RACH PROCEDURES FOR NON-TERRESTRIAL NETWORKS

    公开(公告)号:US20220030638A1

    公开(公告)日:2022-01-27

    申请号:US17359052

    申请日:2021-06-25

    Abstract: A system and method for random access procedures in a non-terrestrial network. In some embodiments, the method includes calculating, by a user equipment (UE), a timing advance based on location information of the UE and on an ephemeris of a non-terrestrial network node. The method may further include randomly selecting a random value from a plurality of values, and sending, at a transmission time, by the UE, to the non-terrestrial network node, a random access (RA) message, which may include a signature. The transmission time may differ from a nominal transmission time by an amount based on the random value, the nominal transmission time being based on the timing advance, or the signature may differ from a nominal signature by a cyclic shift based on the random value.

    INTERLEAVER DESIGN AND PAIRWISE CODEWORD DISTANCE DISTRIBUTION ENHANCEMENT FOR TURBO AUTOENCODER

    公开(公告)号:US20220385307A1

    公开(公告)日:2022-12-01

    申请号:US17726506

    申请日:2022-04-21

    Abstract: A symmetric interleaver for a Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) encoder and a circular padding mode are disclosed. The interleaver interleaves elements of an input block to form an output block in which an output neighborhood of elements for each element of the output block is symmetric to an input neighborhood of elements for each element of the input block. A position of an element of the input block is interleaved based on an index i of the position times a parameter δ modulo K in which the parameter δ is relatively prime with K. A test loss function may be used to train the encoder that includes a Binary Cross Entropy (BCE) loss function plus a function that minimizes a number of codeword pairs based on a Euclidean distance. The RNN encoder may be implemented as part of a Turbo Autoencoder (TurboAE) encoder.

    METHOD AND SYSTEM FOR RATE-MATCHING AUTO-ENCODERS

    公开(公告)号:US20240154722A1

    公开(公告)日:2024-05-09

    申请号:US18471092

    申请日:2023-09-20

    CPC classification number: H04L1/0069 G06N3/0455 H04L1/0013 H04L1/0057

    Abstract: A method and a system are provided in which a message is encoded, by a neural encoder, to generate a codeword having a first length corresponding to a first code rate of the neural encoder. A number of components of the codeword corresponds to the first code rate. At least one of repeating the components or puncturing at least one of the components is performed to generate a rate-matched codeword having a second length corresponding to a second code rate. The rate-matched codeword is estimated and modified to generate an estimated codeword having the first length corresponding to the first code rate of a neural decoder. The estimated codeword is decoded, by the neural decoder, to generate an estimated message.

Patent Agency Ranking