-
公开(公告)号：US10797333B2
公开(公告)日：2020-10-06
申请号：US16066052
申请日：2016-11-22
发明人： Haiying Qin , Cai Zhu , Yongping Hu , Kaijian Chen , Jiabin Liu , Zhe Kong , Hongbo Wang , Yan He , Zhenguo Ji
IPC分类号： H01M8/10 , H01M4/86 , H01M4/88 , H01M4/90 , H01M8/1044 , H01M8/1051 , H01M8/1072 , H01M8/1018
摘要： The present invention discloses a preparation method of an alkaline anion exchange membrane and a use of the membrane in a fuel cell. The preparation method of the alkaline anion exchange membrane contains: taking polyvinyl alcohol as a substrate, which provides mechanical strength for the membrane; taking a commercialized alkaline resin as an anion exchange resin of chemically reactive groups, performing a cross-linking reaction between polyvinyl alcohol and the alkaline resin by mixing; meanwhile, during the process of forming the alkaline anion exchange membrane, adding an organic salt of transition metal, and doping transition metal ions into the membrane. By taking advantages of catalytic characteristics of the transition metal ions, the fuel leaking from the anode of the cell can perform a catalytic reaction in time in the ion exchange membrane, and thereby improve an ion conductivity of the membrane and efficiently decrease a resistance of the cell. The fuel cell assembled by the anion exchange membrane prepared in the present invention shows an excellent power-generating property.
-
42.发明授权公开(公告)号：US12092670B2
公开(公告)日：2024-09-17
申请号：US18009647
申请日：2021-10-21
发明人： Yaguang Kong , Zhangping Chen , Xichao Tang , Hongbo Zou , Na Huang , Fan Zhang , Xiaodong Zhao , Honghuan Chen
摘要： The present invention discloses a multiband resonance frequency tracking circuit applied to ultrasonic machining, including an output current-voltage phase difference direction detection circuit and a multiband resonance frequency tracking circuit, where a detection signal output end of the output current-voltage phase difference direction detection circuit is connected to a signal input end of the multiband resonance frequency tracking circuit. Through the foregoing technical solutions, in the present invention, a system detuning state is quickly determined by using a current-voltage phase difference direction detection signal outputted by a D flip-flop in a chip SN74HC74D, and a dead-time resistor between a 5th pin and a 7th pin in a chip EG3525 can be changed in a timely manner based on a detuning degree of a piezoelectric transducer, so as to change a system driving frequency to track a resonance frequency of the piezoelectric transducer and implement fast and accurate tracking.
-
43.发明公开公开(公告)号：US20240290084A1
公开(公告)日：2024-08-29
申请号：US18491305
申请日：2023-10-20
发明人： Wanzeng KONG , Jiabin ZHU , Jianan HAN , Xuanyu JIN , Li ZHU
IPC分类号： G06V10/94 , G06V10/26 , G06V10/74 , G06V10/776 , G06V10/778 , G06V10/82 , G06V20/40
CPC分类号： G06V10/945 , G06V10/26 , G06V10/761 , G06V10/776 , G06V10/778 , G06V10/82 , G06V20/41 , G06V20/46 , G06V20/49
摘要： The present disclosure provides a method for complex target retrieval from mass videos based on human-machine collaboration. At present, an intelligent system based on machine vision is weak in generalization ability. When an environment changes or a target is shielded or camouflaged, target retrieval from mass videos requires lots of manpower, which is time-consuming and labor-consuming. In the present disclosure, prescreening is performed in a video library using a retrieval model according to a coarse-grained feature of a target, and a candidate target set obtained by screening is made into a brain-eye synergistic rapid serial visual presentation (RSVP) paradigm for presentation for a user. After the user determines the target, a specific feature thereof is input to the retrieval model to realize rapid location and tracking of the target in mass videos.
-
公开(公告)号：US20240289400A1
公开(公告)日：2024-08-29
申请号：US18517355
申请日：2023-11-22
发明人： Changben Zhou , Jian Xu
IPC分类号： G06F16/9537 , G06F16/9536 , G06Q50/00
CPC分类号： G06F16/9537 , G06F16/9536 , G06Q50/01
摘要： The present disclosure relates to the technical field of computer application. In an embodiment, a frequent pattern mining method based on a spatial index includes preprocessing data of a geographic social network, constructing a tree-like spatial index NaR-Tree, mining frequent patterns, setting a target search area, a result set size k and an example pattern c, and returning k patterns with the highest frequency expanded from c in the target area, and returning a result set comprising k patterns.
-
公开(公告)号：US12056957B1
公开(公告)日：2024-08-06
申请号：US18585111
申请日：2024-02-23
发明人： Zhendong Wu , Yanhua Huang
IPC分类号： G06V40/50 , G06V10/26 , G06V10/77 , G06V10/774 , G06V10/776 , G06V10/82 , G06V40/16 , H04L9/08
CPC分类号： G06V40/53 , G06V10/26 , G06V10/7715 , G06V10/774 , G06V10/776 , G06V10/82 , G06V40/162 , G06V40/169 , G06V40/171 , H04L9/0866
摘要： The invention relates to a personalized face biometric key generation method based on deep neural network coding, comprising: preprocessing a face image; converting the preprocessed face image into a feature map with a stability greater than or equal to 80% through a personalized feature extractor Feature_Extraction; outputting a face biometric key with a stability greater than or equal to 99% through a stabilizer Stabilizer; and carrying out error correction with an error correction code on the output biometric key through an error correction coding module and then obtaining a face biometric key with a stability greater than 99.5% through fuzzy extraction by a combined method of error correction code and fuzzy extraction. The finally generated face biometric key has high bit strength and recognition accuracy, can be directly applied to a symmetric cryptographic system and a public key cryptographic system as a key, and satisfies revocability and non-linkability.
-
46.发明授权公开(公告)号：US12025604B2
公开(公告)日：2024-07-02
申请号：US17551695
申请日：2021-12-15
申请人： Zhejiang University , Guangzhou Marine Geological Survey , Dalian University of Technology , Hangzhou Dianzi University
发明人： Jiawang Chen , Bo Xiao , Qiaoling Gao , Jiafei Zhao , Qinghua Sheng
CPC分类号： G01N33/24 , E21B25/18 , G01N1/286 , G01N1/42 , G01N2001/2873
摘要： A transfer and online detection system for deep-sea sediment samples and an application method thereof are provided. A sample gripping and feeding device, a sample segment cutting device, a sample online detection device, a high-pressure ball valve and a pressure-retaining drill disengaging device of the system are coaxially connected with one another. A seawater booster pump is connected with a water inlet ball valve, and a valve control panel is connected with the sample gripping and feeding device, the sample segment cutting device, the high-pressure ball valve and the pressure-retaining drill disengaging device. The pressure-retaining drill disengaging device is configured for disengaging an inner barrel and an inner barrel joint, and the sample gripping and feeding device and the sample segment cutting device are configured for gripping and cutting core samples, and conveying the cut core samples into a subsample pressure-retaining storage cylinder for storage.
-
47.发明公开公开(公告)号：US20240193986A1
公开(公告)日：2024-06-13
申请号：US18474529
申请日：2023-09-26
发明人： Wanzeng KONG , Xuanyu JIN , Ni LI , Jiajia TANG
IPC分类号： G06V40/10 , A61B5/00 , A61B5/117 , A61B5/316 , G06V10/62 , G06V10/764 , G06V10/774 , G06V10/776 , G06V10/82
CPC分类号： G06V40/15 , A61B5/117 , A61B5/316 , A61B5/725 , A61B5/7257 , G06V10/62 , G06V10/764 , G06V10/774 , G06V10/776 , G06V10/82
摘要： The present disclosure provides a task-independent brainprint recognition method based on feature disentanglement by decorrelation. Existing methods fail to mine inherent identity information of a brain, leading to poor robustness of brainprint recognition in a scenario across tasks and difficulty of promotion thereof in practical use. The present disclosure firstly uses two branch networks to perform coarse-grained decomposition of identity information and task related information in an electroencephalogram (EEG). Secondly, in consideration of an influence of a task state on the identity information, a decorrelating method is employed such that the identity information and the task related information are independent as much as possible. Finally, a brainprint feature in the EEG is fully utilized for classification by adversarial self-supervision. The method of the present disclosure is good in performance and capable of realizing efficient task-independent brainprint recognition, and is a brainprint recognition method robustly useful in the real life.
-
公开(公告)号：US20240193752A1
公开(公告)日：2024-06-13
申请号：US18483396
申请日：2023-10-09
发明人： Lingjun Zhang , Hua Zhang , Yifan Wu , Yifei Wu
IPC分类号： G06T7/00
CPC分类号： G06T7/0004 , G06T2207/20081 , G06T2207/20084 , G06T2207/30124
摘要： The present disclosure provides a fabric defect detection method, including the following steps: constructing a data set; preprocessing the data set; constructing a region-based convolutional neural network (R-CNN) model for fabric defect detection; where the R-CNN model for fabric defect detection includes four convolutional layers, four max-pooling layers, and two fully connected layers; training the R-CNN model for fabric defect detection; and reducing a number of false negative (FN) samples by classification threshold reduction. The present disclosure provides a novel R-CNN model for fabric defect detection. The model provides a desirable feature detection accuracy, has a low running cost, and is easy to implement, such that the model can be better applicable to actual operations in an industrial environment.
-
公开(公告)号：US20240161531A1
公开(公告)日：2024-05-16
申请号：US18493635
申请日：2023-10-24
发明人： Min ZHANG , Lingjie HE , Ming JIANG
CPC分类号： G06V40/10 , G06V10/26 , G06V10/806 , G06V10/82 , G06V20/52
摘要： The invention discloses a Transformer-based multi-scale pedestrian re-identification method. The present invention proposes a pedestrian re-identification network based on multi-scale pedestrian feature extraction and Transformer. Firstly, we designed a multi-scale feature cascade module, which aims to mine detailed feature information of pedestrians at different depths and scales, so as to obtain stronger feature representation. Secondly, we constructed a feature extraction based on Transformer to learn pedestrian features at a global scale. Finally, the features output by the Transformer are aggregated to obtain a better expression of pedestrian features, thereby improving the discrimination ability of the model. The result shows that this method has better robustness and adaptive ability, and effectively enhances the generalization ability of the model.
-
50.发明公开公开(公告)号：US20240153243A1
公开(公告)日：2024-05-09
申请号：US18447328
申请日：2023-08-10
发明人： Bishi He , Zhe Xu , Yuanjiao Chen , Diao Wang , Hui Chen
IPC分类号： G06V10/764 , G06T7/00
CPC分类号： G06V10/765 , G06T7/0012 , G06T2207/10081 , G06T2207/20076 , G06T2207/20081 , G06T2207/30061 , G06V2201/031
摘要： A Wasserstein distance and difference metric-combined chest radiograph anomaly identification domain adaptation method and a corresponding system are provided. The method includes the following steps: step 1, data preparation and data pre-processing for chest radiographs; step 2, multi-scale feature extraction based on a swin transformer network; step 3, loss minimization based on a Wasserstein distance and a contrastive domain discrepancy; and step 4, using the model to perform chest radiograph prediction after verifying the model. The method selects source domain samples closest to target domain samples, narrows a distance of the same class between the target domain samples and the source domain samples in feature space, and expands a distance between different classes. Meanwhile, a classification prediction task for the chest radiographs is performed by using the multi-scale features, improving a receptive field and capturing more information conducive to the classification prediction task.
-
-
-
-
-
-
-
-
-
搜索结果
55 条记录 (耗时 0.019 秒)
