中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

1499 records (took 0.029 seconds)

    FEDERATED LEARNING MARKETPLACE
    44.
    发明公开
    FEDERATED LEARNING MARKETPLACE 审中-公开

    公开(公告)号：US20230394516A1

    公开(公告)日：2023-12-07

    申请号：US18132021

    申请日：2023-04-07

    Applicant: UNIVERSITY OF SOUTHERN CALIFORNIA

    Inventor： Jose Luis AMBITE MOLINA ,  Dimitrios STRIPELIS

    IPC: G06Q30/0207 ,  G06N3/098

    CPC classification number: G06Q30/0215 ,  G06N3/098

    Abstract: A federated learning environment includes a central coordinator that is responsible to orchestrate execution of the federated learning environment, and a plurality of clients jointly that trains machine learning and deep learning models on client computing devices without sharing their local private datasets. The clients only share their locally trained model parameters with the central coordinator. Model parameters are encrypted before sharing with the controller. The central coordinator aggregates local models and computes a new global model in encrypted space. This process repeats for a number of synchronization periods or asynchronously until specific convergence criteria are met. A federated learning marketplace is established to incentivize data providers to join federations through a revenue-sharing model, and to facilitate the use of machine-learning models to organizations outside of the federation.

    NONINVASIVE INFARCT SIZE DETERMINATION
    45.
    发明公开
    NONINVASIVE INFARCT SIZE DETERMINATION 审中-公开

    公开(公告)号：US20230389850A1

    公开(公告)日：2023-12-07

    申请号：US18249667

    申请日：2021-10-21

    Applicant: UNIVERSITY OF SOUTHERN CALIFORNIA

    Inventor： Niema M. PAHLEVAN ,  Rashid ALAVI DEHKORDI

    IPC: A61B5/363 ,  A61B5/024 ,  A61B5/00 ,  G16H50/20

    CPC classification number: A61B5/363 ,  A61B5/02438 ,  A61B5/7267 ,  G16H50/20

    Abstract: The present application relates to using noninvasive techniques to determine whether a patient has experienced a cardiac event. The present application also relates to using noninvasive techniques to determine a size of a myocardial infarction experienced by a patient. In some embodiments, arterial pressure waveforms may be obtained, and from the arterial pressure waveform, a set of cardiac parameters may be extracted. The extracted cardiac parameters may be provided, as input, to the trained machine learning model, which may output a result indicating whether the patient experienced a cardiac event, a size of a myocardial infarction experience by a patient, or other information about the patient's cardiac health.

    CONVOLUTION MODELING AND LEARNING SYSTEM FOR PREDICTING GEOMETRIC SHAPE ACCURACY OF 3D PRINTED PRODUCTS
    50.
    发明公开
    CONVOLUTION MODELING AND LEARNING SYSTEM FOR PREDICTING GEOMETRIC SHAPE ACCURACY OF 3D PRINTED PRODUCTS 审中-公开

    公开(公告)号：US20230339185A1

    公开(公告)日：2023-10-26

    申请号：US18028946

    申请日：2021-09-27

    Applicant: UNIVERSITY OF SOUTHERN CALIFORNIA

    Inventor： Qiang HUANG

    IPC: B29C64/386 ,  G05B19/4099

    CPC classification number: B29C64/386 ,  G05B19/4099 ,  B33Y50/00

    Abstract: A system, method, and computer-readable medium having machine instructions provides for predicting geometric shape accuracy of 3D printed products. Such a prediction may involve developing a model of an object and determining ways in which an actually-manufactured 3D object corresponding to the model differs in real life. These differences correspond to shape deviations. Shape deviations may be process dependent and/or path dependent, and different layers of the object as well as the manufacturing process to make the different layers may introduce shape deviations in layers of the object. By developing a transfer functions of the manufacturing process and associated interlayer effects of the layers and then appropriately offsetting inputs to the manufacturing process, the shape deviations may be ameliorated.

Patent Agency Ranking