Memory sharing for application offload from host processor to integrated sensor hub

    公开(公告)号:US10509748B2

    公开(公告)日:2019-12-17

    申请号:US15577658

    申请日:2016-12-30

    Abstract: Memory sharing techniques are provided for offloading an application from a host processor to an integrated sensor hub (ISH). A methodology implementing the techniques according to an embodiment includes allocating a shared region of memory to be accessed by the host processor and by the ISH, in connection with the execution of a location application. The method also includes storing a location database in the shared region of memory. The location database is divided into segments, where each segment is associated with an area, for example, defined by a range of latitudes and longitudes. The method further includes transferring, through a direct memory access (DMA), one or more of the segments between the shared memory region and a second memory associated with the ISH. The method further includes executing at least a portion of the location application on the ISH, based on the data segments stored in the second memory.

    D2D SPATIAL UNDERSTANDING WITH ELECTRIC MAGNETS

    公开(公告)号:US20250012874A1

    公开(公告)日:2025-01-09

    申请号:US18370409

    申请日:2023-09-20

    Abstract: The present application provides a system including a plurality of components to be mounted to a first device in a preset layout and generate a magnetic field; a magnetometer integrated with a second device to detect the magnetic field to generate reading data associated with the magnetic field at the second device; and a processor configured to determine a position of the second device relative to the first device based on the reading data and the preset layout of the plurality of components.

    Unification of classifier models across device platforms

    公开(公告)号:US11126897B2

    公开(公告)日:2021-09-21

    申请号:US15577675

    申请日:2016-12-30

    Abstract: Techniques are provided for unification of classifier models across device platforms of varying form factors and/or sensor calibrations. A methodology implementing the techniques according to an embodiment includes extracting classification features from data provided by sensors associated with a first device platform. The method also includes applying a feature mapping function to the extracted features. The feature mapping function is configured to transform the features such that the are suitable for use by a classifier model that is trained on data provided by sensors associated with a second device platform. The method further includes executing the classifier model on the transformed features to generate classifications, for example recognized activities associated with use of the first device. The feature mapping function is based on application of a statistical distribution distance minimization between a sampling of data provided by sensors of the first device and sensors of the second device.

Patent Agency Ranking