Patents by Inventor Xiaomeng JIN

Xiaomeng JIN 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).

  • Wireless Resource Utilization Rate Determination Method and Apparatus, Electronic Device and Storage Medium
    Publication number: 20240340657
    Abstract: The present disclosure provides a method and apparatus for determining a utilization rate of wireless resources, an electronic device and a storage medium. The method includes acquiring communication data within a statistical period of a cell; determining a channel non-space division occupied wireless resource within in the statistical period; determining a channel space division occupied wireless resource within the statistical period; determining a channel available wireless resource within the statistical period; and determining the utilization rate of wireless resources.
    Type: Application
    Filed: June 9, 2022
    Publication date: October 10, 2024
    Inventors: Yi Li, Guanghai Liu, Fei Li, Yuchao Jin, Xiaomeng Zhu, Yuting Zheng, Tian Xiao, Yongbei Xue, Yuwei Jia, Xinzhou Cheng
  • System and method for machine learning architecture with adversarial attack defense
    Patent number: 11520899
    Abstract: A platform for training deep neural networks using push-to-corner preprocessing and adversarial training. A training engine adds a preprocessing layer before the input data is fed into a deep neural network at the input layer, for pushing the input data further to the corner of its domain.
    Type: Grant
    Filed: May 17, 2019
    Date of Patent: December 6, 2022
    Assignee: ROYAL BANK OF CANADA
    Inventors: Weiguang Ding, Luyu Wang, Ruitong Huang, Xiaomeng Jin, Kry Yik Chau Lui
  • SYSTEM AND METHOD FOR MACHINE LEARNING ARCHITECTURE WITH ADVERSARIAL ATTACK DEFENCE
    Publication number: 20190354688
    Abstract: A platform for training deep neural networks using push-to-corner preprocessing and adversarial training. A training engine adds a preprocessing layer before the input data is fed into a deep neural network at the input layer, for pushing the input data further to the corner of its domain.
    Type: Application
    Filed: May 17, 2019
    Publication date: November 21, 2019
    Inventors: Weiguang DING, Luyu WANG, Ruitong HUANG, Xiaomeng JIN, Kry Yik Chau LUI