Patents by Inventor Ji-Hoon Bae
Ji-Hoon Bae has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11922622Abstract: The present invention relates to a breast image analysis method with four mammogram images which are input to a convolutional neural network as one input and a system therefor and the system includes an image receiving unit which receives four mammogram images; an image size adjusting unit which adjusts a size of a mammogram image received from the image receiving unit; a preprocessing unit which performs preprocessing on the mammogram image adjusted by the image size adjusting unit; a convolutional neural network (CNN)-based CNN learning unit which generates learning information by learning the mammogram image preprocessed by the preprocessing unit; and a CNN inference unit which receives the learning information learned from the CNN learning unit and a mammogram image to be classified from the image receiving unit to diagnose a breast abnormality.Type: GrantFiled: August 22, 2019Date of Patent: March 5, 2024Assignee: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATIONInventors: Myung Hoon Sunwoo, Ji Hoon Bae
-
Patent number: 11304388Abstract: A method for promoting growth and bioactive substances of Crepidiastrum denticulatum including performing a stress treatment on Crepidiastrum denticulatum during cultivation thereof, in which the stress treatment includes at least of applying visible light, drying, exposing to low temperature, irradiating ultraviolet rays, and applying a chemical elicitor.Type: GrantFiled: April 26, 2017Date of Patent: April 19, 2022Assignees: Seoul Viosys Co., Ltd., INDUSTRY-UNIVERSITY COOPERATION FOUNDATION OF CHUNGBUK NATIONAL UNIVERSITYInventors: Myung Min Oh, Song Yi Park, Jin Hui Lee, Ji Hoon Bae, Jong Hyun Koo
-
Publication number: 20220036544Abstract: The present invention relates to a breast image analysis method with four mammogram images which are input to a convolutional neural network as one input and a system therefor and the system includes an image receiving unit which receives four mammogram images; an image size adjusting unit which adjusts a size of a mammogram image received from the image receiving unit; a preprocessing unit which performs preprocessing on the mammogram image adjusted by the image size adjusting unit; a convolutional neural network (CNN)-based CNN learning unit which generates learning information by learning the mammogram image preprocessed by the preprocessing unit; and a CNN inference unit which receives the learning information learned from the CNN learning unit and a mammogram image to be classified from the image receiving unit to diagnose a breast abnormality.Type: ApplicationFiled: August 22, 2019Publication date: February 3, 2022Applicant: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATIONInventors: Myung Hoon SUNWOO, Ji Hoon BAE
-
Patent number: 11144833Abstract: Provided are a data processing apparatus and method for merging and processing deterministic knowledge and non-deterministic knowledge. The data processing apparatus and method may efficiently process various real-time and large-scale data to convert the data into knowledge by merging and processing non-deterministic knowledge and also deterministic knowledge perceived by an expert. Thus, it is possible to adaptively operate in accordance with a dynamically changing application service environment by converting a conversion rule for converting collected data generated from an application service system into semantic data, a context awareness rule for perceiving context information from given information, and a user query for searching for knowledge information into knowledge and gradually augmenting the knowledge information in accordance with an application service environment.Type: GrantFiled: August 31, 2017Date of Patent: October 12, 2021Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Soon Hyun Kwon, Eun Joo Kim, Hong Kyu Park, Hyun Joong Kang, Kwi Hoon Kim, Young Min Kim, Hyun Jae Kim, Ji Hoon Bae, Se Won Oh, Jae Hak Yu, Yeon Hee Lee, Ho Sung Lee, Nae Soo Kim, Sun Jin Kim, Cheol Sig Pyo
-
Publication number: 20200097850Abstract: An apparatus/method for extracting multiple features from time series data collected from a plurality of sensors and for performing transfer learning on them. There is provided an apparatus including: a multi-feature extraction unit for extracting multiple features from a data stream for each sensor inputted from the plurality of sensors; a transfer-learning model generation unit for extracting useful multi-feature information from a learning model which has finished pre-learning, for the multiple features for forwarding the extracted multi-feature information to a multi-feature learning unit to generate a learning model that performs transfer learning on the multiple features; and the multi-feature learning unit for receiving learning variables from the learning model for each of the multiple features and for performing parallel learning for the multiple features, to calculate and output a loss. In addition, there is provided an apparatus for detecting leaks in plant pipelines.Type: ApplicationFiled: September 9, 2019Publication date: March 26, 2020Inventors: Ji Hoon BAE, Gwan Joong KIM, Soon Sung MOON, Jin Ho PARK, Bong Su YANG, Do Yeob YEO, Se Won OH, Doo Byung YOON, Jeong Han LEE, Seong Ik CHO, Nae Soo KIM, Cheol Sig PYO
-
Patent number: 10565699Abstract: Provided are an apparatus and method for detecting an anomaly in a plant pipe using multiple meta-learning. When a multi-sensor data stream about a plant pipe is received, each of a plurality of meta-learning modules for processing different packet section ranges, extracts one or more preset types of features from sensor data of packet section ranges set according to trend from an arbitrary reception time point, generates 2D image features of the features according to multi-sensor-specific times, generates 3D volume features by accumulating the 2D image features in a depth direction according to multiple sensors, and learns the 3D volume features in parallel through multi-sensor-specific learning modules. Results of the learning of the meta-learning modules are aggregated, and it is determined whether there is an anomaly in a plant pipe according to a learning result selected based on an optimal combination of multiple features, multiple sensors, and multiple packet sections.Type: GrantFiled: April 11, 2018Date of Patent: February 18, 2020Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KOREA ATOMIC ENERGY RESEARCH INSTITUTEInventors: Ji Hoon Bae, Gwan Joong Kim, Se Won Oh, Doo Byung Yoon, Wan Seon Lim, Kwi Hoon Kim, Nae Soo Kim, Sun Jin Kim, Cheol Sig Pyo
-
Publication number: 20190150378Abstract: A method for promoting growth and bioactive substances of Crepidiastrum denticulatum including performing a stress treatment on Crepidiastrum denticulatum during cultivation thereof, in which the stress treatment includes at least of applying visible light, drying, exposing to low temperature, irradiating ultraviolet rays, and applying a chemical elicitor.Type: ApplicationFiled: April 26, 2017Publication date: May 23, 2019Applicants: Seoul Viosys Co., Ltd., Industry-University Cooperation Foyndation of Chungbuk National UniversityInventors: Myung Min OH, Song Yi PARK, Jin Hui LEE, Ji Hoon BAE, Jong Hyun KOO
-
Publication number: 20180293723Abstract: Provided are an apparatus and method for detecting an anomaly in a plant pipe using multiple meta-learning. When a multi-sensor data stream about a plant pipe is received, each of a plurality of meta-learning modules for processing different packet section ranges, extracts one or more preset types of features from sensor data of packet section ranges set according to trend from an arbitrary reception time point, generates 2D image features of the features according to multi-sensor-specific times, generates 3D volume features by accumulating the 2D image features in a depth direction according to multiple sensors, and learns the 3D volume features in parallel through multi-sensor-specific learning modules. Results of the learning of the meta-learning modules are aggregated, and it is determined whether there is an anomaly in a plant pipe according to a learning result selected based on an optimal combination of multiple features, multiple sensors, and multiple packet sections.Type: ApplicationFiled: April 11, 2018Publication date: October 11, 2018Applicants: Electronics and Telecommunications Research Institute, KOREA ATOMIC ENERGY RESEARCH INSTITUTEInventors: Ji Hoon BAE, Gwan Joong Kim, Se Won Oh, Doo Byung Yoon, Wan Seon Lim, Kwi Hoon Kim, Nae Soo Kim, Sun Jin Kim, Cheol Sig Pyo
-
Publication number: 20180189655Abstract: Provided is a data meta-scaling method. The data meta-scaling method optimizes an abbreviation criterion for abbreviating data through continuous knowledge augmentation in various dimensions which enable expression of data in a process of performing machine learning.Type: ApplicationFiled: December 26, 2017Publication date: July 5, 2018Applicant: Electronics and Telecommunications Research InstituteInventors: Se Won OH, Yeon Hee Lee, Ji Hoon Bae, Hyun Joong Kang, Soon Hyun Kwon, Kwi Hoon Kim, Young Min Kim, Eun Joo Kim, Hyun Jae Kim, Hong Kyu Park, Jae Hak Yu, Ho Sung Lee, Seong Ik Cho, Nae Soo Kim, Sun Jin Kim, Cheol Sig Pyo
-
Publication number: 20180189679Abstract: Provided are a self-learning system and method for automatically performing machine learning (ML). The self-learning system includes a memory configured to store an ML knowledge database (DB) in which ML knowledge is stored and a program for automatically performing ML based on request information of a user, and a processor configured to execute the program stored in the memory. Here, when executing the program, the processor creates or recommends at least one workflow corresponding to the request information of the user based on the ML knowledge stored in the ML knowledge DB and generates an execution code for performing the created or recommended workflow.Type: ApplicationFiled: January 2, 2018Publication date: July 5, 2018Applicant: Electronics and Telecommunications Research InstituteInventors: Hyun Joong KANG, Hyun Jae Kim, Ho Sung Lee, Soon Hyun Kwon, Kwi Hoon Kim, Young Min Kim, Eun Joo Kim, Hong Kyu Park, Ji Hoon Bae, Se Won Oh, Jae Hak Yu, Yeon Hee Lee, Nae Soo Kim, Sun Jin Kim, Seong Ik Cho, Cheol Sig Pyo
-
Publication number: 20180144250Abstract: Provided are a data processing apparatus and method for merging and processing deterministic knowledge and non-deterministic knowledge. The data processing apparatus and method may efficiently process various real-time and large-scale data to convert the data into knowledge by merging and processing non-deterministic knowledge and also deterministic knowledge perceived by an expert. Thus, it is possible to adaptively operate in accordance with a dynamically changing application service environment by converting a conversion rule for converting collected data generated from an application service system into semantic data, a context awareness rule for perceiving context information from given information, and a user query for searching for knowledge information into knowledge and gradually augmenting the knowledge information in accordance with an application service environment.Type: ApplicationFiled: August 31, 2017Publication date: May 24, 2018Applicant: Electronics and Telecommunications Research InstituteInventors: Soon Hyun KWON, Eun Joo KIM, Hong Kyu PARK, Hyun Joong KANG, Kwi Hoon KIM, Young Min KIM, Hyun Jae KIM, Ji Hoon BAE, Se Won OH, Jae Hak YU, Yeon Hee LEE, Ho Sung LEE, Nae Soo KIM, Sun Jin KIM, Cheol Sig PYO
-
Publication number: 20170156541Abstract: A cup-shaped container capable of being converted into a Dutch coffee machine includes a main body of cup-shape, a drainer protrusion protruding outward from the bottom surface of the main body, and a drain hole to connect to an inside of the drainer protrusion and an inside of the main body. The cup-shaped container can be used as a cup in normal times and can be converted into a Dutch coffee machine by simple operation when necessary.Type: ApplicationFiled: May 27, 2015Publication date: June 8, 2017Applicant: HUMMING PAPER CO.LTDInventors: Jung-hoon BAE, Ji-hoon BAE
-
Patent number: 9418259Abstract: Disclosed herein are a tag transmission apparatus and a signal transmitting method thereof. The tag transmission apparatus converts a plurality of data bits into a symbol, which is one of a plurality of symbols, and multiplies the converted symbol by a square-wave having a predetermined frequency to thereby generate a subcarrier signal. Here, in the case in which the plurality of data bits are n (n is a natural number larger than 2) bits, the number of the plurality of symbols is 2n.Type: GrantFiled: October 6, 2014Date of Patent: August 16, 2016Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Sang Hyun Mo, Ji-Hoon Bae, Chan-Won Park, Cheol Sig Pyo
-
Patent number: 9256771Abstract: A tag of an apparatus for simultaneously identifying massive tags according to the present invention may include an analog circuit unit to communicate with a reader through an analog signal and to receive energy via magnetic coupling with the reader. Further, the tag may include a digital circuit unit to be supplied with power from the analog circuit unit. The digital circuit unit may support a sleep mode for the tag to stand by in a low power state after transmitting an identifier (ID) to the reader and a wait mode for controlling random access to the reader.Type: GrantFiled: October 18, 2013Date of Patent: February 9, 2016Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Ji Hoon Bae, Kwang Soo Cho, Man Sik Park, Won Kyu Choi, Hoe Sung Yang, Chan-Won Park, Jong-Suk Chae, Cheol Sig Pyo
-
Patent number: 9033233Abstract: A reader antenna includes dipole antennas, the dipole antennas including: a horizontal dipole antenna having the characteristic of horizontal polarization; and a dipole antenna perpendicular to the horizontal dipole antenna and including a vertical dipole antenna having the characteristic of vertical polarization, wherein the horizontal dipole antenna and the vertical dipole antenna may both have the characteristic of circular polarization. The reader antenna can be easily stored in an electronic shelf because it is realized in an ultrathin structure using a single-layered dielectric substrate.Type: GrantFiled: January 22, 2013Date of Patent: May 19, 2015Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Won Kyu Choi, Jae-Young Jung, Seung-Hwan Jeong, Ji-Hoon Bae, Gil Young Choi, Jong-Suk Chae, Chan-Won Park, Cheol Sig Pyo
-
Publication number: 20150097654Abstract: Disclosed herein are a tag transmission apparatus and a signal transmitting method thereof. The tag transmission apparatus converts a plurality of data bits into a symbol, which is one of a plurality of symbols, and multiplies the converted symbol by a square-wave having a predetermined frequency to thereby generate a subcarrier signal. Here, in the case in which the plurality of data bits are n (n is a natural number larger than 2) bits, the number of the plurality of symbols is 2n.Type: ApplicationFiled: October 6, 2014Publication date: April 9, 2015Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Sang Hyun MO, Ji-Hoon BAE, Chan-Won PARK, Cheol Sig PYO
-
Publication number: 20150009014Abstract: A tag transmitting apparatus of a passive RFID (radio frequency identification) system generates a pilot tone, a preamble, and an SFD (start frame delimiter) and transmits the pilot, the preamble, and the SFD, using one of a plurality of square waves.Type: ApplicationFiled: April 15, 2014Publication date: January 8, 2015Applicants: Electronics and Telecommunications Research Institute, Seoul National University of Science & Technology, Foundation for Research & BusinessInventors: Sang Hyun MO, Ji-Hoon BAE, Hyung Chul PARK, Jae-young JUNG, Hoe-Sung YANG, Chan-Won PARK, Cheol Sig PYO
-
Patent number: 8890658Abstract: An RFID system using an M pulse amplitude modulation (M-PAM) or M quadrature amplitude modulation (M-QAM) scheme using a plurality of load-modulators, a plurality of antennas, and a communication method thereof are provided. The RFID system includes: an RFID tag; and a reader device communicating with the RFID device, wherein the RFID tag includes: N load-modulators an N antennas communicating with the reader device in any one scheme of M-pulse amplitude modulation (M-PAM) and M-quadrature amplitude modulation (M-QAM) in which modulation of an M level is performed and operated corresponding to the M level.Type: GrantFiled: August 14, 2012Date of Patent: November 18, 2014Assignees: Electronics and Telecommunications Research Institute, Seoul National University of Technology Center for Industry CollaborationInventors: Ji Hoon Bae, Chan Won Park, Hyung Chul Park, Jong Suk Chae, Cheol Sig Pyo
-
Publication number: 20140306805Abstract: A tag apparatus communicating with a reader acquires a command from a signal that is received from the reader, converts data corresponding to the acquired command to a plurality of multi-level parallel data, and generates a plurality of tag load impedances based on bias voltages that are mapped to correspond to each level of the plurality of parallel data. Therefore, a signal having electrical energy corresponding to the plurality of tag load impedances is transmitted to the reader.Type: ApplicationFiled: August 27, 2013Publication date: October 16, 2014Applicant: Electronics and Telecommunications Research InstituteInventors: Jae-young JUNG, Ji-Hoon BAE, Won Kyu CHOI, Kyu Won HAN, Chan-Won PARK, Jong-Suk CHAE, Cheol Sig PYO, Hoe-Sung YANG
-
Patent number: 8724761Abstract: Provided is a symbol synchronization apparatus and method of a passive RFID reader. The symbol synchronization apparatus includes: an edge clock detector generating edge clocks by detecting phase inversion positions of a received signal; a preamble detector detecting a preamble section by analyzing the generation times of the edge clocks; a symbol decision time extractor extracting a symbol decision time by averaging distances between the edge clocks consecutively generated in the preamble section, when the preamble section is detected; and a symbol decider deciding a symbol by analyzing the magnitude of the received signal, when the time reaches the symbol decision time.Type: GrantFiled: July 8, 2010Date of Patent: May 13, 2014Assignee: Electronics and Telecommunications Research InstituteInventors: Ji Hoon Bae, Dong Han Lee, Kwang Soo Cho, Won Kyu Choi, Man Sik Park, Chan Won Park, Cheng Hao Quan, Gil Young Choi, Jong Suk Chae