Patents by Inventor Jiakai YU

Jiakai YU 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).

  • Optical network performance evaluation using a hybrid neural network
    Patent number: 11133865
    Abstract: Aspects of the present disclosure describe systems, methods. and structures in which a hybrid neural network combining a CNN and several ANNs are shown useful for predicting G-ONSR for Ps-256QAM raw data in deployed SSMF metro networks with 0.27 dB RMSE. As demonstrated, the CNN classifier is trained with 80.96% testing accuracy to identify channel shaping factor. Several ANN regression models are trained to estimate G-OSNR with 0.2 dB for channels with various constellation shaping. Further aspects include the tuning of existing optical networks and the characterization of retrofit/upgraded optical networks to estimate capacity—both aspects employing our inventive hybrid neural network methodology.
    Type: Grant
    Filed: November 29, 2020
    Date of Patent: September 28, 2021
    Inventors: Yue-Kai Huang, Shaoliang Zhang, Ezra Ip, Jiakai Yu
  • OPTICAL NETWORK PERFORMANCE EVALUATION USING A HYBRID NEURAL NETWORK
    Publication number: 20210111794
    Abstract: Aspects of the present disclosure describe systems, methods. and structures in which a hybrid neural network combining a CNN and several ANNs are shown useful for predicting G-ONSR for Ps-256QAM raw data in deployed SSMF metro networks with 0.27 dB RMSE. As demonstrated, the CNN classifier is trained with 80.96% testing accuracy to identify channel shaping factor. Several ANN regression models are trained to estimate G-OSNR with 0.2 dB for channels with various constellation shaping. Further aspects include the tuning of existing optical networks and the characterization of retrofit/upgraded optical networks to estimate capacity—both aspects employing our inventive hybrid neural network methodology.
    Type: Application
    Filed: November 29, 2020
    Publication date: April 15, 2021
    Applicant: NEC Laboratories America, Inc.
    Inventors: Yue-Kai HUANG, Shaoliang ZHANG, Ezra IP, Jiakai YU
  • G-OSNR estimation on dynamic PS-QAM channels using hybrid neural networks
    Patent number: 10887009
    Abstract: Aspects of the present disclosure describe systems, methods and structures in which a hybrid neural network combining a CNN and several ANNs are shown useful for predicting G-ONSR for Ps-256QAM raw data in deployed SSMF metro networks with 0.27 dB RMSE. As demonstrated, the CNN classifier is trained with 80.96% testing accuracy to identify channel shaping factor. Several ANN regression models are trained to estimate G-OSNR with 0.2 dB for channels with various constellation shaping.
    Type: Grant
    Filed: October 8, 2019
    Date of Patent: January 5, 2021
    Inventors: Yue-Kai Huang, Shaoliang Zhang, Ezra Ip, Jiakai Yu
  • G-OSNR ESTIMATION ON DYNAMIC PS-QAM CHANNELS USING HYBRID NEURAL NETWORKS
    Publication number: 20200112367
    Abstract: Aspects of the present disclosure describe systems, methods and structures in which a hybrid neural network combining a CNN and several ANNs are shown useful for predicting G-ONSR for Ps-256QAM raw data in deployed SSMF metro networks with 0.27 dB RMSE. As demonstrated, the CNN classifier is trained with 80.96% testing accuracy to identify channel shaping factor. Several ANN regression models are trained to estimate G-OSNR with 0.2 dB for channels with various constellation shaping.
    Type: Application
    Filed: October 8, 2019
    Publication date: April 9, 2020
    Applicant: NEC LABORATORIES AMERICA, INC
    Inventors: Yue-Kai HUANG, Shaoliang ZHANG, Ezra IP, Jiakai YU