CN110349673A - A kind of group's physique assessment method based on Gaussian Mixture distribution - Google Patents
A kind of group's physique assessment method based on Gaussian Mixture distribution Download PDFInfo
- Publication number
- CN110349673A CN110349673A CN201910570304.4A CN201910570304A CN110349673A CN 110349673 A CN110349673 A CN 110349673A CN 201910570304 A CN201910570304 A CN 201910570304A CN 110349673 A CN110349673 A CN 110349673A
- Authority
- CN
- China
- Prior art keywords
- group
- model
- data
- distribution
- gaussian mixture
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pathology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a kind of group's physique assessment methods based on Gaussian Mixture distribution, and described method includes following steps: step 1: unlabelled PE testing data are randomly divided into several segments as test data and training data;Step 2: to each section of test data and training data progress pretreatment operation in step 1;Step 3: extracting each group characteristic using unsupervised-learning algorithm;Step 4: each group characteristic that fit procedure 3 obtains judges the number of mixed distribution;Step 5: weight, the mean value of each mixed distribution are calculated using EM algorithm;Step 6: establishing three-level evaluation model, the observation of step 4 and step 5 and calculated result are substituted into three-level evaluation model and group's physique assessment quantitative formula, obtain grade and appraisal result.Present invention is fully independent of individual evaluation of physical fitness and health result it is not necessary to by individual evaluation as a result, obtaining group's physique assessment result.
Description
Technical field
The invention belongs to physique assessment fields, are related to a kind of physical health appraisal procedure, and in particular to one kind is based on Gauss
Group's physique assessment method of mixed distribution.
Background technique
Constitution refers to the quality of human body, be heredity and it is acquired on the basis of show human figure structure,
Physiological function, the synthesis of psychological factor and metastable feature.Physical health assessment is all health research field all the time
Hot topic.Physique assessment can use index and method the evaluation national physique and health status of science, so constantly improve and
Enhance national physique.So far, about physique monitoring, the research of assessment system, the scholar of many country does a large amount of products
Extremely beneficial exploration and practice is also achieved good results.These existing research achievements are obtained by investigation early period mostly
Expertise is obtained to obtain various evaluation indexes and its weight coefficient, then utilizes ready-made statistical formula or curve matching skill
Art assesses individual constitution.And in nearest vicennial open source literature, assessment group's physical health situation is then to a
The simple statistics of body assessment result.
Machine learning is a branch of artificial intelligence, almost becomes the synonym of artificial intelligence in many cases.Machine
The device learning system object in image for identification, by phonetic transcription at text, by news item, model or product and user
Interest is matched, and selects the correlated results of search.It is also a kind of important medical supplementary means, in medical health field
With important application value.Although assessment models are widely used in other field, under complex data environment
Group's physical health evaluation problem be still one be worth and the problem of do not furtherd investigate.
Summary of the invention
In order to solve the problems, such as existing group's physique assessment, the present invention provides a kind of group's constitutions based on Gaussian Mixture distribution
Appraisal procedure.The core concept of this method is learned automatically from original sport test data unsupervisedly using convolutional neural networks
Feature is practised, and group's constitution three-tiered evaluation model is proposed based on Gaussian Mixture distribution, the feature acquired feeding assessment models are obtained
Group's physique assessment result out.
The purpose of the present invention is what is be achieved through the following technical solutions:
A kind of group's physique assessment method based on Gaussian Mixture distribution, includes the following steps:
Step 1: unlabelled PE testing data are randomly divided into several segments as test data and training data;
Step 2: to each section of test data and training data progress pretreatment operation in step 1;
Step 3: using the pretreated training data of step 2 as each input of convolutional neural networks model, use is non-
Supervised learning algorithm extracts each group characteristic;
Step 4: each group characteristic that fit procedure 3 obtains judges the number of mixed distribution;
Step 5: each group characteristic obtained according to step 3, using EM algorithm calculate each mixed distribution weight,
Value;
Step 6: establishing three-level evaluation model, the observation of step 4 and step 5 and calculated result are substituted into three-level evaluation model
In group's physique assessment quantitative formula, grade and appraisal result are obtained.
Compared with the prior art, the present invention has the advantage that
1, present invention is fully independent of individual evaluation of physical fitness and health result it is not necessary to by individual evaluation as a result, obtaining group
Body physique assessment result.
2, the present invention has fully considered group's constitution distribution characteristics, can be used for each department, people's constitution of all categories assessing,
Has the characteristics that of overall importance, popularity.
Detailed description of the invention
Fig. 1 is that the present invention is based on the training flow charts of group's physique assessment method of Gaussian Mixture distribution;
Fig. 2 is feature extraction convolutional neural networks figure in the present invention;
Fig. 3 is that the present invention is based on group's physique assessment method testing data characteristics distribution maps of Gaussian Mixture distribution;
Fig. 4 is two groups of Gaussian Mixtures distribution broken away view in the present invention under test data.
Specific embodiment
Further description of the technical solution of the present invention with reference to the accompanying drawing, and however, it is not limited to this, all to this
Inventive technique scheme is modified or replaced equivalently, and without departing from the spirit and scope of the technical solution of the present invention, should all be covered
Within the protection scope of the present invention.
The present invention has important influence to group's evaluation of physical fitness and health in view of group's constitutive character distribution situation, proposes one
Group's physique assessment method that kind is distributed based on Gaussian Mixture.This method is proposed using the method for machine learning mainly by feature
The assessment models of the assessment of study and feature physical health dimerous, it is intended to independently of individual assessment result, by dividing
Group's physique test data are analysed, group's physical health status assessment model are established, to grasp Population Health state.Such as Fig. 1 institute
Show, the evaluation of physical fitness and health method specifically includes the following steps:
Step 1: unlabelled PE testing data are divided into several segments as training data.
Unlabelled PE testing data are divided into several segments as training data, training data will be used as convolutional Neural net
The input of network, is input in model.According to different test items, 7 dimensions are splitted data into, are extracted out at random in each dimension
1800 data item are as test data, and remaining data are as training data.In these training datas, randomly select every time
1800 data item are as a training input.
Step 2: carrying out pretreatment operation for each segment data.
Before feature extraction, it would be desirable to carry out standardization processing to data.In feature extraction, standardization is very heavy
It wants.This is because different samples may have multiple features, and the value scale of different characteristic is different.If at specification
Reason, the huge difference of dimension may result in entire model failure.
In this step, we use the data of 7 dimensions, and for the distribution characteristics for maintaining initial data, we are used
0-1 normalization method:
Wherein, it includes training data and test data, X that X, which is input data item,maxFor the maximal term of this group of data, XminFor
The minterm of this group of data.In the present invention, max takes 1, min to take 0.Data normalization formula can be written as:
Finally by all data standards between 0-1.
Step 3: extracting characteristic information using unsupervised-learning algorithm.
In this step, the model being made of two layers of convolutional neural networks is used, a large amount of original signal has been converted
For reduction collection feature.As shown in Fig. 2, convolutional neural networks include two convolutional layers, two active coatings, two pond layers.Convolution
In layer, convolution kernel is dimensioned to 3 × 1, and step-length is designed as 1;Active coating uses ReLu activation primitive;The setting of pond layer filter
It is 2 × 1, uses maximum pond function.Using the data of step 2 as each input of model, by convolutional layer, active coating, pond
After changing layer, the Feature Mapping of constitution data is obtained.In conjunction with the thought from coding, by analysis input data and input is reconstructed
Between reconstructed error, feedback regulation network parameter may finally obtain preferable learning characteristic.Step 3 needs to carry out 5000 times
Iteration can be taken off corresponding characteristic series when error goes to zero.
Step 4: fit characteristic data judge the number of Gaussian Mixture distribution.
In this step, need to observe the mixed distribution situation of characteristic.It is fitted using fitting function in Python
The characteristic that step 3 obtains out observes data distribution, records the distribution number of this mixed distribution.
Step 5: weight, the mean value of each mixed distribution are calculated using EM algorithm.
In this step, each group characteristic obtained using step 3 calculate the weight of each mixed distribution in corresponding group,
Value.EM algorithmic procedure is as shown in table 1:
Table 1
Step 6: establishing three-level evaluation model, the calculated result of step 5 is substituted into group's physique assessment quantitative formula, is obtained
Grade and appraisal result.
Step 6.1:
The three-level evaluation model that this step is established is as shown in table 2:
Table 2
Wherein, K is the number of sub-model, αmaxFor maximum weight in K sub-model, μnWith μmIt is two respectively maximum
Mean value corresponding to weight sub-model.A (0 < a < 1) is the threshold value for describing weight difference, and b (0 < b < 1) is for describing
The distance threshold of maximum two distributions of weight.Weight difference threshold value a=0.3, distance threshold b=0.3 are set in this step.It will step
Rapid 4 with distribution number, the weight, mean value substitution table 2 observing and calculate in step 5, can obtain evaluation of physical fitness and health grade.
When feature shows as a single Gauss model or more Gauss models and meets inequality αmax-(1-αmax) > α when, comment
It is set to A grade;
When feature shows as more Gauss models and meets inequality groupWhen, it is assessed as B grade;
When feature shows as more Gauss models and meets inequality groupWhen, it is assessed as C grade.
Step 6.2: calculating assessment result.
According to distribution number, weight, mean value, can be calculated in conjunction with the group's physique assessment quantitative formula designed in the present invention
The evaluation of physical fitness and health result of affiliated group.Group's physique assessment quantitative formula is as follows:
In formula, h=max (0, x), remaining parameters is identical as step 6.1.
In an experiment, we utilize this method of whole school (schoolgirl) PE testing attainment test disclosed in certain University Websites.
And " national student physical health standard " according to the newest revision of Chinese Ministry of Education, we choose BIM, lung capacity, standing long jump,
Sitting body anteflexion, 50 meters of races, 800 meters of races, one-minute sit-ups obtain various features probability distribution as seven test items
Figure, as shown in Figure 3.
From this probability distribution graph it is found that the basic Gaussian distributed of feature.But the probability distribution of some features is not clothes
From single Gaussian Profile, but Gaussian mixtures are obeyed, according to the three-level evaluation model established in step 6.1, utilizes group's body
Matter project evaluation chain formula is obtained a result, as shown in table 3.
Table 3
Finally the Gaussian Mixture distribution map of BIM and lung capacity can be split as single Gaussian Profile figure, as shown in Figure 4.
Claims (8)
1. a kind of group's physique assessment method based on Gaussian Mixture distribution, it is characterised in that described method includes following steps:
Step 1: unlabelled PE testing data are randomly divided into several segments as test data and training data;
Step 2: to each section of test data and training data progress pretreatment operation in step 1;
Step 3: using the pretreated training data of step 2 as each input of convolutional neural networks model, use is non-supervisory
Learning algorithm extracts each group characteristic;
Step 4: each group characteristic that fit procedure 3 obtains judges the number of mixed distribution;
Step 5: each group characteristic obtained according to step 3 calculates weight, the mean value of each mixed distribution using EM algorithm;
Step 6: establishing three-level evaluation model, the observation of step 4 and step 5 and calculated result are substituted into three-level evaluation model and group
In body physique assessment quantitative formula, grade and appraisal result are obtained.
2. group's physique assessment method according to claim 1 based on Gaussian Mixture distribution, it is characterised in that the step
In rapid 1, every group of data of test data and training data include 1800 data item.
3. group's physique assessment method according to claim 1 based on Gaussian Mixture distribution, it is characterised in that the step
In rapid 2, pretreatment operation is carried out to each section of test data and training data using 0-1 normalization method, in which: data normalization
Formula are as follows:
In formula, X is input data item, XmaxFor the maximal term of this group of data, XminFor the minterm of this group of data.
4. group's physique assessment method according to claim 1 based on Gaussian Mixture distribution, it is characterised in that the step
In rapid 3, convolutional neural networks include two convolutional layers, two active coatings, two pond layers, in which: in convolutional layer, convolution kernel is big
Small to be set as 3 × 1, step-length is designed as 1;Active coating uses ReLu activation primitive;Pond layer filter is set as 2 × 1, using most
Great Chiization function.
5. group's physique assessment method according to claim 1 based on Gaussian Mixture distribution, it is characterised in that the step
In rapid 4, each group characteristic that step 3 obtains is fitted using Python fitting function, data distribution is observed, records this
The distribution number of mixed distribution.
6. group's physique assessment method according to claim 1 based on Gaussian Mixture distribution, it is characterised in that the step
In rapid 5, the E of EM algorithm is walked are as follows:
According to "current" model parameter, sub-model k is calculated to observation data yiResponsiveness, formula is as follows:
Wherein, αkIt is coefficient, αk>=0,φ(yi|θk) it is Gaussian distribution density,μkIt is k-th
The inequality of sub-model,It is the variance of k-th of sub-model;
The M of EM algorithm is walked are as follows:
The model parameter of new round iteration is calculated, formula is as follows:
Wherein,It is the mean value in new round iterative model;It is the variance in new round iterative model;It is new round iteration
Weight in model;It is model k to observation data yiResponsiveness, N be observe data sum.
7. group's physique assessment method according to claim 1 based on Gaussian Mixture distribution, it is characterised in that the step
In rapid 6, three-level evaluation model includes A grade, B grade and C grade, in which:
A grade meets one of the following conditions:
1. feature shows as a single Gauss model, K=1;
2. feature shows as mixed Gauss model, and K >=2, and meet:
αmax-(1-αmax) > a;
B levels characteristic shows as more Gauss models, and K >=2, and meet inequality group:
C levels characteristic shows as more Gauss models, and K >=2, and meet inequality group:
In formula, K is the number of sub-model, αmaxFor maximum weight in K sub-model, μnWith μmRespectively maximum two weights
Mean value corresponding to sub-model, a are used to describe the threshold value of weight difference, b be used to describe weight maximum two be distributed apart from threshold
Value.
8. group's physique assessment method according to claim 1 based on Gaussian Mixture distribution, it is characterised in that the step
In rapid 6, group's physique assessment quantitative formula is defined as:
In formula, K is the number of sub-model, αmaxFor maximum weight in K sub-model, μnWith μmRespectively maximum two weights
Mean value corresponding to sub-model, a are used to describe the threshold value of weight difference, b be used to describe weight maximum two be distributed apart from threshold
Value, function h=max (0, x).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910570304.4A CN110349673B (en) | 2019-06-27 | 2019-06-27 | Group constitution evaluation method based on Gaussian mixture distribution |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910570304.4A CN110349673B (en) | 2019-06-27 | 2019-06-27 | Group constitution evaluation method based on Gaussian mixture distribution |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110349673A true CN110349673A (en) | 2019-10-18 |
CN110349673B CN110349673B (en) | 2022-08-05 |
Family
ID=68177158
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910570304.4A Active CN110349673B (en) | 2019-06-27 | 2019-06-27 | Group constitution evaluation method based on Gaussian mixture distribution |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110349673B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117114436A (en) * | 2023-07-27 | 2023-11-24 | 中冶建筑研究总院有限公司 | Existing prestressed concrete member performance evaluation method based on measured data |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103745122A (en) * | 2014-01-23 | 2014-04-23 | 山东农业大学 | Computer processing method for student exercise prescriptions |
CN104391987A (en) * | 2014-12-13 | 2015-03-04 | 吉林大学 | Large-scale target identification method based on mobile platform |
CN104504296A (en) * | 2015-01-16 | 2015-04-08 | 湖南科技大学 | Gaussian mixture hidden Markov model and regression analysis remaining life prediction method |
CN105338343A (en) * | 2015-10-20 | 2016-02-17 | 北京理工大学 | No-reference stereo image quality evaluation method based on binocular perception |
CN105956392A (en) * | 2016-04-28 | 2016-09-21 | 南京师范大学 | Student physical health evaluation management system and method |
CN107832716A (en) * | 2017-11-15 | 2018-03-23 | 中国科学技术大学 | Method for detecting abnormality based on active-passive Gauss on-line study |
CN108038300A (en) * | 2017-12-07 | 2018-05-15 | 长春理工大学 | Optical fiber state evaluating method based on improved membership function combination neutral net |
CN108172297A (en) * | 2018-01-29 | 2018-06-15 | 广东工业大学 | A kind of appraisal procedure of upper-limbs rehabilitation training robot rehabilitation training function |
CN108563806A (en) * | 2018-01-05 | 2018-09-21 | 哈尔滨工业大学(威海) | Engine air passage parameter long-range forecast method based on similitude and system |
CN109101738A (en) * | 2018-08-24 | 2018-12-28 | 河北工业大学 | A kind of IGBT module degree of aging appraisal procedure |
CN109583500A (en) * | 2018-11-30 | 2019-04-05 | 中共中央办公厅电子科技学院 | A kind of aesthetic images quality prediction system and method based on depth drift-diffusion method |
CN109710763A (en) * | 2018-12-27 | 2019-05-03 | 郑州云海信息技术有限公司 | A kind of classification method of text data, device and system |
CN109859110A (en) * | 2018-11-19 | 2019-06-07 | 华南理工大学 | The panchromatic sharpening method of high spectrum image of control convolutional neural networks is tieed up based on spectrum |
-
2019
- 2019-06-27 CN CN201910570304.4A patent/CN110349673B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103745122A (en) * | 2014-01-23 | 2014-04-23 | 山东农业大学 | Computer processing method for student exercise prescriptions |
CN104391987A (en) * | 2014-12-13 | 2015-03-04 | 吉林大学 | Large-scale target identification method based on mobile platform |
CN104504296A (en) * | 2015-01-16 | 2015-04-08 | 湖南科技大学 | Gaussian mixture hidden Markov model and regression analysis remaining life prediction method |
CN105338343A (en) * | 2015-10-20 | 2016-02-17 | 北京理工大学 | No-reference stereo image quality evaluation method based on binocular perception |
CN105956392A (en) * | 2016-04-28 | 2016-09-21 | 南京师范大学 | Student physical health evaluation management system and method |
CN107832716A (en) * | 2017-11-15 | 2018-03-23 | 中国科学技术大学 | Method for detecting abnormality based on active-passive Gauss on-line study |
CN108038300A (en) * | 2017-12-07 | 2018-05-15 | 长春理工大学 | Optical fiber state evaluating method based on improved membership function combination neutral net |
CN108563806A (en) * | 2018-01-05 | 2018-09-21 | 哈尔滨工业大学(威海) | Engine air passage parameter long-range forecast method based on similitude and system |
CN108172297A (en) * | 2018-01-29 | 2018-06-15 | 广东工业大学 | A kind of appraisal procedure of upper-limbs rehabilitation training robot rehabilitation training function |
CN109101738A (en) * | 2018-08-24 | 2018-12-28 | 河北工业大学 | A kind of IGBT module degree of aging appraisal procedure |
CN109859110A (en) * | 2018-11-19 | 2019-06-07 | 华南理工大学 | The panchromatic sharpening method of high spectrum image of control convolutional neural networks is tieed up based on spectrum |
CN109583500A (en) * | 2018-11-30 | 2019-04-05 | 中共中央办公厅电子科技学院 | A kind of aesthetic images quality prediction system and method based on depth drift-diffusion method |
CN109710763A (en) * | 2018-12-27 | 2019-05-03 | 郑州云海信息技术有限公司 | A kind of classification method of text data, device and system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117114436A (en) * | 2023-07-27 | 2023-11-24 | 中冶建筑研究总院有限公司 | Existing prestressed concrete member performance evaluation method based on measured data |
Also Published As
Publication number | Publication date |
---|---|
CN110349673B (en) | 2022-08-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109857835B (en) | Self-adaptive network security knowledge evaluation method based on cognitive diagnosis theory | |
CN110516085B (en) | Image text mutual retrieval method based on bidirectional attention | |
CN106295186B (en) | A kind of system of the aided disease diagnosis based on intelligent inference | |
Steele | Module 5: Introduction to multilevel modelling concepts | |
Chronis et al. | When is a bishop not like a rook? When it’s like a rabbi! Multi-prototype BERT embeddings for estimating semantic relationships | |
CN110033022A (en) | Processing method, device and the storage medium of text | |
CN107480474A (en) | Grader modeling evaluation method of calibration and system based on gut flora abundance | |
CN111640483B (en) | Fitness scheme recommendation method based on AKC model | |
Mulder et al. | Bayes factor testing of multiple intraclass correlations | |
CN107463766A (en) | Generation method, device and the computer-readable recording medium of blood glucose prediction model | |
CN107180283A (en) | A kind of behavior prediction system and method for being in hospital again combined based on optimal characteristics | |
CN109740734A (en) | A kind of method of neuron spatial arrangement in optimization convolutional neural networks | |
CN109871124A (en) | Emotion virtual reality scenario appraisal procedure based on deep learning | |
CN109086837A (en) | User property classification method, storage medium, device and electronic equipment based on convolutional neural networks | |
Wampold et al. | Research themes in counseling psychology: A cluster analysis of citations in the process and outcomes section of the Journal of Counseling Psychology.. | |
CN110349673A (en) | A kind of group's physique assessment method based on Gaussian Mixture distribution | |
CN109919102A (en) | A kind of self-closing disease based on Expression Recognition embraces body and tests evaluation method and system | |
Richards et al. | Optimisation of competition indices using simulated annealing and artificial neural networks | |
Abaci et al. | A comparation of self confidence levels and personal growth initiative skills between managers and employees | |
Costa et al. | Automatic classification of computational thinking skills in elementary school math questions | |
Su et al. | Assessment of bipolar disorder using heterogeneous data of smartphone-based digital phenotyping | |
Sawant et al. | Spectrogram cross‐correlation can be used to measure the complexity of bird vocalizations | |
CN110321951A (en) | A kind of VR simulated flight device evaluation of training method | |
Dry et al. | Similar but not the same: A comparison of the utility of directly rated and feature-based similarity measures for generating spatial models of conceptual data | |
DeRuiter et al. | Learning disability classification by Bayesian aggregation of test results |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |