An architecture is provided for cooperative target tracking and signal propagation learning using mobile sensors. A method can comprise as a function of sensing data representative of a location of a target device at a first defined moment and model data relating to a motion model representing a probability density function, determining, by a system comprising a processor, a group of locations for the target device at a second defined time point, wherein the probability density function facilitates determining, based on the location of the target device at the first defined moment, a current location of the target device at a third defined moment; and as a function of the group of locations, generating, by the system, a data structure representing a matrix of received signal strength values; and identifying, by the system, a location of the group of locations for the target device at the third defined moment based on the data structure.

Disclosed are a method and system for acquiring massive MIMO beam domain statistical channel information. A refined beam domain channel model involved in the disclosed method is based on a refined sampling steering vector matrix. Compared with a traditional DFT matrix-based beam domain channel model, when antenna size is limited, said model is closer to a physical channel model, and provides a model basis for solving the problem of the universality of massive MIMO for various typical mobile scenarios under a constraint on antenna size. The present invention provides a method for acquiring massive MIMO refined beam domain a priori statistical channel information and a posteriori statistical channel information, the a posteriori statistical channel information comprising mean and variance information of the a posteriori channel. The method of the present invention has low complexity, can be applied to an actual massive MIMO system, provides support for a robust precoding transmission method, and has large application value.

Disclosed are a method and system for acquiring massive MIMO beam domain statistical channel information. A refined beam domain channel model involved in the disclosed method is based on a refined sampling steering vector matrix. Compared with a traditional DFT matrix-based beam domain channel model, when antenna size is limited, said model is closer to a physical channel model, and provides a model basis for solving the problem of the universality of massive MIMO for various typical mobile scenarios under a constraint on antenna size. The present invention provides a method for acquiring massive MIMO refined beam domain a priori statistical channel information and a posteriori statistical channel information, the a posteriori statistical channel information comprising mean and variance information of the a posteriori channel. The method of the present invention has low complexity, can be applied to an actual massive MIMO system, provides support for a robust precoding transmission method, and has large application value.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a base station, an indication of a change in a non-linearity model associated with a power amplifier of the base station. The UE may update a model associated with the power amplifier based at least in part on the indication. The UE may further update at least one parameter associated with slicing received signals based at least in part on the indication. In some aspects, the UE may use at least two coefficients when slicing. Numerous other aspects are described.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a base station, an indication of a change in a non-linearity model associated with a power amplifier of the base station. The UE may update a model associated with the power amplifier based at least in part on the indication. The UE may further update at least one parameter associated with slicing received signals based at least in part on the indication. In some aspects, the UE may use at least two coefficients when slicing. Numerous other aspects are described.

One or more systems and methods for wireless equipment deployment are provided herein. Imagery of locations depicting structures within a list of structures is analyzed to identify features of the structures within the locations. Ranks may be calculated for the structures based upon structure scores and installation scores calculated from the features. In response to a rank for a structure exceeding a threshold, wireless equipment deployment of a communication device may be triggered so that the communication device is controlled to exchange communication signals with devices proximate the structure.

One or more systems and methods for wireless equipment deployment are provided herein. Imagery of locations depicting structures within a list of structures is analyzed to identify features of the structures within the locations. Ranks may be calculated for the structures based upon structure scores and installation scores calculated from the features. In response to a rank for a structure exceeding a threshold, wireless equipment deployment of a communication device may be triggered so that the communication device is controlled to exchange communication signals with devices proximate the structure.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for providing one or more values from a distribution of values to a neural network trained to generate simulated channel responses corresponding to one or more radio frequency (RF) communication channels; and obtaining an output of the neural network based on processing the one or more values by the neural network, the output indicating a simulated channel response corresponding to at least one communication channel of the one or more RF communication channels.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for providing one or more values from a distribution of values to a neural network trained to generate simulated channel responses corresponding to one or more radio frequency (RF) communication channels; and obtaining an output of the neural network based on processing the one or more values by the neural network, the output indicating a simulated channel response corresponding to at least one communication channel of the one or more RF communication channels.

An example of an object of the present disclosure is to provide an interference detection apparatus, an interference detection method, and a non-transitory computer-readable medium that allow a user to determine a priority of interference to be dealt with in communication. The interference detection apparatus according to an example embodiment includes at least one memory configured to store an instruction, and at least one processor configured to execute the instruction. The processor is further configured to learn a signal state model by using a learning signal in a communication signal, acquire a detection target signal in the communication signal, detect interference in the detection target signal, and calculate a severity of interference in the detection target signal by using the detection target signal, a detection result of the interference, and the learned signal state model.