One or more processors control processing of radio frequency (RF) signals using a machine-learning network. The one or more processors receive as input, to a radio communications apparatus, a first representation of an RF signal, which is processed using one or more radio stages, providing a second representation of the RF signal. Observations about, and metrics of, the second representation of the RF signal are obtained. Past observations and metrics are accessed from storage. Using the observations, metrics and past observations and metrics, parameters of a machine-learning network, which implements policies to process RF signals, are adjusted by controlling the radio stages. In response to the adjustments, actions performed by one or more controllers of the radio stages are updated. A representation of a subsequent input RF signal is processed using the radio stages that are controlled based on actions including the updated one or more actions.

A monitoring system and monitoring method for detecting a spectral anomaly in a cellular wireless network, in particular a 5G private uRLLC network, wherein an RF receiver monitors the cellular wireless network spectrum and derives spectrum and/or physical measurement values of the spectrum of the cellular wireless network, and a processing unit of the monitoring system executes a spectral anomaly neural network trained by a machine learning algorithm in a training system, wherein the processing unit obtains the spectrum and/or the physical measurement values of the spectrum and processes it to detect a spectral anomaly information. Further, a training system and training method for training a spectral anomaly neural network, wherein the training system/method is used in a cellular wireless network, in particular a 5G private uRLLC network, and an RF receiver of the training system monitors the cellular wireless network spectrum and derives spectrum and/or physical measurement values of the spectrum of the cellular wireless network, and a processor of the training system executes a machine learning algorithm to train the spectral anomaly neural network based upon the derived spectrum and/or physical measurement values of the spectrum of the cellular wireless network.

One or more processors control processing of radio frequency (RF) signals using a machine-learning network. The one or more processors receive as input, to a radio communications apparatus, a first representation of an RF signal, which is processed using one or more radio stages, providing a second representation of the RF signal. Observations about, and metrics of, the second representation of the RF signal are obtained. Past observations and metrics are accessed from storage. Using the observations, metrics and past observations and metrics, parameters of a machine-learning network, which implements policies to process RF signals, are adjusted by controlling the radio stages. In response to the adjustments, actions performed by one or more controllers of the radio stages are updated. A representation of a subsequent input RF signal is processed using the radio stages that are controlled based on actions including the updated one or more actions.

The present disclosure provides for distortion cancelled by receiving a collided signal comprising first and second signals carrying respective first and second packets; digitizing the collided signal into a first digital signal and decoding the first packet therefrom; calculating a digital linear interference component of the first packet on the second from an estimated signal re-encoding the decoded first packet; synthesizing an analog linear interference component from the digital linear interference component; determining a digital nonlinear interference component of the first packet on the second from the first digital signal; amplifying the collided signal to produce a second amplified signal; removing the analog linear interference component from the second amplified signal to produce a partially de-interfered signal; removing the digital nonlinear interference component from the partially de-interfered signal to produce a de-interfered signal; and decoding the second packet from the de-interfered signal.

The present disclosure provides for distortion cancelled by receiving a collided signal, the collided signal comprising a first signal carrying a first packet and a second signal carrying a second packet; amplifying and digitizing the collided signal into a first digital signal at a first gain and a second digital signal at a second gain that is greater than the first gain; determining a nonlinear interference component of the first packet on the second packet from the first digital signal; decoding the first packet from the first digital signal; re-encoding the first packet with a first estimated channel effect into an estimated signal; calculating a linear interference component of the first packet on the second packet from the estimated signal; removing the linear interference component and the nonlinear interference component from the second digital signal to produce a de-interfered signal; and decoding the second packet from the de-interfered signal.

One or more processors control processing of radio frequency (RF) signals using a machine-learning network. The one or more processors receive as input, to a radio communications apparatus, a first representation of an RF signal, which is processed using one or more radio stages, providing a second representation of the RF signal. Observations about, and metrics of, the second representation of the RF signal are obtained. Past observations and metrics are accessed from storage. Using the observations, metrics and past observations and metrics, parameters of a machine-learning network, which implements policies to process RF signals, are adjusted by controlling the radio stages. In response to the adjustments, actions performed by one or more controllers of the radio stages are updated. A representation of a subsequent input RF signal is processed using the radio stages that are controlled based on actions including the updated one or more actions.

A decoder for decoding a signal received through a transmission channel represented by a channel matrix using a search sphere radius. The decoder comprises a radius determination device for determining a search sphere radius from a preliminary radius. The radius determination device is configured to: i. apply a machine learning algorithm to input data derived from the received signal, the channel matrix and a current radius, the current radius being initially set to the preliminary radius, which provides a current predicted number of lattice points associated with the current radius; ii. compare the current predicted number of lattice points to a given threshold; iii. update the current radius if the current predicted number of lattice points is strictly higher than the given threshold, the current radius being updated by applying a linear function to the current radius; Steps i to iii are iterated until a termination condition is satisfied, the termination condition being related to the current predicted number, the radius determination device being configured to set the search sphere radius to the current radius in response to the termination condition being satisfied.

One or more processors control processing of radio frequency (RF) signals using a machine-learning network. The one or more processors receive as input, to a radio communications apparatus, a first representation of an RF signal, which is processed using one or more radio stages, providing a second representation of the RF signal. Observations about, and metrics of, the second representation of the RF signal are obtained. Past observations and metrics are accessed from storage. Using the observations, metrics and past observations and metrics, parameters of a machine-learning network, which implements policies to process RF signals, are adjusted by controlling the radio stages. In response to the adjustments, actions performed by one or more controllers of the radio stages are updated. A representation of a subsequent input RF signal is processed using the radio stages that are controlled based on actions including the updated one or more actions.

One or more processors control processing of radio frequency (RF) signals using a machine-learning network. The one or more processors receive as input, to a radio communications apparatus, a first representation of an RF signal, which is processed using one or more radio stages, providing a second representation of the RF signal as. Observations about, and metrics of, the second representation of the RF signal are obtained. Past observations and metrics are accessed from storage. Using the observations, metrics and past observations and metrics, parameters of a machine-learning network, which implements policies to process RF signals, are adjusted by controlling the radio stages. In response to the adjustments, actions performed by one or more controllers of the radio stages are updated. A representation of a subsequent input RF signal is processed using the radio stages that are controlled based on actions including the updated one or more actions.

A method and an apparatus for decoding a signal at a receiver in a MIMO communication system is described. A signal y is obtained over a channel from a plurality of transmitters in communication with the receiver, the signal y includes data signals transmitted on a plurality of layers N. A concatenated matrix R representing the channel between the plurality of transmitters and the receiver is obtained based on an estimated channel matrix H. An ordered list is determined based at least on the signal y and the obtained concatenated matrix R. The ordered list is a list of N-dimensional vectors and each vector is a candidate constellation point for the transmitted data signal based on a predefined metric, and is determined using a list search block configured to implement a machine learning algorithm.