FAST ADAPTATION FOR DEEP LEARNING APPLICATION THROUGH BACKPROPAGATION

    公开(公告)号:US20240256922A1

    公开(公告)日:2024-08-01

    申请号:US18104073

    申请日:2023-01-31

    CPC classification number: G06N5/04 G16Y20/10 G16Y30/00

    Abstract: Systems and methods are provided for dynamically adapting configuration setting associated with capturing content as input data for inferencing in the Multi-Access Edge Computing in a 5G telecommunication network. The inferencing is based on a use of a deep neural network. In particular, the method includes determining a gradient of a change in inference data over a change in configuration setting for capturing input data (the inference-configuration gradient). The method further updates the configuration setting based on the gradient of a change in inference data over a change in the configuration setting. The inference-configuration gradient is based on a combination of an input-configuration gradient and an inference-input gradient. The input-configuration gradient indicates a change in input data as the configuration setting value changes. The inference-input gradient indicates, as a saliency of the deep neural network, a change in inference result of the input data as the input data changes.

    Intelligent Internet of Things Integrated Perception System and Method Thereof

    公开(公告)号:US20240214905A1

    公开(公告)日:2024-06-27

    申请号:US17907210

    申请日:2021-09-07

    CPC classification number: H04W40/24 G16Y20/10 H04W4/38 H04W76/10 H04W84/18

    Abstract: The present invention discloses an intelligent internet of things integrated perception system and method thereof, the integrated perception system comprises a data perception layer (1); a connection and transmission layer (2); an edge computation layer (3); a cloud computation layer (4); an application layer (5). The data perception layer (1) is composed of a plurality of sensor device nodes, and transmits the monitored environmental data to the edge computation layer (3) through the connection and transmission layer (2); the cloud computation layer (4) performs data fusion according to data provided by each edge computation device, and forms action instructions for the plurality of application devices. Multi-layer IoT integrated perception is realized, and the requirement for the comprehensive and integrated processing of different types of data in the IoT is satisfied, realizes the deployment of the monitoring network topology of the data perception layer and improves the monitoring efficiency of the sensor device nodes.

    Pressure measuring device using textile sensor, and internet of things-based device control system using same

    公开(公告)号:US11983331B2

    公开(公告)日:2024-05-14

    申请号:US17207356

    申请日:2021-03-19

    Applicant: Jeonghan Uhm

    CPC classification number: G06F3/0202 G06F13/12 G16Y10/25 G16Y20/10

    Abstract: The present disclosure relates to a pressure measuring device using a textile sensor. In one embodiment the pressure measuring device includes: a textile sensor which exhibits conductivity; a power unit which supplies power to the pressure measuring device; and a control unit which is electrically connected to a textile sensor layer and the power unit, checks a resistance change value detected by the textile sensor by a force applied to the textile sensor, and determines the pressure value of the force applied to the textile sensor on the basis of the checked resistance change value, wherein the control unit checks a control command corresponding to the pressure value measured on the basis of the force applied to the textile sensor, and may transmit the control command to a pre-designated peripheral device. A function corresponding to the checked control command may be executed on the pre-designated peripheral device.

Patent Agency Ranking