google advanced patents
updated June 30, 2023
456 patents with my name in title
2008-2013 1
US20160364469A1 - System and method for ... - Google Patents
which claims benefit of priority from U.S. Provisional Patent Application Ser. No. ... [17] S. E. Fienberg, M. M. Meyer, and S. Wasserman. ... US8379967B1 2008-12-04 2013-02-19 Lockheed Martin Corporation Swarm control systems and methods ... Accelerated discrete distribution clustering under wasserstein distance.
2008-2013 2
US9984147B2 - System and method for ... - Google Patents
which claims benefit of priority from U.S. Provisional Patent Application Ser. No. ... [17] S. E. Fienberg, M. M. Meyer, and S. Wasserman. ... US8379967B1 2008-12-04 2013-02-19 Lockheed Martin Corporation Swarm control systems and methods ... Accelerated discrete distribution clustering under wasserstein distance.
2017? see 2 above
Patent US20170083608 - Accelerated discrete distribution clustering under wasserstein distance - Google patents
Accelerated discrete distribution clustering under wasserstein distance. US 20170083608 A1. Abstract. Computationally efficient accelerated D2-clustering algorithms are disclosed for clustering discrete distributions under the Wasserstein distance with improved scalability. Three first-order methods include subgradient ...
Inventor Jianbo Ye Jia Li James Z. Wang
2018-07-03 Application granted
Abstract Computationally efficient accelerated D2-clustering algorithms are disclosed for clustering discrete distributions under the Wasserstein distance with improved scalability. Three first-order methods include subgradient descent method with re-parametrization, alternating direction method of multipliers (ADMM), and a modified version of Bregman ADMM. The effects of the hyper-parameters on robustness, convergence, and speed of optimization are thoroughly examined. A parallel algorithm for the modified Bregman ADMM method is tested in a multi-core environment with adequate scaling efficiency subject to hundreds of CPUs, demonstrating the effectiveness of AD2-clustering.
Accelerated discrete distribution clustering under wasserstein distance
J Ye, J Li, JZ Wang - US Patent 10,013,477, 2018 - Google Patents
Computationally efficient accelerated D2-clustering algorithms are disclosed for clustering discrete distributions under the Wasserstein distance with improved scalability. Three first-order methods include subgradient descent method with re-parametrization, alternating direction method of multipliers (ADMM), and a modified version of Bregman ADMM. The effects of the hyper-parameters on robustness, convergence, and speed of optimization are thoroughly examined. A parallel algorithm for the modified Bregman ADMM method is tested …
<—2 patents in 2008
end 2008
start 2016
2 patents
2016-18 1
Accelerated discrete distribution clustering under wasserstein distance
US US10013477B2 Jianbo Ye The Penn State Research Fondation
Priority 2012-11-19 • Filed 2016-09-30 • Granted 2018-07-03 • Published 2018-07-03
Computationally efficient accelerated D2-clustering algorithms are disclosed for clustering discrete distributions under the Wasserstein distance with improved scalability. Three first-order methods include subgradient descent method with re-parametrization, alternating direction method of … \
US-2017083608-A1
2016-2019 2
… denoising model of confrontation network are generated based on Wasserstein
CN CN110097512A 张意 四川大学
Priority 2019-04-16 • Filed 2019-04-16 • Published 2019-08-06
4. the building of the three-dimensional MRI image denoising model of confrontation network is generated based on Wasserstein according to claim 3 Method, it is characterised in that the noise data of input coding device is successively handled by Three dimensional convolution, at normalization in …
<— 2 in 2016
+ 4 till 2016
= 6
end 2016
start 2017
12 patents
2017 2018 1
Deformable convolution kernel method based on WGAN (Wasserstein-Generative Adversarial Network) model
by XU JING; LI LIPING; LI LIJUN; More... 04/2018
The invention discloses a deformable convolution kernel method based on a WGAN (Wasserstein-Generative Adversarial Network) model, and belongs to the field of...
Patent:
Defrmable convolution kernel method based on WGAN (Wasserstein-Generative
CN Application CN107886162A 周智恒 华南理工大学
Priority 2017-11-14 • Filing 2017-11-14 • Publication 2018-04-06
The invention discloses a deformable convolution kernel method based on a WGAN (Wasserstein-Generative Adversarial Network) model, and belongs to the field of the deep learning neural network. The method comprises the following steps that: S1: constructing an original genera
A kind of deformable convolution kernel method based on WGAN models
CN CN107886162A 周智恒 华南理工大学
Priority 2017-11-14 • Filed 2017-11-14 • Published 2018-04-06
3. a kind of deformable convolution kernel method based on WGAN models according to claim 1, it is characterised in that described Step S5 detailed processes are as follows： S51, the characteristics of image figure that will be obtained after deformable convolution, input in arbiter and are …
2017 2
Global IP News. Software Patent News, Mar 23, 2017
Newspaper Article: Citation Online
Accelerated Discrete Distribution Clustering under Wasserstein Distance slides
O We have developed and compared three rst-order methods for optimizing the Wasserstein centroids in. D -clustering. We refer to the modi ed Bregman ADMM as the main algorithm. O The new methods, collectively called AD -clustering, improve scalability signi cantly. We have also developed a parallel algorithm for the ...
Deformable convolution kernel method based on WGAN (Wasserstein-Generative Adversarial...
by XU JING; LI LIPING; LI LIJUN ; More...
04/2018
The invention discloses a deformable convolution kernel method based on a WGAN (Wasserstein-Generative Adversarial Network) model, and belongs to the field of...
PatentAvailable Online
2017 3
A kind of deformable convolution kernel method based on WGAN models
CN CN107886162A 周智恒 华南理工大学
Priority 2017-11-14 • Filed 2017-11-14 • Published 2018-04-06
A kind of 1. deformable convolution kernel method based on WGAN models, it is characterised in that described deformable convolution kernel method bag Include the following steps： S1, construction are originally generated confrontation network model, and generating image by maker inputs to arbiter …
2017 4
A kind of empty convolution method based on WGAN models
CN CN108021978A 周智恒 华南理工大学
Priority 2017-11-14 • Filed 2017-11-14 • Published 2018-05-11
1. a kind of empty convolution method based on WGAN models, it is characterised in that the empty convolution method includes following step Suddenly： S1, construction are originally generated confrontation network model, and generating image by maker inputs to arbiter progress network training； S2 …
2017-2018 5
A kind of pedestrian detection method based on WGAN models
CN CN108009568A 周智恒 华南理工大学
Priority 2017-11-14 • Filed 2017-11-14 • Published 2018-05-08
1. a kind of pedestrian detection method based on WGAN models, it is characterised in that the pedestrian detection method includes following step Suddenly： S1, construction are originally generated confrontation network model, and generating image by maker inputs to arbiter progress network …
2017-2018 6
A kind of WGAN methods based on text generation
CN CN107590531A 周智恒 华南理工大学
Priority 2017-08-14 • Filed 2017-08-14 • Published 2018-01-16
A kind of 3. WGAN methods based on text generation according to claim 1, it is characterised in that described text data Collection is to belong to same type of content. A kind of 4. WGAN methods based on text generation according to claim 1, it is characterised in that described step S4 tools Body …
2017 7
A kind of WGAN model methods based on depth convolutional neural networks
CN CN107563510A 周智恒 华南理工大学
Priority 2017-08-14 • Filed 2017-08-14 • Published 2018-01-09
A kind of 3. WGAN model methods based on depth convolutional neural networks according to claim 1, it is characterised in that institute The transposition depth convolutional network number of plies of maker and the depth convolutional neural networks number of plies of arbiter are identical in the …
2017 8
A kind of hyper parameter dynamic adjusting method based on WGAN
CN CN107590532A 周智恒 华南理工大学
Priority 2017-08-14 • Filed 2017-08-14 • Published 2018-01-16
A kind of 3. hyper parameter dynamic adjusting method based on WGAN according to claim 1, it is characterised in that described step Rapid S2 is specific as follows： Get out image data set, random initializtion maker, arbiter convolutional neural networks in all parameter and weight, Hyper …
2017 9
A kind of WGAN methods based on text generation
CN CN107590531A 周智恒 华南理工大学
Priority 2017-08-14 • Filed 2017-08-14 • Published 2018-01-16
A kind of 3. WGAN methods based on text generation according to claim 1, it is characterised in that described text data Collection is to belong to same type of content. A kind of 4. WGAN methods based on text generation according to claim 1, it is characterised in that described step S4 tools Body …
2017 10
A kind of decomposition convolution method based on WGAN models
CN CN107943750A 周智恒 华南理工大学
Priority 2017-11-14 • Filed 2017-11-14 • Published 2018-04-20
1. a kind of decomposition convolution method based on WGAN models, it is characterised in that the decomposition convolution method includes following step Suddenly： S1, construction are originally generated confrontation network model, and generating image by maker inputs to arbiter progress …
2017 11
A kind of empty convolution method based on WGAN models
CN CN108021978A 周智恒 华南理工大学
Priority 2017-11-14 • Filed 2017-11-14 • Published 2018-05-11
1. a kind of empty convolution method based on WGAN models, it is characterised in that the empty convolution method includes following step Suddenly： S1, construction are originally generated confrontation network model, and generating image by maker inputs to arbiter progress network training； …
2017 12
A kind of pedestrian detection method based on WGAN model
CN CN108009568A 周智恒 华南理工大学
Priority 2017-11-14 • Filed 2017-11-14 • Published 2018-05-08
1. a kind of pedestrian detection method based on WGAN models, it is characterised in that the pedestrian detection method includes following step Suddenly： S1, construction are originally generated confrontation network model, and generating image by maker inputs to arbiter progress network …
<— 4 till 2016
+ 12 in 2017
= 16 till 2017
end 2017 e17
start 2018
28 patents
2018 1
Wasserstein GAN-based photovoltaic array fault diagnosis method CN-109660206-B
2018
A kind of image search method merging Faster-RCNN and Wasserstein self-encoding encoder
CN CN109086437A 冯永 重庆大学
Priority 2018-08-15 • Filed 2018-08-15 • Published 2018-12-25
2. the image search method of fusion Faster-RCNN and Wasserstein self-encoding encoder as described in claim 1, It is characterized in that, in the S1, builds Caffe deep learning frame. 3. the image search method of fusion Faster-RCNN and Wasserstein self-encoding encoder as described in claim 1, …
2018-2019 2
A kind of diagnosing failure of photovoltaic array method based on Wasserstein …
CN CN109660206A 林培杰 福州大学
Priority 2018-12-20 • Filed 2018-12-20 • Published 2019-04-19
Step S2: the electric current of the step S1 photovoltaic power generation array obtained is plotted on same picture and is saved with voltage data For sample； Step S3: a discriminator network D and a generator network G are designed by Wasserstein GAN； Step S4: being divided into training set for …
2018-2020 3
Human face gender discrimination algorithm based on Wasserstein distance
CN CN111046708A 徐江涛 天津大学青岛海洋技术研究院
Priority 2018-10-15 • Filed 2018-10-15 • Published 2020-04-21
1. The human face gender discrimination algorithm based on the Wasserstein distance is characterized in that: the method comprises three steps, wherein the first step is to construct a comparison library, and select different genders to construct comparison libraries with different distributions;
2018-2020 4
System and method for unsupervised domain adaptation via sliced-wasserstein …
patent number 11,176,477 [Application Number 16/719,668] was granted by the patent office on 2021-11-16 for system and method for unsupervised domain adaptation via sliced-wasserstein distance. This pate
US US20200125982A1 Alexander J. Gabourie Hrl Laboratories, Llc
Priority 2018-02-06 • Filed 2019-12-18 • Published 2020-04-23
The computer program product as set forth in claim 11 , wherein the one or more processors further perform an operation of using sliced-Wasserstein (SW) distance as a dissimilarity measure for determining dissimilarity between the first input data distribution and the second input data distribution.
2018-2019 5
CN CN109389080A 白静 西安电子科技大学
Priority 2018-09-30 • Filed 2018-09-30 • Published 2019-02-26
本发明公开了一种基于半监督WGAN‑GP的高光谱图像分类方法，克服了现有技术在训练数据受限条件下难以提取到丰富的特征信息，无法充利用无标签样本对分类器进行训练，分类精度低的问题。本发明的具体步骤包括：(1)输入待分类的高光谱图像；(2)生成样本集；(3)构建半监督WGAN‑GP网络；(4)训练半监督WGAN‑GP网络；(5)对测试数据进行分类。本发明能通过半监督WGAN‑GP中的生成器接收噪声产生伪高光谱数据辅助判别器分类，可以充分利用有限样本提高分类精度，可用于在精细农业、低质调研等领域中对高光谱图像进行地物目标的分类。
2018-2019 6
Hyperspectral image classification method based on semi-supervised WGAN-GP
CN CN109389080A 白静 西安电子科技大学
Priority 2018-09-30 • Filed 2018-09-30 • Published 2019-02-26
Selected is had supervision batch and the semi-supervised WGAN-GP of noise inputs by (4d), marks training data to optimize the net using having Supervision loss function in network optimizes arbiter network weight； (4e) optimizes the net by selected unsupervised batch and the semi-supervised WGAN- …
2018 7
A kind of image channel fusion method based on WGAN models
CN CN108399422A 周智恒 华南理工大学
Priority 2018-02-01 • Filed 2018-02-01 • Published 2018-08-14
1. a kind of image channel fusion method based on WGAN models, which is characterized in that the image channel fusion method packet Include following steps： S1, construction are originally generated confrontation network model, generate image by generator and are input to arbiter progress network …
2018 8
Patent Number: CN107590532-A CN107590532-B
Patent Assignee: UNIV SOUTH CHINA TECHNOLOGY
Inventor(s): ZHOU Z; LI L.
2018 22020 9
Image retrieval method fusing fast-RCNN and Wasserstein self-encoder
CN CN109086437B
2018 10
It is a kind of based on WGAN-GP model to the uneven classification method of …
CN CN109711452A 赵艺 四川新网银行股份有限公司
Priority 2018-12-20 • Filed 2018-12-20 • Published 2019-05-03
3. a kind of method for constructing WGAN-GP model according to claim 1 or 2, which is characterized in that the step S2 packet Include following steps: The dimensional characteristics of the few class data of S2.1, basis, construct WGAN-GP structure and hyper parameter simultaneously are arranged；
2018 11
A kind of fuzzy detection seed set generation method and generator based on WGAN …
CN CN108549597A 纪守领 浙江大学
Priority 2018-03-05 • Filed 2018-03-05 • Published 2018-09-18
1. a kind of fuzzy detection seed set generator based on WGAN models, which is characterized in that including： Training set acquisition module, has the fuzzy detection tool based on mutation algorithm, the fuzzy detection tool is to common Input carries out random modification and obtains …
2018 12
It is predicted based on difference WGAN network safety situation
CN CN109120652A 王永 重庆邮电大学
Priority 2018-11-09 • Filed 2018-11-09 • Published 2019-01-01
The invention proposes a kind of network security situation prediction methods based on difference WGAN.The invention simulates the development process of situation using confrontation network (Generative adversarial network, GAN) is generated, and realizes Tendency Prediction from time dimension.
2018 13
Hyperspectral image classification method based on semi-supervised WGAN-GP
CN CN109389080A 白静 西安电子科技大学
Priority 2018-09-30 • Filed 2018-09-30 • Published 2019-02-26
Selected is had supervision batch and the semi-supervised WGAN-GP of noise inputs by (4d), marks training data to optimize the net using having Supervision loss function in network optimizes arbiter network weight； (4e) optimizes the net by selected unsupervised batch and the semi-supervised WGAN- …
2018 14
A kind of image channel fusion method based on WGAN models
CN CN108399422A 周智恒 华南理工大学
Priority 2018-02-01 • Filed 2018-02-01 • Published 2018-08-14
1. a kind of image channel fusion method based on WGAN models, which is characterized in that the image channel fusion method packet Include following steps： S1, construction are originally generated confrontation network model, generate image by generator and are input to arbiter progress network …
2018 15
Object Shape Regression Using Wasserstein Distance
EP US JP JP2020098587A ジン・サン パロ アルト リサーチ センター インコーポレイテッド
Priority 2018-12-17 • Filed 2019-11-25 • Published 2020-06-25
Optimizing the parameters of the shape regression model based on the Wasserstein distances calculated by the classifier module. The method of claim 2, wherein optimizing the shape regression model comprises updating parameters of the shape regression model such that the calculated Wasserstein …
2018 16
… plane signal identification detection algorithm based on improvement AC-WGANs
CN CN108197581A 赵彩丹 厦门大学
Priority 2018-01-10 • Filed 2018-01-10 • Published 2018-06-22
4. as described in claim 1 a kind of based on the unmanned plane signal identification detection algorithm for improving AC-WGANs, feature exists In：In step S4, it is described improve AC-WGANs algorithms the specific steps are： S41, according to the characteristics of the loss function of AC-WGANs …
2018 17
A kind of feature recalibration convolution method based on WGAN model
CN CN109359667A 周智恒 华南理工大学
Priority 2018-09-07 • Filed 2018-09-07 • Published 2019-02-19
5. a kind of feature recalibration convolution method based on WGAN model according to claim 1, which is characterized in that described Loss function expression formula are as follows: Wherein, D (x) indicates differentiation of the arbiter to image, and pr indicates the distribution of data …
2018 18. patent. 2018-2020
Object shape regression using wasserstein distance
EP US JP EP3671555A1 Jin Sun Palo Alto Research Center Incorporated
Priority 2018-12-17 • Filed 2019-12-13 • Published 2020-06-24
optimizing parameters of the shape-regression model based on the Wasserstein distance computed by the discriminator module. The method of claim 2, wherein optimizing the shape-regression model comprises updating parameters of the shape-regression model in such a way that the computed Wasserstein …
2018 19. patent
A kind of eGaN HEMT bridge arm clutter reduction driving circuits and its …
CN CN108649777A 张英 南京航空航天大学
Priority 2018-04-12 • Filed 2018-04-12 • Published 2018-10-12
4. a kind of eGaN HEMT bridge arms clutter reduction driving circuit according to claim 1, it is characterised in that：Described One Low ESR bridge arm clutter reduction circuit and the second Low ESR bridge arm clutter reduction circuit structure are identical, include that third switchs The drain …
2018 20 patent
A kind of fuzzy detection seed set generation method and generator based on WGAN …
CN CN108549597A 纪守领 浙江大学
Priority 2018-03-05 • Filed 2018-03-05 • Published 2018-09-18
1. a kind of fuzzy detection seed set generator based on WGAN models, which is characterized in that including： Training set acquisition module, has the fuzzy detection tool based on mutation algorithm, the fuzzy detection tool is to common Input carries out random modification and obtains …
2018 21. patent
A kind of image channel fusion method based on WGAN models
CN CN108399422A 周智恒 华南理工大学
Priority 2018-02-01 • Filed 2018-02-01 • Published 2018-08-14
1. a kind of image channel fusion method based on WGAN models, which is characterized in that the image channel fusion method packet Include following steps： S1, construction are originally generated confrontation network model, generate image by generator and are input to arbiter progress network …
2018 22. patent
It is a kind of based on WGAN-GP model to the uneven classification method of
CN CN109711452A 赵艺 四川新网银行股份有限公司
Priority 2018-12-20 • Filed 2018-12-20 • Published 2019-05-03
3. a kind of method for constructing WGAN-GP model according to claim 1 or 2, which is characterized in that the step S2 packet Include following steps: The dimensional characteristics of the few class data of S2.1, basis, construct WGAN-GP structure and hyper parameter simultaneously are arranged；
2018 23. patent
It is predicted based on difference WGAN network safety situation
CN CN109120652A 王永 重庆邮电大学
Priority 2018-11-09 • Filed 2018-11-09 • Published 2019-01-01
The invention proposes a kind of network security situation prediction methods based on difference WGAN.The invention simulates the development process of situation using confrontation network (Generative adversarial network, GAN) is generated, and realizes Tendency Prediction from time dimension.
2018 24. patent
Hyperspectral image classification method based on semi-supervised WGAN-GP
CN CN109389080A 白静 西安电子科技大学
Priority 2018-09-30 • Filed 2018-09-30 • Published 2019-02-26
Selected is had supervision batch and the semi-supervised WGAN-GP of noise inputs by (4d), marks training data to optimize the net using having Supervision loss function in network optimizes arbiter network weight； (4e) optimizes the net by selected unsupervised batch and the semi-supervised WGAN- …
2018 25. patent
A kind of feature recalibration convolution method based on WGAN model
CN CN109359667A 周智恒 华南理工大学
Priority 2018-09-07 • Filed 2018-09-07 • Published 2019-02-19
5. a kind of feature recalibration convolution method based on WGAN model according to claim 1, which is characterized in that described Loss function expression formula are as follows: Wherein, D (x) indicates differentiation of the arbiter to image, and pr indicates the distribution of data …
2018 26. patent
A kind of diagnosing failure of photovoltaic array method based on Wasserstein …
CN CN109660206A 林培杰 福州大学
Priority 2018-12-20 • Filed 2018-12-20 • Published 2019-04-19
Step S2: the electric current of the step S1 photovoltaic power generation array obtained is plotted on same picture and is saved with voltage data For sample； Step S3: a discriminator network D and a generator network G are designed by Wasserstein GAN； Step S4: being divided into training set for …
2018 27 patent
Human face gender discrimination algorithm based on Wasserstein distance
CN CN111046708A 徐江涛 天津大学青岛海洋技术研究院
Priority 2018-10-15 • Filed 2018-10-15 • Published 2020-04-21
1. The human face gender discrimination algorithm based on the Wasserstein distance is characterized in that: the method comprises three steps, wherein the first step is to construct a comparison library, and select different genders to construct comparison libraries with different distributions;
2018 28. patent
Image retrieval method fusing fast-RCNN and Wasserstein self-encoder
CN CN10908643
<— 16 till 2017
+ 28 in 2018
= 44 till 2018
end 2018. e18
start 2019
58 patents
2019 1
Convolutional neural networks based on Wasserstein distance fight transfer …
CN CN110414383A 袁烨 华中科技大学
Priority 2019-07-11 • Filed 2019-07-11 • Published 2019-11-05
To maximize described in the distance of the Wasserstein between the source domain feature set and the target signature collection and minimum The judgement loss of Wasserstein distance, the judgement penalty values of the source domain breakdown judge collection and target faults judgement …
2019 2
Data correlation method in pedestrian tracking based on Wasserstein measurement
CN CN110110670A 郭春生 杭州电子科技大学
Priority 2019-05-09 • Filed 2019-05-09 • Published 2019-08-09
It is a kind of based on Wasserstein measurement pedestrian tracking in data correlation method, it include: the external appearance characteristic for obtaining pedestrian, the external appearance characteristic extracted is input to a feature extraction network, the external appearance …
2019-2020 3
Clean energy power supply planning method based on Wasserstein distance and …
CN CN110797919A 汪荣华 国网四川省电力公司经济技术研究院
Priority 2019-12-05 • Filed 2019-12-05 • Published 2020-02-14
5. The method for clean energy power planning based on Wasserstein distance and distribution robust optimization according to claim 2, characterized in that the method uses Wasserstein distance to describe the difference between the empirical distribution and the true distribution obtained from a …
2019 4
Finger vein identification method based on deep learning and Wasserstein …
CN CN110555382A 张娜 浙江理工大学
Priority 2019-07-31 • Filed 2019-07-31 • Published 2019-12-10
S52, in the identification stage, extracting feature codes G w (x) 'of the finger vein image through steps S1, S2, S3 and S4, matching the feature codes G w (x) } registered in a database one by one, calculating the Wasserstein distance between G w (x)' and G w (x), and solving the Wasserstein …
2019-2020 5
Object Shape Regression Using Wasserstein Distance
JP2020098587A ジン・サン パロ アルト リサーチ センター インコーポレイテッド
Priority 2018-12-17 • Filed 2019-11-25 • Published 2020-06-25
Optimizing parameters of the shape regression model based on the Wasserstein distances calculated by the discriminator module. The apparatus of claim 9, wherein optimizing the shape regression model comprises updating parameters of the shape regression model such that the calculated Wasserstein …
2019-2020 6
Object shape regression using wasserstein distance
EP US EP3671555A1 Jin Sun Palo Alto Research Center Incorporated
Priority 2018-12-17 • Filed 2019-12-13 • Published 2020-06-24
optimizing parameters of the shape-regression model based on the Wasserstein distance computed by the discriminator module. The method of claim 2, wherein optimizing the shape-regression model comprises updating parameters of the shape-regression model in such a way that the computed Wasserstein …
2019-2020 7
Depth self-coding embedded clustering method based on Sliced-Wasserstein …
CN CN111178427A 郭春生 杭州电子科技大学
Priority 2019-12-27 • Filed 2019-12-27 • Published 2020-05-19
The invention discloses a depth self-coding embedded clustering method based on Sliced-Wasserstein distance, which comprises the following steps: s11, constructing a self-coding network module based on a Sliced-Walserstein distance; s12, constructing a clustering module; s13, combining the built …
2019 8
Finger vein identification method based on deep learning and Wasserstein …
S52, in the identification stage, extracting feature codes G w (x) 'of the finger vein image through steps S1, S2, S3 and S4, matching the feature codes G w (x) } registered in a database one by one, calculating the Wasserstein distance between G w (x)' and G w (x), and solving the Wasserstein …
2019 9
Wasserstein distance-based fault diagnosis method for deep countermeasure …
CN CN110907176A 徐娟 合肥工业大学
Priority 2019-09-30 • Filed 2019-09-30 • Published 2020-03-24
1. A fault diagnosis method of a deep countermeasure migration network based on Wasserstein distance is characterized by comprising the following steps: s1, respectively obtaining source domains D s And a target domain D t The data set of (a); wherein D represents a domain; superscript s denotes …
2019 10
Patent Number: CN110414383-A
Patent Assignee: UNIV HUAZHONG SCI & TECHNOLOGY
Inventor(s): YUAN Y; ZHOU B; CHENG C; et al.
|
2019-2020 11
… typical scene generation method based on BIRCH clustering and Wasserstein …
CN CN110929399A 汤向华 国网江苏省电力有限公司南通供电分公司
Priority 2019-11-21 • Filed 2019-11-21 • Published 2020-03-27
2. The method for generating a typical wind power output scene based on BIRCH clustering and Wasserstein distance as claimed in claim 1, wherein: the specific steps of the BIRCH clustering are as follows: a) setting threshold parameters B, L and T, and inputting wind power scene number S; b) number …
2019 12
Patent Assignee: UNIV ZHEJIANG SCI-TECH
Inventor(s): ZHANG N; TU X; BAO X; et al.
2019 13
Patent Number: CN110197514-A
Patent Assignee: UNIV NANJING AGRIC
Inventor(s): YUAN P; WU M; XU H; et al.
2019 14
Open Access
Convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof
by LI XINGYI; MA GUIJUN; CHENG CHENG; More...
11/2019
The invention relates to a convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof and the...
Patent: Citation Online
2019 15
Open Access
04/2019
本发明涉及种基于Wasserstein GAN的光伏阵列故障诊断方法，首先对光伏阵列电流、电压时序数据进行采集；接着将获取的光伏阵列时序电流与时序电压数据绘制为曲线图形并保存为样本；然后设计Wasserstein GAN网络中的鉴别器D与生成器G；然后训练Wasserstein...
Patent: Citation Online
Photovoltaic array fault diagnosis method based on Wasserstein GAN
[Chinese Fault Diagnosis Method for Photovoltaic Array Based on Wasserstein GAN]
2019 16
Open Access
基于Wasserstein生成对抗网络的三维MRI图像去噪模型的构建方法及应用
08/2019
Patent: Citation Online
Construction method and application of three-dimensional MRI image denoising model based on Wasserstein generative adversarial network
[Chinese Construction method and application of 3D MRI image denoising model based on Wasserstein generative adversarial network]
2019 17
Improved image enhancement method and device based on WGA-GP and U-net, and storage medium
by WANG HONGLING; TANG JIE; LI QINGYU
11/2019
The invention discloses an improved image enhancement method and an improved image enhancement device based on WGAN-GP and U-net, and a storage medium. The...
Patent: Citation Online
2019 18
一种基于WGAN-GP和过采样的不平衡学习方法 - 中南大学教师 ...
faculty.csu.edu.cn › dengxiaoheng › zlcg › content
An imbalanced learning method based on WGAN-GP and oversampling. Click：. Application no： ... Patent Inventor：邓晓衡、黄戎、沈海澜. Open date：2019-05-28.
一种基于WGAN-GP和过采样的不平衡学习方法
05/2019
本发明公开了一种基于WGAN-GP和过采样的不平衡学习方法，包括：生成器网络，由三层全连接网络组成并且每一层的输出都应用了Batch...
Patent: Citation Online
2019 19
Patent Number: CN110197514-A
Patent Assignee: UNIV NANJING AGRIC
Inventor(s): YUAN P; WU M; XU H; et al.
Mathematics Week, 12/2019
NewsletterFull Text Online
2019 20
Patent Number: CN110414383-A
Patent Assignee: UNIV HUAZHONG SCI & TECHNOLOGY
Inventor(s): YUAN Y; ZHOU B; CHENG C; et al.
|
2019 21
Open Access
Convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof
by LI XINGYI; MA GUIJUN; CHENG CHENG; More...
11/2019
The invention relates to a convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof and the...
Patent: Citation Online
2019 22
Open Access
基于Wasserstein生成对抗网络的三维MRI图像去噪模型的构建方法及应用
08/2019
Patent: Citation Online
Construction method and application of three-dimensional MRI image denoising model based on Wasserstein generative adversarial network
[Chinese Construction method and application of 3D MRI image denoising model based on Wasserstein generative adversarial network]
2019 23
一种基于WGAN-GP和过采样的不平衡学习方法 - 中南大学教师 ...
faculty.csu.edu.cn › dengxiaoheng › zlcg › content
An imbalanced learning method based on WGAN-GP and oversampling. Click：. Application no： ... Patent Inventor：邓晓衡、黄戎、沈海澜. Open date：2019-05-28.
一种基于WGAN-GP和过采样的不平衡学习方法
05/2019
本发明公开了一种基于WGAN-GP和过采样的不平衡学习方法，包括：生成器网络，由三层全连接网络组成并且每
2019 24
一种基于WGAN-GP和过采样的不平衡学习方法 - 中南大学教师 ...
faculty.csu.edu.cn › dengxiaoheng › zlcg › content
An imbalanced learning method based on WGAN-GP and oversampling. Click：. Application no： ... Patent Inventor：邓晓衡、黄戎、沈海澜. Open date：2019-05-28.
一种基于WGAN-GP和过采样的不平衡学习方法
05/2019
本发明公开了一种基于WGAN-GP和过采样的不平衡学习方法，包括：生成器网络，由三层全连接网络组成并且每一层的输出都应用了Batch...
Patent: Citation Online
2019 25
Open Access
02/2019
PatentCitation Online
[Chinese Hyperspectral image classification method based on semi-supervised WGAN-GP]
2019 26
Open Access
02/2019
PatentCitation Online
[Chinese Hyperspectral image classification method based on semi-supervised WGAN-GP]
2019 27
Open Access
A feature recalibration convolution method based on WGAN model
by LI LIJUN; ZHOU ZHIHENG
02/2019
The invention discloses a feature recalibration convolution method based on a WGAN model, and belongsto the field of depth learning neural network. The method...
PatentCitation Online
Global IP News: Broadband and Wireless Network Patent News, Aug 31, 2020
Newspaper ArticleCitation Online
2019 28
Open Access
A feature recalibration convolution method based on WGAN model
by LI LIJUN; ZHOU ZHIHENG
02/2019
The invention discloses a feature recalibration convolution method based on a WGAN model, and belongsto the field of depth learning neural network. The method...
PatentCitation Online
Global IP News: Broadband and Wireless Network Patent News, Aug 31, 2020
Newspaper ArticleCitation Online
Global IP News. Broadband and Wireless Network News, Aug 31, 2020
Newspaper ArticleFull Text Online
2019 29
Open Access
A feature recalibration convolution method based on WGAN model
by LI LIJUN; ZHOU ZHIHENG
02/2019
The invention discloses a feature recalibration convolution method based on a WGAN model, and belongsto the field of depth learning neural network. The method...
PatentCitation Online
Global IP News: Broadband and Wireless Network Patent News, Aug 31, 2020
Newspaper ArticleCitation Online
Global IP News. Broadband and Wireless Network News, Aug 31, 2020
Newspaper ArticleFull Text Online
2019 30
Open Access
Differential WGAN based network security situation prediction method
by ZHU JIANG; WANG TINGTING; WANG YONG
01/2019
The invention provides a differential WGAN based network security situation prediction method. The GAN (Generative adversarial network) is used to simulate the...
PatentCitation Online
Global IP News. Security & Protection Patent News, Oct 14, 2019
Newspaper ArticleFull Text Online
Global IP News: Security & Protection Patent News, Oct 14, 2019
Newspaper ArticleCitation Online
2019-2020 31
… consumption prediction method and monitoring prediction system based on WGAN …
CN CN111178626A 傅启明 苏州科技大学
Priority 2019-12-30 • Filed 2019-12-30 • Published 2020-05-19
8. the WGAN algorithm-based building energy consumption prediction method according to claim 1, wherein after completing one GAN prediction model training in step S400, the reinforcement learning algorithm is used to optimize the hyperparameters in GAN, LSTM, and CNN, find and update the optimal …
2019 32
A kind of fuzzy detection seed set generation method and generator based on WGAN …
CN CN108549597A 纪守领 浙江大学
Priority 2018-03-05 • Filed 2018-03-05 • Published 2018-09-18
The invention discloses a kind of fuzzy detection seed set generator based on WGAN models, including：Training set acquisition module, has the fuzzy detection tool based on mutation algorithm, using common input as the identical program of Seed inspection multiple input format, it may be found that …
2019 33
Patent Number: CN108549597-A
Patent Assignee: UNIV ZHEJIANG
Inventor(s): JI S; LV C; CHEN J; et al.
2019 34
Data association method in pedestrian tracking based on Wasserstein measurement
CN CN110110670B 郭春生 杭州电子科技大学
Priority 2019-05-09 • Filed 2019-05-09 • Granted 2022-03-25 • Published 2022-03-25
5. The data association method in pedestrian tracking based on Wasserstein measurement as claimed in claim 1, wherein said second step is specifically: the method comprises the steps that seven video clips on a train sequence of an MOT16 data set are used for making data sets, and the made training …
2019 35
Methods and devices performing adaptive quadratic Wasserstein full-waveform …
US BR GB GB2584196A Wang Diancheng Cgg Services Sas
Priority 2019-03-26 • Filed 2020-03-13 • Published 2020-11-25
8. A seismic data processing apparatus (800) configured to perform seismic exploration of an underground structure using a Wasserstein metric-based full-wave inversion, FWI, the apparatus comprising: an interface (810) configured to obtain seismic data acquired over the explored underground …
20192020 36
Wasserstein barycenter model ensembling
US US20200342361A1 Youssef Mroueh International Business Machines Corporation
Priority 2019-04-29 • Filed 2019-04-29 • Published 2020-10-29
10 . The system according to claim 9 , further comprising inputting side information into the barycenter, wherein the barycenter comprises a Wasserstein barycenter with a Wasserstein distance metric. 11 . The system according to claim 9 , further comprising a plurality of the barycenters to determine …
2019 37
… and embedded clustering based on depth self-coding of Sliced-Wasserstein …
CN CN111178427B 郭春生 杭州电子科技大学
Priority 2019-12-27 • Filed 2019-12-27 • Granted 2022-07-26 • Published 2022-07-26
2. The method for image dimensionality reduction and embedded clustering based on depth self-coding of Sliced-Wasserstein distance according to claim 1, wherein in step S4, the cluster center of the self-coding embedded clustering network after initialization construction is initialized by an …
… for high-dimension unsupervised anomaly detection using kernalized wasserstein
KR KR102202842B1 백명희조 서울대학교산학협력단
Priority 2019-08-13 • Filed 2019-08-13 • Granted 2021-01-14 • Published 2021-01-14
The present invention relates to a learning method and a learning apparatus for high-dimension unsupervised abnormality detection using a kernalized Wasserstein autoencoder to decrease excessive computations of a Christoffel function, and a test method and a test apparatus using the same.
2019 39
A kind of uneven learning method based on WGAN-GP and over-sampling
CN CN109816044A 邓晓衡 中南大学
Priority 2019-02-11 • Filed 2019-02-11 • Published 2019-05-28
3. a kind of uneven learning method based on WGAN-GP and over-sampling as claimed in claim 2, which is characterized in that sentence The loss function of other device, as follows: Wherein, D (), G () respectively indicate the function expression of arbiter and Maker model, P r Indicate the number of …
2019 40
Sketch based on WGAN-GP and U-NET-photo method for transformation
CN CN110175567A 王世刚 吉林大学
Priority 2019-05-28 • Filed 2019-05-28 • Published 2019-08-27
1. a kind of sketch based on WGAN-GP and U-NET -- photo method for transformation, it is characterised in that include the following steps: 1.1 obtain human face sketch -- picture data library: FERET, CUHK, IIIT-D； 1.2 by sketch -- photo keeps the distribution proportion of its face of …
2019 41
New energy capacity configuration method based on WGAN scene simulation and …
CN CN112994115A 马燕峰 华北电力大学（保定）
Priority 2019-12-18 • Filed 2019-12-18 • Published 2021-06-18
1. A new energy capacity configuration method based on Wasserstein generation countermeasure network (WGAN) scene simulation and time sequence production simulation is characterized by mainly comprising the following specific steps: step 1, simulating a large number of wind and light resource …
2019 41
Method, device and storage medium for improving image enhancement based on WGAN …
CN CN110493242B 王红玲 上海网达软件股份有限公司
Priority 2019-08-27 • Filed 2019-08-27 • Granted 2022-02-11 • Published 2022-02-11
1. A method for improved image enhancement based on WGAN-GP and U-net, comprising the steps of: the first step is as follows: de-encapsulating the input video stream or file to obtain a first video code stream and a first audio code stream; the second step is as follows: decoding the first video …
2019 42. patent
Depth self-coding embedded clustering method based on Sliced-Wasserstein …
CN CN111178427A 郭春生 杭州电子科技大学
Priority 2019-12-27 • Filed 2019-12-27 • Published 2020-05-19
The invention discloses a depth self-coding embedded clustering method based on Sliced-Wasserstein distance, which comprises the following steps: s11, constructing a self-coding network module based on a Sliced-Walserstein distance; s12, constructing a clustering module; s13, combining the built …
2019 43. patent
System and method for unsupervised domain adaptation via sliced-wasserstein …
US US20200125982A1 Alexander J. Gabourie Hrl Laboratories, Llc
Priority 2018-02-06 • Filed 2019-12-18 • Published 2020-04-23
The computer program product as set forth in claim 11 , wherein the one or more processors further perform an operation of using sliced-Wasserstein (SW) distance as a dissimilarity measure for determining dissimilarity between the first input data distribution and the second input data distribution.
2019 44 patent
System and method for unsupervised domain adaptation via sliced-wasserstein …
WO EP CN WO2020159638A1 Alexander J. GABOURIE Hrl Laboratories, Llc
Priority 2019-01-30 • Filed 2019-12-18 • Published 2020-08-06
12. The computer program product as set forth in Claim 11, wherein the one or more processors further perform an operation of using sliced-Wasserstein (SW) distance as a dissimilarity measure for determining dissimilarity between the first input data distribution and the second input data …
2019 45 patent
Clean energy power supply planning method based on Wasserstein distance and …
CN CN110797919B 汪荣华 国网四川省电力公司经济技术研究院
Priority 2019-12-05 • Filed 2019-12-05 • Granted 2020-09-01 • Published 2020-09-01
The invention discloses a clean energy power supply planning method based on Wasserstein distance and distribution robust optimization, which relates to the technical field of power system planning, and comprises the following steps: s1: constructing a wind-solar output uncertainty set based on …
2019 46 patent
… typical scene generation method based on BIRCH clustering and Wasserstein …
CN CN110929399A 汤向华 国网江苏省电力有限公司南通供电分公司
Priority 2019-11-21 • Filed 2019-11-21 • Published 2020-03-27
2. The method for generating a typical wind power output scene based on BIRCH clustering and Wasserstein distance as claimed in claim 1, wherein: the specific steps of the BIRCH clustering are as follows: a) setting threshold parameters B, L and T, and inputting wind power scene number S; b) number …
2019 47 atent
Wasserstein distance-based fault diagnosis method for deep countermeasure …
CN CN110907176A 徐娟 合肥工业大学
Priority 2019-09-30 • Filed 2019-09-30 • Published 2020-03-24
2. The method for fault diagnosis of the deep immunity migration network based on Wasserstein distance as claimed in claim 1, wherein in step S3, the objective function of the fault diagnosis model is determined, which includes the following specific steps: s301, extracting the source domain D from …
2019 48 patent
… for high-dimension unsupervised anomaly detection using kernalized wasserstein …
KR KR102202842B1 백명희조 서울대학교산학협력단
Priority 2019-08-13 • Filed 2019-08-13 • Granted 2021-01-14 • Published 2021-01-14
The present invention relates to a learning method and a learning apparatus for high-dimension unsupervised abnormality detection using a kernalized Wasserstein autoencoder to decrease excessive computations of a Christoffel function, and a test method and a test apparatus using the same.
2019 49 patent
Finger vein identification method based on deep learning and Wasserstein …
CN CN110555382A 张娜 浙江理工大学
Priority 2019-07-31 • Filed 2019-07-31 • Published 2019-12-10
6. the finger vein recognition method based on deep learning and Wasserstein distance measurement in claim 1, wherein: the step S5 includes: S51, in the registration stage, acquiring a finger vein image through the step S1, further extracting a feature code G w (x) of the image through the steps S2 …
2019 50 patent
Convolutional neural networks based on Wasserstein distance fight transfer …
CN CN110414383A 袁烨 华中科技大学
Priority 2019-07-11 • Filed 2019-07-11 • Published 2019-11-05
In the step 3.2, the Wasserstein distance is the real number average value and target reality of the source domain set of real numbers The difference of the real number average value of manifold. 5. a kind of convolutional neural networks based on Wasserstein distance according to claim 2 fight …
2019 51. patent
Data association method in pedestrian tracking based on Wasserstein measurement
CN CN110110670B 郭春生 杭州电子科技大学
Priority 2019-05-09 • Filed 2019-05-09 • Granted 2022-03-25 • Published 2022-03-25
5. The data association method in pedestrian tracking based on Wasserstein measurement as claimed in claim 1, wherein said second step is specifically: the method comprises the steps that seven video clips on a train sequence of an MOT16 data set are used for making data sets, and the made training …
2019-2020 52. patent
Wasserstein barycenter model ensembling
US US20200342361A1 Youssef Mroueh International Business Machines Corporation
Priority 2019-04-29 • Filed 2019-04-29 • Published 2020-10-29
, wherein the side information includes class relationships represented by a graph or via an embedding space. 13 . The system according to claim 9 , wherein the optimal transport metric includes a Wasserstein distance. 14 . The system according to claim 11 , wherein the barycenter takes into account the …
019 53. patent
… denoising model of confrontation network are generated based on Wasserstein
CN CN110097512A 张意 四川大学
Priority 2019-04-16 • Filed 2019-04-16 • Published 2019-08-06
The invention discloses a kind of construction method of three-dimensional MRI image denoising model that confrontation network is generated based on Wasserstein and applications, the present invention generates confrontation network as basic model using Wasserstein and handles MRI noise image, it …
019 54. patent
Sketch based on WGAN-GP and U-NET-photo method for transformation
CN CN110175567A 王世刚 吉林大学
Priority 2019-05-28 • Filed 2019-05-28 • Published 2019-08-27
1. a kind of sketch based on WGAN-GP and U-NET -- photo method for transformation, it is characterised in that include the following steps: 1.1 obtain human face sketch -- picture data library: FERET, CUHK, IIIT-D； 1.2 by sketch -- photo keeps the distribution proportion of its face of …
019 55. patent
A kind of horizontal proliferation eGaN HEMT device of integrated backward …
CN CN110212028A 张士英 张士英
Priority 2019-05-22 • Filed 2019-05-22 • Published 2019-09-06
6. the horizontal proliferation eGaN HEMT of a kind of integrated backward dioded according to claim 1 and embedded drain electrode field plate Device, which is characterized in that MIS Schottky diode extended segment (104) and MIS Schottky diode insulating layer (105) are adopted MIS Schottky …
019 56. patent
A kind of eGaN HEMT hybrid solenoid valve circuit and control method
CN CN110224579A 彭子和 南京航空航天大学
Priority 2019-05-16 • Filed 2019-05-16 • Published 2019-09-10
4. the method for controlling eGaN HEMT hybrid solenoid valve circuit as claimed in claim 2, it is characterised in that: keep driving electricity Potential source U dri In running order, DC current source I is opened in starting before eGaN HEMT is opened on_bias , enter in eGaN HEMT It is closed when …
019 57. patent
A kind of uneven learning method based on WGAN-GP and over-sampling
CN CN109816044A 邓晓衡 中南大学
Priority 2019-02-11 • Filed 2019-02-11 • Published 2019-05-28
3. a kind of uneven learning method based on WGAN-GP and over-sampling as claimed in claim 2, which is characterized in that sentence The loss function of other device, as follows: Wherein, D (), G () respectively indicate the function expression of arbiter and Maker model, P r Indicate the number of …
2019 58. 2019-2023
Methods and devices performing adaptive quadratic Wasserstein full-waveform …
US BR GB MX GB2584196B Wang Diancheng Cgg Services Sas
Priority 2019-03-26 • Filed 2020-03-13 • Granted 2023-01-18 • Published 2023-01-18
<— 44 till 2018
+ 58 in 2019
= 102 till 2019
end 2019. e19
start 2020
95 patents
2020 1 2018-202Palo Alto Research Center Submits United States Patent Application for Object Shape Regression Using Wasser...
Global IP News. Information Technology Patent News, Jun 18, 2020
Newspaper ArticleFull Text Online
Palo Alto Research Center Incorporated; "Object Shape Regression Using Wasserstein Distance" in Patent...
Journal of engineering (Atlanta, Ga.), Jul 6, 2020, 5046 patent
Newspaper ArticleFull Text Online
Object shape regression using wasserstein distance
J Sun, SKP Kumar, R Bala - US Patent App. 16/222,062, 2020 - Google Patents
One embodiment can provide a system for detecting outlines of objects in images. During
operation, the system receives an image that includes at least one object, generates a
random noise signal, and provides the received image and the random noise signal to a …
2020 2
System and method for unsupervised domain adaptation via sliced-wasserstein distance
AJ Gabourie, M Rostami, S Kolouri… - US Patent App. 16 …, 2020 - freepatentsonline.com
Described is a system for unsupervised domain adaptation in an autonomous learning
agent. The system adapts a learned model with a set of unlabeled data from a target
domain, resulting in an adapted model. The learned model was previously trained to …
2020 3
Information Technology Newsweekly, 05/2020
NewsletterFull Text Online
2020 4
Adapted wasserstein distances and stability in mathematical finance
BV Julio, D Bartl, B Mathias, E Manu - Finance and Stochastics, 2020 - Springer
Assume that an agent models a financial asset through a measure Q with the goal to
price/hedge some derivative or optimise some expected utility. Even if the model Q is
chosen in the most skilful and sophisticated way, the agent is left with the possibility that Q
does not provide an exact description of reality. This leads us to the following question: will
the hedge still be somewhat meaningful for models in the proximity of Q? If we measure
proximity with the usual Wasserstein distance (say), the answer is No. Models which are …
Cited by 6 Related articles All 11 versions
Journal of mathematics (Atlanta, Ga.), Jun 30, 2020, 949
Newspaper ArticleFull Text Online
Global IP News. Information Technology Patent News, Apr 23, 2020 pate\
Newspaper ArticleFull Text Online
2020 5
Patent Number: CN111476721-A
Patent Assignee: UNIV CHONGQING POSTS & TELECOM
Inventor(s): FENG J; QI S; WU S.
Wasserstein barycenter model ensembling
Y Mroueh, PL Dognin, I Melnyk, J Ross… - US Patent App. 16 …, 2020 - Google Patents
A method, system and apparatus of ensembling, including inputting a set of models that
predict different sets of attributes, determining a source set of attributes and a target set of
attributes using a barycenter with an optimal transport metric, and determining a consensus …
2020 7
… data leakage of halogen conveying pipeline based on S transformation/WGAN
CN CN111460367A 徐敏 淮阴工学院
Priority 2020-03-20 • Filed 2020-03-20 • Published 2020-07-28
4. The algorithm for resolving data imbalance of leakage in a brine transporting pipeline based on S transform/WGAN of claim 1, wherein the WGAN model mainly comprises a generator g (z) and a discriminator d (x); the generator G (z) is used for learning the real signal distribution of the leakage …
2020 8
online OPEN ACCESS
METHODS AND DEVICES PERFORMING ADAPTIVE QUADRATIC WASSERSTEIN FULL-WAVEFORM...
by WANG, Diancheng; WANG, Ping
10/2020
Methods and devices for seismic exploration of an underground structure apply W2-based full-wave inversion to transformed synthetic and seismic data. Data...
PatentAvailable Online
Preview
Cite this item Email this item Save this item More actions
2020 9 online OPEN ACCESS
Image rapid enhancement method based on Wasserstein distance
by QI SHUANG; WU SHANHONG; FENG JIANGFAN
07/2020
The invention relates to an image rapid enhancement method based on a Wasserstein distance, and belongs to the field of computer vision. The method comprises...
PatentAvailable Online
2020 10 online OPEN ACCESS
Depth domain adaptive image classification method based on Waserstein distance
by WU QIANG; LIU JU; SUN SHUANG ; More...
07/2020
The invention provides a Wasserstein distance-based depth domain adaptive image classification method and apparatus, and a computer readable storage medium....
PatentAvailable Online
2020 11 online OPEN ACCESS
Method for embedding and clustering depth self-coding based on Sliced-Waserstein distance
by CHEN HUAHUA; YING NA; GUO CHUNSHENG ; More...
05/2020
The invention discloses a deep self-encoding embedding clustering method based on a Sliced-Waserstein distance. The method comprises the following steps: S11,...
PatentAvailable Online
2020 12 online OPEN ACCESS
Semi-supervised deep learning fault diagnosis method based on Wasserstein distance and...
by SONG ZHIHUAN; GE ZHIQIANG; ZHANG HONGYI
04/2020
The invention discloses a semi-supervised deep learning fault diagnosis method based on a Wasserstein distance and an auto-encoder. The semi-supervised deep...
PatentAvailable Online
Preview
Cite this item Email this item Save this item More actions
2020 13 online OPEN ACCESS
Wind power output typical scene generation method based on BIRCH clustering and Wasserstein distance
by JIANG HUI; WANG SHENGQIANG; WANG DONG ; More...
03/2020
The invention discloses a wind power output typical scene generation method based on BIRCH clustering and a Wasserstein distance, and the method comprises the...
PatentAvailable Online
Preview
Cite this item Email this item Save this item More actions
2020 14 online OPEN ACCESS
Fault diagnosis method for deep adversarial migration network based on Wasserstein distance
by SHI YONGFANG; XU PENGFEI; HUANG JINGKUN ; More...
03/2020
The invention discloses a fault diagnosis method for a deep adversarial migration network based on a Wasserstein distance. The distance of the feature...
PatentAvailable Online
2020 15 online OPEN ACCESS
基于Wasserstein距离的人脸性别判别算法
04/2020 ...
PatentAvailable Online
2020 16
online
OPEN ACCESS
基于信号分布Wasserstein距离度量的Wi-Fi室内定位方法
10/2020 ...
PatentAvailable Online
2020 17 online OPEN ACCESS
一种基于Wasserstein GAN的光伏阵列故障诊断方法
05/2020
本发明涉及一种基于Wasserstein GAN的光伏阵列故障诊断方法，首先对光伏阵列电流、电压时序数据进行采集；接着将获取的光伏阵列时序电流与时序电压数据绘制为曲线图形并保存为样本；然后设计Wasserstein GAN网络中的鉴别器D与生成器G；然后训练Wasserstein...
PatentAvailable Online
Preview
2020 18
by ZHAO JIANYANG; SHAN JINGSONG; DING WEIHONG ; More...
07/2020
The invention relates to the technical field of halogen conveying pipeline detection, and discloses an algorithm for solving imbalance of leakage data of a...
PatentAvailable Online
2020 19
一种基于WGAN的超参数动态调整方法
09/2020
PatentAvailable Onlin
2020 20
online
OPEN ACCESS
Building energy consumption prediction method based on WGAN algorithm and monitoring and...
by LU YOU; WANG ZHECHAO; WU HONGJIE ; More...
05/2020
The invention relates to a building energy consumption prediction method based on a WGAN algorithm and a building energy consumption monitoring and prediction...
PatentAvailable Online
2020 21
online
OPEN ACCESS
基于改进WGAN-GP的多波段图像同步融合与增强方法
09/2020
PatentAvailable Online
2020 22
Wasserstein barycenter model ensembling
US US20200342361A1 Youssef Mroueh International Business Machines Corporation
Priority 2019-04-29 • Filed 2019-04-29 • Published 2020-10-29
10 . The system according to claim 9 , further comprising inputting side information into the barycenter, wherein the barycenter comprises a Wasserstein barycenter with a Wasserstein distance metric. 11 . The system according to claim 9 , further comprising a plurality of the barycenters to determine …
2020 23
Difference privacy greedy grouping method adopting Wasserstein distance
CN CN112307514A 杨悦 哈尔滨工程大学
Priority 2020-11-26 • Filed 2020-11-26 • Published 2021-02-02
1. A differential privacy greedy grouping method adopting Wasserstein distance is characterized by comprising the following steps: step 1: reading a data set D received at the ith time point i ； Step 2: will D i Data set D released from last time point i-1 Performing Wasserstein distance similarity …
2020 24
Wi-Fi indoor positioning method based on signal distribution Wasserstein …
CN CN111741429A 周牧 重庆邮电大学
Priority 2020-06-23 • Filed 2020-06-23 • Published 2020-10-02
2. The Wi-Fi indoor positioning method based on the signal distribution Wasserstein distance metric according to claim 1, wherein said ninth step comprises the steps of: step nine (one), w corresponding to each RP m,n Sequencing all RPs from small to large to obtain an RP sequencing set u related to …
2020 25
Wasserstein distance-based image rapid enhancement method
CN CN111476721A 丰江帆 重庆邮电大学
Priority 2020-03-10 • Filed 2020-03-10 • Published 2020-07-31
4. The Wasserstein distance-based image rapid enhancement method according to claim 3, characterized in that: in step S21, the motion-blurred image has 256 features, including texture features, color features, and edge features. 5. The Wasserstein distance-based image rapid enhancement method …
2020 26
Patent Number: US2020342361-A1
Patent Assignee: INT BUSINESS MACHINES CORP
Inventor(s): MROUEH Y; DOGNIN P L; MELNYK I; et al.
2020 27
Wasserstein-based high-energy image synthesis method and device for generating …
CN CN112634390A 郑海荣 深圳先进技术研究院
Priority 2020-12-17 • Filed 2020-12-17 • Published 2021-04-09
updating the preset generation countermeasure network model based on the first loss value and the first judgment result until the preset generation countermeasure network model converges, and determining the converged preset generation countermeasure network model as the Wasserstein generation …
2020 78
Patent Number: US2021281361-A1
Patent Assignee: US SEC OF NAVY
2020 79
Wasserstein distance-based image rapid enhancement method
CN CN111476721A 丰江帆 重庆邮电大学
Priority 2020-03-10 • Filed 2020-03-10 • Published 2020-07-31
4. The Wasserstein distance-based image rapid enhancement method according to claim 3, characterized in that: in step S21, the motion-blurred image has 256 features, including texture features, color features, and edge features. 5. The Wasserstein distance-based image rapid enhancement method …
2020 80
Patent Number: CN107590531-A
Patent Assignee: UNIV SOUTH CHINA TECHNOLOGY
Inventor(s): ZHOU Z; LI L.
2020 81
Wi-Fi indoor positioning method based on signal distribution Wasserstein
distance measurement.
CN CN111741429A 周牧 重庆邮电大学
Priority 2020-06-23 • Filed 2020-06-23 • Published 2020-10-02
2. The Wi-Fi indoor positioning method based on the signal distribution Wasserstein distance metric according to claim 1, wherein said ninth step comprises the steps of: step nine (one), w corresponding to each RP m,n Sequencing all RPs from small to large to obtain an RP sequencing set u related to …
2020 82
High-energy image synthesis method and device based on wasserstein generative …
WO WO2022126480A1 郑海荣 深圳先进技术研究院
Filed 2020-12-17 • Published 2022-06-23
The preset generative adversarial network model is updated based on the first loss value and the first discrimination result until the preset generative adversarial network model converges, and the converged preset generative adversarial network model is determined as the Wasserstein generative …
2020 83
Difference privacy greedy grouping method adopting Wasserstein distance
CN CN112307514A 杨悦 哈尔滨工程大学
Priority 2020-11-26 • Filed 2020-11-26 • Published 2021-02-02
1. A differential privacy greedy grouping method adopting Wasserstein distance is characterized by comprising the following steps: step 1: reading a data set D received at the ith time point i ； Step 2: will D i Data set D released from last time point i-1 Performing Wasserstein distance similarity …
2020 84
System and Method for Generaring Highly Dense 3D Point Clouds using Wasserstein …
KR20220088216A 권준석 중앙대학교 산학협력단
Filed 2020-12-18 • Published 2022-06-27
The present invention generates a high-resolution 3D point cloud using a Wasserstein distribution to generate a set of several 3D points by generating several input vectors from a prior distribution and expressing it as a Wasserstein distribution A prior distribution input unit for inputting a …
2020 85
Multi-band image synchronous fusion and enhancement method based on improved WGAN-GP
CN CN111696066A 李大威 中北大学
Priority 2020-06-13 • Filed 2020-06-13 • Published 2020-09-22
1. The multiband image synchronous fusion and enhancement method based on the improved WGAN-GP is characterized by comprising the following steps of: designing and constructing a generation countermeasure network: generating a countermeasure network into a generator model and a discriminator model;
2020 86
Non-linear industrial process modeling method based on WGANs data enhancement
CN CN112966429A 褚菲 中国矿业大学
Priority 2020-08-11 • Filed 2020-08-11 • Published 2021-06-15
2. The WGANs data enhancement-based nonlinear industrial process modeling method of claim 1, wherein: the step B comprises the following steps: preprocessing the data set acquired in the step A, and specifically comprises the following steps: 1) the initial acquisition data comprises industrial …
22020 87
… attack flow data enhancement method and system combining self-encoder and WGAN
CN CN112688928A 姚叶鹏 中国科学院信息工程研究所
Priority 2020-12-18 • Filed 2020-12-18 • Published 2021-04-20
The invention discloses a network attack flow data enhancement method and system combining a self-encoder and a WGAN, which relate to the field of network space security, abnormal flow detection of a communication network and the field of artificial intelligence.
2020 88. patent
Non-linear industrial process modeling method based on WGANs data enhancement
CN CN112966429A 褚菲 中国矿业大学
Priority 2020-08-11 • Filed 2020-08-11 • Published 2021-06-15
2. The WGANs data enhancement-based nonlinear industrial process modeling method of claim 1, wherein: the step B comprises the following steps: preprocessing the data set acquired in the step A, and specifically comprises the following steps: 1) the initial acquisition data comprises industrial …
2020 89. patent
Difference privacy greedy grouping method adopting Wasserstein distance
CN CN112307514A 杨悦 哈尔滨工程大学
Priority 2020-11-26 • Filed 2020-11-26 • Published 2021-02-02
1. A differential privacy greedy grouping method adopting Wasserstein distance is characterized by comprising the following steps: step 1: reading a data set D received at the ith time point i ； Step 2: will D i Data set D released from last time point i-1 Performing Wasserstein distance similarity …
2020 90. patent
Wi-Fi indoor positioning method based on signal distribution Wasserstein …
CN CN111741429B 周牧 重庆邮电大学
Priority 2020-06-23 • Filed 2020-06-23 • Granted 2022-05-03 • Published 2022-05-03
1. the Wi-Fi indoor positioning method based on signal distribution Wasserstein distance measurement is characterized by comprising the following steps of: step one, off-line stage, the Wi-Fi received signal from the mth AP at the nth Reference Point (RP) is strengthenedThe sequence of degrees ( …
2020 91. patent
Wasserstein distance-based depth domain adaptive image classification method
CN CN111428803A 吴强 山东大学
Priority 2020-03-31 • Filed 2020-03-31 • Published 2020-07-17
The invention provides a Wasserstein distance-based depth domain adaptive image classification method and device and a computer-readable storage medium. First, features are extracted using a convolution structure. Secondly, the number of features is reduced by adopting layer-by-layer mapping of the …
2020 92. patent
Wasserstein distance-based image rapid enhancement method
CN CN111476721B 丰江帆 重庆邮电大学
Priority 2020-03-10 • Filed 2020-03-10 • Granted 2022-04-29 • Published 2022-04-29
5. The Wasserstein distance-based image rapid enhancement method according to claim 1, characterized in that: the up-samplin
2020 93 . 2020-2023
… and device for generating countermeasure network model based on Wasserstein
CN112634390B 郑海荣 深圳先进技术研究院
Filed 2020-12-17 • Granted 2023-06-13 • Published 2023-06-13
the Wasserstein generation countermeasure network model is obtained through training of a preset generation countermeasure network model based on a low-energy image sample, a standard high-energy image and a preset loss function, and the Wasserstein generation countermeasure network model comprises …
2020 94. patent
Difference privacy greedy grouping method adopting Wasserstein distance
CN CN112307514A 杨悦 哈尔滨工程大学
Priority 2020-11-26 • Filed 2020-11-26 • Published 2021-02-02
1. A differential privacy greedy grouping method adopting Wasserstein distance is characterized by comprising the following steps: step 1: reading a data set D received at the ith time point i ； Step 2: will D i Data set D released from last time point i-1 Performing Wasserstein distance similarity …
2020 95
Wi-Fi indoor positioning method based on signal distribution Wasserstein …
CN CN111741429B 周牧 重庆邮电大学
Priority 2020-06-23 • Filed 2020-06-23 • Granted 2022-05-03 • Published 2022-05-03
1. the Wi-Fi indoor positioning method based on signal distribution Wasserstein distance measurement is characterized by comprising the following steps of: step one, off-line stage, the Wi-Fi received signal from the mth AP at the nth Reference Point (RP) is strengthenedThe sequence of degrees ( …
<—102 till 2019
+ 95 for 2020
=197 till 2020
end 2020 e20
start 2021
115 patents in 2021
2021 1
Patent Number: DE102019210270-A1 US2020372297-A1 CN111985638-A
Patent Assignee: BOSCH GMBH ROBERT
Inventor(s): TERJEK D.
2021 2
Patent Number: WO2021022850-A1
Patent Assignee: HUAWEI TECHNOLOGIES CO LTD
Inventor(s): GE Y; SHI W; TONG W.
2021 3
Palo Alto Research Center Incorporated issued patent titled "Object shape regression using wasserstein...
News Bites - Private Companies, Mar 11, 2021
Newspaper ArticleCitation Online
Preview Cite this item Email this item Save this item More actions
Palo Alto Research Center Obtains Patent for Object Shape Regression Using Wasserstein Distance
Global IP News. Optics & Imaging Patent News; New Delhi [New Delhi]09 Mar 2021.
Palo Alto Research Center Obtains Patent for Object Shape Regression Using Wasserstein Distance
Global IP News. Optics & Imaging Patent News, Mar 9, 2021
Newspaper ArticleFull Text Online
Preview Cite this item Email this item Save this item More actions
Palo Alto Research Center Obtains Patent for Object Shape Regression Using Wasserstein Distance
Palo Alto Research Center Obtains Patent for Object Shape Regression Using Wasserstein Distance
2021 4
(03/10/2021). "US Patent Issued to Palo Alto Research Center on March 9 for "Object shape regression using wasserstein distance" (California, New York Inventors)". US Fed News Service, Including US State News US Patent Issued to Palo Alto Research Center on March 9 for "Object shape regression using wasser...
US Fed News Service, Including US State News, Mar 10, 2021
Newspaper ArticleCitation Online
US Fed News Service, Including US State News, Mar 10, 2021
2021 5
Patent Number: US2021033536-A1
Patent Assignee: UNIV WASHINGTON; LEW M; NEHORAI A; et. al
Inventor(s): LEW M; NEHORAI A; MAZIDISHARFABADI H.
WASSERSTEIN F-TESTS AND CONFIDENCE BANDS FOR THE FRECHET REGRESSION OF DENSITY RESPONSE CURVES
By: Petersen, Alexander; Liu, Xi; Divani, Afshin A.
ANNALS OF STATISTICS Volume: 49 Issue: 1 Pages: 590-611 Published: FEB 2021
2021 6
Object shape regression using wasserstein distance
by Palo Alto Research Center Incorporated
03/2021
One embodiment can provide a system for detecting outlines of objects in images. During operation, the system receives an image that includes at least one...
PatentAvailable Online
2021 7
01/2021
크리스토펠 함수의 과다한 연산량을 커널화 와서스타인 오토인코더를 이용하여 개선한 고차원 비지도 이상 탐지 학습 방법이 개시된다. 즉, (a) 학습 장치가, 복수 개의 성분을 가진 적어도 하나의 학습 데이터 매트릭스가 획득되면, 적어도 하나의 와서스타인 인코딩 네트워크로 하여금, 각각의...
2021 8 OPEN ACCESS
02/2021
...
PatentCitation Online
Preview
Cite this item Email this item Save this item More actions
[Chinese A Differential Privacy Greedy Grouping Method Using Wasserstein Distance'
2021 9 OPEN ACCESS
一种基于Wasserstein距离的深度对抗迁移网络的故障诊断方法
02/2021
...
PatentCitation Online
Preview
Cite this item Email this item Save this item More actions
[Chinese A Fault Diagnosis Method Based on Wasserstein Distance for Deep Confrontation Migration Network]
2021 10 OPEN ACCESS
LEARNING METHOD AND LEARNING DEVICE FOR HIGH-DIMENSION UNSUPERVISED ANOMALY DETECTION USING
KERNALIZED WASSERSTEIN...
by PAIK MYUNGHEE CHO; CHANG HYUN WOONG; KIM YOUNG GEUN
01/2021
크리스토펠 함수의 과다한 연산량을 커널화 와서스타인 오토인코더를 이용하여 개선한 고차원 비지도 이상 탐지 학습 방법이 개시된다. 즉, (a) 학습 장치가, 복수 개의 성분을 가진 적어도 하나의 학습 데이터 매트릭스가 획득되면, 적어도 하나의 와서스타인 인코딩 네트워크로 하여금, 각각의...
PatentCitation Online
Preview
2021 11
Patent Number: CN112488956-A
Patent Assignee: UNIV NANJING INFORMATION SCI & TECHNOLOG
Inventor(s): FANG W; GU E; WANG W.
Select record9
2021 12
Patent Number: CN112258425-A
Patent Assignee: CHINA TELECOM WANWEI INFORMATION TECHNOL
Inventor(s): ZHAO W; WANG Z; HAO D; et al.
2021 13
Wasserstein space-based visual dimension reduction method
CN CN112765426A 秦红星 重庆邮电大学
Priority 2021-01-18 • Filed 2021-01-18 • Published 2021-05-07
6. The visualization dimension reduction method based on Wasserstein space according to claim 5, wherein: the S5 specifically includes: note P i Is the ith row, Q, of the matrix P i Similarly, considered as a column vector; w represents the 1-Wasserstein distance and the dual form of the loss function …
2021 14 OPEN ACCESS
一种基于WGAN网络进行图像修复的方法
03/21
[Chinese A method of image restoration based on WGAN network]
Patent Available Online
2021 15
合自编码器和WGAN的网络攻击流量数据增强方法及系统
Chinese Network attack flow data enhancement method and system based on self-encoder and WGAN]
04/2021
PatentAvailable Online
2021 16 OPEN ACCESS
[Chinese A Visualized Dimensionality Reduction Method Based on Wasserstein Space]
Visual dimension reduction method based on Wasserstein space
05/2021
PatentAvailable Online
2021 patent 17
Patent Number: CN113505477-A
Patent Assignee: UNIV NORTHWEST NORMAL
Inventor(s): XU J; ZHANG Q; LIU Y; et al.
Inventor(s): XU J; ZHANG Q; LIU Y; et al.
CN10725654 29 Jun 2021
2021 patent 18
Patent Number: CN113298297-A
Patent Assignee: UNIV INNER MONGOLIA TECHNOLOGY
Inventor(s): WANG Y; WU Y; XU H; et al.
CN10503783 10 May 2021
2021 19
Patent Number: CN113276119-A
Patent Assignee: TSINGHUA SHENZHEN INT GRADUATE SCHOOL
Inventor(s): XIA C; LIANG B; WANG X; et al.
CN10571993 25 May 2021
1021 20
Patent Number: CN113205461-A
Patent Assignee: SHANGHAI HUIHU INFORMATION TECHNOLOGY CO LTD
Inventor(s): LI S; LI Y; PAN J.
CN10360991 02 Apr 2021
2021 21
Patent Number: CN113126082-A
Patent Assignee: UNIV SUN YAT-SEN
Inventor(s): XU S; LEI X; ZHU N; et al.
CN10347426 31 Mar 2021
2021 22
CN113554645-ACN113554645-B
Inventor(s) HOU D; GUO J and HANG T
Assignee(s) CHANGZHOU MICRO-INTELLIGENCE TECHNOLOGY
Derwent Primary Accession Number
2021-C2916J
2021 23
CN112488956-A
Inventor(s) FANG W; GU E and WANG W
Assignee(s) UNIV NANJING INFORMATION SCI & TECHNOLOG
Derwent Primary Accession Number
2021-30425T
2021 24
CN113537467-A
Inventor(s) TIAN P; SUN J; (...); JIANG L
Assignee(s) UNIV NANJING POST & TELECOM
Derwent Primary Accession Number
2021-C5057X
2021 25
CN113569632-A
Inventor(s) LI Y; BAI X; (...); ZHOU F
Assignee(s) PLA NO 32203 TROOPS and UNIV XIDIAN
Derwent Primary Accession Number
2021-C64797
2021 26
CN112994115-A
Inventor(s) MA Y; FU Y; (...); ZHAO S
Assignee(s) UNIV NORTH CHINA ELECTRIC POWER
Derwent Primary Accession Number
2021-721792
2021 27
CN112966429-A
Inventor(s) CHU F; DING P; (...); MA X
Assignee(s) UNIV CHINA MINING & TECHNOLOGY BEIJING
Derwent Primary Accession Number
2021-68724L
2021 28
CN113673347-A
Inventor(s) YOU Y; HE G; (...); ZHU L
Assignee(s) UNIV HANGZHOU DIANZI
Derwent Primary Accession Number
2021-D7113L
2021 29
US2021319847-A1WO2021211233-A1
Inventor(s) DURDANOVIC I; GRAF H P; (...); MIN R
Assignee(s) NEC LAB AMERICA INC
Derwent Primary Accession Number
2021-B70701
2021 30
US11188795-B1
Inventor(s) ULBRICHT D and LEE C
Assignee(s) APPLE INC
Derwent Primary Accession Number
2021-D7162W
2021 31
CN112946600-A
Inventor(s) WANG P; LIU H; (...); JIU B
Assignee(s) UNIV XIDIAN
Derwent Primary Accession Number
2021-70971U
2021 32
CN112634390-A
Inventor(s) ZHENG H; HU Z; (...); ZHOU H
Assignee(s) SHENZHEN INST ADVANCED TECHNOLOGY
Derwent Primary Accession Number
2021-41197G
2021 33
CN112837356-A
Inventor(s) WANG Y; PENG W; (...); WU H
Assignee(s) UNIV HUNAN
Derwent Primary Accession Number
2021-60602R
2021 34
CN113722893-A
Inventor(s) WANG Z
Assignee(s) UNIV CHINA PETROLEUM BEIJING
Derwent Primary Accession Number
2021-E61157
2021 35
CN112765426-A
Assignee(s) UNIV CHONGQING POSTS & TELECOM
Derwent Primary Accession Number
2021-525281
2021 36
US2021281361-A1
Inventor(s) CRANCH G A; MENKART N; (...); HUTCHINSON M N
Assignee(s) US SEC OF NAVY
Derwent Primary Accession Number
2021-A3597D
2021 37
US11049605-B1
Inventor(s) PETERS F L
Assignee(s) CORTERY AB
Derwent Primary Accession Number
2021-72556R
2021 38
CN113536116-A
Inventor(s) XIE H; ZUO Z; (...); NIE J
Assignee(s) UNIV CHINA OCEAN
Derwent Primary Accession Number
2021-C4660T
2021 39
CN113486931-A
Inventor(s) GE H; ZHANG Q; (...); CHEN J
Assignee(s) UNIV NANJING AERONAUTICS & ASTRONAUTICS
Derwent Primary Accession Number
2021-B8909U
2021 40
CN113536697-A
Inventor(s) ZHAO Z; XU J and SHEN Y
Assignee(s) UNIV JIANGNAN
Derwent Primary Accession Number
2021-C4734E
2021 41
CN113537313-A
Inventor(s) CHEN Z; ZHANG L; (...); XU Y
Assignee(s) UNIV HANGZHOU DIANZI
Derwent Primary Accession Number
2021-C40982
2021 42
CN113505477-A
Inventor(s) XU J; ZHANG Q; (...); GAO S
Assignee(s) UNIV NORTHWEST NORMAL
Derwent Primary Accession Number
2021-C05218
2021 43
US2021319847-A1WO2021211233-A1
Inventor(s) DURDANOVIC I; GRAF H P; (...); MIN R
Assignee(s) NEC LAB AMERICA INC
Derwent Primary Accession Number
2021-B70701
2021 44
CN112712857-A
Inventor(s) ZHU L; DING J; (...); ZHUANG W
Assignee(s) UNIV BEIJING INFORMATION SCI & TECHNOLOG
Derwent Primary Accession Number
2021-51255C
2021 45
CN112837356-A
Inventor(s) WANG Y; PENG W; (...); WU H
Assignee(s) UNIV HUNAN
Derwent Primary Accession Number
2021-60602R
2021 46
CN113553624-A
Inventor(s) NIE P; HAN Z; (...); YANG Z
Assignee(s) UNIV TIANJIN
Derwent Primary Accession Number
2021-C5045Q
2021 47
CN113298297-A
Inventor(s) WANG Y; WU Y; (...); LIU G
Assignee(s) UNIV INNER MONGOLIA TECHNOLOGY
Derwent Primary Accession Nu
CN113505477-A
Inventor(s) XU J; ZHANG Q; (...); GAO S
Assignee(s) UNIV NORTHWEST NORMAL
Derwent Primary Accession Number
2021-C05218
2021 49
Wasserstein space-based visual dimension reduction method
CN CN112765426A 秦红星 重庆邮电大学
Priority 2021-01-18 • Filed 2021-01-18 • Published 2021-05-07
6. The visualization dimension reduction method based on Wasserstein space according to claim 5, wherein: the S5 specifically includes: note P i Is the ith row, Q, of the matrix P i Similarly, considered as a column vector; w represents the 1-Wasserstein distance and the dual form of the loss function …
2021 50
… for high-dimension unsupervised anomaly detection using kernalized wasserstein …
KR KR102202842B1 백명희조 서울대학교산학협력단
Priority 2019-08-13 • Filed 2019-08-13 • Granted 2021-01-14 • Published 2021-01-14
The present invention relates to a learning method and a learning apparatus for high-dimension unsupervised abnormality detection using a kernalized Wasserstein autoencoder to decrease excessive computations of a Christoffel function, and a test method and a test apparatus using the same.
2021 51
Industrial anomaly detection method and device based on WGAN
CN CN113554645A 杭天欣 常州微亿智造科技有限公司
Priority 2021-09-17 • Filed 2021-09-17 • Published 2021-10-26
constructing an original WGAN model, wherein the original WGAN model comprises a generator and a discriminator; inputting the first data set and the second data set into the original WGAN model to train the original WGAN model to obtain the WGAN anomaly detection model, wherein the first data set …
Patent Number: CN112634390-A
Patent Assignee: SHENZHEN INST ADVANCED TECHNOLOGY
Inventor(s): ZHENG H; HU Z; LIANG D; et al.
2021 53
Method for generating biological Raman spectrum data based on WGAN (WGAN) …
CN CN112712857A 祝连庆 北京信息科技大学
Priority 2020-12-08 • Filed 2020-12-08 • Published 2021-04-27
1. A method of generating bio-raman spectral data based on a WGAN antagonistic generation network, the method comprising the steps of: a, extracting part of Raman spectrum data from a Raman spectrum database to serve as a real sample, and preprocessing the Raman spectrum data; b, creating a normal …
Method for generating biological Raman spectrum data based on WGAN (WGAN) …
CN CN112712857A 祝连庆 北京信息科技大学
Priority 2020-12-08 • Filed 2020-12-08 • Published 2021-04-27
The invention provides a method for generating biological Raman spectrum data based on a WGAN antagonistic generation network, which comprises the following steps: step a, extracting partial Raman spectrum data from a Raman spectrum database to
2021 54
Method for image restoration based on WGAN network
CN CN112488956A 方巍 南京信息工程大学
Priority 2020-12-14 • Filed 2020-12-14 • Published 2021-03-12
3. The method for image inpainting based on WGAN network of claim 1, wherein in the step (1.3), through optimizing parameters and function algorithm: wherein, the activation function is specifically described as follows: 4. the method for image restoration based on WGAN network of claim 1, wherein …
2021 55
WGAN-based fuzzy aerial image processing method
CN CN113538266A 李业东 南京国电南自电网自动化有限公司
Priority 2021-07-07 • Filed 2021-07-07 • Published 2021-10-22
the fuzzy image processing model takes a WGAN network as a basic network and comprises a generator network and a discriminator network, wherein the generator network comprises a down-sampling network block and an up-sampling network block which are sequentially arranged, the discriminator network …
2021 56
Anti-disturbance image generation method based on WGAN-GP
CN CN113537467A 蒋凌云 南京邮电大学
Priority 2021-07-15 • Filed 2021-07-15 • Published 2021-10-22
2. The WGAN-GP-based disturbance rejection image generation method according to claim 1, wherein: target loss function L WGAN-GP The expression of the calculation is： In the formula (2), d (x) represents that the discriminator determines whether the x class label belongs to the class information in …
2021 57
New energy capacity configuration method based on WGAN scene simulation and …
CN CN112994115A 马燕峰 华北电力大学（保定）
Priority 2019-12-18 • Filed 2019-12-18 • Published 2021-06-18
A new energy capacity configuration method based on Wasserstein generation countermeasure network (WGAN) scene simulation and time sequence production simulation is characterized by mainly comprising the following specific steps: step 1, simulating a large number of wind and light resource …
2021 58
Road texture picture enhancement method coupling traditional method and WGAN-GP
CN113850855A 徐子金 北京工业大学
Filed 2021-08-27 • Published 2021-12-28
1. A road texture picture enhancement method coupling a traditional method and WGAN-GP is characterized in that a new high-quality texture picture is generated by utilizing a road surface macro texture picture obtained by a commercial handheld three-dimensional laser scanner through a traditional …
2021 59
Wind power output power prediction method based on isolated forest and WGAN …
CN CN113298297A 王永生 内蒙古工业大学
Priority 2021-05-10 • Filed 2021-05-10 • Published 2021-08-24
7. The isolated forest and WGAN network based wind power output power prediction method of claim 6, wherein the interpolation operation comprises the following steps: step 2.1, inputting the random noise vector z into a generator G to obtain a generated time sequence G (z), wherein G (z) is a …
2021 60
Wgan-based unsupervised multi-view three-dimensional point cloud joint …
WO CN WO2022165876A1 王耀南 湖南大学
Priority 2021-02-06 • Filed 2021-02-25 • Published 2022-08-11
A kind of unsupervised multi-view three-dimensional point cloud joint registration method based on WGAN according to claim 8, is characterized in that, described step S51 is specifically: The WGAN network trains the discriminator network f ω with the parameter ω and the last layer is not a …
2021 61
… life prediction method based on improved residual error network and WGAN
CN CN113536697A 沈艳霞 江南大学
Priority 2021-08-24 • Filed 2021-08-24 • Published 2021-10-22
8. The improved residual network and WGAN based bearing remaining life prediction method of claim 1, wherein: in step S3, the WGAN model uses the Wasserstein distance to measure the distribution difference between two feature sets, and optimizes the generator under the domain discriminator to …
2021 62
Process industry soft measurement data supplementing method based on SVAE-WGAN
CN CN113505477B 高世伟 西北师范大学
Priority 2021-06-29 • Filed 2021-06-29 • Granted 2022-05-20 • Published 2022-05-20
1. A SVAE-WGAN-based process industry soft measurement data supplementing method in the industrial field is characterized by comprising the following steps: step 1: determining input and output of a model according to an industrial background, selecting a proper training data set, inputting time …
2021 63
Patent Number: CN112906976-A
Patent Assignee: UNIV YANSHAN
Inventor(s): HAO X; LIU L; HUANG G; et al.
2021 64
Method for constructing radar HRRP database based on WGAN-GP
CN CN112946600A 王鹏辉 西安电子科技大学
Priority 2021-03-17 • Filed 2021-03-17 • Published 2021-06-11
The invention discloses a WGAN-GP-based HRRP database construction method, which comprises the following steps: (1) generating a training set; (2) constructing a WGAN-GP network; (3) generating a sample set; (4) training the WGAN-GP network; (5) and completing the construction of the HRRP database.
2021 65
Mechanical pump small sample fault diagnosis method based on WGAN-GP-C and …
CN CN114037001A 王雪仁 中国人民解放军92578部队
Priority 2021-10-11 • Filed 2021-10-11 • Published 2022-02-11
(2.3) when the WGAN-GP-C which is trained is used for generating a sample, screening the generated sample data; (2.4) the quality of the generated sample data is evaluated by adopting the maximum mean difference MMD and the model is adjusted according to the maximum mean difference MMD. 5. The WGAN …
2021 66
sEMG data enhancement method based on BiLSTM and WGAN-GP networks
CN CN114372490A 方银锋 杭州电子科技大学
Priority 2021-12-29 • Filed 2021-12-29 • Published 2022-04-19
A sEMG data enhancement method based on a BilSTM and WGAN-GP network comprises the following specific steps: s1, collecting surface electromyogram signals and preprocessing the signals; step S2, standardizing the preprocessed real electromyographic data, and dividing the standardized real …
2021 67
… local surface slow-speed moving object classification method based on WGAN
CN CN113569632A 周峰 西安电子科技大学
Priority 2021-06-16 • Filed 2021-06-16 • Published 2021-10-29
5. The method for classifying a small sample local area slow moving target according to claim 4, wherein in the substep 2.2, the WGAN introduces Wasserstein distance to measure the difference between the generated data distribution and the real data distribution when performing network training;
2021 68
Unbalanced data set analysis method based on WGAN training convergence
CN CN113537313A 许艳萍 杭州电子科技大学
Priority 2021-06-30 • Filed 2021-06-30 • Published 2021-10-22
1. An imbalance data set analysis method based on WGAN training convergence is characterized in that: the method specifically comprises the following steps: step one, data acquisition and pretreatment Collecting network security data, dividing the network security data into a multi-class data …
2021 69
WGAN dynamic punishment-based network security unbalance data set analysis …
CN CN114301667A 许艳萍 杭州电子科技大学
Priority 2021-12-27 • Filed 2021-12-27 • Published 2022-04-08
2. The method of claim 1 wherein the method of analyzing an imbalance data set based on WGAN training convergence comprises: the imbalance IR and oversampling ratio R between different classes of data are defined as: wherein N is + And N - Respectively the quantity of the multi-class data and the small …
2021 70
Data depth enhancement method based on WGAN-GP data generation and Poisson …
CN CN114219778A 侯越 北京工业大学
Priority 2021-12-07 • Filed 2021-12-07 • Published 2022-03-22
The invention discloses a data depth enhancement method based on WGAN-GP data generation and Poisson fusion, wherein WGAN-GP is a generation confrontation network with gradient punishment and is a generation model based on a game idea, and the generation model comprises two networks, namely a …
2021 71
Clothing attribute editing method based on improved WGAN
CN CN113793397A 张建明 浙江大学
Priority 2021-07-30 • Filed 2021-07-30 • Published 2021-12-14
1. A garment attribute editing method based on improved WGAN comprises a training stage and a testing stage, wherein the training stage is optimized in a supervised learning mode; in the testing stage, the converged network is adopted to generate clothing attributes; the method is characterized by …
2021 72
Micro-seismic record denoising method based on improved WGAN network and CBDNet
CN CN114218982A 盛冠群 三峡大学
Priority 2021-11-26 • Filed 2021-11-26 • Published 2022-03-22
1. The microseism record denoising method based on the improved WGAN network and the CBDNet is characterized by comprising the following steps of: the method comprises the following steps: collecting micro-seismic data; step two: generating forward simulation signals under different dominant …
2021 73
Rapid identification method for ship attachment based on WGAN-GP and YOLO
CN CN113792785A 陈琦 上海理工大学
Priority 2021-09-14 • Filed 2021-09-14 • Published 2021-12-14
wherein L is the objective function of WGAN-GP; is the loss function of WGAN at Wasserstein distance; is a gradient penalty that is applied independently for each sample on a WGAN basis. 5. The WGAN-GP and YOLO based ship body attachment rapid identification method as claimed in claim 1, wherein …
2021 74
One-dimensional time sequence data amplification method based on WGAN
CN CN113627594A 孙博 北京航空航天大学
Priority 2021-08-05 • Filed 2021-08-05 • Published 2021-11-09
4. The method of claim 1, wherein the WGAN-based one-dimensional time series data augmentation method comprises: in the "network model constructed by training" described in the third step, gaussian noise z to n (μ, σ) having a mean value of 0 and a standard deviation of 1 is used, μ is 0, and σ is …
2021 75
Power system harmonic law calculation method based on WGAN
CN CN114217132A 梅文波 江苏弈赫能源科技有限公司
Priority 2021-11-11 • Filed 2021-11-11 • Published 2022-03-22
2. The WGAN-based electric power system harmonic law calculation method according to claim 1, wherein a sampling frequency of the current data in the first step is two times or more of a highest frequency in the signal. 3. The WGAN-based power system harmonic law calculation method according to …
2021 76
Road texture picture enhancement method coupling traditional method and WGAN-GP
CN CN113850855A 徐子金 北京工业大学
Priority 2021-08-27 • Filed 2021-08-27 • Published 2021-12-28
1. A road texture picture enhancement method coupling a traditional method and WGAN-GP is characterized in that a new high-quality texture picture is generated by utilizing a road surface macro texture picture obtained by a commercial handheld three-dimensional laser scanner through a traditional …
2021 77
Anti-disturbance image generation method based on WGAN-GP
CN CN113537467A 蒋凌云 南京邮电大学
Priority 2021-07-15 • Filed 2021-07-15 • Published 2021-10-22
2. The WGAN-GP-based disturbance rejection image generation method according to claim 1, wherein: target loss function L WGAN-GP The expression of the calculation is： In the formula (2), d (x) represents that the discriminator determines whether the x class label belongs to the class information in …
2021 78
WGAN-GP privacy protection system and method based on improved PATE
CN CN113553624A 杨张妍 天津大学
Priority 2021-07-30 • Filed 2021-07-30 • Published 2021-10-26
6. The WGAN-GP privacy protection system based on an improved PATE as claimed in claim 2, wherein in the student discriminator module: the student arbiter generates a sample through analysis and a prediction label output by the conditional differential privacy aggregator corresponding to the sample …
2021 79
Wind power output power prediction method based on isolated forest and WGAN …
CN CN113298297A 王永生 内蒙古工业大学
Priority 2021-05-10 • Filed 2021-05-10 • Published 2021-08-24
7. The isolated forest and WGAN network based wind power output power prediction method of claim 6, wherein the interpolation operation comprises the following steps: step 2.1, inputting the random noise vector z into a generator G to obtain a generated time sequence G (z), wherein G (z) is a …
2021 80
Micro-seismic record denoising method based on improved WGAN network and CBDNet
CN CN114218982A 盛冠群 三峡大学
Priority 2021-11-26 • Filed 2021-11-26 • Published 2022-03-22
Micro-seismic record denoising method based on improved WGAN network and CBDNet Technical Field The invention relates to a microseism monitoring technology, in particular to a microseism record denoising method based on an improved WGAN network and CBDNet. Background The micro-seismic monitoring …
2021 81
Rapid identification method for ship attachment based on WGAN-GP and YOLO
CN CN113792785A 陈琦 上海理工大学
Priority 2021-09-14 • Filed 2021-09-14 • Published 2021-12-14
Rapid identification method for ship attachment based on WGAN-GP and YOLO Technical Field The invention relates to the technical field of ship body attachment cleaning, in particular to a method for quickly identifying ship body attachments based on WGAN-GP and YOLO. Background The ocean occupies …
CN CN113378959B 潘杰 中国矿业大学
Priority 2021-06-24 • Filed 2021-06-24 • Granted 2022-03-15 • Published 2022-03-15
wherein L is WGAN Representing the loss of the production countermeasure network, D (v, s) representing the result of the visual features v and the original semantic features s being fed to the discriminator network D, indicating that a visual trait is to be synthesized And the result of the original …
Early fault detection method based on Wasserstein distance
CN CN114722888A 曾九孙 中国计量大学
Priority 2021-10-27 • Filed 2021-10-27 • Published 2022-07-08
3. The early fault detection method based on Wasserstein distance as claimed in claim 2, characterized in that, by constructing dual form of model, the model is solved by Riemann block coordinate descent method, comprising the following steps: s2.1, adding two Lagrange multipliers to construct a …
2021 83
Wasserstein distance-based motor imagery electroencephalogram migration …
CN CN113010013A 罗浩远 华南理工大学
Priority 2021-03-11 • Filed 2021-03-11 • Published 2021-06-22
6. The Wasserstein distance-based motor imagery electroencephalogram migration learning method according to claim 1, wherein: in step 4), the Wasserstein distance training deep migration learning model is used, and the method comprises the following steps: 4.1) inputting the source domain data and …
2021 84
… method for generating countermeasure network based on conditional Wasserstein
CN CN114154405A 陈乾坤 东风汽车集团股份有限公司
Priority 2021-11-19 • Filed 2021-11-19 • Published 2022-03-08
3. The motor data enhancement method based on the conditional Wasserstein generation countermeasure network as claimed in claim 1, wherein the conditional Wasserstein generation countermeasure network is a combination of the conditional warerstein generation countermeasure network and the …
2021 85
Wasserstein distance-based object envelope multi-view reconstruction and …
CN CN113034695A 何力 广东工业大学
Priority 2021-04-16 • Filed 2021-04-16 • Published 2021-06-25
7. The Wasserstein distance-based object envelope multi-view reconstruction and optimization method according to claim 5, wherein the specific process of step S4-3 is as follows: embedding the Wasserstein-based distance cost function into three-dimensional reconstruction, including: in equation (3) …
2021 86
Characteristic similarity countermeasure network based on Wasserstein distance
CN CN113673347A 祝磊 杭州电子科技大学
Priority 2021-07-20 • Filed 2021-07-20 • Published 2021-11-19
6. The Wasserstein distance-based characterized similar countermeasure network of claim 1, wherein in S5: obtaining the round-trip probability of the destination domain of the source domain comprises multiplying the resulting P st 、P ts The formula is as follows: P sts ＝P st P ts ； in the formula, P sts …
2021 87
Domain self-adaptive rolling bearing fault diagnosis method based on Wasserstein …
CN CN113239610A 王晓东 昆明理工大学
Priority 2021-01-19 • Filed 2021-01-19 • Published 2021-08-10
3. The implementation principle of the Wasserstein distance-based domain-adaptive rolling bearing fault diagnosis method according to claim 2 is characterized in that: StepA, extracting features through convolutional neural network, convolutional layer containing a filter w and an offset b, let X n …
2021 88
… robust optimization scheduling method based on improved Wasserstein measure
CN CN113962612A 刘鸿鹏 东北电力大学
Priority 2021-11-25 • Filed 2021-11-25 • Published 2022-01-21
2. The electric-heat combined system distribution robust optimization scheduling method based on improved Wasserstein measure of claim 1, characterized in that power error data set is predicted according to historical wind power Building an empirical distribution Where N is the total number of …
2021 89
Power system bad data identification method based on improved Wasserstein GA
CN CN114330486A 臧海祥 河海大学
Priority 2021-11-18 • Filed 2021-11-18 • Published 2022-04-12
5. The improved Wasserstein GAN-based power system bad data identification method as claimed in claim 1, wherein the training process of the C4.5 decision tree model in the step (5) comprises: firstly, a calculation formula for determining the sample information entropy in the C4.5 decision tree …
2021 90
Robot motion planning method and system based on graph Wasserstein self-coding …
CN CN113276119A 夏崇坤 清华大学深圳国际研究生院
Priority 2021-05-25 • Filed 2021-05-25 • Published 2021-08-20
8. The method for robot motion planning based on Wasserstein self-encoded network as claimed in claim 1, wherein step S2 comprises the following steps: s2-1, initializing encoder network parameter Q ψ And decoder network parameters Initializing a potential discriminator D τ (ii) a …
2021 91
Cross-domain recommendation method based on double-current sliced wasserstein …
CN CN113536116A 聂婕 中国海洋大学
Priority 2021-06-29 • Filed 2021-06-29 • Published 2021-10-22
The invention belongs to the technical field of cross-domain recommendation, and discloses a cross-domain recommendation method based on a double-current slotted Wasserstein self-encoder.
2021 92
Topic modeling method based on Wasserstein self-encoder and Gaussian mixture …
CN CN114417852A 刘洪涛 重庆邮电大学
Priority 2021-12-06 • Filed 2021-12-06 • Published 2022-04-29
5. The method for modeling a subject based on a Wasserstein self-encoder and a gaussian mixture distribution as a priori as claimed in any one of claims 1 to 4, wherein the step S4 specifically comprises: s41: decoding the theme distribution theta obtained in the step S2 to obtain Representing the …
2021 93
Distribution robust optimization method based on Wasserstein measurement and …
CN CN114243683A 侯文庭 周口师范学院
Priority 2021-11-23 • Filed 2021-11-23 • Published 2022-03-25
6. The distributed robust optimization method based on Wasserstein measurement and kernel density estimation as claimed in claim 5, wherein the objective function of the distributed robust block combination model in step S4 is: in the formula: SU i 、SD i Respectively starting and stopping expenses of …
2021 94 see 2020
System and method for unsupervised domain adaptation via sliced-wasserstein distance
AJ Gabourie, M Rostami, S Kolouri, K Kim - US Patent 11,176,477, 2021 - Google Patents
US11176477B2 - System and method for unsupervised domain adaptation via sliced-wasserstein
distance - Google Patents US11176477B2 - System and method for unsupervised …
Cited by 3 Related articles All 4 versions
2021 95 2021-2022
Industrial anomaly detection method and device based on WGAN
CN CN113554645B 杭天欣 常州微亿智造科技有限公司
Priority 2021-09-17 • Filed 2021-09-17 • Granted 2022-01-11 • Published 2022-01-11
performing anomaly detection on the screened image to be detected by adopting the WGAN anomaly detection model, specifically, performing data preprocessing on the screened image to be detected to obtain a secondary image to be detected, inputting the secondary image to be detected into the WGAN …
2021 96
Ship body attachment rapid identification method based on WGAN-GP and YOLO
ZHU DAQI ; CHU ZHENZHONG ; CHEN QI ; REN CHENHUI2021
OPEN ACCESS
Ship body attachment rapid identification method based on WGAN-GP and YOLO
No Online Access
2021 97
WGAN-based one-dimensional time series data augmentation method
FENG QIANG ; WU ZEYU ; YANG DEZHEN ; REN YI ; SUN BO ; WANG ZILI ; QIAN CHENG2021
OPEN ACCESS
WGAN-based one-dimensional time series data augmentation method
No Online Access
2021 98
Bearing residual life prediction method based on improved residual network and WGAN
SHEN YANXIA ; XU JIAJIE ; ZHAO ZHIPU2021
OPEN ACCESS
Bearing residual life prediction method based on improved residual network and WGAN
No Online Access
2021 99
≈∂çTIAN RAN ; GAO SHIWEI ; QIU SULONG ; ZHANG QINGSONG ; MA ZHONGYU ; LIU YANXING ; XU JINPENG2021
OPEN ACCESS
Process industrial soft measurement data supplement method based on SVAE-WGAN
No Online Access
2021 100
Wind power output power prediction method based on isolated forest and WGAN network
XU ZHIWEI ; LIU GUANGWEN ; WANG YONGSHENG ; XU HAO ; WU YUHAO ; SU XIAOMING2021
OPEN ACCESS
Wind power output power prediction method based on isolated forest and WGAN network
No Online Access
2021 101
Zhao, Yinan ; Tian, Shengwei ; Yu, Long ; Xing, YanSpectroscopy (Springfield, Or.), 2021, Vol.36 (4), p.28
Combining the WGAN and ResNeXt Networks to Achieve Data Augmentation and Classification of the FT-IR Spectra of Strawberries
Available Online
2021 102. patent
sEMG data enhancement method based on BiLSTM and WGAN-GP networks
CN CN114372490A 方银锋 杭州电子科技大学
Priority 2021-12-29 • Filed 2021-12-29 • Published 2022-04-19
A sEMG data enhancement method based on a BilSTM and WGAN-GP network comprises the following specific steps: s1, collecting surface electromyogram signals and preprocessing the signals; step
2021 103. patent
… robust optimization scheduling method based on improved Wasserstein measure
CN CN113962612A 刘鸿鹏 东北电力大学
Priority 2021-11-25 • Filed 2021-11-25 • Published 2022-01-21
An electric heating combined system distribution robust optimization scheduling method based on improved Wasserstein measure relates to the technical field of renewable energy scheduling in an electric heating combined system. The method aims to solve the problem that an uncertainty set …
2021 104
… method for generating countermeasure network based on conditional Wasserstein
CN CN114154405A 陈乾坤 东风汽车集团股份有限公司
Priority 2021-11-19 • Filed 2021-11-19 • Published 2022-03-08
3. The motor data enhancement method based on the conditional Wasserstein generation countermeasure network as claimed in claim 1, wherein the conditional Wasserstein generation countermeasure network is a combination of the conditional warerstein generation countermeasure network and the …
2021105. patent
Early fault detection method based on Wasserstein distance
\\\CN CN114722888A 曾九孙 中国计量大学
Priority 2021-10-27 • Filed 2021-10-27 • Published 2022-07-08
s3, analyzing data statistical characteristics of Wasserstein distance in the principal component space and the residual error space, and establishing monitoring statistics based on hypothesis test in the principal component space and the residual error space for judging whether a fault occurs or …
2021 106
… and apparatus for conditional data genration using conditional wasserstein …
KR KR20230023464A 조명희 서울대학교산학협력단
Priority 2021-08-10 • Filed 2021-08-10 • Published 2023-02-17
Wherein the learned conditional Wasserstein generator outputs a future video frame as a response when the past video frame is input as condition data. According to claim 7, The learned conditional Wasserstein generator is learned by setting a past video frame and a future video frame as condition …
2021 107
Characteristic similarity countermeasure network based on Wasserstein distance
CN CN113673347A 祝磊 杭州电子科技大学
Priority 2021-07-20 • Filed 2021-07-20 • Published 2021-11-19
6. The Wasserstein distance-based characterized similar countermeasure network of claim 1, wherein in S5: obtaining the round-trip probability of the destination domain of the source domain comprises multiplying the resulting P st 、P ts The formula is as follows: P sts ＝P st P ts ； in the formula, P sts …
2021 108
Cross-domain recommendation method based on double-current sliced wasserstein …
CN CN113536116A 聂婕 中国海洋大学
Priority 2021-06-29 • Filed 2021-06-29 • Published 2021-10-22
The invention belongs to the technical field of cross-domain recommendation, and discloses a cross-domain recommendation method based on a double-current slotted Wasserstein self-encoder.
2021 109
Robot motion planning method and system based on graph Wasserstein self-coding …
CN CN113276119B 夏崇坤 清华大学深圳国际研究生院
Priority 2021-05-25 • Filed 2021-05-25 • Granted 2022-06-28 • Published 2022-06-28
1. A robot motion planning method based on a graph Wasserstein self-coding network is characterized by comprising the following steps: s1, constructing a graph Wasserstein self-coding network GraphWAE; the GraphWAE represents the non-obstacle area of the configuration space in a pre-training mode …
2021 110
Wasserstein distance-based motor imagery electroencephalogram migration …
CN CN113010013A 罗浩远 华南理工大学
Priority 2021-03-11 • Filed 2021-03-11 • Published 2021-06-22
7. The Wasserstein distance-based motor imagery electroencephalogram migration learning method according to claim 1, wherein: in step 5), calculating the classification accuracy and kappa coefficient of the deep migration learning model to the target domain data, specifically as follows: …
2021 111
Domain self-adaptive rolling bearing fault diagnosis method based on Wasserstein …
CN CN113239610A 王晓东 昆明理工大学
Priority 2021-01-19 • Filed 2021-01-19 • Published 2021-08-10
3. The implementation principle of the Wasserstein distance-based domain-adaptive rolling bearing fault diagnosis method according to claim 2 is characterized in that: StepA, extracting features through convolutional neural network, convolutional layer containing a filter w and an offset b, let X n …
2021 112
System and Method for Generaring Highly Dense 3D Point Clouds using Wasserstein …
KR KR102456682B1 권준석 중앙대학교 산학협력단
Priority 2020-12-18 • Filed 2020-12-18 • Granted 2022-10-19 • Published 2022-10-19
The present invention generates a high-resolution 3D point cloud using a Wasserstein distribution to generate a set of several 3D points by generating several input vectors from a prior distribution and expressing it as a Wasserstein distribution A prior distribution input unit for inputting a …
2021 113
Wasserstein-based high-energy image synthesis method and device for generating …
CN112634390A 郑海荣 深圳先进技术研究院
Priority 2020-12-17 • Filed 2020-12-17 • Published 2021-04-09
updating the preset generation countermeasure network model based on the first loss value and the first judgment result until the preset generation countermeasure network model converges, and determining the converged preset generation countermeasure network model as the Wasserstein generation …
101` 114
High-energy image synthesis method and device based on wasserstein generative …
WO WO2022126480A1 郑海荣 深圳先进技术研究院
Priority 2020-12-17 • Filed 2020-12-17 • Published 2022-06-23
The preset generative adversarial network model is updated based on the first loss value and the first discrimination result until the preset generative adversarial network model converges, and the converged preset generative adversarial network model is determined as the Wasserstein generative …
2021 115. patent
Wasserstein distance-based object envelope multi-view reconstruction a
CN CN113034695A 何力 广东工业大学
Priority 2021-04-16 • Filed 2021-04-16 • Published 2021-06-25
7. The Wasserstein distance-based object envelope multi-view reconstruction and optimization method according to claim 5, wherein the specific process of step S4-3 is as follows: embedding the Wasserstein-based distance cost function into three-dimensional reconstruction, including: in equation (3) …
<—197 till 2020
+ 115 jn 2021
= 312 till 2021
end 2021 e21
start 2022
Bbb
start 2022
48 patents
2022 1
CN113793397-A
Inventor(s) WANG Z; WANG W and ZHANG J
Assignee(s) UNIV YUYAO ZHEJIANG ROBOTICS RES CENT and UNIV ZHEJIANG
Derwent Primary Accession Number
2022-00125T
2022 2
CN113792785-A
Inventor(s) CHU Z; REN C; (...); CHEN Q
Assignee(s) UNIV SHANGHAI SCI & TECHNOLOGY
Derwent Primary Accession Number
2022-00216M
2022.3
Global IP News. Broadband and Wireless Network News; New Delhi [New Delhi]. 12 Mar 2022.
2022.4
CN113850855-A
Inventor(s) HOU Y; WANG Y; (...); XU Z
Assignee(s) UNIV BEIJING TECHNOLOGY
Derwent Primary Accession Number
2022-35384T
2022 .5
CN113887672-A
Inventor(s) CAO X; ZHAO M; (...); LI Z
Assignee(s) UNIV MINJIANG
Derwent Primary Accession Number
2022-11243X
2022.6
CN113935240-A
Inventor(s) YANG C; XIANG T and YANG M
Assignee(s) UNIV XIHUA
Derwent Primary Accession Number
2022.7 see 2021
Global IP News. Biotechnology Patent News, Mar 17, 2022
Newspaper Article
Full Text Online
2022 8
Rotating machine state monitoring method based on Wasserstein depth digital twin model
CN CN114662712A 胡文扬 清华大学
Filed 2022-02-22 • Published 2022-06-24
and if the similarity of the twin sample and the physical health sample reaches a set standard, obtaining the trained WGAN-GP network based on the Wasserstein deep digital twin model through consistency test. 3. The method for monitoring the condition of a rotating machine based on the Wasserstein …
2022 9
Wasserstein distance-based battery SOH estimation method and device
CN CN114839552A 林名强 泉州装备制造研究所
Priority 2022-04-08 • Filed 2022-04-08 • Published 2022-08-02
3. The wasserstein distance-based battery SOH estimation method according to claim 1, wherein: in S1, the aging data of the pouch batteries is specifically aging data of eight nominal 740Ma · h pouch batteries recorded in advance. 4. A wasserstein distance-based battery SOH estimation method …
2022 10
Application of evidence Wasserstein distance algorithm in component …
CN CN114818957A 肖富元 肖富元
Priority 2022-05-10 • Filed 2022-05-10 • Published 2022-07-29
1. The application of the evidence Wasserstein distance algorithm in component identification is characterized in that: the Wasserstein distance is EWD, and the EWD is verified by the following method: 1): let m1 and m2 be the quality function of the multi-intersection element set Θ, where γ i, j …
2022 11
CAN bus fuzzy test case generation method based on WGAN-GP and fuzzy test system
CN114936149A 黄柯霖 华中科技大学
Filed 2022-04-27 • Published 2022-08-23
the model generation module is used for building and training a WGAN-GP model based on a neural network through the training data set; the test case generation module is used for configuring a noise vector for the trained WGAN-GP model, so that the WGAN-GP model generates a plurality of virtual CAN …
2022 12
Global IP News. Energy Patent News, Jun 23, 2022
2022 13
patent Wire Feed Full Text
Global IP News. Electrical Patent News; New Delhi [New Delhi]. 04 July 2022.
2022 14
Wire Feed Full Text
Univ Xidian Submits Chinese Patent Application for Radar HRRP Database Construction Method Based on WGAN-GP
Global IP News. Software Patent News; New Delhi [New Delhi]. 06 June 2022.
2022 15
CAN bus fuzzy test case generation method based on WGAN-GP and fuzzy test system
CN CN114936149A 黄柯霖 华中科技大学
Priority 2022-04-27 • Filed 2022-04-27 • Published 2022-08-23
the model generation module is used for building and training a WGAN-GP model based on a neural network through the training data set; the test case generation module is used for configuring a noise vector for the trained WGAN-GP model, so that the WGAN-GP model generates a plurality of virtual CAN …
2022 16
Rotating machine state monitoring method based on Wasserstein depth digital …
CN CN114662712A 胡文扬 清华大学
Priority 2022-02-22 • Filed 2022-02-22 • Published 2022-06-24
The invention relates to the technical field of artificial intelligence, and discloses a method for monitoring the state of a rotating machine based on a Wasserstein depth digital twin model, which comprises the steps of acquiring operation and maintenance data of the rotating machine in a healthy …
2022 17
Application of evidence Wasserstein distance algorithm in component …
CN CN114818957A 肖富元 肖富元
Priority 2022-05-10 • Filed 2022-05-10 • Published 2022-07-29
1. The application of the evidence Wasserstein distance algorithm in component identification is characterized in that: the Wasserstein distance is EWD, and the EWD is verified by the following method: 1): let m1 and m2 be the quality function of the multi-intersection element set Θ, where γ i, j …
022 18
Wasserstein distance-based battery SOH estimation method and device
CN CN114839552A 林名强 泉州装备制造研究所
Priority 2022-04-08 • Filed 2022-04-08 • Published 2022-08-02
3. The wasserstein distance-based battery SOH estimation method according to claim 1, wherein: in S1, the aging data of the pouch batteries is specifically aging data of eight nominal 740Ma · h pouch batteries recorded in advance. 4. A wasserstein distance-based battery SOH estimation method …
2022 19 patent news
Univ China Mining Applies for Patent on Nonlinear Industrial Process Modeling Method Based on Wgans...
Global IP News: Industrial Patent News, Jun 14, 2022
Newspaper ArticleCitation Online
2022 20 patent news
Univ Hunan Files Chinese Patent Application for Unsupervised Multi-View Three-Dimensional Point Cloud Joint Registration Method Based on WGAN
Global IP News: Software Patent News, Apr 28, 2022
Newspaper ArticleCitation Online
2022 21 patent news
The Chinese Peoples Liberation Army No.92578 Troops Applies for Patent on Mechanical Pump Small Sample Fault Diagnosis Method Based on WGAN...
Global IP News. Information Technology Patent News, Oct 7, 2022
Newspaper Article Full Text Online
2022 22 patent news TO PATENT
Univ Yanshan Submits Chinese Patent Application for Cement Clinker Free Calcium Sample Data Enhancement and Prediction Method Based on R-WGAN
Global IP News: Construction Patent News, May 24, 2022
Newspaper ArticleCitation Online
2022 23 patent news see 2021
Univ Yanshan Submits Chinese Patent Application for Cement Clinker Free Calcium Sample Data Enhancement and Prediction Method Based on R-WGAN
Global IP News. Construction Patent News, May 24, 2022
Newspaper ArticleCitation Online
2022 24 patent news
Inst Inf Eng, CAS Files Chinese Patent Application for Network Attack Traffic Data Enhancement Method and System Combining Auto-Encoder and WGA
Global IP News: Broadband and Wireless Network Patent News, Mar 12, 2022
Newspaper ArticleCitation Online
2022 25 patent news
State Intellectual Property Office of China Releases Univ Guangdong Technology's Patent Application for Wasserstein...
Global IP News. Packaging & Containers Patent News, Jul 12, 2022
Newspaper ArticleCitation Online
Rotating machine state monitoring method based on Wasserstein depth digital …
CN CN114662712A 胡文扬 清华大学
Priority 2022-02-22 • Filed 2022-02-22 • Published 2022-06-24
The invention relates to the technical field of artificial intelligence, and discloses a method for monitoring the state of a rotating machine based on a Wasserstein depth digital twin model, which comprises the steps of acquiring operation and maintenance data of the rotating machine in a healthy …
2022 27
基于WGAN-GP的CAN总线模糊测试用例生成方法及模糊测试系统
OPEN ACCESS
基于WGAN-GP的CAN总线模糊测试用例生成方法及模糊测试系统
No Online Access
[Chinese CAN bus fuzz test case generation method and fuzz test system based on WGAN-GP]
2022 28
FC-VoVNet and WGAN-based B ultrasonic image denoising method
WEI JIANHUA ; CHEN DEHAI2022
OPEN ACCESS
FC-VoVNet and WGAN-based B ultrasonic image denoising method
No Online Access
2022 29
2022
OPEN ACCESS
基于SVAE-WGAN的过程工业软测量数据补充方法
No Online Access
[Chines VAE-WGAN-based data supplementation method for soft sensing in process industry
]
2022 30 see 2020
OPEN ACCESS
基于改进WGAN-GP的多波段图像同步融合与增强方法
No Online Access
[Chinese Synchronous fusion and enhancement method of multi-band image based on improved WGAN-GP
]
P2022 31
一种基于BiLSTM和WGAN-GP网络的sEMG数据增强方法
OPEN ACCESS
一种基于BiLSTM和WGAN-GP网络的sEMG数据增强方法
No Online Access
[Chinese A sEMG data augmentation method based on BiLSTM and WGAN-GP network]
2022 32
OPEN ACCESS
基于WGAN动态惩罚的网络安全不平衡数据集分析方法
No Online Access
[Chinese Hyperspectral image classification method based on semi-supervised WGAN-GP
]
2022 33
OPEN ACCESS
一种基于孤立森林与WGAN网络的风电输出功率预测方法
No Online Access
[Chinese A wind power output power prediction method based on isolated forest and WGAN network]
2022 34
Data depth enhancement method based on WGAN-GP data generation and Poisson fusion
ZHANG HUITING ; LIU ZHUO ; HOU YUE ; CHEN NING ; CHEN YANYAN2022
OPEN ACCESS
Data depth enhancement method based on WGAN-GP data generation and Poisson fusion
No Online Access
2022 35
Microseism record denoising method based on improved WGAN network and CBDNet
SHENG GUANQUN ; MA KAI ; JING TANG ; ZHENG YUELIN ; YU MEI ; ZHANG JINGLAN2022
OPEN ACCESS
Microseism record denoising method based on improved WGAN network and CBDNet
No Online Access
2022 36 see 2021
Power system harmonic law calculation method based on WGAN
WU OU ; PAN YANYI ; YAO CHANGQING ; MEI WENBO ; MEI ZHICHAO ; ZHU SHUAI2022
OPEN ACCESS
Power system harmonic law calculation method based on WGAN
No Online Access
2022 37
OPEN ACCESS
基于WGAN-GP的雷达HRRP数据库构建方法
No Online Access
[Chinese Construction method of radar HRRP database based on WGAN-GP]
2022 38
基于WGAN-GP和U-net改进的图像增强的方法、装置及存储介质
OPEN ACCESS
基于WGAN-GP和U-net改进的图像增强的方法、装置及存储介质
No Online Access
[Chinese mproved image enhancement method, device and storage medium based on WGAN-GP and U-net]
2022 39
基于改进WGAN-GP的半监督恶意流量检测方法
11/2022
Patent Available Online
Open Access
[Chinese Semi-supervised malicious traffic detection method based on improved WGAN-GP]
2022 40
基于WGAN-CNN煤矿井下粉尘浓度预测方法和系统
11/2022
Patent Available Online
[Chinese Prediction method and system of underground dust concentration in coal mine based on WGAN-CNN]
2022 41 patent news
Beijing Industrial Univ Seeks Patent for Data Depth Enhancement Method Based on
WGAN-GP Data Generation and Poisson Fusion
Global IP News. Information Technology Patent News, Nov 21, 2022
Newspaper Article Full Text Online
2022 42 patent news
Jiangsu Chegah Energy Tech Submits Chinese Patent Application for Power System Harmonic Law Calculation Method Based on WGAN
Global IP News. Electrical Patent News, Nov 19, 2022
Newspaper Article Full Text Online
2022 43 patent news
State Intellectual Property Office of China Receives Three Gorges Univ's Patent Application for Microseism Record Denoising Method Based on Improved WGAN...
Global IP News. Broadband and Wireless Network News, Nov 21, 2022
Newspaper Article Full Text Online
2022 44 patent news
State Intellectual Property Office of China Publishes Dongfeng Automobile Group Stock Ltd and Dongfeng Pleasure Science and Tech Limited's Patent Application for Motor Fault Data Enhancement Method Based on Conditional Wasserstein...
Global IP News: Automobile Patent News, Nov 4, 2022
Newspaper ArticleCitation Online
2022 45 piatent
CN115273019-A
Inventor(s) LIN J
Assignee(s) JIUSHI ZHIXING BEIJING TECHNOLOGY CO LTD
Derwent Primary Accession Number
2022-D93909
2022 46 patent
CN115294179-A
Inventor(s) LUO Z; LI Z and LEI N
Assignee(s) UNIV DALIAN TECHNOLOGY
Derwent Primary Accession Number
2022-D9871X
more_horiz
2922 47 patent
CN115239588-A
Inventor(s) QIN Y; JIANG W; (...); DI J
Assignee(s) UNIV GUANGDONG TECHNOLOGY
Derwent Primary Accession Number
2022-D5413F
2022 48
Zhou Kou Teaching Univ Submits Patent Application for Distribution Robust Optimization Method Based on Wasserstein...
Global IP News. Measurement & Testing Patent News, Nov 26, 2022
Newspaper ArticleCitation Online
2022 49 patent news
Beijing Industrial Univ Seeks Patent for Data Depth Enhancement Method Based on WGAN-GP Data...
Global IP News: Information Technology Patent News, Nov 21, 2022
Newspaper ArticleCitation Online
8
2022 50 patent news
Beijing Industrial Univ Seeks Patent for Data Depth Enhancement Method Based on WGAN-GP Data...
Global IP News. Information Technology Patent News, Nov 21, 2022
Newspaper Article Full Text Online
2022 51 Wire Feed patent news
State Intellectual Property Office of China Releases Hangzhou Electronics Science and Technology Univ's Patent Application for Network Security Unbalanced Data Set Analysis Method Based on WGAN Dynamic Penalty
Global IP News. Security & Protection Patent News; New Delhi [New Delhi]. 10 Dec 2
2022 52 patent news Wire Feed
State Intellectual Property Office of China Receives River and Sea Univ's Patent Application for Power System Bad Data Identification Method Based on Improved Wasserstein Gan
Global IP News. Electrical Patent News; New Delhi [New Delhi]. 17 Dec 2022.
Cite Email Full Text
DetailsFull text
2022 53 paint news
State Intellectual Property Office of China Releases Hangzhou Electronics Science and Technology Univ's Patent Application for Network Security Unbalanced Data Set Analysis Method Based on WGAN...
Global IP News: Security & Protection Patent News, Dec 10, 2022
Newspaper Article
State Intellectual Property Office of China Releases Hangzhou Electronics Science and Technology Univ's Patent Application for Network Security Unbalanced Data Set Analysis Method Based on WGAN...
Global IP News. Security & Protection Patent News, Dec 10, 2022
Newspaper Article Full Text Online
2022 54 patent
Cloud environment intrusion detection method based on WGAN and LightGBM
CN116248344A 裴廷睿 湘潭大学
Filed 2022-12-28 • Published 2023-06-09
6. The cloud environment intrusion detection method according to claim 1, wherein S33 includes the WGAN model taking the preprocessing data as an input of the discrimination model, the random noise as an input of the generation model, performing a reciprocal game using the generation model and the …
2022 55 patent
Grid deformation data enhancement method based on WGAN-GP model
CN CN115937038A 李静 上海大学
Priority 2022-12-27 • Filed 2022-12-27 • Published 2023-04-07
The invention discloses a method for enhancing grid deformation data based on a WGAN-GP model, which relates to the technical field of image processing and data enhancement and comprises the following steps: constructing a training data set and a test data set; constructing a WGAN-GP model;
2022 56patent
Method for selecting drive resistor of eGaN HEMT power converter
CN CN115859889A 贺远航 广东工业大学
Priority 2022-11-16 • Filed 2022-11-16 • Published 2023-03-28
10. The method for selecting the drive resistor of the eGaN HEMT power converter according to claim 1, wherein S3.6 specifically comprises: the method for improving the overall efficiency of the converter is to select a reasonable driving resistor to obtain a reasonable driving waveform, reduce the …
2022 57 patent
Antagonistic sample generation method and system based on WGAN-Unet
CN CN115761399A 秦中元 东南大学
Priority 2022-11-01 • Filed 2022-11-01 • Published 2023-03-07
s3, constructing a WGAN-Unet-based anti-attack network model: the anti-attack network model consists of a generator, a discriminator and the target network model obtained in the step S2, wherein the generator is constructed according to original sample data based on a Unet framework, performs …
2022 58 patent
WGAN-based FRP sheet and concrete interface bonding slippage model generation …
CN CN115544864A 贺畅 同济大学
Priority 2022-09-16 • Filed 2022-09-16 • Published 2022-12-30
2. The method for generating the WGAN-based FRP sheet and concrete interface bonding slip model according to claim 1, wherein the step 1: strain data acquisition is realized by modeling through finite element software LS-DYNA, and data corresponding to strain at every two seconds, namely average …
2022
2022 59 patent
Vehicle following behavior modeling method based on Transformer-WGAN
CN CN115630683A 徐东伟 浙江工业大学
Priority 2022-09-14 • Filed 2022-09-14 • Published 2023-01-20
2. The method of claim 1, wherein the method for modeling vehicle-following behavior based on Transformer-WGAN is characterized in that: acquiring state sequence data of a plurality of groups of following vehicles and vehicle
2022 60 atent
Micro-seismic signal denoising method combining WGAN-GP and SADNet
CN CN115600089A 余梅 三峡大学（Cn）
Priority 2022-09-02 • Filed 2022-09-02 • Published 2023-01-13
1. A micro-seismic signal denoising method combining WGAN-GP and SADNet is characterized by comprising the following steps: inputting a microseism signal sample into a WGAN-GP network, adding a noise signal condition, generating a large number of training sample sets by generating a confrontation …
2022 61 patent
… system for predicting underground dust concentration of coal mine based on WGAN …
CN CN115310361A 秦波涛 中国矿业大学
Priority 2022-08-16 • Filed 2022-08-16 • Published 2022-11-08
9. The WGAN-CNN-based coal mine dust concentration prediction system of claim 8, the prediction model building module further comprises: and the reliability inspection unit is used for inputting the test data set into the coal mine underground dust concentration prediction model to obtain a …
2022 -atent
Satellite cloud picture prediction method based on WGAN-GP network and optical …
CN CN115546257A 谈玲 南京信息工程大学
Priority 2022-08-09 • Filed 2022-08-09 • Published 2022-12-30
5. The W
2022 62 patent
Semi-supervised malicious flow detection method based on improved WGAN-GP
CN CN115314254A 刘胜利 中国人民解放军战略支援部队信息工程大学
Priority 2022-07-07 • Filed 2022-07-07 • Published 2022-11-08
The invention belongs to the technical field of malicious traffic detection, and particularly relates to a semi-supervised malicious traffic detection method based on improved WGAN-GP. The method carries out detection according to the established semi-supervised malicious flow detection model.
2022 63 iatent
XRF-EGAN model-based soil XRF spectrogram background subtraction method
CN CN114861541A 赵彦春 电子科技大学长三角研究院(湖州)
Priority 2022-05-13 • Filed 2022-05-13 • Published 2022-08-05
and step 3: and loading an XRF-EGAN generator network model, carrying out XRF spectrum background deduction on new soil XRF spectrum data measured by an XRF fluorescence analyzer by using the XRF-EGAN generator network, and obtaining output after background deduction. 4. The XRF-EGAN model-based …
2023 64 patent 55
Laplace noise and Wasserstein regularization-based multi-test EEG source …
CN CN116152372A 刘柯 重庆邮电大学
Priority 2023-02-07 • Filed 2023-02-07 • Published 2023-05-23
s4, establishing a multi-test robust EEG diffuse source imaging model based on Laplace noise and Wasserstein regularization in a projection space according to the lead matrix, the difference operator and the minimum distance matrix, and obtaining a multi-test estimated source by utilizing an ADMM …
2022 65. patent
… recognition domain self-adaption method and system combining Wasserstein …
CN CN115601535A 陈元姣 杭州电子科技大学（Cn）
Priority 2022-11-08 • Filed 2022-11-08 • Published 2023-01-13
5. The chest radiograph abnormality recognition domain adaptation method combining Wasserstein distance and difference measure of claim 4, wherein the construction of the total objective function through the obtained Wasserstein distance and contrast domain difference in step S3 comprises the …
2022 66
Telecom customer churn prediction method based on condition Wasserstein GAN
CN CN115688048A 苏畅 重庆邮电大学
Priority 2022-10-31 • Filed 2022-10-31 • Published 2023-02-03
3. the method of claim 2, wherein the conditional Wasserstein GAN-based telecommunications customer churn prediction method comprises: in S2, the mixed attention mechanism CBAM includes two parts: channel attention module CAM and spatial attention module SAM; the overall attention process for CBAM …
2022 67
Road network pixelation-based Wasserstein generation countermeasure flow data …
CN CN115510174A 王蓉 重庆邮电大学
Priority 2022-09-29 • Filed 2022-09-29 • Published 2022-12-23
6. The road network pixelation-based Wasserstein generation countermeasure network traffic data interpolation method as claimed in claim 1, wherein the process of repairing missing data by a road network traffic data generation countermeasure network model comprises: splicing traffic flow data to …
2022 68
Maximum slice Wasserstein measurement-based pedestrian target association …
CN CN115630190A 陈亮 南京信息技术研究院
Priority 2022-09-07 • Filed 2022-09-07 • Published 2023-01-20
5. The method for monitoring network pedestrian target association based on maximum slice Wasserstein measurement as claimed in claim 1, wherein said step S4 specifically comprises the steps of: s401: associating R' according to cross-mirror pedestrian target " j According to (C) i1 ，T i1,j1 ，T i, …
2022 69 see 2018 patent
Wasserstein distance-based battery SOH estimation method and device
CN CN114839552A 林名强 泉州装备制造研究所
Priority 2022-04-08 • Filed 2022-04-08 • Published 2022-08-02
3. The wasserstein distance-based battery SOH estimation method according to claim 1, wherein: in S1, the aging data of the pouch batteries is specifically aging data of eight nominal 740Ma · h pouch batteries recorded in advance. 4. A wasserstein distance-based ba
<—312 till 2021
+ 69 patents in 2022
= 381 patents till 2022
end 2022 e22
Start 2023
2023 1 patent news
Chongqing Post and Telecommunication Univ's Patent Application for Theme Modeling Method Based on Wasserstein Auto-Encoder and Gaussian Mixture Distribution as Prior
Global IP News. Telecom Patent News; New Delhi [New Delhi]. 06 Jan 2023.
Cite Email
Full Text DetailsFull text
2023 2 patent news
State Intellectual Property Office of China Receives Chongqing Post and Telecommunication Univ's Patent Application for Theme Modeling Method Based on Wasserstein Auto-Encoder and Gaussian...
Global IP News. Telecom Patent News, Jan 6, 2023
Newspaper Article Full Text Online
2023 3 patent
一种基于WGAN-Unet...
03/2023
Patent Available Online
Open Access
[Chinese.A WGAN-Unet based...|
2023 4. patent news
Univ Jiliang China Submits Chinese Patent Application for Early Fault Detection Method Based on Wasserstein...
Global IP News. Measurement & Testing Patent News, 03/2023
NewsletterCitation Online
Univ Qinghua Seeks Patent for Rotating Machine State Monitoring Method Based on Wasserstein...
Global IP News. Tools and Machinery Patent News, 03/2023
NewsletterCitation Online
Quick Look
Univ Jiliang China Submits Chinese Patent Application for Early Fault Detection Method Based on Wasserstein...
Global IP News: Measurement & Testing Patent News, Mar 15, 2023
Newspaper ArticleCitation Online
Univ Qinghua Seeks Patent for Rotating Machine State Monitoring Method Based on Wasserstein...
Global IP News: Tools and Machinery Patent News, Mar 1, 2023
Newspaper ArticleCitation Online
2023 5. -patent news Wire Feed
Wuxi Cansonic Medical Science & Tech Seeks Patent for FC-VoVNet and WGAN-Based B Ultrasonic Image Denoising Method
Global IP News. Optics & Imaging Patent News; New Delhi [New Delhi]. 23 Mar 2023.
Wuxi Cansonic Medical Science & Tech Seeks Patent for FC-VoVNet and WGAN-Based B Ultrasonic Image Denoising Method
Global IP News. Optics & Imaging Patent News; New Delhi [
The patent application number is CN202011617451 2
2023 6 patent news see journal article
Quanzhou Institute of Equipment Mfg Submits Chinese Patent Application for Wasserstein...
Global IP News. Electrical Patent News, 04/2023
Newsletter Full Text Online
Wasserstein PAC-Bayes Learning: A Bridge Between Generalisation and Optimisation
Quanzhou Institute of Equipment Mfg Submits Chinese Patent Application for Wasserstein...
Global IP News: Electrical Patent News, Apr 10, 2023
Newspaper Article
2023 7 patent news see2022 patent
Xiao Fuyuan Applies for Patent on Application of Evidence Wasserstein...
Global IP News: Software Patent News, Apr 5, 2023
Newspaper ArticleCitation Online
Evidence Wasserstein Distance Algorithm in Aspect of Component
2023 8. patent news. Wire Feed
Quanzhou Institute of Equipment Mfg Submits Chinese Patent Application for Wasserstein Distance-Based Battery SOH (State of Health) Estimation Method and Device
Global IP News. Electrical Patent News; New Delhi [New Delhi]. 10 Apr 2023.
2023 9. patent news Wire Feed
Xiao Fuyuan Applies for Patent on Application of Evidence Wasserstein Distance Algorithm in Aspect of Component Identification
Global IP News. Software Patent
2023 10 patent
US Patent Issued to CGG SERVICES on April 25 for
"Methods and devices performing adaptive quadratic Wasserstein...
US Fed News Service, Including US State News, 04/2023
023 11 patent news Wire Feed
Global IP News. Information Technology Patent News; New Delhi [New Delhi]. 28 Apr 2023.
2023 12 patent
CN115937038-A
Inventor(s) SHEN N; HU P and LI J
Assignee(s) UNIV SHANGHAI
Derwent Primary Accession Number
2023-42316D
2023 13 patent news
CGG Services SAS Gets Patent for Methods and Devices Performing Adaptive Quadratic Wasserstein Full-Waveform Inversion
Global IP News. Information Technology Patent News, 04/2023
Newsletter Full Text Online
2023 14 patent news
Univ Jiliang China Submits Chinese Patent Application for Early Fault Detection Method Based on Wasserstein Distanc
Global IP News. Measurement & Testing Patent News, 03/2023
Newsletter Full Text Online
2023 15 patent news
Xiao Fuyuan Applies for Patent on Application of Evidence Wasserstein Distance Algorithm in Aspect of Component Identification
Global IP News. Software Patent News, 04/2023
Newsletter Full Text Online
2023 16 patent news
Univ Qinghua Seeks Patent for Rotating Machine State Monitoring Method Based on Wasserstein Depth Digital Twinborn Model
Global IP News. Tools and Machinery Patent News, 03/2023
Newsletter Full Text Online
2023 17 patent news
US Patent Issued to CGG SERVICES on April 25 for "Methods and devices performing adaptive quadratic Wasserstein full-waveform...
US Fed News Service, Including US State News, 04/2023
Newsletter Full Text Online
2023 18 patent news
Quanzhou Institute of Equipment Mfg Submits Chinese Patent Application for Wasserstein Distance-Based Battery SOH (State of...
Global IP News. Electrical Patent News, 04/2023
Newsletter Full Text Online
2023 19 patent news
Billionaire’s Love Child Sues His Other Kids for $100M: Bruce Wasserstein died in 2009, but a feud over his assets rages on
by Kirsch, Noah
The Daily Beast, May 2, 2023
Newspaper Article Full Text Online
2023. 20 PATENT
Monitoring network pedestrian target association method based on maximum slice Wasserstein measurement
JU LIWEI ; CHEN LIANG ; LI QI ; ZHANG JING
2023
OPEN ACCESS
2023 21 PATENT
METHOD AND APPARATUS FOR CONDITIONAL DATA GENRATION USING CONDITIONAL WASSERSTEIN GENERATOR
CHO MYUNG HEE ; LEE KYUNG BOK ; KIM YOUNG GEUN
2023
OPEN ACCESS
METHOD AND APPARATUS FOR CONDITIONAL DATA GENRATION USING CONDITIONAL WASSERSTEIN GENERATOR
2023 22 PATENT
Wasserstein distance and difference measurement-combined chest radiograph anomaly recognition domain self-adaptive method and Wasserstein distance and difference measurement-combined chest radiograph anomaly recognition domain self-adaptive system
CHEN YUANJIAO ; HE BISHI ; WANG DIAO ; XU ZHE ; CHEN HUI
2023
OPEN ACCESS
2023 23 payent
一种基于Laplace噪声和Wasserstein正则的多试次EEG源成像方法
2023
OPEN ACCESS
一种基于Laplace噪声和Wasserstein正则的多试次EEG源成像方法
[Chinese A Multi-trial EEG Source Imaging Method Based on Laplace Noise and Wasserstein Regularization]
2023 24. patent news. NEWSLETTER ARTICLE
Wuxi Cansonic Medical Science & Tech Seeks Patent for FC-VoVNet and WGAN-Based B Ultrasonic Image Denoising Method
New Delhi: Pedia Content Solutions Pvt. Ltd
Global IP News. Optics & Imaging Patent News, 2023
2023 25. patent news. NEWSLETTER ARTICLE
New Delhi: Pedia Content Solutions Pvt. LtdGlobal IP News. Optics & Imaging Patent News, 2023
... Status: Application Beijing, March 23 -- Wuxi Cansonic Medical Science & Tech has sought patent for FC-VoVNet and WGAN-based B ultrasonic image denoising method...
2023 26. PATENT
Adversarial sample generation method and system based on WGAN-Unet
CHEN YUQING ; SUN LEI ; QIN ZHONGYUAN ; YAO TIAN ; ZHANG QUNFANG
2023
OPEN ACCESS
2023.27 PATENT
Transform-WGAN-based vehicle following behavior modeling method
XU DONGWEI ; GAO GUANGYAN ; LI JIANGPENG ; LI CHENGBIN
2023
OPEN ACCESS
2023 28. PATENT
WGAN-GP and SADNet combined microseismic signal denoising method
SHENG GUANQUN ; MA KAI ; JING TANG ; WANG XIANGYU ; ZHENG YUELIN ; YU MEI
2023
OPEN ACCESS
2023. 29. PATENT
Building photovoltaic data completion method based on WGAN and whale optimization algorithm
CUI LEI ; LI FENG ; YANG YANG ; YIN JIE ; CAO QINGWEI ; LI DONG ; GUO XI ; CAO KENAN
2023
OPEN ACCESS
2023.30 PATENT
Software measurement defect data augmentation method based on VAE and WGAN
GUO ZHAOYANG
2023
OPEN ACCESS
2023 31 PATENT
2023
OPEN ACCESS
[Chinese. Bearing Fault Diagnosis Method Based on Improved WGAN Network]
2023 32. PATENT
2023
OPEN ACCESS
[Chinese. An Algorithm Based on S-Transform/WGAN to Solve the Data Imbalance of Brine Pipeline Leakage]
2023. 33. PATENT
基于SVAE-WGAN模型的局部放电故障数据增强处理方法及装置
2023
OPEN ACCESS
[Chinese. Partial discharge fault data enhancement processing method and device based on SVAE-WGAN model]
2023. 34. PATENT
基于改进WGAN-GP和Alxnet的轴承故障诊断方法
2023
OPEN ACCESS
[Chinese. ]
CN CN115962946A 付文龙 三峡大学
2023. 35. PATENT
2023
OPEN ACCESS
[Chinese. Bearing fault diagnosis method based on improved WGAN-GP and Alxnet] 置，Δg＝g-g 0 ，g 0 为原图-原图的形变网格。 8.根据权利要求6所述的一种
Assignee(s) SICHUAN AOTU ENVIRONMENTAL PROTECTION
Derwent Primary Accession Number
2023 37
Method for modeling a vehicle following behavior based on WGAN, involves making discriminator difficult to judge result of prediction is false, so as to minimize error between prediction result and real result
CN115630683-A
Inventor(s) LI J; LI C; (...); XU D
Assignee(s) UNIV ZHEJIANG TECHNOLOGY
Derwet Primary Accession Number
2023-13424N
2023 38
CN115546257-A
Inventor(s) XIA J; KANG R and TAN L
Assignee(s) UNIV NANJING INFORMATION SCI & TECHNOLOG
Derwent Primary Accession Number
2023-05050N
2023 39
CN115761399-A
Inventor(s) CHEN Y; SUN L; (...); QIN Z
Assignee(s) UNIV SOUTHEAST
Derwent Primary Accession Number
2023-26661P
2023 40
CN115688982-A
Inventor(s) YANG Y; CAO K; (...); CUI L
Assignee(s) HUANENG JIANGSU INTEGRATED ENERGY SERVIC
Derwent Primary Accession Number
2023-195556
2023 41 patent
Bearing fault diagnosis method based on improved WGAN network
CN CN116223038A 张辉 江苏科技大学
Priority 2023-01-09 • Filed 2023-01-09 • Published 2023-06-06
5. The method for diagnosing bearing failure based on the improved WGAN network as claimed in claim 4, wherein: the R-FCN network model is built in the step (3.2) as a discriminator model for improving the WGAN network, the discriminator model is utilized to judge the picture generated by the …
2023 42 patent
Bearing fault diagnosis method based on improved WGAN-GP and Alxnet
CN CN115962946A 付文龙 三峡大学
Priority 2023-01-18 • Filed 2023-01-18 • Published 2023-04-14
8. The bearing fault diagnosis method based on improved WGAN-GP and Alxnet according to claim 1, characterized in that: the step 5 comprises the following steps: s5.1: taking the expanded balanced data set as input, and extracting deep features through the convolutional layer, the Relu activation …
2023 43
Electronic device for colorizing black and white image using gan based model …
KR KR20230025676A 이범식 조선대학교산학협력단
Priority 2023-02-03 • Filed 2023-02-03 • Published 2023-02-22
According to claim 4, The GAN-based model is trained using a total loss (L total ) considering all pixel wise (L1) loss function (L L1 ), VGG loss function (L VGG ), and WGAN loss function (L wgan ), The pixel wise (L1) loss function (L L1 ), the VGG loss function (L VGG ), the WGAN loss function ( …
2023 44 patent see 2022
Bearing fault diagnosis method based on improved WGAN-GP and Alxnet
CN CN115962946A 付文龙 三峡大学
Priority 2023-01-18 • Filed 2023-01-18 • Published 2023-04-14
8. The bearing fault diagnosis method based on improved WGAN-GP and Alxnet according to claim 1, characterized in that: the step 5 comprises the following steps: s5.1: taking the expanded balanced data set as input, an
2023 45. patent 55
Laplace noise and Wasserstein regularization-based multi-test EEG source …
CN CN116152372A 刘柯 重庆邮电大学
Priority 2023-02-07 • Filed 2023-02-07 • Published 2023-05-23
s4, establishing a multi-test robust EEG diffuse source imaging model based on Laplace noise and Wasserstein regularization in a projection space according to the lead matrix, the difference operator and the minimum distance matrix, and obtaining a multi-test estimated source by utilizing an ADMM …
<—381 titles before 2023
+ 45 patents in 2023
= 426 patents till 2013
end 2023. E23
426 patents till 2023
+ 30 unsorted titles below
= 456 total
————————————— 30 titles not sorted by year—>
start unsorted by year titles
——31 patent titles from Web of Science —>
1.
Patent Number: CN112539887-A
Patent Assignee: UNIV NORTHEAST PETROLEUM
Inventor(s): DONG H; ZHOU Y; LU J; et al.
2.
Patent Number: CN111797844-A
Patent Assignee: SUZHOU AISPEECH INFORMATION TECHNOLOGY C
Inventor(s): QIAN Y; CHEN Z; WANG S.
3
Patent Number: CN111767962-A
Patent Assignee: CHINESE ACAD SCI AUTOMATION INST
Inventor(s): TANG S; ZHENG Q; ZHU H; et al.
4
Patent Number: CN111582348-A
Patent Assignee: UNIV WUHAN POLYTECHNIC
Inventor(s): LI Y; XU X; YUAN C.
5.
Patent Number: CN111564160-A
Patent Assignee: UNIV CHONGQING POSTS & TELECOM
Inventor(s): HU Z; XU X; LUO Y; et al.
6.
Patent Number: CN111488763-A
Patent Assignee: UNIV TIANJIN QINGDAO OCEAN TECHNOLOGY
Inventor(s): XU J; SHI X; WANG R; et al.
7
Patent Number: CN111476721-A
Patent Assignee: UNIV CHONGQING POSTS & TELECOM
Inventor(s): FENG J; QI S; WU S.
8.
Patent Number: CN111460367-A
Patent Assignee: HUAIYIN TECHNOLOGY INST
Inventor(s): XU M; DING W; ZHAO J; et al.
9.
Patent Number: CN111428803-A
Patent Assignee: UNIV SHANDONG
Inventor(s): WU Q; SUN S; LIU J; et al.
10.
Patent Number: CN111192221-A
Patent Assignee: UNIV CENT SOUTH
Inventor(s): CHEN X; PAN M; XIE Y; et al.
11.
Patent Number: CN111178427-A
Patent Assignee: UNIV HANGZHOU DIANZI
Inventor(s): GUO C; RONG P; CHEN H; et al.
12.
Patent Number: CN111046708-A
Patent Assignee: UNIV TIANJIN QINGDAO OCEAN TECHNOLOGY
Inventor(s): XU J; SHI X; WANG R; et al.
13.
Patent Number: CN111026058-A
Patent Assignee: UNIV ZHEJIANG
Inventor(s): GE Z; ZHANG H; SONG Z.
14.
Patent Number: CN110929399-A
Patent Assignee: STATE GRID JIANGSU ELECTRIC POWER CO LTD
Inventor(s): TANG X; LI Q; WANG S; et al.
15.
Patent Number: CN110907176-A
Patent Assignee: UNIV HEFEI TECHNOLOGY
Inventor(s): XU J; HUANG J; ZHOU L; et al.
16.
Patent Number: CN110826688-A
Patent Assignee: JIANGSU AIJIA HOUSEHOLD PROD CO LTD
Inventor(s): CHEN X; LV C; LIN S.
17.
Patent Number: CN110797919-A CN110797919-B
Patent Assignee: STATE GRID SICHUAN ELECTRIC POWER CO ECO; STATE GRID HENAN ELECTRIC POWER CO ECONO
Inventor(s): WANG R; LIU Y; ZHU M; et al.
18.
Patent Number: CN110555382-A
Patent Assignee: UNIV ZHEJIANG SCI-TECH
Inventor(s): ZHANG N; TU X; BAO X; et al.
19.
Patent Number: CN110414383-A
Patent Assignee: UNIV HUAZHONG SCI & TECHNOLOGY
Inventor(s): YUAN Y; ZHOU B; CHENG C; et al.
20.
Patent Number: CN110197514-A
Patent Assignee: UNIV NANJING AGRIC
Inventor(s): YUAN P; WU M; XU H; et al.
21.
Patent Number: CN110110670-A
Patent Assignee: UNIV HANGZHOU DIANZI
Inventor(s): GUO C; LIU Y; YING N; et al.
22.
Patent Number: CN110097512-A
Patent Assignee: UNIV SICHUAN
Inventor(s): ZHANG Y; RAN M; ZHOU J.
23.
Patent Number: CN109660206-A CN109660206-B
Patent Assignee: UNIV FUZHOU
Inventor(s): LIN P; CHENG S; LU X; et al.
24.
Patent Number: CN109360199-A
Patent Assignee: UNIV NANJING TECHNOLOGY
Inventor(s): DU Z; YE C; LI X; et al.
25.
Patent Number: CN109146868-A
Patent Assignee: BEIJING QINGYAN XIANGYUN TECHNOLOGY CO
Inventor(s): WU J; ZHANG Q; HU F.
26.
Patent Number: CN109120652-A
Patent Assignee: UNIV CHONGQING POSTS & TELECOM
Inventor(s): WANG Y; WANG T; ZHU J.
27.
Patent Number: CN109086437-A
Patent Assignee: UNIV CHONGQING; UNIV GUILIN ELECTRONIC TECHNOLOGY
Inventor(s): FENG Y; ZHANG Y; SHANG J; et al.
Patent Number: CN112598125-A
Patent Assignee: UNIV XIAN SCI & TECHNOLOGY; SHAANXI ZHONGYI TIMES TECHNOLOGY CO LTD
Inventor(s): LIU B; GAO N; HUANG M; et al.
Handwritten number generation method for generating countermeasure network based on double-discriminator weighting
29. 2014-2016
Patent Number: US2015293884-A1 JP2015203946-A
Patent Assignee: UNIV KYOTO
Inventor(s): CUTURI CAMETO M; CUTURI M.
30. 2012-2014
Patent Number: CN102609913-A CN102609913-B
Patent Assignee: UNIV ZHEJIANG
Inventor(s): KONG D; PENG J; WANG J; et al.
https://patents.google.com › patent › CN102609913B
CN102609913B - Method for enhancing liver blood vessel and ...
Priority to CN201210014249.9A. 2012-07-25. Publication of CN102609913A. 2014-07-09. Application granted. 2014-07-09. Publication of CN102609913B ...
—————
Search links
Web of Science
Google books
Google patents advanced search
PSU ;library
ProQuest Advanced Search
————————————————
8 results sorted by relevance
aaa bbb