Patents by Inventor Thomas Paul Repoff

Thomas Paul Repoff 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).

  • Patent number: 8824769
    Abstract: The invention relates generally to a process of analyzing and visualizing the expression of biomarkers in an individual cell wherein the cell is examined to develop patterns of expression by using a grouping algorithm, and a system to perform and display the analysis.
    Type: Grant
    Filed: February 27, 2013
    Date of Patent: September 2, 2014
    Assignee: General Electric Company
    Inventors: Brion Daryl Sarachan, Thomas Paul Repoff, Colin Craig McCulloch, Fiona Mary Ginty, Megan Pearl Rothney, Zhengyu Pang
  • Patent number: 8533147
    Abstract: A method for creating a dynamic systems based hybrid model for reasoning systems is described. The method receives, at a server, a plurality of expert identified deal attributes. The method presents a conjoint analysis questionnaire for input by one or more respondents. The conjoint analysis questionnaire includes questions based on the plurality of expert identified deal attributes. The method receives responses of the one or more respondents to the conjoint analysis questionnaire. The method then defines an expert reasoning model based on the responses of the one or more respondents to the conjoint analysis questionnaire. The method accesses historical deal information of one or more deals, the historical deal information including one or more deals, each deal including a plurality of expert identified deal attributes and a part-worth associated with each of the deal attributes. Finally, the method validates the expert reasoning model based on the historical deal information.
    Type: Grant
    Filed: December 17, 2010
    Date of Patent: September 10, 2013
    Assignee: General Electric Company
    Inventors: Paul Venditti, Thomas Paul Repoff, Michael Craig Clark
  • Publication number: 20120158640
    Abstract: A method for creating a dynamic systems based hybrid model for reasoning systems is described. The method receives, at a server, a plurality of expert identified deal attributes. The method presents a conjoint analysis questionnaire for input by one or more respondents. The conjoint analysis questionnaire includes questions based on the plurality of expert identified deal attributes. The method receives responses of the one or more respondents to the conjoint analysis questionnaire. The method then defines an expert reasoning model based on the responses of the one or more respondents to the conjoint analysis questionnaire. The method accesses historical deal information of one or more deals, the historical deal information including one or more deals, each deal including a plurality of expert identified deal attributes and a part-worth associated with each of the deal attributes. Finally, the method validates the expert reasoning model based on the historical deal information.
    Type: Application
    Filed: December 17, 2010
    Publication date: June 21, 2012
    Applicant: GENERAL ELECTRIC COMPANY
    Inventors: Paul Venditti, Thomas Paul Repoff, Michael Craig Clark
  • Publication number: 20110091081
    Abstract: The present application discloses a technique for obtaining and storing data on expression of multiple biomarkers in individual cells or the compartments of individual cells in a tissue specimen and methods of utilizing that data to create groups, the members of which share some degree of similarity greater than the general population from which the data is drawn, by an analysis of digital images of a portion of the tissue specimen which has been iteratively stained to generate optical signals, typically fluorescent, reflective of the amount of each of the biomarkers examined.
    Type: Application
    Filed: October 16, 2009
    Publication date: April 21, 2011
    Applicant: General Electric Company
    Inventors: Brion Daryl Sarachan, Thomas Paul Repoff, Colin Craig McCulloch, Fiona Mary Ginty, Megan Pearl Rothney, Zhengyu Pang
  • Patent number: 7541577
    Abstract: Disclosed herein are methods for analyzing ion mobility data. In one embodiment, a method for analyzing ion mobility spectrometry data is disclosed. The method comprises conducting a number of ion mobility scans on a sample, generating an ion map comprising a first ion line, comparing the first ion line to a standard deviation, wherein the standard deviation is calculated from the system measurement noise, and determining if the sample is a contraband substance.
    Type: Grant
    Filed: June 26, 2006
    Date of Patent: June 2, 2009
    Assignees: General Electric Company, GE Homeland Protection, Inc.
    Inventors: David Michael Davenport, Thomas Paul Repoff, Pierino Gianni Bonanni, Richard Louis Zinser
  • Publication number: 20080067341
    Abstract: Disclosed herein are methods for analyzing ion mobility data. In one embodiment, a method for analyzing ion mobility spectrometry data is disclosed. The method comprises conducting a number of ion mobility scans on a sample, generating an ion map comprising a first ion line, comparing the first ion line to a standard deviation, wherein the standard deviation is calculated from the system measurement noise, and determining if the sample is a contraband substance.
    Type: Application
    Filed: June 26, 2006
    Publication date: March 20, 2008
    Inventors: David Michael Davenport, Thomas Paul Repoff, Pierino Gianni Bonanni, Richard Louis Zinser
  • Patent number: 6834256
    Abstract: The reliability and remaining time before failure for electric motor systems and the like is determined with an ascertained statistical confidence based on continually monitored system parameters and a database comprised of historical failure mode/cause and repair data concerning the same motor and/or similar motor systems. A computational process is followed that relies upon hierarchical failure-tree structures, Weibull probability distributions and directed causal networks and which updates the probabilities and models used to forecast the remaining time before system failure based on the monitored parameters. Motor system operational parameter data is continually monitored at the site of the motor system and up-loaded via wireless or other communications network to a remote computer system where a database is maintained and reliability analysis is performed.
    Type: Grant
    Filed: August 30, 2002
    Date of Patent: December 21, 2004
    Assignee: General Electric Company
    Inventors: Michael Brynn House, Gregory Lee Flickinger, Calvin Thomas Fritz, Hunt Adams Sutherland, Thomas Paul Repoff
  • Publication number: 20040044499
    Abstract: The reliability and remaining time before failure for electric motor systems and the like is determined with an ascertained statistical confidence based on continually monitored system parameters and a database comprised of historical failure mode/cause and repair data concerning the same motor and/or similar motor systems. A computational process is followed that relies upon hierarchical failure-tree structures, Weibull probabillity distributions and directed causal networks and which updates the probabilities and models used to forecast the remaining time before system failure based on the monitored parameters. Motor system operational parameter data is continually monitored at the site of the motor system and up-loaded via wireless or other communications network to a remote computer system where a database is maintained and reliability analysis is performed.
    Type: Application
    Filed: August 30, 2002
    Publication date: March 4, 2004
    Inventors: Michael Brynn House, Gregory Lee Flickinger, Calvin Thomas Fritz, Hunt Adams Sutherland, Thomas Paul Repoff