Patents by Inventor Yeonghyeon PARK

Yeonghyeon PARK 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).

  • Publication number: 20250046072
    Abstract: The present invention relates to a device for detecting a defect of a solar panel and a method for operating same, wherein the device for detecting a defect of a solar panel comprises: a model providing unit that provides a pre-trained model; a communication module that receives captured images of a solar panel from an image sensor; a processing module functionally connected to the model providing unit and the communication module, wherein the processing module is configured to collect the captured images of the solar panel, apply the captured images to the pre-trained model to create an attention map, and determine whether there is a defect in the solar panel depending on whether the attention map is abnormal.
    Type: Application
    Filed: October 23, 2024
    Publication date: February 6, 2025
    Inventor: Yeonghyeon PARK
  • Publication number: 20240395013
    Abstract: Embodiments relate to acquiring a spectral image of a liquid product including a liquid substance injected therein. A data cube corresponding to the spectral image captured for the liquid substance of the liquid product is acquired. The data cube may be divided into windows of a predetermined size. A current relationship matrix indicating a relationship between pixel values included in the divided windows is obtained. Whether the liquid product contains a foreign matter is determined, based on the current relationship matrix.
    Type: Application
    Filed: May 27, 2024
    Publication date: November 28, 2024
    Inventor: Yeonghyeon PARK
  • Publication number: 20240394860
    Abstract: A captured image of a target area corresponding to a parking lot is captured through a camera and generate a depth map for the captured image. Binarized data for the generated depth map is produced. The number of vehicles parked in the target area is calculated based on the binarized data, and parking situation analysis is performed according to the number of parked vehicles. Processing is performed according to a result of the parking situation analysis. Also, flooding is predicted using a learning model.
    Type: Application
    Filed: May 24, 2024
    Publication date: November 28, 2024
    Inventor: Yeonghyeon PARK
  • Publication number: 20240378448
    Abstract: An electronic device and method are provided for generating abnormal data among learning data required for training a machine learning model. In addition, an electronic device and method are provided for a product anomaly detection using a model trained based on unsupervised learning. Embodiments may solve the data imbalance problem for learning by generating as much abnormal data as necessary based on normal data and provide an unsupervised learning-based anomaly detection method and electronic device that can provide stable performance without increasing the size or complexity of the artificial neural network and thus requiring relatively high-performance computing equipment.
    Type: Application
    Filed: May 3, 2024
    Publication date: November 14, 2024
    Inventor: Yeonghyeon PARK
  • Publication number: 20240337624
    Abstract: Deriving a dangerous area of a road based on a vehicle's noise generated on the road or analyzing a road surface condition based on a driving noise for each vehicle type. An audio signal is collected by a sensor device and send to a noise processing unit. The noise processing unit generates an attenuated audio signal by attenuating a noise other than a noise-of-interest including at least one of a vehicle horn noise and a vehicle sudden brake noise in the received audio signal. An information processing unit detects the noise-of-interest by analyzing the attenuated audio signal through a learned detection model, and establishes a road area within a predetermined radius from the sensor device as the dangerous area of the road based on an accumulated number of times the noise-of-interest is detected.
    Type: Application
    Filed: June 21, 2024
    Publication date: October 10, 2024
    Inventors: JongHee JUNG, Yeonghyeon PARK, JoonSung LEE
  • Publication number: 20240296328
    Abstract: A method for interpolating a missing value of the present invention comprises the steps of: collecting, by a data processing unit, a data set obtained by selecting an intact whole signal without a missing part from among a plurality of unit signals configuring a sensor signal; training, by a training unit, an interpolation network for interpolating a missing part in a missing signal having the missing part, wherein at least a part of a sensor signal is missing, by using the data set; receiving, by an interpolation unit, an input of the missing signal in which at least a part of the sensor signal is missing; and generating, by the interpolation unit, an interpolation signal by interpolating the missing part by using the interpolation network.
    Type: Application
    Filed: April 26, 2024
    Publication date: September 5, 2024
    Inventors: Yeonghyeon PARK, Joonsung LEE
  • Publication number: 20240255933
    Abstract: A method for labeling comprises: a clustering unit forms a plurality of nodes, upon the input of a plurality of pieces of data, by projecting the plurality of pieces of input data onto a predetermined vector space; the clustering unit generates clusters by clustering the plurality of nodes; a labeling unit carries out connected component analysis of the generated clusters to derive one or more connected components; and the labeling unit labels the connected components. In addition, an anomaly detection method based on clustering of the present invention comprises the step in which a detecting unit determines whether difference between a mock data cluster and an input data cluster is equal to or greater than a preset threshold value and, if the difference is determined to be equal to or greater than a preset threshold value, determines that there is an anomaly in the input data cluster.
    Type: Application
    Filed: April 11, 2024
    Publication date: August 1, 2024
    Inventor: Yeonghyeon PARK
  • Publication number: 20240203096
    Abstract: A device and method are provided for detecting foreign matters in a cathode active material by identifying, based on a spectral image of the cathode active material, whether the cathode active material contains foreign matters. In addition, a device and method are provided for managing residues in a cathode active material by controlling the residual amount of a removal target in the cathode active material, based on a spectral image of the cathode active material.
    Type: Application
    Filed: December 18, 2023
    Publication date: June 20, 2024
    Inventor: Yeonghyeon PARK
  • Publication number: 20240070851
    Abstract: The present invention relates to a data set generation method and an electronic device supporting the same. The method includes collecting an original good product image and an original defect image for the purpose of generating a training data set, extracting a defective part from the original defect image, and mixing the extracted defective part with the original good product image. In the method, mixing includes performing mixing of latent vectors between the defective part and the original good product image.
    Type: Application
    Filed: August 24, 2023
    Publication date: February 29, 2024
    Inventor: Yeonghyeon PARK
  • Publication number: 20230349752
    Abstract: According to the present invention, a sound anomaly detection method includes acquiring, by an audio unit, a noise from an inspection target; generating, by a data processing unit, an input value that is a feature vector matrix including a plurality of feature vectors from the noise; generating, by a detection unit, a restored value imitating the input value through a detection neural network that is a deep neural network learned for the input value; determining, by the detection unit, whether a restoration error indicating a difference between the input value and the restored value is greater than or equal to a calculated reference value; and determining, by the detection unit, that there is an anomaly in the inspection target when determining that the restoration error is greater than or equal to the reference value.
    Type: Application
    Filed: July 12, 2023
    Publication date: November 2, 2023
    Inventors: Yeonghyeon PARK, Jong Hee JUNG
  • Publication number: 20230184722
    Abstract: Analyzing the condition of a road surface by using a frequency-of-interest or a resonance sound in a tire. A training audio signal is sent to a learning unit, a label generator and a frequency selection model that does not complete learning. The training audio signal is obtained by collecting driving noise generated when a vehicle travels on a road. The label generator generates a label audio-of-interest signal by attenuating a band other than a frequency-of-interest band in the training audio signal. The frequency selection model derives a training imitated audio-of-interest signal imitating an audio-of-interest signal by performing a plurality of operations in which an unlearned weight is applied to the training audio signal. The learning unit calculates a generation loss that is a difference between the training imitated audio-of-interest signal and the label audio-of-interest signal, and performs optimization of updating the weight of the frequency selection model.
    Type: Application
    Filed: September 6, 2022
    Publication date: June 15, 2023
    Inventor: Yeonghyeon PARK
  • Publication number: 20230169856
    Abstract: The present invention relates to: an apparatus and system for detecting a road surface condition, wherein the road surface condition is determined through a sound signal; and a method for detecting a road surface condition by using same. The apparatus for detecting a road surface condition according to the present invention comprises: a sensor unit which is installed on a road and measures a sound signal generated according to a moving of a moving object on the road; and a control unit which distinguishes the sound signal measured by the sensor unit into normality or abnormality and determines, in case of the abnormality, the road surface condition including at least one of rainfall (wet), frozenness (icy), slush, and snow cover (snowy) so that a quick and accurate action corresponding to the road surface condition of a specific section can be made from a distanced place.
    Type: Application
    Filed: May 13, 2021
    Publication date: June 1, 2023
    Inventors: Jong Hee JUNG, Yeonghyeon PARK
  • Publication number: 20230160853
    Abstract: Deriving a dangerous area of a road based on a vehicle's noise generated on the road or analyzing a road surface condition based on a driving noise for each vehicle type. An audio signal is collected by a sensor device and send to a noise processing unit. The noise processing unit generates an attenuated audio signal by attenuating a noise other than a noise-of-interest including at least one of a vehicle horn noise and a vehicle sudden brake noise in the received audio signal. An information processing unit detects the noise-of-interest by analyzing the attenuated audio signal through a learned detection model, and establishes a road area within a predetermined radius from the sensor device as the dangerous area of the road based on an accumulated number of times the noise-of-interest is detected.
    Type: Application
    Filed: September 6, 2022
    Publication date: May 25, 2023
    Inventors: JongHee JUNG, Yeonghyeon PARK, JoonSung LEE
  • Publication number: 20230065385
    Abstract: An anomaly detection method and apparatus are provided using an attention mechanism or based on an artificial neural network for minimizing computational cost. In an embodiment, the anomaly detection method may include entering, by a detection unit, input data into a detection network; generating, by the detection network, an attention map and output data through a plurality of operations in which a plurality of layer weights are applied to the input data; generating, by the detection unit, an attention map by overlapping the attention map with the input data when an attention region having an attention value greater than or equal to a predetermined threshold exists in the attention map; detecting, by the detection unit, whether the input data is normal or abnormal according to the output data; and outputting, by the detection unit, the detection map and an anomaly detection result indicating whether the input data is normal or abnormal.
    Type: Application
    Filed: August 24, 2022
    Publication date: March 2, 2023
    Inventor: Yeonghyeon PARK