Patents by Inventor Wenjing Kang

Wenjing Kang 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: 20250209593
    Abstract: Systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. Methods can include training machine learning models on images. A request is received to evaluate quality of an image included in a current version of a digital component generated by the computing device. The machine learning models are deployed on the image to generate a score for each quality characteristic of the image. A weight is assigned to each score to generate weighted scores. The weighted scores are combined to generate a combined score for the image. The combined score is compared to one or more thresholds to generate a quality of the image.
    Type: Application
    Filed: March 14, 2025
    Publication date: June 26, 2025
    Inventors: Catherine Shyu, Xiyang Luo, Feng Yang, Junjie Ke, Yicong Tian, Chao-Hung Chen, Xia Li, Luying Li, Wenjing Kang, Shun-Chuan Chen
  • Patent number: 12277693
    Abstract: Systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. Methods can include training machine learning models on images. A request is received to evaluate quality of an image included in a current version of a digital component generated by the computing device. The machine learning models are deployed on the image to generate a score for each quality characteristic of the image. A weight is assigned to each score to generate weighted scores. The weighted scores are combined to generate a combined score for the image. The combined score is compared to one or more thresholds to generate a quality of the image.
    Type: Grant
    Filed: August 6, 2020
    Date of Patent: April 15, 2025
    Assignee: Google LLC
    Inventors: Catherine Shyu, Xiyang Luo, Feng Yang, Junjie Ke, Yicong Tian, Chao-Hung Chen, Xia Li, Luying Li, Wenjing Kang, Shun-Chuan Chen
  • Publication number: 20250010302
    Abstract: Systems and methods for high throughput microdroplet-based single cell assays in microdroplets are provided. The system and methods use parallel devices and switches to enable simultaneous analysis of different cells or cell combinations, or different assay conditions, on a single microfluidic chip. Interconnections between the inlets of individual devices on a common chip enable simultaneous screening of the effect of different combinations of drugs on single cells. The use of an oil inlet and microchannels with matched total flow resistance allows the synchronous generation of droplets with the same dimensions and/or volumes.
    Type: Application
    Filed: September 20, 2024
    Publication date: January 9, 2025
    Inventors: Wenjing KANG, Tania Konry, Saheli Sarkar
  • Patent number: 12121899
    Abstract: A high throughput microdroplet-based system for single cell assays in microdroplets is provided. The system integrates parallel devices and switches to enable simultaneous analysis of different cells or cell combinations, or different assay conditions, on a single microfluidic chip. Interconnections between the inlets of individual devices on a common chip enable simultaneous screening of the effect of different combinations of drugs on single cells. The use of an oil inlet and microchannels with matched total flow resistance allows the synchronous generation of droplets with the same dimensions and/or volumes.
    Type: Grant
    Filed: July 24, 2019
    Date of Patent: October 22, 2024
    Assignee: Northeastern University
    Inventors: Wenjing Kang, Tania Konry, Saheli Sarkar
  • Publication number: 20240346546
    Abstract: Systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. Methods can include identifying content assets including one or more images that are combined to create different digital components distributed to one or more client devices. A quality of each of the one or more images is evaluated using one or more machine learning models trained to evaluate one or more visual aspects that are deemed indicative of visual quality. An aggregate quality for the content assets is determined based, at least in part, on an output of the one or more machine learning models indicating the visual quality of each of the one or more images. A graphical user interface of a first computing device is updated to present a visual indication of the aggregate quality of the content assets.
    Type: Application
    Filed: February 22, 2024
    Publication date: October 17, 2024
    Inventors: Catherine Shyu, Luying Li, Feng Yang, Junjie Ke, Xiyang Luo, Hao Feng, Chao-Hung Chen, Wenjing Kang, Zheng Xia, Shun-Chuan Chen, Yicong Tian, Xia Li, Han Ke
  • Publication number: 20240303485
    Abstract: The disclosure provides an apparatus, method, device, and medium for loss balancing in MTL. The apparatus includes interface circuitry and processor circuitry. The processor circuitry is configured to initialize parameters of shared layers of a deep neural network for MTL using a pre-trained neural network; determine a custom interval consisting of a designated number of mini-batch training steps and a designated window of N custom intervals (N>2); for each task, calculate a loss change rate between each pair of N?1 pairs of neighboring custom intervals within a designated window prior to a present custom interval and a gradient magnitude with respect to selected shared weights within the designated window prior to the present custom interval, and adjust, a weight of the task, based on the calculated loss change rate and gradient magnitude with respect to selected shared weights.
    Type: Application
    Filed: December 2, 2021
    Publication date: September 12, 2024
    Inventors: Wenjing KANG, Xiaochuan LUO, Xianchao XU
  • Publication number: 20220358537
    Abstract: Systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. Methods can include identifying content assets including one or more images that are combined to create different digital components distributed to one or more client devices. A quality of each of the one or more images is evaluated using one or more machine learning models trained to evaluate one or more visual aspects that are deemed indicative of visual quality. An aggregate quality for the content assets is determined based, at least in part, on an output of the one or more machine learning models indicating the visual quality of each of the one or more images. A graphical user interface of a first computing device is updated to present a visual indication of the aggregate quality of the content assets.
    Type: Application
    Filed: August 6, 2020
    Publication date: November 10, 2022
    Inventors: Catherine Shyu, Luying Li, Feng Yang, Junjie Ke, Xiyang Luo, Hao Feng, Chao-Hung Chen, Wenjing Kang, Zheng Xia, Shun-Chuan Chen, Yicong Tian, Xia Li, Han Ke
  • Publication number: 20220301141
    Abstract: Systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. Methods can include training machine learning models on images. A request is received to evaluate quality of an image included in a current version of a digital component generated by the computing device. The machine learning models are deployed on the image to generate a score for each quality characteristic of the image. A weight is assigned to each score to generate weighted scores. The weighted scores are combined to generate a combined score for the image. The combined score is compared to one or more thresholds to generate a quality of the image.
    Type: Application
    Filed: August 6, 2020
    Publication date: September 22, 2022
    Inventors: Catherine Shyu, Xiyang Luo, Feng Yang, Junjie Ke, Yicong Tian, Chao-Hung Chen, Xia Li, Luying Li, Wenjing Kang, Shun-Chuan Chen
  • Publication number: 20210308681
    Abstract: A high throughput microdroplet-based system for single cell assays in microdroplets is provided. The system can include microdroplet sorting. Methods of use of the system are provided.
    Type: Application
    Filed: July 24, 2019
    Publication date: October 7, 2021
    Inventors: Wenjing KANG, Tania KONRY, Saheli SARKAR
  • Publication number: 20190191999
    Abstract: The invention addresses confounding difficulties involving continuous sweat analyte measurement. Specifically, the present invention provides: at least one component capable of monitoring whether a sweat sensing device is in sufficient contact with a wearer's skin to allow proper device operation; at least one component capable of monitoring whether the device is operating on a wearer's skin; at least one means of determining whether the device wearer is a target individual within a probability range; at least one component capable of generating and communicating alert messages to the device user(s) related to: wearer safety, wearer physiological condition, compliance with a requirement to wear a device, device operation; compliance with a behavior requirement, or other purposes that may be derived from sweat sensor data; and the ability to utilize aggregated sweat sensor data that may be correlated with information external to the device to enhance the predictive capabilities of the device.
    Type: Application
    Filed: February 24, 2019
    Publication date: June 27, 2019
    Applicant: University of Cincinnati, a University of the Stat e of Ohio
    Inventors: Jason Heikenfeld, Daniel P. Rose, Ian Papautsky, Wenjing Kang, Xiao Wang, Michael Ratterman
  • Publication number: 20190191998
    Abstract: The invention addresses confounding difficulties involving continuous sweat analyte measurement. Specifically, the present invention provides: at least one component capable of monitoring whether a sweat sensing device is in sufficient contact with a wearer's skin to allow proper device operation; at least one component capable of monitoring whether the device is operating on a wearer's skin; at least one means of determining whether the device wearer is a target individual within a probability range; at least one component capable of generating and communicating alert messages to the device user(s) related to: wearer safety, wearer physiological condition, compliance with a requirement to wear a device, device operation; compliance with a behavior requirement, or other purposes that may be derived from sweat sensor data; and the ability to utilize aggregated sweat sensor data that may be correlated with information external to the device to enhance the predictive capabilities of the device.
    Type: Application
    Filed: February 24, 2019
    Publication date: June 27, 2019
    Applicant: University of Cincinnati, a University of the State of Ohio
    Inventors: Jason Heikenfeld, Daniel P. Rose, Ian Papautsky, Wenjing Kang, Xiao Wang, Michael Ratterman
  • Publication number: 20190192001
    Abstract: The invention addresses confounding difficulties involving continuous sweat analyte measurement. Specifically, the present invention provides: at least one component capable of monitoring whether a sweat sensing device is in sufficient contact with a wearer's skin to allow proper device operation; at least one component capable of monitoring whether the device is operating on a wearer's skin; at least one means of determining whether the device wearer is a target individual within a probability range; at least one component capable of generating and communicating alert messages to the device user(s) related to: wearer safety, wearer physiological condition, compliance with a requirement to wear a device, device operation; compliance with a behavior requirement, or other purposes that may be derived from sweat sensor data; and the ability to utilize aggregated sweat sensor data that may be correlated with information external to the device to enhance the predictive capabilities of the device.
    Type: Application
    Filed: February 24, 2019
    Publication date: June 27, 2019
    Applicant: University of Cincinnati, a University of the State of Ohio
    Inventors: Jason Heikenfeld, Daniel P. Rose, Ian Papautsky, Wenjing Kang, Xiao Wang, Michael Ratterman
  • Publication number: 20190192000
    Abstract: The invention addresses confounding difficulties involving continuous sweat analyte measurement. Specifically, the present invention provides: at least one component capable of monitoring whether a sweat sensing device is in sufficient contact with a wearer's skin to allow proper device operation; at least one component capable of monitoring whether the device is operating on a wearer's skin; at least one means of determining whether the device wearer is a target individual within a probability range; at least one component capable of generating and communicating alert messages to the device user(s) related to: wearer safety, wearer physiological condition, compliance with a requirement to wear a device, device operation; compliance with a behavior requirement, or other purposes that may be derived from sweat sensor data; and the ability to utilize aggregated sweat sensor data that may be correlated with information external to the device to enhance the predictive capabilities of the device.
    Type: Application
    Filed: February 24, 2019
    Publication date: June 27, 2019
    Applicant: University of Cincinnati, a University of the State of Ohio
    Inventors: Jason Heikenfeld, Daniel P. Rose, Ian Papautsky, Wenjing Kang, Xiao Wang, Michael Ratterman
  • Patent number: 10258262
    Abstract: The invention addresses confounding difficulties involving continuous sweat analyte measurement. Specifically, the present invention provides: at least one component capable of monitoring whether a sweat sensing device is in sufficient contact with a wearer's skin to allow proper device operation; at least one component capable of monitoring whether the device is operating on a wearer's skin; at least one means of determining whether the device wearer is a target individual within a probability range; at least one component capable of generating and communicating alert messages to the device user(s) related to: wearer safety, wearer physiological condition, compliance with a requirement to wear a device, device operation; compliance with a behavior requirement, or other purposes that may be derived from sweat sensor data; and the ability to utilize aggregated sweat sensor data that may be correlated with information external to the device to enhance the predictive capabilities of the device.
    Type: Grant
    Filed: November 28, 2016
    Date of Patent: April 16, 2019
    Assignee: University of Cincinnati, A University of the State of Ohio
    Inventors: Jason Heikenfeld, Daniel P. Rose, Ian Papautsky, Wenjing Kang, Xiao Wang, Michael Ratterman
  • Patent number: 10201279
    Abstract: The invention addresses confounding difficulties involving continuous sweat analyte measurement. Specifically, the present invention provides: at least one component capable of monitoring whether a sweat sensing device is in sufficient contact with a wearer's skin to allow proper device operation; at least one component capable of monitoring whether the device is operating on a wearer's skin; at least one means of determining whether the device wearer is a target individual within a probability range; at least one component capable of generating and communicating alert messages to the device user(s) related to: wearer safety, wearer physiological condition, compliance with a requirement to wear a device, device operation; compliance with a behavior requirement, or other purposes that may be derived from sweat sensor data; and the ability to utilize aggregated sweat sensor data that may be correlated with information external to the device to enhance the predictive capabilities of the device.
    Type: Grant
    Filed: November 28, 2016
    Date of Patent: February 12, 2019
    Assignee: University of Cincinnati, A University of the State of Ohio
    Inventors: Jason Heikenfeld, Daniel P. Rose, Ian Papautsky, Wenjing Kang, Xiao Wang, Michael Ratterman
  • Patent number: 9867539
    Abstract: The invention addresses confounding difficulties involving continuous sweat analyte measurement. Specifically, the present invention provides: at least one component capable of monitoring whether a sweat sensing device is in sufficient contact with a wearer's skin to allow proper device operation; at least one component capable of monitoring whether the device is operating on a wearer's skin; at least one means of determining whether the device wearer is a target individual within a probability range; at least one component capable of generating and communicating alert messages to the device user(s) related to: wearer safety, wearer physiological condition, compliance with a requirement to wear a device, device operation; compliance with a behavior requirement, or other purposes that may be derived from sweat sensor data; and the ability to utilize aggregated sweat sensor data that may be correlated with information external to the device to enhance the predictive capabilities of the device.
    Type: Grant
    Filed: November 28, 2016
    Date of Patent: January 16, 2018
    Assignee: Eccrine Systems, Inc.
    Inventors: Jason Heikenfeld, Daniel P. Rose, Ian Papautsky, Wenjing Kang, Xiao Wang, Michael Ratterman