公开(公告)号：US11699086B1

公开(公告)日：2023-07-11

申请号：US17732683

申请日：2022-04-29

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O'Shea ,  Kiran Karra ,  T. Charles Clancy

IPC: G06N5/046 ,  H04B17/309 ,  G06N20/00 ,  H04B17/391 ,  G06N3/02

CPC classification number: G06N5/046 ,  G06N3/02 ,  G06N20/00 ,  H04B17/309 ,  H04B17/3912

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learning estimation networks in a communications system. One of the methods includes: processing first information with ground truth information to generate a first RF signal by altering the first information by channel impairment having at least one channel effect, using a receiver to process the first RF signal to generate second information, training a machine-learning estimation network based on a network architecture, the second information, and the ground truth information, receiving by the receiver a second RF signal transmitted through a communication channel including the at least one channel effect, inferring by the trained estimation network the receiver to estimate an offset of the second RF signal caused by the at least one channel effect, and correcting the offset of the RF signal with the estimated offset to obtain a recovered RF signal.

公开(公告)号：US11334807B1

公开(公告)日：2022-05-17

申请号：US16017904

申请日：2018-06-25

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O'Shea ,  Kiran Karra ,  T. Charles Clancy

IPC: G06N5/04 ,  G06N3/02 ,  H04B17/309 ,  H04B17/391 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learning estimation networks in a communications system. One of the methods includes: processing first information with ground truth information to generate a first RF signal by altering the first information by channel impairment having at least one channel effect, using a receiver to process the first RF signal to generate second information, training a machine-learning estimation network based on a network architecture, the second information, and the ground truth information, receiving by the receiver a second RF signal transmitted through a communication channel including the at least one channel effect, inferring by the trained estimation network the receiver to estimate an offset of the second RF signal caused by the at least one channel effect, and correcting the offset of the RF signal with the estimated offset to obtain a recovered RF signal.

公开(公告)号：US12223443B1

公开(公告)日：2025-02-11

申请号：US18218855

申请日：2023-07-06

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O'Shea ,  Kiran Karra ,  T. Charles Clancy

IPC: H04B17/309 ,  G06N3/02 ,  G06N5/046 ,  G06N20/00 ,  H04B17/391

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learning estimation networks in a communications system. One of the methods includes: processing first information with ground truth information to generate a first RF signal by altering the first information by channel impairment having at least one channel effect, using a receiver to process the first RF signal to generate second information, training a machine-learning estimation network based on a network architecture, the second information, and the ground truth information, receiving by the receiver a second RF signal transmitted through a communication channel including the at least one channel effect, inferring by the trained estimation network the receiver to estimate an offset of the second RF signal caused by the at least one channel effect, and correcting the offset of the RF signal with the estimated offset to obtain a recovered RF signal.