-
公开(公告)号:US20250165683A1
公开(公告)日:2025-05-22
申请号:US18946547
申请日:2024-11-13
Applicant: Korea Electronics Technology Institute
Inventor: Jaekyu Lee , Sang Yub Lee , Inpyo Cho
IPC: G06F30/28 , G01R31/367
Abstract: Proposed is an artificial intelligence (AI) model-based analysis method for an optimal design of a secondary battery electrolyte. The AI model-based analysis method may include obtaining a tomography image of a calendared battery material, and inputting the tomography image to a pre-trained AI model. The method may also include outputting a viscosity and a transmittance of a battery electrolyte through the AI model. The AI model may include a first AI model configured to analyze porosity distribution and tortuosity information about the tomography image input thereto. The AI model may also include a second AI model configured to output a viscosity and a transmittance corresponding to the electrolyte, based on the porosity distribution and tortuosity information.
-
公开(公告)号:US20250149020A1
公开(公告)日:2025-05-08
申请号:US18396025
申请日:2023-12-26
Applicant: Korea Electronics Technology Institute
Inventor: Young Han LEE , Tae Woo KIM , Choong Sang CHO
IPC: G10L13/027 , G10L13/08
Abstract: There is provided a training dataset construction method for speech synthesis through fusion of language, speaker, emotion within an utterance. A training dataset construction method of a speech synthesis model according to an embodiment collects speech data having different speech utterance information, increases the speech data by fusing the collected speech data within one utterance, and generates a training dataset by using the increased speech data. Accordingly, a training dataset for speech synthesis is constructed through fusion of language, speaker, emotion within one utterance, so that quality of speech synthesis of multi-speaker/multi-language/emotion can be enhanced.
-
公开(公告)号:US20250148682A1
公开(公告)日:2025-05-08
申请号:US18938478
申请日:2024-11-06
Applicant: Korea Electronics Technology Institute
Inventor: Choong Il KIM , Sa Im SHIN , Jin Yea JANG , San KIM , Byung Gill JOE
Abstract: Provided are a method and a system for generating a human animation from SMPL series parameters. An animation generation method according to an embodiment includes: extracting, by a motion extraction module, motion information from an image content; converting, by a motion conversion module, the extracted motion information into parameters required by an animation generation module; and generating, by the animation generation module, a motion image of a human object from the converted motion information. Accordingly, an animation accurately showing motions of an object appearing in an image content by a more realistic 3D model may be generated and digital human contents of high reality may be created and used.
-
公开(公告)号:US20250117696A1
公开(公告)日:2025-04-10
申请号:US18524989
申请日:2023-11-30
Applicant: Korea Electronics Technology Institute
Inventor: JaeWon Moon , Seung Woo Kum , Seungtaek Oh
IPC: G06N20/00
Abstract: A method of generating a predictive model is proposed. The method may include receiving single time-series data or multiple types of time-series data collected in a specific domain, drawing time-series data corresponding to the same domain and time interval, among the received single time-series data or multiple types of time-series data. The method may also include pre-processing the drawn time-series data by applying a pre-processing pipeline built by applying at least one pre-processing module to the drawn time-series data, and generating a pattern classification model for classifying patterns of the pre-processed time-series data based on the clustering of the pre-processed time-series data. The method may further include generating a predictive model for predicting feature information of the drawn time-series data based on a cluster that is generated as the results of the clustering of the pre-processed time-series data, and storing the pattern classification model and the predictive model.
-
公开(公告)号:US20250105275A1
公开(公告)日:2025-03-27
申请号:US18823190
申请日:2024-09-03
Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE
Inventor: Woo Suk CHO , Hyun Seung KIM , Jun Ho SONG , Ji Sang YU , Kyung Su KIM
Abstract: Proposed is a positive electrode containing a positive electrode active material having a multimodal particle-size distribution to suppress particle crack of the positive electrode active material caused by pressure applied during a positive electrode and cell manufacturing process, thereby exhibiting excellent electrical characteristics. In addition, an all-solid-state battery including the positive electrode is proposed. The positive electrode may include a positive electrode active material formed of a lithium transition metal oxide and having a multimodal particle-size distribution in which particles with relatively small particle diameters have greater particle strength than particles with relatively large particle diameters.
-
公开(公告)号:US20250093815A1
公开(公告)日:2025-03-20
申请号:US18713785
申请日:2021-12-06
Applicant: Korea Electronics Technology Institute
Inventor: Sung Hee HONG , Young Min KIM , Ji Soo HONG
IPC: G03H1/04
Abstract: A continuous hologram recording method is provided. A holographic printer according to an embodiment of the present invention comprises: a light source that emits light; a modulator that modulates the light emitted from the light source, to generate a holographic fringe pattern in units of hogels; a stage having placed thereon a hologram recording medium on which a holographic fringe pattern generated by the modulator is to be recorded in units of hogels; a first driving unit that moves the position of the stage in a first axial direction by using a first-type motor; and a second driving unit that moves the position of the stage in a second axial direction by using a second-type motor different from the first type. Accordingly, continuous hologram recording is enabled by appropriately implementing a motor that moves the stage on which the hologram recording medium is placed, according to vibration characteristics, thereby remarkably reducing the printing time for large holograms, which used to take several days to tens of days, and thus accelerating the commercialization of hologram printing.
-
公开(公告)号:US12256055B2
公开(公告)日:2025-03-18
申请号:US18332596
申请日:2023-06-09
Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE
Inventor: Sung-Gyun Lim , Yong Hwan Kim , Hyun-Ho Kim , Yura Kim
IPC: H04N13/161 , H04N19/136
Abstract: A patch based depth mapping method and apparatus for high-efficiency encoding/decoding of a plenoptic video is proposed. The method may be performed in an electronic apparatus to classify a reference image and an additional image from a plenoptic video during encoding the plenoptic video and then generate an atlas including a patch using the additional image. The method may include mapping a depth value by applying minimum-maximum linear scaling in units of an input viewpoint image. The method may also include finding a minimum value and a maximum value of the depth value per the patch and remapping the depth value through minimum-maximum linear scaling.
-
公开(公告)号:US12244051B2
公开(公告)日:2025-03-04
申请号:US17877165
申请日:2022-07-29
Applicant: Korea Electronics Technology Institute
Inventor: Ki Jin Kim , Kwang Ho Ahn , Soo Chang Chae
Abstract: There is provided an ultra-small size broadband coupler. A Lange coupler according to an embodiment includes: first lines which are formed in a spiral shape, and have a first port and a second port formed at one end thereof and have connection ends formed at the other end thereof; and second lines which are formed in a spiral shape, and have connection ends formed at one end thereof to be connected to the connection ends of the first lines, and have a third port and a fourth port formed at the other end thereof. Accordingly, the Lange coupler maintains broadband characteristics while minimizing its area, so that it is possible to design a small component for mobile communication and to noticeably reduce an insertion loss.
-
公开(公告)号:US20250028280A1
公开(公告)日:2025-01-23
申请号:US18713728
申请日:2021-12-06
Applicant: Korea Electronics Technology Institute
Inventor: Sung Hee HONG , Young Min KIM , Ji Soo HONG
Abstract: A method and a system for foveated hologram rendering are provided. A method for foveated hologram rendering according to an embodiment of the present invention comprises: tracking a user's line of sight, rendering a hologram having a first resolution in the user's central line of sight, and rendering a hologram having a resolution lower than the first resolution in the user's peripheral line of sight. Accordingly, a hologram content with high quality and high resolution can be generated and reproduced at high speed through foveated hologram rendering in which holograms having different resolutions are rendered in the user's central line of sight and peripheral line of sight.
-
公开(公告)号:US12199450B2
公开(公告)日:2025-01-14
申请号:US18058688
申请日:2022-11-23
Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE
Inventor: Yong Ju Park , Yong Seok Lim , Yong Seong Kim , Hae Yong Jung , Hye Jung Kim
Abstract: A system for foreign object detection (FOD) in wireless power transfer is proposed. The system may include a balanced coil which is disposed between a transmitter coil and a receiver coil and which includes a Maxwell bridge circuit. The system may also include a temperature sensor configured to measure a temperature of the transmitter coil. The system may further include a processor configured to determine whether an FO is present between the transmitter coil and the receiver coil on the basis of voltage values detected at both ends of the bridge circuit. The FOD system can recognize the FO by finding a maximum resonant frequency at which a metal reacts using resonant frequency sweeping in a bridge circuit.
-
-
-
-
-
-
-
-
-