MULTI-ACCESS EDGE COMPUTING FOR REMOTE LOCATIONS

    公开(公告)号:US20240330451A1

    公开(公告)日:2024-10-03

    申请号:US18742266

    申请日:2024-06-13

    IPC分类号: G06F21/55

    CPC分类号: G06F21/554 G06F2221/034

    摘要: The present disclosure provide multi-access edge computing systems and methods. One such system comprises a plurality of sensor devices that are configured to collect construction site sensor data and transmit the sensor data to a local computing system that is configured to combine the sensor data with user feedback data and transmit the combined data to an edge computing system. The edge computing system is configured to process the combined data and transmit the combined data to a cloud computing system, where the cloud computing system that is configured to process the transmitted data from the edge computing system. The edge computing system or the cloud computing system is configured to execute a site risk prediction application and predict a hazard within a construction site based on the collected construction site sensor data and generate an output signal to equipment operating at the construction site.

    HEATED PEAT AS A SLOW RELEASE ORGANIC FERTILIZER

    公开(公告)号:US20240246883A1

    公开(公告)日:2024-07-25

    申请号:US18422115

    申请日:2024-01-25

    发明人: Mica F. MCMILLAN

    IPC分类号: C05G3/40 C05F11/04

    CPC分类号: C05G3/40 C05F11/04

    摘要: In one aspect, the disclosure relates to slow-release fertilizers including a peat and an optional filler material such as, for example sand, methods of making the same, methods of improving the growth of plants including using the same, and plants grown using the disclosed methods. The slow-release fertilizers are environmentally safe and conducive to the establishment of various plants, including ground cover plants. In some aspects, the slow-release fertilizers induce soil-water repellency in systems in which they are applied and can be useful for research as well as horticultural purposes. In another aspect, the slow-release fertilizers provide increased levels of ammonia, amino acids, and other nutrients relative to conventional fertilizers. This abstract is intended as a scanning tool for purposes of searching in the particular art and is not intended to be limiting of the present disclosure.

    AUTOMATIC ACCESSIBILITY MAPPING USING AI
    7.
    发明公开

    公开(公告)号:US20240203118A1

    公开(公告)日:2024-06-20

    申请号:US18544015

    申请日:2023-12-18

    IPC分类号: G06V20/10 G06T7/73 G06V20/17

    摘要: The present disclosure presents systems and methods for automatically performing an accessibility audit using Artificial Intelligence (AI) techniques. One such method, among others, comprises acquiring geospatial imaging data of a location site; identifying, using artificial intelligence, accessible features of the location site that are determined to be accessible to a person having a physical disability; identifying, using artificial intelligence, inaccessible features of the location site that are determined to be inaccessible to a person having a physical disability; and/or generating, using Global Information System mapping processes, an aerial map of a location site using the geospatial imaging data, wherein the aerial map comprises a first layer denoting the accessible features of the location site using specific colors, wherein the aerial map comprises a second layer denoting the inaccessible features of the location site using different specific colors.

    HIGH DIMENSIONAL AND ULTRAHIGH DIMENSIONAL DATA ANALYSIS WITH KERNEL NEURAL NETWORKS

    公开(公告)号:US20240127050A1

    公开(公告)日:2024-04-18

    申请号:US18267184

    申请日:2021-12-08

    IPC分类号: G06N3/08 G06N5/022

    CPC分类号: G06N3/08 G06N5/022

    摘要: Various examples are provided related to the application of a kernel neural network (KNN) to the analysis of high dimensional and ultrahigh dimensional data for, e.g., risk prediction. In one embodiment, a method includes training a KNN with a training set to produce a trained KNN model, determining a likelihood of a condition based at least in part upon an output indication of the trained KNN corresponding to one or more phenotypes, identifying treatment or prevention strategy for an individual based at least in part upon the likelihood of the condition. The KNN model includes a plurality of kernels as a plurality of layers to capture complexity between the data with disease phenotypes. The training set of data includes genetic information applied as inputs to the KNN and the phenotype(s), and the output indication is based upon analysis of data comprising genetic information from the individual by the trained KNN.