Patents by Inventor Douglas Kirkpatrick

Douglas Kirkpatrick 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: 12237850
    Abstract: A wideband-tunable radio frequency (RF) receiver having a tunable RF bandpass filter (RF BPF) and passive mixer-first receiver (PMF-Rx) is disclosed. The tunable RF BPF and PMF-Rx operate synergistically, exploiting the intrinsic impedance translation property of the PMF-Rx, to suppress out-of-band interferers as well as in-band interferers at the receiver front end and thereby enhance the receiver's signal-to-noise ratio and overall dynamic range. In one embodiment of the invention the tunable RF BPF and PMF-Rx are independently tunable and afford the receiver the ability to reject or suppress interferers that might not otherwise be able to be rejected or suppressed.
    Type: Grant
    Filed: September 23, 2022
    Date of Patent: February 25, 2025
    Assignee: Eridan Communications, Inc.
    Inventors: Hazal Yüksel, Douglas Kirkpatrick, Dubravko Babić
  • Publication number: 20250006362
    Abstract: A neural network is trained using transfer learning to analyze medical image data, including 2D, 3D, and 4D images and models. Where the target medical image data is associated with a species or problem class for which there is not sufficient labeled data available for training, the system may create enhanced training datasets by selecting labeled data from other species, and/or labeled data from different problem classes. During training and analysis, image data is chunked into portions that are small enough to obfuscate the species source, while being large enough to preserve meaningful context related to the problem class (e.g., the image portion is small enough that it cannot be determined whether it is from a human or canine, but abnormal liver tissues are still identifiable). A trained checkpoint may then be used to provide automated analysis and heat mapping of input images via a cloud platform or other application.
    Type: Application
    Filed: September 16, 2024
    Publication date: January 2, 2025
    Applicant: AI:ON Innovations, Inc.
    Inventors: Sean Thomas Curtin, Curtis Mitchel Stewart, Ryan Matthew Gilbride, Douglas Kirkpatrick, Christopher Iovino
  • Patent number: 12094605
    Abstract: A neural network is trained using transfer learning to analyze medical image data, including 2D, 3D, and 4D images and models. Where the target medical image data is associated with a species or problem class for which there is not sufficient labeled data available for training, the system may create enhanced training datasets by selecting labeled data from other species, and/or labeled data from different problem classes. During training and analysis, image data is chunked into portions that are small enough to obfuscate the species source, while being large enough to preserve meaningful context related to the problem class (e.g., the image portion is small enough that it can't be determined whether it is from a human or canine, but abnormal liver tissues are still identifiable). A trained checkpoint may then be used to provide automated analysis and heat mapping of input images via a cloud platform or other application.
    Type: Grant
    Filed: June 13, 2023
    Date of Patent: September 17, 2024
    Assignee: AI:ON Innovations, Inc.
    Inventors: Sean Thomas Curtin, Curtis Mitchel Stewart, Ryan Matthew Gilbride, Douglas Kirkpatrick, Christopher Iovino
  • Publication number: 20240106464
    Abstract: A wideband-tunable radio frequency (RF) receiver having a tunable RF bandpass filter (RF BPF) and passive mixer-first receiver (PMF-Rx) is disclosed. The tunable RF BPF and PMF-Rx operate synergistically, exploiting the intrinsic impedance translation property of the PMF-Rx, to suppress out-of-band interferers as well as in-band interferers at the receiver front end and thereby enhance the receiver's signal-to-noise ratio and overall dynamic range. In one embodiment of the invention the tunable RF BPF and PMF-Rx are independently tunable and afford the receiver the ability to reject or suppress interferers that might not otherwise be able to be rejected or suppressed.
    Type: Application
    Filed: September 23, 2022
    Publication date: March 28, 2024
    Inventors: Hazal Yüksel, Douglas Kirkpatrick, Dubravko Babic
  • Publication number: 20230326592
    Abstract: A neural network is trained using transfer learning to analyze medical image data, including 2D, 3D, and 4D images and models. Where the target medical image data is associated with a species or problem class for which there is not sufficient labeled data available for training, the system may create enhanced training datasets by selecting labeled data from other species, and/or labeled data from different problem classes. During training and analysis, image data is chunked into portions that are small enough to obfuscate the species source, while being large enough to preserve meaningful context related to the problem class (e.g., the image portion is small enough that it can't be determined whether it is from a human or canine, but abnormal liver tissues are still identifiable). A trained checkpoint may then be used to provide automated analysis and heat mapping of input images via a cloud platform or other application.
    Type: Application
    Filed: June 13, 2023
    Publication date: October 12, 2023
    Applicant: AI:ON Innovations, Inc.
    Inventors: Sean Thomas Curtin, Curtis Mitchel Stewart, Ryan Matthew Gilbride, Douglas Kirkpatrick, Christopher Iovino
  • Patent number: 11705245
    Abstract: A neural network is trained using transfer learning to analyze medical image data, including 2D, 3D, and 4D images and models. Where the target medical image data is associated with a species or problem class for which there is not sufficient labeled data available for training, the system may create enhanced training datasets by selecting labeled data from other species, and/or labeled data from different problem classes. During training and analysis, image data is chunked into portions that are small enough to obfuscate the species source, while being large enough to preserve meaningful context related to the problem class (e.g., the image portion is small enough that it can't be determined whether it is from a human or canine, but abnormal liver tissues are still identifiable). A trained checkpoint may then be used to provide automated analysis and heat mapping of input images via a cloud platform or other application.
    Type: Grant
    Filed: March 10, 2021
    Date of Patent: July 18, 2023
    Assignee: AI:ON Innovations, Inc.
    Inventors: Sean Thomas Curtin, Curtis Mitchel Stewart, Ryan Matthew Gilbride, Douglas Kirkpatrick, Christopher Iovino
  • Publication number: 20210287045
    Abstract: A neural network is trained using transfer learning to analyze medical image data, including 2D, 3D, and 4D images and models. Where the target medical image data is associated with a species or problem class for which there is not sufficient labeled data available for training, the system may create enhanced training datasets by selecting labeled data from other species, and/or labeled data from different problem classes. During training and analysis, image data is chunked into portions that are small enough to obfuscate the species source, while being large enough to preserve meaningful context related to the problem class (e.g., the image portion is small enough that it can't be determined whether it is from a human or canine, but abnormal liver tissues are still identifiable). A trained checkpoint may then be used to provide automated analysis and heat mapping of input images via a cloud platform or other application.
    Type: Application
    Filed: March 10, 2021
    Publication date: September 16, 2021
    Inventors: Sean Thomas Curtin, Curtis Mitchel Stewart, Ryan Matthew Gilbride, Douglas Kirkpatrick, Devan Ohst, Christopher Iovino
  • Patent number: 9188413
    Abstract: A shaped charge casing 1 designed to be nested to reduce overall volume, which benefits storage or carriage. A lid portion 5 is connected at 8 to a body portion 9 by means of a screw thread. A shaped charge liner 12 can be positioned onto lip 11. The lid portion 5 and body portion 9 can be separated to allow filling or unpacking of explosive material.
    Type: Grant
    Filed: October 12, 2010
    Date of Patent: November 17, 2015
    Assignee: The Secretary of State for Defense
    Inventors: Stephen James McLean, Douglas Kirkpatrick, Nigel Chapman
  • Publication number: 20140060369
    Abstract: A shaped charge casing 1 designed to be nested to reduce overall volume, which benefits storage or carriage. A lid portion 5 is connected at 8 to a body portion 9 by means of a screw thread. A shaped charge liner 12 can be positioned onto lip 11. The lid portion 5 and body portion 9 can be separated to allow filling or unpacking of explosive material.
    Type: Application
    Filed: October 12, 2010
    Publication date: March 6, 2014
    Inventors: Stephen James Mclean, Douglas Kirkpatrick, Nigel Chapman