Patents by Inventor Chongya Song

Chongya Song 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).

  • Systems and methods using angle-based stochastic gradient descent
    Patent number: 11347997
    Abstract: Systems and methods for optimizing and/or solving objective functions are provided. Angle-based stochastic gradient descent (AG-SGD) can be used to alleviate pattern deviation(s) not resolved by related art systems and methods. AG-SGD can use the angle between the current gradient (CG) and the previous gradient (PG) to determine the new gradient (NG).
    Type: Grant
    Filed: June 8, 2021
    Date of Patent: May 31, 2022
    Assignee: THE FLORIDA INTERNATIONAL UNIVERSITY BOARD OF TRUSTEES
    Inventors: Chongya Song, Alexander Perez-Pons
  • Systems and methods for network-based intrusion detection
    Patent number: 10911471
    Abstract: Systems and methods for network-based intrusion detection are provided. An anti-adversarial Hidden Markov Model can be used to effectively detect evasion patterns for network-based intrusion detection, using dynamic window and threshold techniques to achieve adaptive, anti-adversarial, and online learning abilities. The concepts of pattern entropy, pattern entropy reduction, window width, local optimal window width, and dynamic window can be used in the model.
    Type: Grant
    Filed: November 27, 2019
    Date of Patent: February 2, 2021
    Assignee: The Florida International University Board of Trustees
    Inventors: Chongya Song, Alexander Pons