公开(公告)号：US20230232794A1

公开(公告)日：2023-07-27

申请号：US17956771

申请日：2022-09-29

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY ,  YONSEI UNIVERSITY, UNIVERSITY - INDUSTRY FOUNDATION (UIF)

Inventor： Seok Gu KANG ,  Jeong Ho LEE ,  Joo Ho LEE ,  Jeong Eun LEE

IPC: A01K67/027

CPC classification number: A01K67/0276 ,  A01K2217/075 ,  A01K2227/105 ,  A01K2217/15 ,  A01K2267/0331

Abstract: The present invention relates to a brain tumor animal model that directly reflects the phenomenon in a human patient and a method of preparing the same, and more specifically, a brain tumor animal model that mutations are introduced into p53, Pten, and EGFR genes, a screening method of a therapeutic agent for a brain tumor using the animal model, and a preparing method thereof.

公开(公告)号：US20230221876A1

公开(公告)日：2023-07-13

申请号：US18151645

申请日：2023-01-09

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Myoungsoo JUNG ,  Miryeong KWON ,  Donghyun Gouk

IPC: G06F3/06

CPC classification number: G06F3/0644 ,  G06F3/061 ,  G06F3/0679

Abstract: A computational storage supporting graph machine learning acceleration includes a solid state drive (SSD) configured to store a graph data set; and a field-programmable gate array (FPGA) configured to download, to a memory, a graph machine learning model programmed in a form of a data flow graph by a host, wherein a hardware logic built in the FPGA performs access to the SSD through a peripheral component interconnect-express (PCIe) switch.

公开(公告)号：US20230221386A1

公开(公告)日：2023-07-13

申请号：US18149232

申请日：2023-01-03

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Kab-Jin Kim ,  Jun-Ho KANG

IPC: G01R33/07 ,  G01R33/02

CPC classification number: G01R33/07 ,  G01R33/0206

Abstract: A magnetic sensor includes a silicon substrate, a cross-shaped metal pattern formed on the silicon substrate and directly contacting the silicon substrate, and an insulating layer covering the cross-shaped metal pattern.

公开(公告)号：US20230216585A1

公开(公告)日：2023-07-06

申请号：US17775207

申请日：2020-03-03

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Yun Chur CHUNG ,  Byunggon KIM ,  Sunghyun BAE ,  Minsik KIM

IPC: H04B10/2513 ,  H04B10/516

CPC classification number: H04B10/2513 ,  H04B10/516

Abstract: Proposed are an optimal operation method of a high-frequency dithering technique for compensating for interference noise in an analog optical transmission-based mobile fronthaul network, and a transmitter using same. An interference noise compensation method using high-frequency phase dithering performed in an analog optical transmission-based mobile fronthaul network may include the steps in which: a frequency-multiplexed wireless signal is converted in an optical transmitter to an intensity-modulated optical signal; and the phase of the optical signal intensity-modulated in the optical transmitter is dithered with an Orthogonal Frequency-Division Multiplexing (OFDM) signal.

公开(公告)号：US20230216344A1

公开(公告)日：2023-07-06

申请号：US17752349

申请日：2022-05-24

Applicant: Korea Advanced Institute of Science and Technology

Inventor： In Gwun JANG ,  Mingi KIM ,  Minseok KANG

IPC: H02J50/12 ,  H02J50/40 ,  H02J50/80

CPC classification number: H02J50/12 ,  H02J50/40 ,  H02J50/80 ,  H02J50/90

Abstract: The embodiments relate to a real-time approximation method and apparatus of a mutual inductance between transmitters and receivers for determining an optimal operating condition in a multiple-receiver wireless power transfer system, and it may be configured to approximate a mutual inductance in the multiple-receiver wireless power transfer system according to a configuration status of the receivers, and determine an operating condition of the multiple-receiver wireless power transfer system based on the mutual inductance. According to the various example embodiments, the inductance may comprise a mutual inductance between the transmitter and the receivers, and a mutual inductance between the receivers.

公开(公告)号：US20230215133A1

公开(公告)日：2023-07-06

申请号：US17901148

申请日：2022-09-01

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sang Wan LEE ,  Shin Young JOO

IPC: G06V10/70 ,  G06N3/04

CPC classification number: G06V10/70 ,  G06N3/0454

Abstract: Disclosed is a method for self-supervised reinforcement learning (RL) by analogy executed by a computer device, the method including configuring a self-supervised RL with analogical reasoning (SRAR) model; and learning a policy for problem solving in a situation in which a task domain changes using the configured SRAR model.

公开(公告)号：US11695351B2

公开(公告)日：2023-07-04

申请号：US17580187

申请日：2022-01-20

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Seong Su Kim ,  Hyunsoo Hong ,  Muhammad Salmam Sarfraz ,  Wonvin Kim

IPC: H02N1/04

CPC classification number: H02N1/04

Abstract: Provided is a triboelectricity-based energy harvesting material including a first carbon composite layer, a second carbon composite layer, a first charge layer and a second charge layer applied onto the first carbon composite layer and the second carbon composite layer, respectively, and a spacer that is provided between the first charge layer and the second charge layer and maintains a predetermined interval between the first charge layer and the second charge layer, wherein the spacer is provided only in a partial region of the first charge layer and the second charge layer, and accordingly, the first charge layer and the second charge layer come into contact with each other according to deformation of the material in a region in which the spacer is not provided so as to generate triboelectricity.

公开(公告)号：US11682970B2

公开(公告)日：2023-06-20

申请号：US17843689

申请日：2022-06-17

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Gyu Hyeong Cho ,  Yeun Hee Huh ,  Se Un Shin ,  Sung Won Choi ,  Yong Min Ju ,  Sang Jin Lim

IPC: H02M3/158

CPC classification number: H02M3/158

Abstract: The present invention relates to a multi-path converter, which adds a current transfer path using a capacitor to a current transfer path using an inductor to supply a current that is output to an output end (load) to a plurality of parallel paths, thereby reducing a total RMS current flowing through the inductor, and a control method therefor.

公开(公告)号：US11681912B2

公开(公告)日：2023-06-20

申请号：US16759878

申请日：2017-11-16

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Kyung-su Kim ,  Yukyung Choi ,  Sung-jin Kim

IPC: G06N3/08 ,  G06N3/04 ,  G06T7/00 ,  G06T7/55 ,  G06T1/00 ,  G06V20/00

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06T1/00 ,  G06T7/0006 ,  G06T7/55 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V20/00

Abstract: Provided are an AI system for simulating functions such as recognition, determination, and so forth of human brains by using a mechanical learning algorithm like deep learning, or the like, and an application thereof. In particular, according to the AI system and the application thereof, a neural network training method includes obtaining a plurality of first images belonging to a particular category and a plurality of second images for which a category is not specified, training a neural network model for category recognition, based on the plurality of first images belonging to the particular category, recognizing at least one second image corresponding to the particular category among the plurality of second images, by using the trained neural network model, and modifying and refining the trained neural network model based on the recognized at least one second image.

公开(公告)号：US20230186113A1

公开(公告)日：2023-06-15

申请号：US17905316

申请日：2021-01-18

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Wonjoon Kim ,  JongHwan SUH

IPC: G06N5/022 ,  G06Q50/18

CPC classification number: G06N5/022 ,  G06Q50/184

Abstract: Disclosed are a machine learning-based future innovation prediction method and a system therefor. The machine learning-based future innovation prediction method according to an embodiment of the present invention may comprise the steps of: collecting patent data for each of predetermined companies, data relating to research and development of each of the companies, and performance data during a predetermined period; classifying feature sets according to respective features by using each piece of the collected data; and predicting future innovation of a corresponding company on the basis of machine learning using the classified feature sets as inputs, wherein the collecting step includes collecting patent data including the number of claims, an assignee, the number of assignees, an inventor, the number of inventors, the number of backward citations, and the number of forward citations for each of registered patents during a predetermined period with respect to each of the companies.