中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.017 seconds)

    DEVICE-INVARIANT, FREQUENCY-DOMAIN SIGNAL PROCESSING WITH MACHINE LEARNING
    1.
    发明申请
    DEVICE-INVARIANT, FREQUENCY-DOMAIN SIGNAL PROCESSING WITH MACHINE LEARNING 有权

    公开(公告)号：US20220269958A1

    公开(公告)日：2022-08-25

    申请号：US17245951

    申请日：2021-04-30

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Mohsin Yusuf Ahmed ,  Li Zhu ,  Korosh Vatanparvar ,  Md Mahbubur Rahman ,  Tousif Ahmed ,  Jilong Kuang ,  Jun Gao

    IPC: G06N5/04 ,  G06N20/00

    Abstract: Device-invariant, frequency-domain signal processing with machine learning includes retrieving with a host device a device-specific alien dataset corresponding to an alien device. The device-specific alien dataset is retrieved from a remote data storage device communicatively coupled with the host device. A plurality of frequency-domain features are extracted from the device-specific alien dataset and a machine learning model is trained using the plurality of frequency-domain features. The host device extracts frequency-domain features from signals generated by sensors operatively coupled with the host device. Real-time frequency bin adaptation of the frequency-domain features extracted by the host device is performed. Based on the frequency-domain features extracted by the host device, as adapted, an inference is performed using the machine learning model.

    EARLY DETECTION OF INFECTIOUS RESPIRATORY DISEASES
    4.
    发明申请
    EARLY DETECTION OF INFECTIOUS RESPIRATORY DISEASES 有权

    公开(公告)号：US20220122740A1

    公开(公告)日：2022-04-21

    申请号：US17071763

    申请日：2020-10-15

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Ebrahim Nematihosseinabadi ,  Md M. Rahman ,  Viswam Nathan ,  Korosh Vatanparvar ,  Tousif Ahmed ,  Jilong Kuang ,  Jun Gao

    IPC: G16H50/80 ,  G16H40/67 ,  G16H50/70 ,  G16H10/60 ,  G16H50/20 ,  G16H50/30 ,  G16H10/20 ,  H04L29/08 ,  H04W4/029 ,  A61B5/08 ,  A61B5/1455

    Abstract: Early detection of infectious respiratory diseases includes monitoring, during a predetermined time interval, electronic communications generated by network-connected portable devices, each portable device used by one of a plurality of users. The electronic communications are processed by extracting from each electronic communication biomarkers obtained by processing signals captured by the portable devices, the signals generated in response to sensor-detected respiratory activity of the portable device users. Clusters of users are generated based on the biomarkers and are conditioned based on pre-condition data extracted from the electronic communications, the pre-condition data corresponding to users determined to have pre-existing health conditions. Based on context data extracted from the electronic communications, user co-locations and pre-symptomatic biomarker variation co-occurrences are determined for users who exhibit pre-symptomatic biomarker variations associated with an infectious respiratory disease. An outbreak of the infectious respiratory disease is predicted along with the likelihood of infection for individuals based on the user co-locations and pre-symptomatic biomarker variation co-occurrences.

    SYSTEM AND METHOD FOR PASSIVE SUBJECT SPECIFIC MONITORING
    5.
    发明申请
    SYSTEM AND METHOD FOR PASSIVE SUBJECT SPECIFIC MONITORING 有权

    公开(公告)号：US20210134319A1

    公开(公告)日：2021-05-06

    申请号：US16999027

    申请日：2020-08-20

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Korosh Vatanparvar ,  Tousif Ahmed ,  Viswam Nathan ,  Ebrahim Nematihosseinabadi ,  Md Mahbubur Rahman ,  Jilong Kuang ,  Jun Gao

    IPC: G10L25/66 ,  G10L15/16

    Abstract: A method includes obtaining, by an electronic device, an audio segment comprising one or more audio events of a target subject. The method also includes extracting, by the electronic device, audio embeddings from the one or more audio events using an embedding model, the embedding model comprising a trained machine learning model. The method further includes comparing, by the electronic device, the extracted audio embeddings with a match profile of the target subject, the match profile generated during an enrollment stage. The method also includes generating, by the electronic device, a label for the audio segment based on whether or not the extracted audio embeddings match the match profile, wherein the label enables correlation of the audio segment with the target subject for monitoring a health condition of the target subject.

    SYSTEMS AND METHODS TO DETECT AND CHARACTERIZE STRESS USING PHYSIOLOGICAL SENSORS
    9.
    发明公开
    SYSTEMS AND METHODS TO DETECT AND CHARACTERIZE STRESS USING PHYSIOLOGICAL SENSORS 审中-公开

    公开(公告)号：US20230233123A1

    公开(公告)日：2023-07-27

    申请号：US18156292

    申请日：2023-01-18

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Md Mahbubur Rahman ,  Viswam Nathan ,  Li Zhu ,  Tousif Ahmed ,  Jungmok Bae ,  Jilong Kuang ,  Jeong Woo Kim ,  Jun Gao

    IPC: A61B5/16 ,  A61B5/00

    CPC classification number: A61B5/165 ,  A61B5/486 ,  A61B5/7246 ,  A61B5/6802 ,  A61B5/7267

    Abstract: A method includes receiving multimodal data collected using at least one wearable device during an assessment window. The method also includes extracting biomarker features from the multimodal data, based on changes in the extracted biomarker features. The method also includes detecting that a stress event occurred during the assessment window. The method also includes accessing a plurality of templates of patterns in biomarker features, wherein a first subset of the templates is associated with unhealthy response to stress and a second subset of the templates is associated with healthy response to stress. The method also includes determining whether the stress event corresponds to a healthy response or an unhealthy response based on similarities between a pattern in the extracted biomarker features and the plurality of templates. The method also includes responsive to the stress event corresponding to an unhealthy response, providing a stress management recommendation.

Patent Agency Ranking