Tamoghna Roy

US Patent:

20220264328, Aug 18, 2022

Filed:

Feb 1, 2022

Appl. No.:

17/589979

Inventors:

- Arlington VA, US
Ben Hilburn - Reston VA, US
Nathan West - Washington DC, US
Tamoghna Roy - Arlington VA, US

International Classification:

H04W 24/02

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media for characterizing radio propagation channels. One method includes receiving, at a first modem, a first unit of communication over a radio frequency (RF) communication path from a second modem, wherein the first modem and the second modem process information for RF communications. The first modem identifies fields in the first unit of communication, the fields used to analyze the RF communication path. The first modem extracts data from the fields. The first modem accesses a channel model for approximating a channel representative of the RF communication path from the first modem to the second modem, wherein the channel model includes machine learning models. The first modem trains the channel model using the extracted data. The first modem applies the trained channel model to simulate a set of channel effects associated with the communication path.

US Patent:

20200257985, Aug 13, 2020

Filed:

Feb 10, 2020

Appl. No.:

16/786281

Inventors:

- Arlington VA, US
Tamoghna Roy - Arlington VA, US
Timothy J. O'Shea - Arlington VA, US
Ben Hilburn - Reston VA, US

International Classification:

G06N 3/08
G06N 3/04

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for adversarially generated communication. In some implementations, first information is used as input for a generator machine-learning network. Information is taken from both the generator machine-learning network and target information that includes sample signals or other data. The information is sent to a discriminator machine-learning network which produces decision information including whether the information originated from the generator machine-learning network or the target information. An optimizer takes the decision information and performs one or more iterative optimization techniques which help determine updates to the generator machine-learning network or the discriminator machine-learning network. One or more rounds of updating the generator machine-learning network or the discriminator machine-learning network can allow the generator machine-learning network to produce information that is similar to the target information.

US Patent:

20200143279, May 7, 2020

Filed:

Nov 6, 2019

Appl. No.:

16/676229

Inventors:

- Arlington VA, US
Tamoghna Roy - Arlington VA, US
Ben HILBURN - Reston VA, US

International Classification:

G06N 7/00
G06F 16/906
G06N 3/04
G06N 20/00

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for radio frequency band segmentation, signal detection and labelling using machine learning. In some implementations, a sample of electromagnetic energy processed by one or more radio frequency (RF) communication receivers is received from the one or more receivers. The sample of electromagnetic energy is examined to detect one or more RF signals present in the sample. In response to detecting one or more RF signals present in the sample, the one or more RF signals are extracted from the sample, and time and frequency bounds are estimated for each of the one or more RF signals. For each of the one or more RF signals, at least one of a type of a signal present, or a likelihood of signal being present, in the sample is classified.

US Patent:

20200145842, May 7, 2020

Filed:

Nov 7, 2019

Appl. No.:

16/676600

Inventors:

- Arlington VA, US
Ben Hilburn - Reston VA, US
Nathan West - Washington DC, US
Tamoghna Roy - Arlington VA, US

International Classification:

H04W 24/02

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media for characterizing radio propagation channels. One method includes receiving, at a first modem, a first unit of communication over a radio frequency (RF) communication path from a second modem, wherein the first modem and the second modem process information for RF communications. The first modem identifies fields in the first unit of communication, the fields used to analyze the RF communication path. The first modem extracts data from the fields. The first modem accesses a channel model for approximating a channel representative of the RF communication path from the first modem to the second modem, wherein the channel model includes machine learning models. The first modem trains the channel model using the extracted data. The first modem applies the trained channel model to simulate a set of channel effects associated with the communication path.

US Patent:

20200145951, May 7, 2020

Filed:

Jan 2, 2020

Appl. No.:

16/732412

Inventors:

- Arlington VA, US
Ben Hilburn - Reston VA, US
Tamoghna Roy - Arlington VA, US
Nathan West - Washington DC, US

International Classification:

H04W 56/00
G06N 20/00
H04L 5/00
H04W 72/04
G06N 3/08
H04B 17/391
H04L 12/24
H04W 16/22

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. In some implementations, information is obtained. An encoder network is used to process the information and generate a first RF signal. The first RF signal is transmitted through a first channel. A second RF signal is determined that represents the first RF signal having been altered by transmission through the first channel. Transmission of the first RF signal is simulated over a second channel implementing a machine-learning network, the second channel representing a model of the first channel. A simulated RF signal that represents the first RF signal having been altered by simulated transmission through the second channel is determined. A measure of distance between the second RF signal and the simulated RF signal is calculated. The machine-learning network is updated using the measure of distance.

US Patent:

20190274108, Sep 5, 2019

Filed:

Mar 4, 2019

Appl. No.:

16/291936

Inventors:

- Arlington VA, US
Ben Hilburn - Reston VA, US
Tamoghna Roy - Arlington VA, US
Nathan West - Washington DC, US

International Classification:

H04W 56/00
G06N 20/00
G06N 3/08
H04W 72/04
H04L 5/00

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. In some implementations, information is obtained. An encoder network is used to process the information and generate a first RF signal. The first RF signal is transmitted through a first channel. A second RF signal is determined that represents the first RF signal having been altered by transmission through the first channel. Transmission of the first RF signal is simulated over a second channel implementing a machine-learning network, the second channel representing a model of the first channel. A simulated RF signal that represents the first RF signal having been altered by simulated transmission through the second channel is determined. A measure of distance between the second RF signal and the simulated RF signal is calculated. The machine-learning network is updated using the measure of distance.