Abstract:
Methods and apparatus are provided in which channel matrices at time slots are estimated using reference signals received from a base station (BS) at the time slots. A sequence of channel matrices at future time slots are estimated using the estimated channel matrices as input to a neural network (NN) trained based on known sets of past and future channel matrices. A parameter is determined using at least one channel matrix from the sequence of channel matrices.
Abstract:
A method and system for training a neural network are herein provided. According to one embodiment, a method includes generating a first labelled dataset corresponding to a first modulation scheme and a second labelled dataset corresponding to a second modulation scheme, determining a first gradient of a cost function between a first neural network layer and a second neural network layer based on back-propagation using the first labelled dataset and the second labelled dataset, and determining a second gradient of the cost function between the second neural network layer and a first set of nodes of a third neural network layer based on back-propagation using the first labelled dataset. The first set of nodes of the third neural network layer correspond to a first plurality of detector classes associated with the first modulation scheme.
Abstract:
A method of signal demodulation includes receiving, by a signal receiver, a first signal modulated by a symbol corresponding to a point in a constellation; generating, by the signal receiver and on the basis of the first signal, a modulation estimate; identifying, by the signal receiver and on the basis of the modulation estimate, a row or column of a candidate lookup table, the row or column corresponding to a region of the constellation; reading, by the signal receiver, from the row or column of the candidate lookup table one or more candidate points of the constellation, at least one among the one or more candidate points being more distant, from a center of the region, than a point, in the constellation, not among the one or more candidate points, and demodulating, by the signal receiver and on the basis of the one or more candidate points, the first signal.
Abstract:
A method and system for selecting a symbol detector are herein provided. A method includes extracting a first set of features for a k-th resource element (RE), where k is an integer greater than one, extracting a second set of features from a first RE to a (k−1)th RE, and selecting a symbol detector for the k-th RE using a reinforcement learning (RL) neural network based on the extracted first set of features and the extracted second set of features.
Abstract:
Systems and methods for blind detection of a numerology of a received signal are described. In one aspect, a method is provided for a user equipment (UE) to blindly detect the numerology of a received signal. The method includes correlating cyclic prefix (CP) signals in the received signal in the time domain based on a plurality of hypotheses of subcarrier spacing (SCS) and determining a numerology of the received signal for a corresponding hypothesis of SCS of the plurality of hypotheses based on the correlated CP signals.
Abstract:
A method and system are herein disclosed. The method includes receiving sounding reference signals (SRS) at a massive multiple-input multiple-output (MIMO) base station (BS) from a user equipment (UE), determining, at the BS, beamformers for known channels of the SRS, determining, at the BS, beamformers for unknown channels of the SRS based on the determined beamformers for the known channels, and selecting a modulation and coding scheme (MCS) based on the determined beamformers.
Abstract:
An electronic device and a method for managing an electronic key thereof are provided. The electronic device includes a wireless communication circuit, a hardware-based security element comprising circuitry configured to provide a timestamp, a processor operatively coupled with the communication circuit and the security element, and a memory operatively coupled with the processor. The memory stores instructions that when executed by the processor, control the electronic device to: launch an application related with an electronic key of a door lock, receive an input for using the electronic key to open the door lock through the application, determine the validity of credential information related with the input, based at least in part on the timestamp, and open the door lock based on the validity of the credential information.
Abstract:
A method and apparatus are provided. The method includes, but is not limited to, receiving a universal synchronization signal (USS) including a universal primary synchronization signal (UPSS) and a universal secondary synchronization signal (USSS), wherein the USS is coded using a mother code which is extended to m resource blocks (RBs) and n orthogonal frequency division multiplexing (OFDM) symbols and a code cover of m RBs and n symbols is applied to the mother code, determining a cell identity based on the USS, determining a frame timing based on the USS, and connecting a user equipment to a network using the cell identity and the frame timing.
Abstract:
A system and method for blind detection of preempted resources in an orthogonal frequency division multiplexing (OFDM) system is herein disclosed. According to one embodiment, a method for blind detection of resources in an eMBB pre-empted by a URLLC includes receiving soft information including at least one code block, attempting to decode the at least one code block, and running URLLC blind detection on the at least one code block with the decoding attempt fails.
Abstract:
A computing system includes: an inter-device interface configured to determine receiver description for representing a receiver signal corresponding to serving signal contemporaneous with an interference signal from an interference source at an interference-aware receiver; a communication unit, coupled to the inter-device interface, configured to: generate a pre-coding candidate set based on the receiver description for adjusting the serving signal or a subsequent instance thereof, determine a sum-rate condition for representing the serving signal along with the interference signal, and generate a pre-coding adjustment maximizing the sum-rate condition from the pre-coding candidate set for communicating the serving signal or a subsequent instance thereof.