中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

60 records (took 0.027 seconds)

    REAL-TIME ANOMALY DETECTION FOR INDUSTRIAL PROCESSES
    54.
    发明申请
    REAL-TIME ANOMALY DETECTION FOR INDUSTRIAL PROCESSES 有权

    公开(公告)号：US20220066435A1

    公开(公告)日：2022-03-03

    申请号：US17523559

    申请日：2021-11-10

    Applicant: Intel Corporation

    Inventor： Tara K. Thimmanaik ,  Rita Chattopadhyay ,  David J. Austin

    IPC: G05B23/02 ,  G06T7/00

    Abstract: In one embodiment, a device comprises interface circuitry and processing circuitry. The processing circuitry receives, via the interface circuitry, a video stream captured by a camera during performance of an industrial process, wherein the video stream comprises a sequence of frames; detects, based on analyzing the sequence of frames, a degree of particle scatter that occurs during performance of the industrial process; and determines, based on the degree of particle scatter, that an anomaly occurs during performance of the industrial process.

    MEMORY-EFFICIENT SYSTEM FOR DECISION TREE MACHINE LEARNING
    55.
    发明申请
    MEMORY-EFFICIENT SYSTEM FOR DECISION TREE MACHINE LEARNING 有权

    公开(公告)号：US20210097449A1

    公开(公告)日：2021-04-01

    申请号：US17120059

    申请日：2020-12-11

    Applicant: Intel Corporation

    Inventor： Rita Chattopadhyay ,  Rajesh Bansal

    IPC: G06N20/20 ,  G06N5/00 ,  G06N5/04

    Abstract: In one embodiment, a processing device for training a decision tree model includes memory and processing circuitry. The processing circuitry allocates a tree node array in memory, where the number of array elements in the tree node array equals the number of data samples in a training dataset. The processing circuitry also obtains the training dataset, which contains data samples captured at least partially by sensor(s). The processing circuitry then trains the decision tree model. For example, a root node is initially assigned to the data samples in the training dataset. The root node is recursively split into child nodes based on identified branch conditions, where each child node is assigned to a subset of data samples. The tree node array is continuously updated during training to identify the child nodes assigned to the data samples. The processing circuitry then stores the trained decision tree model in memory.

    Optimized data discretization
    56.
    发明授权
    Optimized data discretization 有权

    公开(公告)号：US10685081B2

    公开(公告)日：2020-06-16

    申请号：US15628123

    申请日：2017-06-20

    Applicant: Intel Corporation

    Inventor： Rita Chattopadhyay ,  Ravindra V. Narkhede

    IPC: G06F17/50 ,  G06F17/12 ,  G06F16/903 ,  H03M7/30 ,  G06T9/00 ,  G06F30/23

    Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store data. The processor is to: store a first dataset on the memory; identify a plurality of bin sizes for compressing the first dataset; compute a plurality of performance costs associated with the plurality of bin sizes; identify a minimum performance cost of the plurality of performance costs; identify an optimal bin size based on the particular bin size associated with the minimum performance cost; partition the first dataset into a plurality of bins based on the optimal bin size; identify a plurality of bin counts associated with the plurality of bins; generate a second dataset based on the plurality of bin counts, wherein the second dataset is smaller than the first dataset; and store the second dataset on the memory, wherein the second dataset is stored using less memory space than the first dataset.

    Robust monitoring gauges
    58.
    发明授权
    Robust monitoring gauges 有权

    公开(公告)号：US10354137B2

    公开(公告)日：2019-07-16

    申请号：US15283146

    申请日：2016-09-30

    Applicant: Intel Corporation

    Inventor： Anne M. Russell ,  Nikhil Jog ,  Rita Chattopadhyay

    IPC: G06K9/00

    Abstract: Methods, systems, and storage media for robust monitoring a gauge are disclosed herein. In an embodiment, a digital image of a gauge may be received to identify an analog value indicator of the gauge and to form an indicator representation corresponding to the analog value indicator. Robust optical character recognition and image filter may provide enhanced gauge reading and/or monitoring. Other embodiments may be disclosed and/or claimed.

    TECHNOLOGIES FOR AUTONOMOUS DRIVING QUALITY OF SERVICE DETERMINATION AND COMMUNICATION
    60.
    发明申请
    TECHNOLOGIES FOR AUTONOMOUS DRIVING QUALITY OF SERVICE DETERMINATION AND COMMUNICATION 审中-公开

    公开(公告)号：US20190049259A1

    公开(公告)日：2019-02-14

    申请号：US16143894

    申请日：2018-09-27

    Applicant: Intel Corporation

    Inventor： Magdiel F. Galan-Oliveras ,  Rita Chattopadhyay ,  Subramanian Anandaraj

    IPC: G01C21/34 ,  G05D1/00

    Abstract: Technologies for autonomous vehicle driving quality of service (QoS) determination and communication include an advanced vehicle with a vehicle computing device. The computing device determines multiple route segments of one or more routes to a destination. The computing device determines, for each route segment, one or more autonomous driving factors that are each indicative of an autonomy level achievable by the advanced vehicle for the associated route segment. Factors may include map availability, weather conditions, road conditions, or other factors. The computing device determines, for each route segment, an autonomous QoS score based on the autonomous driving factors. The computing device may rank multiple routes to the destination based on the autonomous QoS scores associated with the route segments of those routes. The computing device may display a proposed route to a user of the advanced vehicle and receive a selection from the user. Other embodiments are described and claimed.

Patent Agency Ranking