知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

24 records (took 0.028 seconds)

    MICROFLUIDIC SYSTEM FOR ROBUST LONG-TERM ELECTRICAL MEASUREMENT AND/OR STIMULATION OF CELL STRUCTURES
    12.
    发明申请
    MICROFLUIDIC SYSTEM FOR ROBUST LONG-TERM ELECTRICAL MEASUREMENT AND/OR STIMULATION OF CELL STRUCTURES 有权

    公开(公告)号：US20240425787A1

    公开(公告)日：2024-12-26

    申请号：US18701341

    申请日：2022-10-21

    Applicant: ALPVISION S.A. ,  FINALSPARK SARL

    Inventor： Jean-Marc COMBY ,  Flavio MOR ,  Martin KUTTER ,  Frédéric JORDAN

    IPC: C12M3/06 ,  C12M1/00 ,  C12M1/36 ,  C12M3/00

    Abstract: A microfluidics system to maintain alive and control cell cultures such as neuronal cell cultures over an air-liquid interface is arranged to prevent formation of air bubbles and liquid overflows in fully automated 24/7 operation over the mid-long term. A pumping device pushes a liquid through an inlet of the microfluidics channel, then through an area of the microfluidics channel that is under the air-liquid interface, then through an outlet of the microfluidics channel, assisted with geometrical arrangements of the microfluidics channel outlet and optionally inlet placements relative to the porous membranes of the air-liquid interface. The pumping device is programmed with different flow rates, flow directions, and flow durations according to cell culture features and events detected with a computer vision system and/or an electrophysiological signal processing system to automatically adapt the parameters of the pumping device to the current state of the cell culture over the air-liquid interface.

    Authentication machine learning from multiple digital presentations
    15.
    发明授权
    Authentication machine learning from multiple digital presentations 有权

    公开(公告)号：US11461582B2

    公开(公告)日：2022-10-04

    申请号：US16956028

    申请日：2018-12-20

    Applicant: ALPVISION S.A.

    Inventor： Frederic Jordan ,  Nicolas Rudaz ,  Yves Delacretaz ,  Martin Kutter

    IPC: G06K9/62 ,  G06T7/70

    Abstract: A machine learning system may automatically produce classifier algorithms and configuration parameters by selecting them into a set of predetermined unitary algorithms and associated parametrization values. Multiple digital representations of input object items may be produced by varying the position and orientation of the object to be classified and/or of the sensor to capture a digital representation of the object, and/or by varying a physical environment parameter which changes the digital representation capture of the object by the sensor. A robot arm or a conveyor may vary the object and/or the sensor positions and orientations. The machine learning system may employ generic programming to facilitate the production of classifiers suitable for the classification of multiple digital representations of input object items. The machine learning system may automatically generate reference template signals as configuration parameters for the unitary algorithms to facilitate the production of classifiers suitable for the classification of multiple digital representations of input object items.

    COGNITIVE COMPUTING METHODS AND SYSTEMS BASED ON BILOGIVAL NEUROL NETWORKS
    20.
    发明申请
    COGNITIVE COMPUTING METHODS AND SYSTEMS BASED ON BILOGIVAL NEUROL NETWORKS 有权

    公开(公告)号：US20210334657A1

    公开(公告)日：2021-10-28

    申请号：US17274020

    申请日：2019-09-08

    Applicant: ALPVISION S.A.

    Inventor： Frederic JORDAN ,  Martin KUTTER ,  Yves DELACRETAZ

    IPC: G06N3/08 ,  G06N3/06 ,  G06N3/00

    Abstract: A Biological Neural Network (BNN) core unit comprising a neural cell culture, an input stimulation unit, an output readout unit may be controlled through its various life cycles to provide data processing functionality. An automation system comprising an environmental and chemical controller unit adapted to operate with the BNN stimulation and readout data interfaces facilitates the monitoring and adaptation of the BNN core unit parameters. Pre-processing and post-processing of the BNN interface signals may further facilitate the training and reinforcement learning by the BNN. Multiple BNN core units may also be assembled together as a stack. The proposed system provides a BNN Operating System as a core component for a wetware server to receive, process and transmit data for different client applications without exposing the BNN core unit components to the client user while requiring significantly less energy than conventional silicon-based hardware and software information processing for high-level cognitive computing tasks.

Patent Agency Ranking