Patents by Inventor Chun Hing Cheng
Chun Hing Cheng 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: 20240070461Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.Type: ApplicationFiled: November 6, 2023Publication date: February 29, 2024Inventors: CHUN HING CHENG, JULIA BREANNE EVERETT, MICHAEL TODD PURDY, TRAVIS MICHAEL STEVENS, DAVID ALLAN VIBERG, DALE BARRY YEE
-
Patent number: 11853887Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.Type: GrantFiled: November 9, 2022Date of Patent: December 26, 2023Assignee: Orpyx Medical Technologies Inc.Inventors: Chun Hing Cheng, Julia Breanne Everett, Michael Todd Purdy, Travis Michael Stevens, David Allan Viberg, Dale Barry Yee
-
Publication number: 20230085511Abstract: A method and system for heterogeneous event detection. Sensor data is obtained and divided into discrete data windows. Each data window is defined by and corresponds to a time period of the sensor data. A time-frequency representation over the time period is calculated for each data window. A filter mask is calculated based on the data window corresponding to the time-frequency representation. The filter mask is applied for reverting the time-frequency representation to a time representation, resulting in filtered data. Features, such as extrema or other inflection points, are identified in the filtered data. The features define events, and transforming the time-frequency representation back into the time domain emphasizes differences between more and less prominent frequencies, facilitating identification of heterogeneous events. The method and system may be applied to body movements of people or animals, automaton movement, audio signals, light intensity, or any suitable time-dependent variable.Type: ApplicationFiled: October 17, 2022Publication date: March 16, 2023Applicant: ORPYX MEDICAL TECHNOLOGIES INC.Inventors: CHUN HING CHENG, MICHAEL TODD PURDY, TRAVIS MICHAEL STEVENS
-
Publication number: 20230060953Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.Type: ApplicationFiled: November 9, 2022Publication date: March 2, 2023Inventors: CHUN HING CHENG, JULIA BREANNE EVERETT, MICHAEL TODD PURDY, TRAVIS MICHAEL STEVENS, DAVID ALLAN VIBERG, DALE BARRY YEE
-
Patent number: 11526749Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.Type: GrantFiled: August 22, 2018Date of Patent: December 13, 2022Assignee: Orpyx Medical Technologies Inc.Inventors: Chun Hing Cheng, Julia Breanne Everett, Michael Todd Purdy, Travis Michael Stevens, David Allan Viberg, Dale Barry Yee
-
Patent number: 11504030Abstract: A method and system for heterogeneous event detection. Sensor data is obtained and divided into discrete data windows. Each data window is defined by and corresponds to a time period of the sensor data. A time-frequency representation over the time period is calculated for each data window. A filter mask is calculated based on the data window corresponding to the time-frequency representation. The filter mask is applied for reverting the time-frequency representation to a time representation, resulting in filtered data. Features, such as extrema or other inflection points, are identified in the filtered data. The features define events, and transforming the time-frequency representation back into the time domain emphasizes differences between more and less prominent frequencies, facilitating identification of heterogeneous events. The method and system may be applied to body movements of people or animals, automaton movement, audio signals, light intensity, or any suitable time-dependent variable.Type: GrantFiled: June 28, 2018Date of Patent: November 22, 2022Assignee: ORPYX MEDICAL TECHNOLOGIES INC.Inventors: Chun Hing Cheng, Michael Todd Purdy, Travis Michael Stevens
-
Publication number: 20200218974Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.Type: ApplicationFiled: August 22, 2018Publication date: July 9, 2020Applicant: KINETYX SCIENCES INC.Inventors: CHUN HING CHENG, JULIA BREANNE EVERETT, MICHAEL TODD PURDY, TRAVIS MICHAEL STEVENS, DAVID ALLAN VIBERG, DALE BARRY YEE
-
Publication number: 20200178849Abstract: A method and system for heterogeneous event detection. Sensor data is obtained and divided into discrete data windows. Each data window is defined by and corresponds to a time period of the sensor data. A time-frequency representation over the time period is calculated for each data window. A filter mask is calculated based on the data window corresponding to the time-frequency representation. The filter mask is applied for reverting the time-frequency representation to a time representation, resulting in filtered data. Features, such as extrema or other inflection points, are identified in the filtered data. The features define events, and transforming the time-frequency representation back into the time domain emphasizes differences between more and less prominent frequencies, facilitating identification of heterogeneous events. The method and system may be applied to body movements of people or animals, automaton movement, audio signals, light intensity, or any suitable time-dependent variable.Type: ApplicationFiled: June 28, 2018Publication date: June 11, 2020Applicant: ORPYX MEDICAL TECHNOLOGIES INC.Inventors: CHUN HING CHENG, MICHAEL TODD PURDY, TRAVIS MICHAEL STEVENS
-
Patent number: 9818187Abstract: An image processing device and methods for performing Rotationally Invariant S-transform (RIST) for an image are provided herein. An example method of determining the RIST magnitude at a pixel is provided herein. Further, an example method of determining RIST magnitudes and statistics in a region of interest is provided herein.Type: GrantFiled: September 26, 2016Date of Patent: November 14, 2017Assignee: Mayo Foundation for Medical Education and ResearchInventors: Chun Hing Cheng, Joseph Ross Mitchell
-
Publication number: 20170103537Abstract: An image processing device and methods for performing an S-transform (ST) are provided herein. An example method of generating a compressed form of values of a one-dimensional ST for a time series and generating an approximate form of ST is provided herein. Additionally, an example method of determining local spectrum at a pixel is provided herein. Further, an example method of determining ST magnitudes and statistics in a region of interest (ROI) is provided herein.Type: ApplicationFiled: September 26, 2016Publication date: April 13, 2017Inventors: Chun Hing Cheng, Joseph Ross Mitchell
-
Publication number: 20170084013Abstract: An image processing device and methods for performing Rotationally Invariant S-transform (RIST) for an image are provided herein. An example method of determining the RIST magnitude at a pixel is provided herein. Further, an example method of determining RIST magnitudes and statistics in a region of interest is provided herein.Type: ApplicationFiled: September 26, 2016Publication date: March 23, 2017Inventors: Chun Hing Cheng, Joseph Ross Mitchell
-
Publication number: 20150193671Abstract: An image processing device and methods for performing Rotationally Invariant Stransform (RIST) for an image are provided herein. An example method of determining the RIST magnitude at a pixel is provided herein. Further, an example method of determining RIST magnitudes and statistics in a region of interest is provided herein.Type: ApplicationFiled: November 23, 2012Publication date: July 9, 2015Inventors: Chun Hing Cheng, Joseph Ross Mitchell
-
Publication number: 20150125080Abstract: An image processing device and methods for performing an S-transform (ST) are provided herein. An example method of generating a compressed form of values of a one-dimensional ST for a time series and generating an approximate form of ST is provided herein. Additionally, an example method of determining local spectrum at a pixel is provided herein. Further, an example method of determining ST magnitudes and statistics in a region of interest (ROI) is provided herein.Type: ApplicationFiled: November 21, 2012Publication date: May 7, 2015Inventors: Chun Hing Cheng, Joseph Ross Mitchell
-
Publication number: 20080247649Abstract: Methods are provided for determining the silhouette of an object in an image against a fairly plain background. The method performs initial processing to create small regions of pixels in the image that have the same grey level value. Modifying the grey level values in these regions by setting the grey level value equal to the number of pixels in the region and then performing a threshold operation aids in defining a coarse boundary of the object. Analyzing grey level values of pixels in the image external to the object defines the coarse boundary. Analyzing grey level values of pixels in the image internal to the object defines the silhouette. Additional processing steps in the method help to further define the silhouette. Steps of the method can be repeated to further refine the shape of the silhouette. The invention does not require the detection of edges, in fact it is considered to be independent of the original grey level values of pixels in the image being processed.Type: ApplicationFiled: July 7, 2005Publication date: October 9, 2008Inventor: Chun Hing Cheng