Patents by Inventor Andrew Polar

Andrew Polar 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).

  • Publication number: 20210241029
    Abstract: A method for identification of multiple discrete Urysohn operators, arranged in a tree and connected in both parallel and sequential ways, capable of replacing adequately any continuous multivariate function, which may be considered as a generic tool for mapping an ordered data into a scalar, and used as training process for artificial intelligence.
    Type: Application
    Filed: February 4, 2020
    Publication date: August 5, 2021
    Inventors: Andrew Polar, Michael Poluektov
  • Publication number: 20200349218
    Abstract: A computationally inexpensive and stable method for real-time identification of multiple-input Urysohn models, designed and intended for usage in machine learning processes of robotic devices.
    Type: Application
    Filed: July 5, 2020
    Publication date: November 5, 2020
    Inventors: Andrew Polar, Michael Poluektov
  • Publication number: 20200050649
    Abstract: A computationally inexpensive and stable method for real-time identification of nonlinear objects of the Urysohn type conducted by applying a model improvement steps for every set of recorded instantaneous input and output values.
    Type: Application
    Filed: August 11, 2018
    Publication date: February 13, 2020
    Inventors: Andrew Polar, Michael Poluektov
  • Patent number: 7315266
    Abstract: Method of reversible compression of low-order bits in digital images that uses image palette as a look up table for high versus low order bit fragments and replaces actual low-order bit fragments in the image by relative sequential indexes that identify the position of correspondent low-order bit fragment in palette array. Said relative sequential indexes are smaller than low-order bit fragments because they are introduced and incremented within the same high-order bit expression in palette array and have significantly different statistical distribution properties compared to distribution of original low-order bit fragments. For successful reconstruction of said low-order bit fragments from said relative sequential indexes the critical part of palette array is saved in compressed data. In spite of additional data buffer the method significantly improves compression ratio and has dual effect: first is compression of low-order bits and second is possibility to ignore then low-order bits in data modeling.
    Type: Grant
    Filed: September 1, 2006
    Date of Patent: January 1, 2008
    Inventor: Andrew Polar