CN103838963A - Bra pressure comfort evaluation method - Google Patents
Bra pressure comfort evaluation method Download PDFInfo
- Publication number
- CN103838963A CN103838963A CN201410060526.9A CN201410060526A CN103838963A CN 103838963 A CN103838963 A CN 103838963A CN 201410060526 A CN201410060526 A CN 201410060526A CN 103838963 A CN103838963 A CN 103838963A
- Authority
- CN
- China
- Prior art keywords
- pressure
- brassiere
- pressure distribution
- bra
- comfort
- 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
Images
Landscapes
- Corsets Or Brassieres (AREA)
Abstract
The invention belongs to a bra comfort evaluation technology and particularly relates to a bra pressure comfort evaluation method based on a body pressure distribution index and visual simulation scale coupling model. First, a bra pressure part is decomposed, a bra pressure testing part is divided into five parts, namely a shoulder belt, a cup, a steel ring, a shrinking table and a back belt, then by body pressure distribution testing, body pressure distribution index data of the five parts are obtained, the pressure comfort of the five parts is obtained through a visual simulation scale, and finally the coupling model between a body pressure distribution index and subjective assessment is established through a GA-Elman neural network. Quantifiable data support is provided for bra comfort designing, excessive dependence on subjective experience of a designer is effectively lowered, and waste of manpower, material resources and financial resources caused by blind experiments is avoided. In addition, the increasingly-rising requirement for customization comfort bra production can be met, and the comfort of a bra is improved.
Description
Technical field
The present invention relates to a kind of brassiere pressure comfort evaluation method based on pressure distribution index and visual simulation scale coupling model, belong to brassiere Comfort Evaluation technical field.
Background technology
According to the survey, 78% women does not understand the brassiere that How to choose is suitable to root, and 34% women is owing to selecting wrong brassiere or dressing the improper breast deformation that causes, even depauperation.Brassiere comfortableness becomes one of principal character of female consumer demand day by day, is close to human body due to it while dress, therefore its comfortableness is required to seem particularly important.Pressure comfort is the major influence factors of brassiere comfortableness, although for example brassiere earthen platform can promote the aesthetics of chest, can oppress stomach, the brassiere that pressure comfort is low can cause female mammary gland disease, therefore study brassiere pressure comfort and be related to women's health, there is realistic meaning.
Known brassiere pressure comfort evaluation method mainly contains two kinds, and one is subjective evaluation method, and another kind is method for objectively evaluating.Simple subjective assessment, lacks quantizating index, can only provide qualitatively and analyze, and individual difference will affect the accuracy of evaluation result; Simple objective evaluation can provide a series of index and data, but these indexs and data can not reflect people's subjective feeling.Current brassiere pressure comfort research lacks the coupling model of effective subjective evaluation index relevance, thereby is difficult to provide for brassiere design the Data support of pressure comfort aspect.
Summary of the invention
The technical problem to be solved in the present invention is the Data support that pressure comfort aspect is provided for brassiere design.
In order to solve the problems of the technologies described above, technical scheme of the present invention has been to provide a kind of brassiere pressure comfort evaluation method, and brassiere used is the known brassiere style with earthen platform, it is characterized in that, step is:
The first step, utilize pressure distribution image system to gather the pressure distribution data at shoulder belt position, cup position, steel ring position, Ji Houbi position, position, earthen platform, utilize these pressure distribution data calculate the maximum pressure at shoulder belt position and steel ring position and evaluate pressure as pressure distribution achievement data, contact area, maximum pressure, evaluation pressure, maximum pressure gradient and the average pressure gradient at cup position are as pressure distribution achievement data, and the contact area at Ji Houbi position, position, earthen platform, maximum pressure and evaluation pressure are as pressure distribution achievement data;
Second step, utilize visual simulation scale, dressed after brassiere by subject, provide the comfortableness subjective assessment data at shoulder belt position, cup position, steel ring position, Ji Houbi position, position, earthen platform;
Coupling model between pressure distribution achievement data and the corresponding comfortableness subjective assessment data at the 3rd step, employing GA-Elman neural network shoulder belt position, cup position, steel ring position, Ji Houbi position, position, earthen platform, GA-Elman neural network is the initial network weights that adopt genetic algorithm optimization Elman neural network structure.
Preferably, described visual simulation scale adopts the smooth straight line of certain length, described shoulder belt position, cup position, steel ring position, the respectively corresponding smooth straight line in Ji Houbi position, position, earthen platform, every respectively corresponding two kinds of extremities in smooth straight line two ends, subject is according to the impression of dressing after brassiere, at shoulder belt position, cup position, steel ring position, on the corresponding smooth straight line in Ji Houbi position, position, earthen platform, draw a vertical line, position according to vertical line on smooth straight line obtains corresponding shoulder belt position, cup position, steel ring position, the comfortableness subjective assessment data at Ji Houbi position, position, earthen platform.
Preferably, the step of the initial network weights of described employing genetic algorithm optimization Elman neural network structure is:
Step 3.1, setting parameter: comprise individual coded strings length L, group size M, stop genetic algebra G, crossover operator P
cwith mutation operator P
m;
Step 3.2, individual binary coding, generate initial population;
Step 3.3, calculate ideal adaptation degree value by fitness function;
If step 3.4 optimum individual fitness value reaches anticipation error, stop heredity, go to step 3.7, otherwise, go to step 3.5;
Step 3.5, the genetic manipulation that passes through selection, intersects and make a variation, produce population of future generation;
Step 3.6, G reach anticipation error for the fitness value of interior optimum individual, and algorithm stops, otherwise goes to step 3.3;
Step 3.7, give Elman neural network W optimum individual
1, W
2with W
3network initial weight, wherein, W
1for accepting layer and the weights that are connected of hidden layer, W
2for input layer is to the connection weights of hidden layer, W
3for hidden layer is to the connection weights of output layer.
Preferably, carrying out before described the 3rd step, first every pressure distribution achievement data and comfortableness subjective assessment data are carried out to min-max standardization calculating, will after the data linear transformation of different dimensions and varying number level size, be mapped in interval [0,1].
The technical characterstic of the inventive method is:
1, the inventive method is based on pressure distribution index and visual simulation scale coupling model, by the coupling model between the subjective assessment of GA-Elman neural network and pressure distribution index, can pass through the comfortableness of the pressure distribution index prediction human body corresponding position at the multiple positions of brassiere, thereby carry out the evaluation of digitized brassiere pressure comfort.
2, the inventive method is different from the method that in the past merely uses subjectivity or objective evaluation brassiere comfortableness, is different from subjective experience in the past and the way of repetition test, for the design of brassiere comfortableness provides quantifiable Data support.
Therefore, the present invention has following beneficial effect:
Utilize this to evaluate flow process and method, can carry out the evaluation of digitized brassiere pressure comfort based on pressure distribution index and visual simulation scale coupling model, for the brassiere comfortableness design of brassiere enterprise provides Data support, effectively reduce the undue dependence to designer's subjective experience, saved the human and material resources that blindly experiment causes and the waste of financial resources.In addition, can meet the demand of the customized comfortable brassiere production growing to even greater heights, improve the comfortableness of brassiere.
Accompanying drawing explanation
Fig. 1 is that brassiere pressure comfort is evaluated process flow diagram;
Fig. 2 is brassiere pressure position exploded view;
Fig. 3 is brassiere pressure comfort visual simulation scale;
Fig. 4 is algorithm flow chart;
Fig. 5 is the coupling model structure based on Elman neural network.
Embodiment
For the present invention is become apparent, hereby with preferred embodiment, and coordinate accompanying drawing to be described in detail below.
The invention provides a kind of brassiere pressure comfort evaluation method based on pressure distribution index and visual simulation scale coupling model, this evaluation method brassiere used is the known brassiere style with earthen platform, the pressure of such brassiere mainly concentrates on 5 positions as shown in Figure 2, shoulder belt position 1, cup position 2, steel ring position 3, position, earthen platform 4 and rear than position 5, in subjective and objective experiment, the main comfortableness data that gather these 5 pressure positions are as experiment input, in conjunction with Fig. 1, the steps include:
The first step, utilization gather shoulder belt position 1, cup position 2, steel ring position 3, position, earthen platform 4 and rear than the pressure distribution data at position 5 by the pressure distribution image system of XSENSOR company.Xsensor system is set up and is formed a flexible capacitance type pressure pad by capacitive sensor, can be folding arbitrarily according to chest structure, can between any two real surface of contact, realtime graphicization show pressure distribution, there is higher accuracy, thin thickness, dirigibility, and reliability.Pressure range is 10-200mmHg, and data transmission rate reaches 500Hz/s.The function of the test of XSensor pressure distribution and analytic system is that the pressure distribution of any surface of contact is carried out to Static and dynamic measurement, show in real time profile and the various data of pressure distribution with directly perceived, vivid two dimension, three-dimensional color image, and whole measuring process is carried out to " video recording ", storage, user can check, analyze survey record at any time.In use pressure pad is trapped among to chest and back, at its outside brassiere of dressing, can records the pressure distribution situation of brassiere and chest surface of contact.
In objective experiment by Xsensor system obtain each tested on brassiere curved surface accurate pressure distribution figure, and derive test data.The step of pressure distribution test experiments is generally:
(1) all tested all agree to voluntary participation experiment identification experiment agreements before experiment;
(2) the Preparatory work of experiment stage, pressure distribution mat is trapped among to tested chest;
(3) require tested normal stand, brassiere is worn on outside pressure distribution mat, guarantee that pressure pad does not produce fold, keep the fitness of pressure pad, brassiere and chest;
(4) open pressure distribution testing software, gather experimental data.After the image of Xsensor pressure distribution tends towards stability, in software, stop pressure distribution data acquisition.
According to the computing formula of pressure distribution index, calculate respectively 5 indexs: contact area, maximum pressure, average pressure, maximum pressure gradient and average pressure gradient.
(1) contact area is defined as:
S=△S.N
In formula, △ S is the area of single-point pressure transducer effect, and N is measuring point number.
(2) maximum pressure is the maximal value in whole test points, that is:
P
m=max(P
1，P
2，……，P
N)
In formula, P
1to P
nrepresent the pressure that sensor records, N is measuring point number.
(3) average pressure is the arithmetic mean of whole pressure spot pressure, that is:
In formula, N
pfor pressurized is counted, N is measuring point number, obviously has N
p≤ N.
(4) pressure gradient is the rate of change of pressure along a direction, maximum pressure gradient G
mhave:
G
m=max(gradG
1，gradG
2，...，gradG
N)
In formula, N is measuring point number, gradG
1to gradG
nit is the pressure gradient of the 1st measuring point to a N measuring point.
(5) average pressure gradient is the arithmetic mean of each pressure spot pressure gradient, that is:
In formula, N
pfor pressurized is counted, obviously there is N
p≤ N.
Cup position adopts S, P
m, P
v, G
mand G
vas pressure distribution achievement data; Shoulder belt and steel ring position surface of contact are less, adopt P
mand P
vas pressure distribution achievement data; The body shape changes at He Houbi position, earthen platform is less, and the pressure gradient of formation is less, adopts S, P
mand P
vas pressure distribution achievement data.
Second step, subjective assessment, its step is generally:
(1) after pressure distribution data acquisition system finishes, brassiere pressure comfort visual simulation scale is provided to subject, brassiere pressure comfort visual simulation scale as shown in Figure 3, mainly be made up of the smooth straight line of test and appraisal shoulder belt, cup, steel ring, earthen platform and five pressure position comfortablenesses of rear ratio, it is uncomfortable and comfortable that left and right two-stage is respectively.
People's subjective feeling has continuity, and brassiere pressure comfort visual simulation scale does not have the smooth straight line of anchor point to form by one, and left and right two-stage has respectively the scope of two numeric representation degree.When application, under subject is standardized on the relevant position of straight line according to the impression of oneself, researcher by measuring the position of drawing, obtains mark again.
(2) please subject according to the current actual pressure situation of wearing brassiere, shoulder belt position 1, cup position 2, steel ring position 3, position, earthen platform 4 and rear comfortableness than 5 five positions, position are evaluated.Tested essential information of filling on scale then, according to the impression of oneself, draws a vertical line respectively on 5 visual simulation yardsticks, represents the degree of this position comfortableness.
Brassiere pressure comfort visual simulation scale adopts the smooth straight line of 10cm length conventionally, and straight line two-stage represents respectively two kinds of extremities, on straight line without any scale or word.The impression of tested basis oneself draws a vertical line on straight line, can obtain one than the more numerical value of accurate quantification test and appraisal of interval scale after scribing position is measured.
Etc. (3) tested determine filled in after, regain scale, take off tested brassiere and pressure pad with it.
The 3rd step, employing GA-Elman neural network shoulder belt position 1, cup position 2, steel ring position 3, position, earthen platform 4 and rear than the coupling model between the pressure distribution achievement data at position 5 and corresponding comfortableness subjective assessment data, GA-Elman neural network is the initial network weights that adopt genetic algorithm optimization Elman neural network structure.
Elman neural network is a kind of typical local regression network, and it has increased by one and has accepted layer in the hidden layer of feed forward type network, gives its dynamic memory function, makes it possess the ability that adapts to time-varying characteristics, has the advantages such as discrimination is high, robustness is good.Genetic algorithm (genetic algorithm, GA) is that simulation biological evolution process and mechanism develop and the method for the randomization search optimum solution come.On the one hand, consider dynamic perfromance and the individual difference of chest pressure distribution; On the other hand, there is local minimum problem in Elman neural network, and the selection of initial value affects convergence of algorithm speed.Therefore, the present invention adopts GA to optimize the initial weight of Elman neural network structure, set up the coupling model of pressing distribution index and subjective comfortableness based on GA-Elman neural network network, as shown in Figure 4, to characterize the nonlinear relationship of brassiere pressure distribution and comfortableness, realize evaluation and the forecast function of comfortableness.
(1) data normalization processing
In order to accelerate neural network model convergence, every pressure distribution index and subjective comfortableness data are carried out to min-max standardization calculating, will after the data linear transformation of different dimensions and varying number level size, be mapped in interval [0,1], computing formula is:
In formula, X is certain sample data, X
minwith X
maxbe respectively minimum value and maximal value in whole sample datas, X
ffor the numerical value after min-max standardization.
(2) Elman neural network structure
As shown in Figure 5, the expression formula of its non-linear state space is Elman Artificial Neural Network Structures of the present invention:
In formula, input vector u is r dimension pressure distribution index S, P
m, P
v, G
mand G
v; Y is 5 dimension pressure comfort output valves, mapping shoulder belt position 1, cup position 2, steel ring position 3, position, earthen platform 4 and rear than the subjective comfortableness value at 5 these 5 positions, position; T is iterations; X is k dimension hidden layer node unit vector; x
bfor k dimension feedback vector.W
1for accepting layer and the weights that are connected of hidden layer; W
2for input layer is to the connection weights of hidden layer; W
3for hidden layer is to the connection weights of output layer; F (.) and g (.) are respectively hidden layer and the neuronic activation functions of output layer, and f (.) adopts Sigmoid function, and g (.) adopts TanH function, and computing formula is as follows:
Use gradient descent algorithm, obtained by formula (1):
In formula, x
b(t) depend on not weights W in the same time
1 t-1and W
2 t-1thereby, realize dynamic memory process.Adopt BP algorithm, carry out weights correction with sum of squared errors function.Be expressed as:
In formula, y
t(W) be actual output, d
t(W) be desired output, W is the set of all weights in network.
(3) genetic algorithm optimization
The present invention adopts GA to optimize the initial weight of Elman network, and the basic step of algorithm is as follows:
Step 1 setting parameter, comprises individual coded strings length L, group size M, stops genetic algebra G, crossover operator P
cwith mutation operator P
m;
The individual binary coding of step 2, generates initial population;
Step 3 is calculated ideal adaptation degree value by fitness function;
If step 4 optimum individual fitness value reaches anticipation error, stop heredity, go to step 7; Otherwise, go to step 5;
Step 5, by the genetic manipulation of selecting, intersecting and make a variation, produces population of future generation;
In step 6 G generation,, the fitness value of interior optimum individual reached anticipation error, and algorithm stops; Otherwise go to step 3;
Step 7 is given Elman network W of the present invention optimum individual
1, W
2with W
3initial weight.
(4) evaluation index of model
Adopt square error (mean squared error, MSE), related coefficient (correlation coefficient, CC) to evaluate error and the Generalization Capability of brassiere pressure comfort coupling model, their computing formula is as follows:
In formula, P
(ij)the predicted value of individual j in sample i, Q
jit is the expectation of individual j.MSE is less, and the precision of model is higher.
In formula, cov (P, Q) is covariance, σ
p, σ
qbe respectively the standard variance of P and Q.It is generally acknowledged that CC reaches more than 0.85, the generalization ability of model is better.
Table 1 has been enumerated the comparison of three coupling models to Comfort Evaluation result, adopts respectively GA-Elman, Elman and the pressure distribution index of BP neural network shoulder belt, cup, steel ring, earthen platform and rear ratio and the coupling model of subjective comfortableness.By contrast, the MSE of GA-Elman model and CC are all better than other 2 models.Experimental result shows, GA-Elman shows less error and better Generalization Capability in the evaluation of brassiere pressure comfort, verified the validity of the inventive method.
As can be seen here, the present invention has reached the Expected Results that specific model brassiere pressure comfort is evaluated.
The coupling model Comfort Evaluation effect comparison that table 1GA-Elman, Elman and BP set up
Claims (4)
1. a brassiere pressure comfort evaluation method, brassiere used is the known brassiere style with earthen platform, it is characterized in that, step is:
The first step, utilize pressure distribution image system to gather shoulder belt position (1), cup position (2), steel ring position (3), position, earthen platform (4) and rear than the pressure distribution data of position (5), utilize these pressure distribution data calculate the maximum pressure of shoulder belt position (1) and steel ring position (3) and evaluate pressure as pressure distribution achievement data, the contact area at cup position (2), maximum pressure, evaluate pressure, maximum pressure gradient and average pressure gradient are as pressure distribution achievement data, position, earthen platform (4) and rear than the contact area of position (5), maximum pressure and evaluation pressure are as pressure distribution achievement data,
Second step, utilize visual simulation scale, dressed after brassiere by subject, providing shoulder belt position (1), cup position (2), steel ring position (3), position, earthen platform (4) and rear than the comfortableness subjective assessment data of position (5);
The 3rd step, adopt GA-Elman neural network shoulder belt position (1), cup position (2), steel ring position (3), position, earthen platform (4) and rear than the coupling model between the pressure distribution achievement data of position (5) and corresponding comfortableness subjective assessment data, GA-Elman neural network is the initial network weights of employing genetic algorithm optimization Elman neural network structure.
2. a kind of brassiere pressure comfort evaluation method as claimed in claim 1, it is characterized in that, described visual simulation scale adopts the smooth straight line of certain length, described shoulder belt position (1), cup position (2), steel ring position (3), position, earthen platform (4) and rear than position (5) respectively corresponding smooth straight line, every respectively corresponding two kinds of extremities in smooth straight line two ends, subject is according to the impression of dressing after brassiere, in shoulder belt position (1), cup position (2), steel ring position (3), position, earthen platform (4) and rear than drawing a vertical line on position (5) corresponding smooth straight line, position according to vertical line on smooth straight line obtains corresponding shoulder belt position (1), cup position (2), steel ring position (3), position, earthen platform (4) and rear than the comfortableness subjective assessment data of position (5).
3. a kind of brassiere pressure comfort evaluation method as claimed in claim 1, is characterized in that, the step of the initial network weights of described employing genetic algorithm optimization Elman neural network structure is:
Step 3.1, setting parameter: comprise individual coded strings length L, group size M, stop genetic algebra G, crossover operator P
cwith mutation operator P
m;
Step 3.2, individual binary coding, generate initial population;
Step 3.3, calculate ideal adaptation degree value by fitness function;
If step 3.4 optimum individual fitness value reaches anticipation error, stop heredity, go to step 3.7, otherwise, go to step 3.5;
Step 3.5, the genetic manipulation that passes through selection, intersects and make a variation, produce population of future generation;
Step 3.6, G reach anticipation error for the fitness value of interior optimum individual, and algorithm stops, otherwise goes to step 3.3;
Step 3.7, give Elman neural network W optimum individual
1, W
2with W
3network initial weight, wherein, W
1for accepting layer and the weights that are connected of hidden layer, W
2for input layer is to the connection weights of hidden layer, W
3for hidden layer is to the connection weights of output layer.
4. a kind of brassiere pressure comfort evaluation method as claimed in claim 1, it is characterized in that, carrying out before described the 3rd step, first every pressure distribution achievement data and comfortableness subjective assessment data are carried out to min-max standardization calculating, to after the data linear transformation of different dimensions and varying number level size, be mapped in interval [0,1].
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410060526.9A CN103838963A (en) | 2014-02-21 | 2014-02-21 | Bra pressure comfort evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410060526.9A CN103838963A (en) | 2014-02-21 | 2014-02-21 | Bra pressure comfort evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103838963A true CN103838963A (en) | 2014-06-04 |
Family
ID=50802451
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410060526.9A Pending CN103838963A (en) | 2014-02-21 | 2014-02-21 | Bra pressure comfort evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103838963A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106108139A (en) * | 2016-08-26 | 2016-11-16 | 红豆集团无锡远东服饰有限公司 | Adjust the intelligent bra of comfortableness |
| CN106236019A (en) * | 2016-08-26 | 2016-12-21 | 五墨(上海)智能科技有限公司 | A kind of female healths based on many intelligence sensors test underwear |
| CN108830381A (en) * | 2018-09-03 | 2018-11-16 | 陈怡� | It is a kind of to throw medicine ball posture correcting method based on Elman artificial neural network and genetic algorithms |
| CN109146960A (en) * | 2018-09-03 | 2019-01-04 | 吴佳雨 | A kind of medicine ball throwing gesture antidote based on intelligent data acquisition |
| CN109284696A (en) * | 2018-09-03 | 2019-01-29 | 吴佳雨 | A kind of image makings method for improving based on intelligent data acquisition Yu cloud service technology |
| CN109341729A (en) * | 2018-10-19 | 2019-02-15 | 浙江理工大学 | A kind of device and method measuring women zoarium brassiere |
| CN109800866A (en) * | 2017-11-16 | 2019-05-24 | 北京航空航天大学 | A kind of reliability growth forecast method based on GA-Elman neural network |
| CN109840379A (en) * | 2019-01-31 | 2019-06-04 | 东华大学 | A kind of construction method of chest gather effect and brassiere pressure comfort relationship |
| WO2021160063A1 (en) * | 2020-02-12 | 2021-08-19 | 爱慕股份有限公司 | Sports bra shock absorption effect evaluation method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101040727A (en) * | 2007-04-29 | 2007-09-26 | 东华大学 | Method for colligated judging of the fitness of the bra on the basis of layer analysis |
| CN102937645A (en) * | 2012-11-12 | 2013-02-20 | 东华大学 | Evaluating method for pressure of tight seamless underwear based on double logarithmic model |
-
2014
- 2014-02-21 CN CN201410060526.9A patent/CN103838963A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101040727A (en) * | 2007-04-29 | 2007-09-26 | 东华大学 | Method for colligated judging of the fitness of the bra on the basis of layer analysis |
| CN102937645A (en) * | 2012-11-12 | 2013-02-20 | 东华大学 | Evaluating method for pressure of tight seamless underwear based on double logarithmic model |
Non-Patent Citations (4)
| Title |
|---|
| 占辉等: "服装压力舒适性研究及应用", 《北京纺织》 * |
| 段杏元: "主塑形功能文胸设计与舒适性评价", 《中国博士学位论文全文数据库 工程科技I辑》 * |
| 耿跃峰等: "遗传优化神经网络的驾驶椅舒适度评价", 《机械设计与制造》 * |
| 马佳等: "基于人工神经网络的汽车座椅舒适度评价模型", 《工业工程》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106108139A (en) * | 2016-08-26 | 2016-11-16 | 红豆集团无锡远东服饰有限公司 | Adjust the intelligent bra of comfortableness |
| CN106236019A (en) * | 2016-08-26 | 2016-12-21 | 五墨(上海)智能科技有限公司 | A kind of female healths based on many intelligence sensors test underwear |
| CN109800866A (en) * | 2017-11-16 | 2019-05-24 | 北京航空航天大学 | A kind of reliability growth forecast method based on GA-Elman neural network |
| CN109800866B (en) * | 2017-11-16 | 2020-12-29 | 北京航空航天大学 | Reliability increase prediction method based on GA-Elman neural network |
| CN108830381A (en) * | 2018-09-03 | 2018-11-16 | 陈怡� | It is a kind of to throw medicine ball posture correcting method based on Elman artificial neural network and genetic algorithms |
| CN109146960A (en) * | 2018-09-03 | 2019-01-04 | 吴佳雨 | A kind of medicine ball throwing gesture antidote based on intelligent data acquisition |
| CN109284696A (en) * | 2018-09-03 | 2019-01-29 | 吴佳雨 | A kind of image makings method for improving based on intelligent data acquisition Yu cloud service technology |
| CN109341729A (en) * | 2018-10-19 | 2019-02-15 | 浙江理工大学 | A kind of device and method measuring women zoarium brassiere |
| CN109840379A (en) * | 2019-01-31 | 2019-06-04 | 东华大学 | A kind of construction method of chest gather effect and brassiere pressure comfort relationship |
| WO2021160063A1 (en) * | 2020-02-12 | 2021-08-19 | 爱慕股份有限公司 | Sports bra shock absorption effect evaluation method and system |
| GB2597633A (en) * | 2020-02-12 | 2022-02-02 | Aimer Co Ltd | Sports bra shock absorption effect evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103838963A (en) | Bra pressure comfort evaluation method | |
| US6597369B2 (en) | Virtual shape generation method and device using the same | |
| US20040078285A1 (en) | Production of made to order clothing | |
| CN102314712B (en) | Pelvis modeling and pelvis parameter measurement method based on three-dimensional imaging technology | |
| CN109002686A (en) | A kind of more trade mark chemical process soft-measuring modeling methods automatically generating sample | |
| CN107154071A (en) | The method that Case-based Reasoning generates individual face body Model according to anthropological measuring size data | |
| CN103514566A (en) | Risk control system and method | |
| CN103617347A (en) | Method for dynamically monitoring abnormal states of users of treadmill | |
| Kuzmichev et al. | Virtual design of knitted compression garments based on bodyscanning technology and the three-dimensional-to-two-dimensional approach | |
| CN111783516A (en) | Ploughing quality natural grade evaluation method based on deep learning | |
| CN105224764A (en) | Bone modeling and simulation method | |
| KR102236191B1 (en) | A System Providing Auto Revision of Pattern with Artificial Neural Network | |
| Chao | Estimating project overheads rate in bidding: DSS approach using neural networks | |
| Stringer | Implementing approximate Bayesian inference using adaptive quadrature: the aghq package | |
| CN101458733A (en) | Integration intelligent optimizing method for clothing physical design | |
| Liu et al. | A novel evaluation technique for human body perception of clothing fit | |
| CN106228417A (en) | A kind of bra fit detection method | |
| CN102136110A (en) | Method for generating specification and size comparison table for scale clothes ordering and scale clothes ordering production method | |
| CN105224808B (en) | Projecting integral's function skin condition integrated evaluating method based on three-dimensional coordinate | |
| CN110491510A (en) | Body measuring device, method and health control comments generating means | |
| CN115374709A (en) | Land analysis method and system based on deep forest model and FLUS model | |
| CN110119885B (en) | Subway platform sign effectiveness evaluation method based on virtual reality technology | |
| EP1341427A2 (en) | Production of made to order clothing | |
| Galada et al. | Developing a prediction model for improving bifurcated garment fit for mass customization | |
| KR102236199B1 (en) | A System Making Patterns with Artificial Neural Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20140604 |