TECHNOLOGIES FOR ADAPTIVE COLLABORATIVE OPTIMIZATION OF INTERNET-OF-THINGS SYSTEMS

    公开(公告)号:US20200034205A1

    公开(公告)日:2020-01-30

    申请号:US16291235

    申请日:2019-03-04

    Abstract: Technologies for collaborative optimization include multiple Internet-of-Things (IoT) devices in communication over a network with an optimization server. Each IoT device selects an optimization strategy based on device context and user preferences. The optimization strategy may be full-local, full-global, or hybrid. Each IoT device receives raw device data from one or more sensors/actuators. If the full-local strategy is selected, the IoT device generates processed data based on the raw device data, generates optimization results based on the processed data, and generates device controls/settings for the sensors/actuators based on the optimization results. If the full-global strategy is selected, the optimization server performs those operations. If the hybrid strategy is selected, the IoT device generates the processed data and the device controls/settings, and the optimization server generates the optimization results. The optimization server may provision plugins to the IoT devices to perform those operations. Other embodiments are described and claimed.

    TECHNOLOGIES FOR ADAPTIVE COLLABORATIVE OPTIMIZATION OF INTERNET-OF-THINGS SYSTEMS

    公开(公告)号:US20180181088A1

    公开(公告)日:2018-06-28

    申请号:US15392855

    申请日:2016-12-28

    CPC classification number: G06F9/5072

    Abstract: Technologies for collaborative optimization include multiple Internet-of-Things (IoT) devices in communication over a network with an optimization server. Each IoT device selects an optimization strategy based on device context and user preferences. The optimization strategy may be full-local, full-global, or hybrid. Each IoT device receives raw device data from one or more sensors/actuators. If the full-local strategy is selected, the IoT device generates processed data based on the raw device data, generates optimization results based on the processed data, and generates device controls/settings for the sensors/actuators based on the optimization results. If the full-global strategy is selected, the optimization server performs those operations. If the hybrid strategy is selected, the IoT device generates the processed data and the device controls/settings, and the optimization server generates the optimization results. The optimization server may provision plugins to the IoT devices to perform those operations. Other embodiments are described and claimed.

    Methods and apparatus for conditional classifier chaining in a constrained machine learning environment

    公开(公告)号:US10863329B2

    公开(公告)日:2020-12-08

    申请号:US16226131

    申请日:2018-12-19

    Abstract: Methods, apparatus, systems, and articles of manufacture for conditional classifier chaining in a constrained machine learning environment are disclosed. An example apparatus includes a classification controller to select a first model to be utilized to classify a first feature identified from sensor data. A memory controller is to copy the first model to a memory. A machine learning processor is to apply the first model to the first feature to create a first classification output, the first classification output indicating an identified class. The classification controller is to, in response to a determination that the first classification output identifies a second model to be used for classification, instruct the memory controller to load the second model into the memory. The machine learning processor is to apply the second model to the second feature to create a second classification output.

    Technologies for adaptive collaborative optimization of internet-of-things systems

    公开(公告)号:US10223169B2

    公开(公告)日:2019-03-05

    申请号:US15392855

    申请日:2016-12-28

    Abstract: Technologies for collaborative optimization include multiple Internet-of-Things (IoT) devices in communication over a network with an optimization server. Each IoT device selects an optimization strategy based on device context and user preferences. The optimization strategy may be full-local, full-global, or hybrid. Each IoT device receives raw device data from one or more sensors/actuators. If the full-local strategy is selected, the IoT device generates processed data based on the raw device data, generates optimization results based on the processed data, and generates device controls/settings for the sensors/actuators based on the optimization results. If the full-global strategy is selected, the optimization server performs those operations. If the hybrid strategy is selected, the IoT device generates the processed data and the device controls/settings, and the optimization server generates the optimization results. The optimization server may provision plugins to the IoT devices to perform those operations. Other embodiments are described and claimed.

    METHODS AND APPARATUS TO FACILITATE END-USER DEFINED POLICY MANAGEMENT

    公开(公告)号:US20170302704A1

    公开(公告)日:2017-10-19

    申请号:US15581827

    申请日:2017-04-28

    Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to facilitate end-user defined policy management. An example apparatus includes an edge node interface to detect addition of a networked user device to a service gateway, and to extract publish information from the networked user device. The example apparatus also includes a device context manager to identify tag parameters based on the publish information from the networked user device, and a tag manager to prohibit unauthorized disclosure of the networked user device by setting values of the tag parameters based on a user profile associated with a type of the networked user device.

Patent Agency Ranking