ADAPTIVE VEHICLE AND TRAFFIC MANAGEMENT CONSIDERING COMPLIANCE RATES

    公开(公告)号:US20240416950A1

    公开(公告)日:2024-12-19

    申请号:US18335084

    申请日:2023-06-14

    Abstract: A system and method is provided for implementing computer-controlled systems (e.g., vehicle safety and traffic management systems) based on compliance rates. A vehicle system and method are provided that estimate compliance rates in real-time, and have the capability to dynamically modify the computer-controlled instructions generated by a computer-controlled system (e.g., vehicle safety and traffic management systems) in a manner that improves compliance, and in-turn improves overall system performance. For example, a vehicle includes sensors receiving data from a plurality of communicative connected vehicles. The received data is associated with a real-time monitoring of traffic conditions for the vehicle. The vehicle also includes a controller device estimating a compliance rate in real-time based on the received data. The controller device of the vehicle also controls an automated operation of the vehicle using a modified computer-controlled instruction based on the estimated compliance rate.

    METHOD AND SYSTEM FOR DETERMINING INDIVIDUALIZED HEAD RELATED TRANSFER FUNCTIONS

    公开(公告)号:US20240349001A1

    公开(公告)日:2024-10-17

    申请号:US18580344

    申请日:2022-07-18

    Abstract: There is provided a system and method for determining individualized head related transfer functions (HRTF) for a user. The method including: receiving measurement data from the user, the measurement data generated by repeatedly emitting an audible reference sound at positions in space around the user and, during each emission, recording sounds received near each ear of the user, the measurement data including, for each emission, the recorded sounds and positional information of the emission; determining the individualized HRTF by updating a decoder of a trained generative artificial neural network model, the decoder receives the measurement data as input, the trained generative artificial neural network model including an encoder and the decoder, the generative artificial neural network model is trained using data gathered from a plurality of test subjects with known spectral representations and directions for associated HRTFs at different positions in space; and outputting the individualized HRTF.

    SYSTEMS, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR EVALUATING MACHINE LEARNING MODEL PERFORMANCE

    公开(公告)号:US20240273386A1

    公开(公告)日:2024-08-15

    申请号:US18436182

    申请日:2024-02-08

    CPC classification number: G06N5/04

    Abstract: A system, method and computer program product for evaluating a multi-label classification machine learning model. A model labelled dataset is received from the model and includes a plurality of data elements each labelled with zero or more model predicted labels of q potential classes. A multi-label confusion matrix is defined to include q+1 rows with q rows for true labels and 1 row for no true label and q+1 columns with q columns for predicted labels and 1 column for no predicted label. The matrix is populated by comparing the model labelled dataset with a true labelled dataset. At least one performance metric is calculated from the populated multi-label confusion matrix.

Patent Agency Ranking