知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

216 records (took 0.037 seconds)

    Detecting respiratory tract infection based on changes in coughing sounds
    2.
    发明授权
    Detecting respiratory tract infection based on changes in coughing sounds 有权

    公开(公告)号：US10813559B2

    公开(公告)日：2020-10-27

    申请号：US16854883

    申请日：2020-04-21

    Applicant: Facense Ltd.

    Inventor： Ari M Frank ,  Arie Tzvieli ,  Ori Tzvieli ,  Gil Thieberger

    IPC: A61B5/12 ,  A61B5/01 ,  A61B5/00 ,  G01J5/12 ,  A61B5/16 ,  G01J5/02 ,  G01J5/00

    Abstract: Detecting a respiratory tract infection (RTI) based on changes in coughing sounds, which can provide an early warning of infection with a disease like COVID-19, as well as indications of its progression and severity. In one embodiment, the system includes smartglasses, with sensors mounted thereto, which include an acoustic sensor mounted at a fixed position relative to a user's head, and a movement sensor. A computer receives current measurements of the user, taken with the sensors, while there were head movements that characterize coughing, and also earlier measurements of the user, taken with the sensors, while the user had a known extent of the RTI and while there were head movements that characterize coughing. The computer detects a change relative to the known extent of the RTI based on a difference between the current measurements and the earlier measurements.

    Method and system for assigning vulnerability levels to sessions
    3.
    发明授权
    Method and system for assigning vulnerability levels to sessions 有权

    公开(公告)号：US10778741B2

    公开(公告)日：2020-09-15

    申请号：US14482293

    申请日：2014-09-10

    Applicant: Valens Semiconductor Ltd.

    Inventor： Eyran Lida ,  Aviv Salamon

    IPC: H04L29/06 ,  H04L12/911 ,  H04L12/64 ,  H04L12/26 ,  H04L12/24 ,  H04L12/46 ,  H04L29/08

    Abstract: Methods and systems for indicating vulnerability of streaming sessions to additional latency variations, including the steps of: determining a threshold, based on a limit associated with an allowable end-to-end latency variation of a first session. Estimating the end-to-end latency variation of the first streaming session. Determining that the estimated end-to-end latency variation is higher than the threshold. Setting a first vulnerability indicator of the first streaming session at the first output port to a first level. Setting a second vulnerability indicator of a second existing streaming session at a second output port of a second switch to a second level, based on first level of the first vulnerability indicator. Receiving requests to establish new streaming sessions over first and second new paths passing through the first and second output ports. And rejecting the requests based on the first and second vulnerability indicators.

    Identification of posture-related syncope using head-mounted sensors
    4.
    发明授权
    Identification of posture-related syncope using head-mounted sensors 审中-公开

    公开(公告)号：US10667697B2

    公开(公告)日：2020-06-02

    申请号：US16453993

    申请日：2019-06-26

    Applicant: Facense Ltd.

    Inventor： Ori Tzvieli ,  Ari M Frank ,  Arie Tzvieli ,  Gil Thieberger

    IPC: G01J5/12 ,  A61B5/01 ,  G01J5/02 ,  A61B5/00 ,  A61B5/16 ,  G01J5/00

    Abstract: Described herein are embodiments of systems and a method to identify orthostatic hypotension and postural-orthostatic tachycardia syndrome. One system includes a head-mounted device configured to measure photoplethysmographic signal (PPG signal) at a region on a user's head, and a head-mounted camera configured to capture images indicative of the user's posture. Additionally, the system includes a computer that calculates systolic and diastolic blood pressure values based on the PPG signal, and identifies orthostatic hypotension based on a drop of systolic blood pressure below a first threshold, and/or a drop of diastolic blood pressure below a second threshold, within a predetermined duration from a transition in the posture from supine to sitting posture, or from sitting to standing posture.

    Human-curated glossary for rapid hybrid-based transcription of audio
    5.
    发明授权
    Human-curated glossary for rapid hybrid-based transcription of audio 有权

    公开(公告)号：US10607599B1

    公开(公告)日：2020-03-31

    申请号：US16594809

    申请日：2019-10-07

    Applicant: Verbit Software Ltd.

    Inventor： Eric Ariel Shellef ,  Yaakov Kobi Ben Tsvi ,  Iris Getz ,  Tom Livne ,  Roman Himmelreich ,  Elad Shtilerman

    IPC: G10L15/06 ,  G10L15/30 ,  G10L15/26 ,  G10L15/187

    Abstract: Described herein are curation of a glossary and its utilization for automatic speech recognition (ASR). In one embodiment, a server receives an audio recording of speech, taken over a period spanning at least two hours. During the first hour, the server generates, utilizing an ASR system, a transcription of a segment of the audio, recorded during the first twenty minutes. The server receives, from a transcriber, a phrase that does not appear in the transcription, but was spoken in the segment, and adds the phrase to a glossary. After the first hour of the period, the server generates, utilizing the ASR system, a second transcription of a second segment of the audio, provides the second transcription and the glossary to a second transcriber, and receives a corrected transcription, in which the second transcriber substituted a second phrase in the second transcription, which was not in the glossary, with the phrase.

    Network-based calculation of prevalence of repeated medical imaging
    6.
    发明授权
    Network-based calculation of prevalence of repeated medical imaging 有权

    公开(公告)号：US10600512B1

    公开(公告)日：2020-03-24

    申请号：US16543571

    申请日：2019-08-18

    Applicant: Medigate tech Ltd.

    Inventor： Vitali Sepetnitsky ,  Eden Zvi Neiberg ,  Itay Kirshenbaum

    IPC: G16H30/40 ,  H04L12/26 ,  G16H30/20

    Abstract: This disclosure describes a system, a method, and a computer program that enable calculation of prevalence of repeated medical imaging at a medical facility. In one embodiment, a computer receives packets transmitted over a communication network, where the packets include data related to operation of one or more medical imaging devices at the medical facility. The computer performs deep packet inspection (DPI) of the packets, and extracts, from results of the DPI, values indicative of medical images acquired using the one or more medical imaging devices. The computer identifies, based on the values, instances of repeated images, where a repeated image involves acquiring images of the same patient and body part multiple times, utilizing a certain type of medical imaging device within a predetermined period. The computer calculates, based on the instances, a value indicative of the prevalence of repeated medical imaging at the medical facility.

    On-demand isolated execution of specific tasks
    7.
    发明授权
    On-demand isolated execution of specific tasks 有权

    公开(公告)号：US10467045B1

    公开(公告)日：2019-11-05

    申请号：US15643040

    申请日：2017-07-06

    Applicant: Binaris Inc

    Inventor： Avner Braverman ,  Michael Adda

    IPC: G06F9/48 ,  G06F9/52 ,  G06F9/50 ,  G06F9/30

    Abstract: System and methods for on-demand isolated execution of specific tasks. A system receives, via a communication interface, requests to execute tasks. The system reacts to each of the requests by allocating, on-demand and per the request received, a unique sub-set of physical computational resources, so as to result in several such unique sub-sets of resources. The system executes, per each of the tasks, the respective commands of the task, by converting the respective commands of the task into executable instructions and running the executable instructions. The respective commands of each of the tasks are converted so as to cause the resulting executable instruction to refrain from accessing other unique sub-sets that were not allocated to the task, thereby facilitating said on-demand isolated execution of each of the tasks.

    Mode-conversion digital canceller for high bandwidth differential signaling
    10.
    发明授权
    Mode-conversion digital canceller for high bandwidth differential signaling 有权

    公开(公告)号：US10256920B2

    公开(公告)日：2019-04-09

    申请号：US15170019

    申请日：2016-06-01

    Applicant: Valens Semiconductor Ltd.

    Inventor： Eyran Lida ,  Aviv Salamon ,  Gaby Gur Cohen ,  Israel Greiss

    IPC: H04B15/00 ,  H04B1/38 ,  H04B1/10 ,  H04L25/03

    Abstract: Systems and methods for recovering rapidly from a mode-conversion of a common mode interference. One exemplary transceiver includes: a slicer configured to generate slicing decisions and slicing errors based on a differential signal, transmitted at a rate above 500 Mbps, which is received from a second transceiver; and a common mode sensor analog front end (CMS-AFE) configured to sense a common mode component of the differential signal. The CMS-AFE is coupled to a fast-adaptive mode-conversion canceller (FA-MCC) configured to generate a compensation signal that compensates for differential interferences that are correlated with the common mode component. Wherein, within less than 1 millisecond from an occurrence of a differential interference that causes the packet loss to exceed 10% as a result of the mode-conversion, the transceiver is configured to utilize the slicing errors to adapt the FA-MCC to a level that reduces the packet loss rate to below 1%.

Patent Agency Ranking