中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

1499 records (took 0.032 seconds)

    Novel and efficient Graph neural network (GNN) for accurate chemical property prediction
    75.
    发明申请
    Novel and efficient Graph neural network (GNN) for accurate chemical property prediction 有权

    公开(公告)号：US20220406416A1

    公开(公告)日：2022-12-22

    申请号：US17843341

    申请日：2022-06-17

    Applicant: University of Southern California

    Inventor： Daniel Sylvinson Muthiah Ravinson ,  Mark E. Thompson

    IPC: G16C20/30 ,  G16C20/60 ,  G16C10/00 ,  G16C20/70

    Abstract: A method for selecting a material having a desired molecular property comprises generating a combinatorial library of molecule structures derived from a core molecular structure, splitting the library into a training set configured to train a graph neural network (GNN) machine learning (ML) model, a test set configured to test the validity of and assess accuracy of the GNN model, and a prediction set where predictions are made using the GNN model, optimizing geometries of the molecular structures, computing excited state energies of the optimized geometries, encoding molecular structure information into a matrix, determining three mutually orthogonal principal axes, transforming spatial coordinates into mutually orthogonal coordinates, constructing a molecular graph with n nodes, feeding the molecular graph into the GNN model as an input, and selecting a material having a suitable desired molecular property based on the output of the GNN model.

    Inexpensive metal-free organic redox flow battery (ORBAT) for grid-scale storage
    76.
    发明授权
    Inexpensive metal-free organic redox flow battery (ORBAT) for grid-scale storage 有权

    公开(公告)号：US11532830B2

    公开(公告)日：2022-12-20

    申请号：US16785715

    申请日：2020-02-10

    Applicant: UNIVERSITY OF SOUTHERN CALIFORNIA

    Inventor： Sri Narayan ,  Surya G. K. Prakash ,  Bo Yang ,  Lena Hoober-Burkhardt ,  Sankarganesh Krishnamoorthy

    IPC: H01M8/18 ,  H01M8/20 ,  H01M8/08

    Abstract: A flow battery includes a positive electrode, a positive electrode electrolyte, a negative electrode, a negative electrode electrolyte, and a polymer electrolyte membrane interposed between the positive electrode and the negative electrode. The positive electrode electrolyte includes water and a first redox couple. The first redox couple includes a first organic compound which includes a first moiety in conjugation with a second moiety. The first organic compound is reduced during discharge while during charging the reduction product of the first organic compound is oxidized to the first organic compound. The negative electrode electrolyte includes water and a second redox couple. The second couple includes a second organic compound including a first moiety in conjugation with a second moiety. The reduction product of the second organic compound is oxidized to the second organic compound during discharge.

    Miniature fixed and adjustable flow restrictor for the body
    77.
    发明授权
    Miniature fixed and adjustable flow restrictor for the body 有权

    公开(公告)号：US11523939B2

    公开(公告)日：2022-12-13

    申请号：US16418899

    申请日：2019-05-21

    Applicant: California Institute of Technology ,  University of Southern California

    Inventor： Yu-Chong Tai ,  Aubrey M. Shapero ,  Nicholas E. Scianmarello ,  Mark S. Humayun

    IPC: A61F9/00 ,  A61K9/00 ,  A61M31/00 ,  G02C7/04

    Abstract: A microfluidic flow restrictor that uses micron-sized beads to impede flow is described. The flow rate can be adjusted by adding or removing the beads using injection needles through self-sealing ports, one injection needle injecting or aspirating beads and another injection needle pushing or pulling fluid from outside of a bead trap within the flow restrictor. In alternative embodiments, the beads or other filler material can be trapped in a manifold bead trap such that they block a subset of fluid channels of the flow restrictor, allowing fluid to flow freely through the rest of the fluid channels. The flow restrictor can be integrated with a contact lens or implantable medical device for use in dispensing liquid therapeutic agents at flow rates of microliters per minute or moving body fluids at a controlled rate from one part of the body to another.

    Noise speed-ups in hidden markov models with applications to speech recognition
    80.
    发明授权
    Noise speed-ups in hidden markov models with applications to speech recognition 有权

    公开(公告)号：US11495213B2

    公开(公告)日：2022-11-08

    申请号：US14802760

    申请日：2015-07-17

    Applicant: UNIVERSITY OF SOUTHERN CALIFORNIA

    Inventor： Kartik Audhkhasi ,  Osonde Osoba ,  Bart Kosko

    IPC: G10L25/36 ,  G10L15/14 ,  G10L15/06 ,  G10L25/33

    Abstract: A learning computer system may estimate unknown parameters and states of a stochastic or uncertain system having a probability structure. The system may include a data processing system that may include a hardware processor that has a configuration that: receives data; generates random, chaotic, fuzzy, or other numerical perturbations of the data, one or more of the states, or the probability structure; estimates observed and hidden states of the stochastic or uncertain system using the data, the generated perturbations, previous states of the stochastic or uncertain system, or estimated states of the stochastic or uncertain system; and causes perturbations or independent noise to be injected into the data, the states, or the stochastic or uncertain system so as to speed up training or learning of the probability structure and of the system parameters or the states.

Patent Agency Ranking