ubuntu D.png, wherein video.mp4 is the animal behavior video for the mp4 format initially recorded, and the picture ultimately produced is entitled out1.png、out2.png、out3.png…。
- The behavior analysis method 8. animal according to claim 1 based on automated image identification itches, which is characterized in that step Suddenly in (6), the specifically used method of Python training program are as follows: python train_network.py--dataset images--model santa_not_santa.model.The source code of train_network.py is as detailed below.
- The behavior analysis method 9. animal according to claim 1 based on automated image identification itches, which is characterized in that step Suddenly in (7), Python compares the specifically used method of program are as follows: python test_network.py--model santa_ not_santa.model--image santa_01.png.The source code of test_network.py is as detailed below.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910615140.2A CN110334662A (en) | 2019-07-09 | 2019-07-09 | A kind of animal based on automated image identification itches behavior analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910615140.2A CN110334662A (en) | 2019-07-09 | 2019-07-09 | A kind of animal based on automated image identification itches behavior analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110334662A true CN110334662A (en) | 2019-10-15 |
Family
ID=68144875
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910615140.2A Pending CN110334662A (en) | 2019-07-09 | 2019-07-09 | A kind of animal based on automated image identification itches behavior analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110334662A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046805A (en) * | 2019-12-15 | 2020-04-21 | 深圳市具安科技有限公司 | Animal balance analysis method and device and computer equipment |
| CN111144380A (en) * | 2020-01-06 | 2020-05-12 | 南通大学 | Animal misstep behavior analysis method based on automatic image recognition |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390193A (en) * | 2013-07-30 | 2013-11-13 | 浙江大学 | Automatic training device for navigation-oriented rat robot, and rat behavior identification method and training method |
| CN108182423A (en) * | 2018-01-26 | 2018-06-19 | 山东科技大学 | A kind of poultry Activity recognition method based on depth convolutional neural networks |
-
2019
- 2019-07-09 CN CN201910615140.2A patent/CN110334662A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390193A (en) * | 2013-07-30 | 2013-11-13 | 浙江大学 | Automatic training device for navigation-oriented rat robot, and rat behavior identification method and training method |
| CN108182423A (en) * | 2018-01-26 | 2018-06-19 | 山东科技大学 | A kind of poultry Activity recognition method based on depth convolutional neural networks |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046805A (en) * | 2019-12-15 | 2020-04-21 | 深圳市具安科技有限公司 | Animal balance analysis method and device and computer equipment |
| CN111046805B (en) * | 2019-12-15 | 2023-09-26 | 深圳市具安科技有限公司 | Animal balance analysis method, device and computer equipment |
| CN111144380A (en) * | 2020-01-06 | 2020-05-12 | 南通大学 | Animal misstep behavior analysis method based on automatic image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334662A (en) | A kind of animal based on automated image identification itches behavior analysis method | |
| Briefer et al. | Mother goats do not forget their kids’ calls | |
| EP4064229A1 (en) | Artificial intelligence-based difficult airway evaluation method and device | |
| CN107316257A (en) | A kind of Method of Teaching Quality Evaluation analyzed based on classroom students ' behavior and system | |
| Frank et al. | Exploring word learning in a high-density longitudinal corpus | |
| CN110059614A (en) | A kind of intelligent assistant teaching method and system based on face Emotion identification | |
| CN1759804A (en) | Intelligent analyzing and differentiating method of herbalist doctor through integrated references form four parts of diagnosis | |
| CN109934203A (en) | A kind of cost-sensitive increment type face identification method based on comentropy selection | |
| CN106446753A (en) | Negative expression identifying and encouraging system | |
| Zürcher et al. | Are dialects socially learned in marmoset monkeys? Evidence from translocation experiments | |
| CN113177612B (en) | Agricultural pest image identification method based on CNN few samples | |
| CN204500970U (en) | For studying the experimental provision of batch toy anxiety/frightened behavior reaction | |
| CN112926412A (en) | Self-adaptive teaching classroom monitoring method and system | |
| CN111553206B (en) | Cell identification method and device based on machine learning | |
| CN114581948A (en) | Animal face identification method | |
| CN103020198B (en) | One searches for mesh calibration method in video | |
| CN102692498B (en) | Automatic code reading device and automatic code reading method of sulfanilamide type medicine residue detecting reagent strip | |
| CN110600127A (en) | Video acquisition and analysis system and method for realizing cognitive disorder screening function by video excitation of facial expressions | |
| Morita et al. | Animals exhibit consistent individual differences in their movement: A case study on location trajectories of Japanese macaques | |
| Shin et al. | Using automated live cell imaging to reveal early changes during human motor neuron degeneration | |
| CN113505678B (en) | Monkey face recognition method based on deep separable convolution | |
| Zanoli et al. | Inter-sexual multimodal communication during mating in wild geladas: the leading role of females | |
| CN116502799A (en) | Intelligent monitoring system for animal dynamic carbon emission | |
| Wang et al. | Dog Face Dataset and Detection Benchmarking | |
| WO2023221951A2 (en) | Cell differentiation based on machine learning using dynamic cell images |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191015 |