Jonathan L Walker

US Patent:

7184763, Feb 27, 2007

Filed:

Jan 21, 2003

Appl. No.:

10/347777

Inventors:

Aloke Roy - Gaithersburg MD, US
Jonathan Walker - Crofton MD, US

Assignee:

Honeywell International, Inc. - Morristown NJ

International Classification:

H04Q 7/20

US Classification:

455431, 455441, 455513, 455525

Abstract:

An apparatus, method and computer program for initiating and maintaining a virtual connection between a mobile radio and a ground station, including receiving a plurality of ground station radio signals from a mobile radio; accumulating over a time period signal quality information relative to each of the ground station radio signals; determining a signal quality parameter trend for each of the ground station radio signals as a function of the accumulated signal quality information; deciding to switch a current virtual connection between the mobile radio and a first ground station to a virtual connection between the mobile radio and a different second ground station as a function of comparing the signal quality parameter to a pre-selected minimum acceptable threshold signal quality parameter; and switching the virtual connection of the mobile radio from the first ground station to the second ground station.

US Patent:

20220374732, Nov 24, 2022

Filed:

Jun 30, 2022

Appl. No.:

17/854264

Inventors:

- Cary NC, US
Mohammadreza Nazari - Philadelphia PA, US
Davood Hajinezhad - Cary NC, US
Jorge Manuel Gomes da Silva - Durham NC, US
Jonathan Lee Walker - Raleigh NC, US
Hardi Desai - Raleigh NC, US
Robert Blanchard - San Diego CA, US
Varunraj Valsaraj - Cary NC, US
Ruiwen Zhang - Cary NC, US
Weichen Wang - Cary NC, US
Ye Liu - Morrisville NC, US
Hamoon Azizsoltani - Raleigh NC, US
Prathaban Mookiah - San Diego CA, US

International Classification:

G06N 5/02

Abstract:

A computing device trains a machine state predictive model. A generative adversarial network with an autoencoder is trained using a first plurality of observation vectors. Each observation vector of the first plurality of observation vectors includes state variable values for state variables and an action variable value for an action variable. The state variables define a machine state, wherein the action variable defines a next action taken in response to the machine state. The first plurality of observation vectors successively defines sequential machine states to manufacture a product. A second plurality of observation vectors is generated using the trained generative adversarial network with the autoencoder. A machine state machine learning model is trained to predict a subsequent machine state using the first plurality of observation vectors and the generated second plurality of observation vectors. A description of the machine state machine learning model is output.