-
公开(公告)号：US11433392B2
公开(公告)日：2022-09-06
申请号：US16903415
申请日：2020-06-17
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Long Meng , Hairong Zheng , Kaiyue Wang , Wei Zhou , Lili Niu , Xiaowei Huang
IPC: B01L3/00
Abstract: A microfluidic chip (100), an apparatus, a system, and a control and preparation method therefor. The method comprises: a substrate (101), and an electrode layer (102) and a functional layer (103) sequentially formed on the substrate (101), said electrode layer (102) comprising a plurality of electrode groups (1021) arranged in an array, the electrode groups (1021) being used for converting electrical signals into acoustic signals when an electrode group is activated, and transmitting the acoustic signals to the functional layer (103); and the functional layer (103) being used for carrying a sample to be tested, and for absorbing the acoustic wave signals emitted by the activated electrode group (1021) and converting same into thermal energy for heating the sample to be tested that is carried at the position corresponding to the activated electrode group (1021).
-
公开(公告)号：US20220253975A1
公开(公告)日：2022-08-11
申请号：US17729890
申请日：2022-04-26
Inventor： Qin YANG , Pengfei WEI , Liping WANG
Abstract: The present invention provides a panoramic presentation method and apparatus. The present invention presents a panoramic image by using a combined structure of a single fisheye projector and a spherical screen in hardware, employs a geometrical relationship between a fisheye lens and the position of a viewer and isometric projection transformation, and enables 180° fisheye projection to present 720° environment information to the viewer in the center of the spherical screen, greatly simplifying the image conversion process and realizing zero distortion. According to a 720° panorama one-step generation method based on a single virtual camera in software, complex steps of collecting six images by a plurality of cameras, synthesizing a cube map and then converting the cube map into a panorama are not needed, the vertex position of a scene is directly adjusted in the process from a 3D space to a 2D image
-
23.发明申请公开(公告)号：US20220222592A1
公开(公告)日：2022-07-14
申请号：US17619112
申请日：2020-03-26
Applicant: Shenzhen Institutes of Advanced Technology
Inventor： Lei PENG , Kangshuai ZHANG , Huiyun LI
Abstract: A method and an apparatus for determining a service area of a parking lot, a device and a storage medium are provided. The method includes the following: clustering is performed on all first parking lots to obtain at least one second parking lot set according to an initial weight and initial position information of each first parking lot in a first parking lot set; a transition probability matrix corresponding to each second parking lot in each second parking lot set is determined according to the initial weight and the initial position information, where a transition probability in the transition probability matrix is used for indicating a probability that a parking user transfers to another second parking lot in the same second parking lot set when there is no empty parking space in the second parking lot; and a service capacity value of each second parking lot is determined.
-
公开(公告)号：US20220188978A1
公开(公告)日：2022-06-16
申请号：US17340117
申请日：2021-06-07
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Zhanli HU , Hairong ZHENG , Na ZHANG , Xin LIU , Dong LIANG , Yongfeng YANG , Hanyu SUN
Abstract: The present application relates to a method and system for generating multi-task learning-type generative adversarial network for low-dose PET reconstruction, and relates to the field of deep learning. The method includes connecting layers of the encoder with layers of the decoder by skip connection to provide a U-Net type picture generator; generating a group of generative adversarial networks by matching a plurality of picture generators with a plurality of discriminators in one-to-one manner; obtaining a first multi-task learning-type generative adversarial network; designing a joint loss function 1 for improving image quality; and training the first multi-task learning-type generative adversarial network according to the joint loss function 1 in combination with an optimizer to provide a second multi-task learning-type generative adversarial network.
-
公开(公告)号：US11295619B2
公开(公告)日：2022-04-05
申请号：US17121141
申请日：2020-12-14
Applicant: Shenzhen Institutes of Advanced Technology
Inventor： Lei Peng , Yuqiang Sun , Huiyun Li
Abstract: A parking lot data repair method and apparatus, a device, and a storage medium. The method comprises: calculating spatial similarity between two parking lots according to the spatial features of the parking lots and a spatial similarity measurement model; clustering the parking lots into different parking lot clusters according to the spatial similarity, and calculating a spatial similarity probability corresponding to each parking lot cluster; calculating data similarity between two sample parking lots in the same parking lot cluster, and according to the data similarity and the spatial similarity probability corresponding to the parking lot cluster, calculating the data similarity probability of the parking lot cluster under a similar spatial condition; and when the data similarity probability under the similar spatial condition exceeds a probability threshold value, performing data repair on the parking lot to be repaired in the parking lot cluster by means of a cyclic generation-type confrontation network.
-
Patent Agency Ranking
26.发明申请公开(公告)号：US20220092336A1
公开(公告)日：2022-03-24
申请号：US17542692
申请日：2021-12-06
Applicant: Shenzhen Institutes of Advanced Technology
Abstract: An adversarial image generation method, a computer device, and a computer-readable storage medium are provided. The method includes the following. A reference model classification-equivalent with a target classification model is generated according to the target classification model. A target image is obtained and an original noise for the target image is generated according to the reference model. A first noise and the original noise are input into an adversarial model and a second noise corresponding to the first noise is output when the adversarial model meets a convergence condition, where the second noise enhances an information entropy of the original noise. An enhanced noise image corresponding to the target image is generated according to the second noise and the target image, where a classification accuracy of the enhanced noise image in the target classification model is less than a classification accuracy of the target image in the target classification model.
-
公开(公告)号：US11212672B2
公开(公告)日：2021-12-28
申请号：US17036222
申请日：2020-09-29
Inventor： Fangmin Sun , Ye Li
IPC: H04M1/66 , H04M1/68 , H04M3/16 , H04W12/0431 , H04W4/80 , H04W12/041 , H04L9/08 , H04W12/037
Abstract: The embodiments of the present disclosure are applicable to the technical field of computer science and application technology, and disclose a wireless body area network, a key generation method and a key distribution method in the wireless body area network, and a related device. The gait acceleration signal is extracted synchronously through the respective acceleration acquisition devices integrated with the coordinator and the wearable equipment, the position information corresponding to the peak value and the valley value in the gait acceleration signal is correspondingly extracted and is taken as the gait common information, and the gait common information is used to perform key distribution in the wireless body area network, the security and the consistency are higher, the calculation is simplified, the key distribution method is suitable for wearable devices having limited resources.
-
公开(公告)号：US11203112B2
公开(公告)日：2021-12-21
申请号：US16862603
申请日：2020-04-30
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Guoru Zhao , Yongfeng Wang
Abstract: A three-degree-of-freedom parallel mechanism, includes a fixed platform, a movable platform, and three kinematic chains, where at least one of the three kinematic chains is a flexible chain; and the flexible chain includes a first connecting rod, a second connecting rod, and an axis-variable revolute pair, the axis-variable revolute pair includes a fixed member, a movable member, and a spherical pair, one end of the fixed member is fastened on the fixed platform, the other end of the fixed member fits and abuts against an inclined surface of the movable member, the spherical pair is accommodated in the fixed member, a spherical hinge connecting rod of the spherical pair penetrates the movable member, the first connecting rod is rotatably connected to the spherical hinge connecting rod and the second connecting rod, and the second connecting rod is spherically hinged to the movable platform.
-
公开(公告)号：US20210217419A1
公开(公告)日：2021-07-15
申请号：US16960496
申请日：2019-12-31
Inventor： Shixiong CHEN , Mingxing ZHU , Xiaochen WANG , Guanglin LI , Zijian YANG , Xin WANG
Abstract: The present application discloses a lip-language recognition AAC system based on surface electromyography, which includes: a training subsystem configured to collect the facial and neck EMG signals during lip-language movements through the high-density electrode array, improve the signal quality through the signal preprocessing algorithm, classify the lip-language movements through the classification algorithm, select the optimal number of electrodes and optimal positions through the channel selection algorithm, and establish the optimal matching template between the EMG signals and the lip-language information, and upload it to the network terminal for storage; and a detection subsystem configured to collect the EMG signals at the optimal positions during the lip-language movements based on the optimal number and positions of electrodes selected by the training subsystem, call the optimal matching template, classify and decode the EMG signals, recognize the lip-language information, and convert it into corresponding voice and picture information for display in real time.
-
30.发明申请公开(公告)号：US20210128049A1
公开(公告)日：2021-05-06
申请号：US16927948
申请日：2020-07-13
Applicant: SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY
Inventor： Shixiong CHEN , Mingxing ZHU , Guanglin LI , Zijian YANG , Jiashuo ZHUANG , Xiaochen WANG , Xin WANG
Abstract: A pronunciation function evaluation system based on array high-density surface electromyography, this system includes a host computer and a slave computer, the slave computer is configured to obtain faciocervical electromyography signal through electromyography electrode arrays in a pronunciation process and to transmit the faciocervical electromyography signals to the host computer; the host computer is configured to analyze a physiological relevance between faciocervical array high-density electromyography signal features change and pronunciation function in the pronunciation process, to establish a three-dimensional dynamic energy distribution diagram of faciocervical muscular movement in the pronunciation process, to obtain dynamic visual temporal and spatial characteristic of articulatory muscles related to pronunciation, to extract electromyography features, to establish a faciocervical electromyography feature distribution standard database with normal pronunciation function, and to analyze a dysfunction condition and a damage degree of the pronunciation muscle group using a template matching and differentiation analysis algorithm.
-
-
-
-
-
-
-
-
-
Search Results
292
records
(took 0.026 seconds)
