Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a transmitter node may predict a future state associated with a wireless channel at a future time instance using a machine learning model, wherein the future state is predicted based at least in part on one or more of weights associated with the machine learning model, a current state associated with the wireless channel, or one or more previous states associated with the wireless channel. The transmitter node may select one or more parameters for a transmission to occur at the future time instance based at least in part on the future state associated with the wireless channel. The transmitter node may perform the transmission using the one or more parameters. Numerous other aspects are described.

Systems, methods, and apparatuses for providing optimization of network resources. The system is operable to monitor the electromagnetic environment, analyze the electromagnetic environment, and extract environmental awareness of the electromagnetic environment. The system extracts the environmental awareness of the electromagnetic environment by including customer goals. The system is operable to use the environmental awareness with the customer goals and/or user defined policies and rules to extract actionable information to help the customer optimize the network resources.

A method for preprocessing data for device operations can include preprocessing measurement data using a machine learning technique, determining, by a Kalman filter and based on (1) the preprocessed measurement data or the measurement data and (2) prediction data from a prediction model predicting a measurement associated with the measurement data, corrected measurement data, and providing the corrected measurement data based on the predicted measurement and the preprocessed measurement data.

A system and method of propagating signal links by using artificial neural networks using a relay link selection protocol to predict an optimal link or path, providing a reliable mechanism to meet 5G-new radio requirements. The artificial neural networks used in the method classify training and testing datasets into sufficient signal strengths and insufficient signal strengths, such that paths are evaluated for predicted propagation links, and such that the strongest propagation link can be selected. Specifically, a multilayer perceptron method is used to identify and characterize new link candidates using the path loss parameter or the received signal strength, such that optimal links can be selected and updated. To determine the sufficiency of a signal, a threshold energy strength is determined (for example, a threshold of −120 dBm can be used; any energy strength below the threshold is considered a poor propagation and is classified as an insufficient signal).

A method for checking the operation of an electronic device configured to transmit signals via a radio communication channel is implemented by a checking device. The method includes: receiving, on the radio communication channel, a signal from the electronic device; and determining the operation of the electronic device based on noise present in the received signal.

A method for predicting channel state information includes determining, by a user equipment, channel prediction information based on a reference signal from a network device, and sending channel prediction information. The channel prediction information is useable to predict the channel information.

A wireless network can generate candidate signal configurations for physical transmissions to or from a user equipment (UE) in a radio environment. The generation of candidate signal configurations can be performed using a first neural network that is associated with the UE. These signal configurations can then be evaluated using a second neural network that is associated with the radio environment. The second neural network can be trained using measurements from previous physical transmissions in the radio environment. The trained second neural network generates a reward value that is associated with the candidate signal configurations. The first neural network is then trained using the reward values from the second neural network to produce improved candidate signal configurations. When a signal configuration that produces a suitable reward value is generated, this signal configuration can be used for the physical transmission in the radio environment.

Systems and methods for localizing individuals in a region using wireless signals in accordance with embodiments are illustrated. One embodiment includes a method for localizing individuals in a region between wireless devices of a system. The method receives wireless signal strength data for signals transmitted along signal paths between several wireless playback devices transmitting on a wireless channel during synchronous playback of media content by the several wireless playback devices and determines a first signal strength for each of several portions of the wireless channel. The method calculates, for each signal path between each of the several wireless playback devices, a difference in the determined first signal strength from a second signal strength for each of the several subcarriers, and determines, based on the calculated differences, a state for a set of one or more individuals in the region.

Implementations relate to selection of a physics-specific model for determination of characteristics of radio frequency signal propagation. In some implementations, a method includes receiving a plurality of first propagation characteristics of a radio frequency (RF) signal, determining a feature vector based on the first propagation characteristics, inputting the feature vector to a machine-learning meta-model, and executing the machine learning meta-model to select a particular physics-specific model from multiple physics-specific models, where each of the physics-specific models is for a different RF signal propagation environment. The feature vector is input to the particular physics-specific model, and the particular physics-specific model is executed to output an estimate of one or more second propagation characteristics of the RF signal based on the feature vector.

A method for improving wireless communication for a drone swarm, the method comprising, at a computing system, receiving, from a plurality of drones of a drone swarm, data comprising radio frequency signal characteristics detected by the plurality of drones; generating a model of a radio frequency environment for the drone swarm based on the data received from the plurality of drones; and controlling at least one wireless communication system to improve wireless communication for the drone swarm based on the model of the radio frequency environment.