Patents by Inventor Zhe S. CHEN

Zhe S. CHEN 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).

  • System, method and portable devices for detection and enhancement of sleep spindles
    Patent number: 11664110
    Abstract: A method for administering stimulations to a sleeping subject is provided. The method includes obtaining brain wave data generated based on brain wave activity of the subject over a predetermined time frame and determining a spectral power ratio of a spindle band to delta and theta bands of the brain wave data at a time within the predetermined time frame. The spectral power ratio and brain wave data are sent to the input of a pretrained deep neural network to generate a probability score that sleep spindles are being detected in the brain wave activity. The method may continue to obtain brain wave data and analyze the data using the pretrained deep neural network. A determination that sleep spindles are detected may be made when the probability score is above a predetermined threshold score for a predetermined threshold period of time.
    Type: Grant
    Filed: October 2, 2019
    Date of Patent: May 30, 2023
    Assignee: NEW YORK UNIVERSITY
    Inventors: Zhe S. Chen, Prathamesh M. Kulkarni, Zhengdong Xiao, Jing Wang
  • SYSTEM, METHOD AND PORTABLE DEVICES FOR DETECTION AND ENHANCEMENT OF SLEEP SPINDLES
    Publication number: 20200105398
    Abstract: A method for administering stimulations to a sleeping subject is provided. The method includes obtaining brain wave data generated based on brain wave activity of the subject over a predetermined time frame and determining a spectral power ratio of a spindle band to delta and theta bands of the brain wave data at a time within the predetermined time frame. The spectral power ratio and brain wave data are sent to the input of a pretrained deep neural network to generate a probability score that sleep spindles are being detected in the brain wave activity. The method may continue to obtain brain wave data and analyze the data using the pretrained deep neural network. A determination that sleep spindles are detected may be made when the probability score is above a predetermined threshold score for a predetermined threshold period of time.
    Type: Application
    Filed: October 2, 2019
    Publication date: April 2, 2020
    Inventors: Zhe S. CHEN, Parathamesh M. KULKARNI, Zhengdong Xiao, Jing WANG