Patents by Inventor Yuki HIRAKAWA

Yuki HIRAKAWA 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: 20240104914
    Abstract: A learning model generates a plurality of prototype vectors and generates an integrated similarity vector that indicates similarity between an input image and each prototype for a plurality of prototypes in accordance with similarity between one prototype vector and each pixel vector in a feature map acquired from an CNN. An image processing apparatus obtains prototype belongingness (distributed prototype belongingness) for each image by distributing prototype belongingness of a belonged prototype of each class to each of two or more images that belong to one class. Then, the learning model is subjected to machine learning in accordance with the distributed prototype belongingness of each prototype vector for each image so that each prototype vector is brought closer to any pixel vector in the feature map corresponding to each image.
    Type: Application
    Filed: September 20, 2023
    Publication date: March 28, 2024
    Applicants: Glory Ltd., Chubu University Educational Foundation
    Inventors: Yuki UKAI, Hironobu FUJIYOSHI, Takayoshi YAMASHITA, Tsubasa HIRAKAWA
  • Publication number: 20240075341
    Abstract: In a running analysis system, an information acquirer acquires position information and motion information of a user as a runner, measured at each point of passage in a run by a certain measurement device. A measurement value acquirer acquires measurement values of multiple types of motion analysis indices indicating a running motion state of a user for each certain unit measurement section, based on the position information and the motion information chronologically consecutive. A classification processing unit classifies measurement values in multiple measurement sections for each type of motion analysis indices, using a certain classification method for classification by property. A mode determination unit determines an output mode of a classified measurement value based on comparison with a certain comparison target. An output unit is capable of outputting at least information regarding the classified measurement value, based on the determined output mode.
    Type: Application
    Filed: August 30, 2023
    Publication date: March 7, 2024
    Applicant: ASICS CORPORATION
    Inventors: Yuki KO, Nao HIRAKAWA, Yasuhiro NOMURA, Kazunaga NAKAYAMA
  • Publication number: 20230375559
    Abstract: Provided are a measuring reagent and a method for accurately measuring a high concentration of ferritin. The ferritin measuring reagent and the method for measuring ferritin are characterized by using liver-derived ferritin as a standard-solution raw material.
    Type: Application
    Filed: September 24, 2021
    Publication date: November 23, 2023
    Applicant: Denka Company Limited
    Inventors: Yuki HIRAKAWA, Takamichi TAKAHASHI, Ritsuko TACHIBANA