-
公开(公告)号:US20220036564A1
公开(公告)日:2022-02-03
申请号:US17352229
申请日:2021-06-18
Inventor: JongChul Ye , Sangjoon Park , Yujin Oh , Gwanghyun Kim
Abstract: Disclosed are a method of classifying lesions of chest x-ray radiographs based on data normalization and local patches and an apparatus thereof. The method includes converting an input chest x-ray radiograph into a normalized image, segmenting the converted normalized image into an organ area by using a first neural network based on a pre-learned segmentation model, generating local patches for the segmented organ area, and classifying a lesion in the input chest x-ray radiograph by using a second neural network based on a pre-learned classification model for the generated local patches.
-
公开(公告)号:US20220034908A1
公开(公告)日:2022-02-03
申请号:US17280567
申请日:2019-08-30
Inventor: Yong Mahn HAN , Hyo Sang DO
IPC: G01N33/68 , A23L33/13 , A61K31/713
Abstract: The present invention relates to a pharmaceutical composition for preventing or treating Fabry disease, containing a TSP1 protein inhibitor as an active ingredient. Particularly, in vascular endothelial cells produced by knocking out a TSP1 gene in induced pluripotent stem cells derived from a Fabry disease patient, of the present invention, the recovery of cell morphology, a decrease in the expression of a TSP1 gene, a decrease in the expression levels of a TSP1 protein and a phosphorylated-SMAD protein, which are anti-angiogenic factors, and an increase in the expression levels of a KDR protein and an eNOS protein, which are angiogenic factors, have been confirmed, and thus a TSP1 gene expression inhibitor or a TSP1 protein activity inhibitor can be effectively used in the treatment of Fabry disease.
-
993.
公开(公告)号:US11239479B2
公开(公告)日:2022-02-01
申请号:US16830649
申请日:2020-03-26
Inventor: Sai P. Katikaneni , Joongmyeon Bae , Jiwoo Oh , Minseok Bae , Dongyeon Kim
IPC: H01M8/04701 , H01M8/04223 , H01M8/04746 , H01M8/0612
Abstract: In accordance with one or more embodiments of the present disclosure, a method of starting a fuel reformer including a heating element and a subsequent autothermal reformer includes contacting a first fluid comprising oxygen with the heating element, passing the first fluid into the autothermal reformer to preheat a reformer catalyst within the autothermal reformer to a first temperature, reducing flow of the first fluid into the autothermal reformer, introducing a fuel into the autothermal reformer subsequent to preheating the reformer catalyst to initiate a partial oxidation reaction and generating additional heat, increasing flow of the fuel and first fluid to initiate autothermal reforming, and controlling the temperature of the reformer catalyst by supplying a cooling fluid, the first fluid, and the fuel and adjusting flow of each.
-
公开(公告)号:US20220028096A1
公开(公告)日:2022-01-27
申请号:US17169092
申请日:2021-02-05
Inventor: Doyeon KIM , Sihaeng LEE , Janghyeon LEE , Minki JO , Junmo KIM
IPC: G06T7/50
Abstract: A device includes an encoder configured to generate a plurality of feature data by encoding an image; a bottleneck circuit configured to generate enhanced feature data from first bottleneck data among the plurality of feature data; and a decoder configured to generate a depth map corresponding to the image by decoding the enhanced feature data and the plurality of feature data except the first bottleneck data.
-
公开(公告)号:US20220027741A1
公开(公告)日:2022-01-27
申请号:US17332696
申请日:2021-05-27
Inventor: JongChul Ye , Byeongsu Sim , Gyutaek Oh
Abstract: Disclosed are an unsupervised learning method and an apparatus therefor applicable to general inverse problems. An unsupervised learning method applicable to inverse problems includes receiving a training data set and training an unsupervised learning-based neural network generated based on an optimal transport theory and a penalized least square (PLS) approach using the training data set, wherein the receiving of the training data set includes receiving the training data set including unmatched data.
-
996.
公开(公告)号:US20220020155A1
公开(公告)日:2022-01-20
申请号:US17376588
申请日:2021-07-15
Inventor: JongChul Ye , Boah Kim
Abstract: Disclosed is an image segmentation method including receiving an image to be segmented and segmenting the received image by using a neural network learned through a Mumford-Shah function-based loss function.
-
公开(公告)号:US20220013734A1
公开(公告)日:2022-01-13
申请号:US17038319
申请日:2020-09-30
Inventor: Kum Hee LEE , Seungyeon KWAK , Aram JEON , Whail CHOI , Kyuyoung HWANG , Yoonhyun KWAK , Sangdong KIM , Won-joon SON , Byoungki CHOI , Hyeonho CHOI , Wooyoun KIM
Abstract: An organometallic compound represented by Formula 1: M(L1)n1(L2)n2 Formula 1 In Formula 1, M is a transition metal; L1 is a ligand represented by Formula 2 as disclosed herein; L2 is a monodentate ligand, a bidentate ligand, a tridentate ligand, or a tetradentate ligand; n1 is 1, 2, or 3, wherein, when n1 is 2 or greater, ligands L1 are identical to or different from each other; and n2 is 0, 1, 2, 3, or 4, wherein, when n2 is 2 or greater, ligands L2 are identical to or different from each other.
-
公开(公告)号:US20220006110A1
公开(公告)日:2022-01-06
申请号:US17367871
申请日:2021-07-06
Inventor: Sai P. Katikaneni , Kunho Lee , Kangyong Lee , Joongmyeon Bae , WooChul Jung
IPC: H01M8/0656 , H01M8/0662 , C01B3/04 , H01M4/86 , H01M4/90
Abstract: According to embodiments of the present disclosure, a solid oxide fuel cell includes a cathode, an anode, and a solid oxide electrolyte between the anode and the cathode. The solid oxide electrolyte includes a solid oxide, and the anode includes a porous scaffold. The porous scaffold includes a solid oxide having metal-based catalysts disposed on one or more surfaces of the porous scaffold. In embodiments, at least one ammonia decomposition layer is disposed proximate the surface of the porous scaffold and is configured to convert ammonia into hydrogen and nitrogen for subsequent feed of hydrogen to the anode. The ammonia decomposition layer also includes a metal decomposition catalyst.
-
公开(公告)号:US20220002884A1
公开(公告)日:2022-01-06
申请号:US17367890
申请日:2021-07-06
Inventor: Sai P. Katikaneni , Kunho Lee , Kangyong Lee , Joongmyeon Bae , WooChul Jung
IPC: C25B1/27 , H01M8/1246 , H01M8/1213 , H01M4/88 , H01M4/92 , C25B1/50 , C25B9/19 , C25B11/054 , C25B11/067 , C25B11/081 , C25B13/07
Abstract: According to embodiments of the present disclosure, a solid oxide fuel cell includes a cathode, an anode, and a solid oxide electrolyte disposed between the anode and the cathode. The anode includes a porous scaffold that includes a solid oxide having one or more metal nanoparticles disposed on one or more surfaces of the porous scaffold. The porous scaffold and the solid oxide electrolyte are formed from La0.8Sr0.2Ga0.83Mg0.17O2.815 (LSGM), and the metal nanoparticles are selected from the group consisting of platinum, nickel, gold, and combinations thereof. Methods of synthesizing ammonia using the fuel cell are also described.
-
公开(公告)号:US20210409871A1
公开(公告)日:2021-12-30
申请号:US17347415
申请日:2021-06-14
Inventor: Keonjae Lee , Young Hoon Jung , Jae Hyun Han , Hee Seung Wang , Mingi Chung
IPC: H04R17/02 , H01L41/053 , H01L41/09 , H01L41/187 , H01L41/318 , H03F3/183 , H04R3/04 , H04R1/04 , H04R17/00 , H04R7/04
Abstract: Provided is a voice sensor comprising a piezoelectric material layer includes a substrate, a support layer, a metal layer, a piezoelectric material layer on the metal layer and an electrode on the piezoelectric material layer, and the substrate integrally supports a device layer of the voice sensor by exposing a part of a thin film including the piezoelectric material layer, the electrode and a polymer layer.
-
-
-
-
-
-
-
-
-