Methods and systems are provided for dynamically disabling beamforming functionality of a first frequency band. The first frequency band is determined to have beamforming enabled. The user device is detected as being connected to the first frequency band for access to a wireless telecommunications network. A first fading channel measurement of the first frequency band is determined to be above a threshold. In response to determining that the first fading channel measurement is above the threshold, beamforming of the first frequency band is dynamically disabled.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for processing communications signals using a machine-learning network are disclosed. In some implementations, pilot and data information are generated for a data signal. The data signal is generated using a modulator for orthogonal frequency-division multiplexing (OFDM) systems. The data signal is transmitted through a communications channel to obtain modified pilot and data information. The modified pilot and data information are processed using a machine-learning network. A prediction corresponding to the data signal transmitted through the communications channel is obtained from the machine-learning network. The prediction is compared to a set of ground truths and updates, based on a corresponding error term, are applied to the machine-learning network.

The disclosure provides a wireless channel scenario identification method and system. The method includes: simulating different wireless channel scenarios to obtain a channel scenario baseband signal y(t).sub.pq; extracting a feature parameter of y(t).sub.pq, extracting an autocorrelation function A.sub.h(t).sub.pq and performing a Fourier transform thereon to obtain a power spectral density function S(t).sub.pq; normalizing S(t).sub.pq to obtain a normalized channel scenario power spectral density function S(t).sub.pq; designing a deep learning network and inputting S(t).sub.pq and a category label pair to train the deep learning network; and for a system with a channel scenario to be identified, collecting a passband signal at its receiving end, obtaining the normalized scenario power spectral density function Ŝ(t).sub.pq, and using Ŝ(t).sub.pq as an input of the trained classifier, the output of the classifier being a label sequence of the channel scenario, and the channel scenario is effectively determined.

In a multiuser (MU) multiple antenna system (MAS), a central processing unit is communicatively coupled to multiple distributed wireless terminals (WTs) via a network. The central processing unit processes channel measurements indicative of channel conditions between the multiple distributed WTs and a plurality of user devices and selects a plurality of WTs from the multiple distributed WTs to enhance channel space diversity within the MU-MAS. The central processing unit calculates (Multiple Input, Multiple Output) MIMO weights from the channel measurements for precoding a plurality of data streams that are transmitted concurrently from the plurality of WTs to the plurality of users, wherein the MIMO weights provide for a plurality of independent MIMO channels.

Systems and associated methods for reciprocity calibration of multiple-input multiple-output (MIMO) wireless communication are disclosed herein. In one embodiment, a method for reciprocity calibration of the MIMO system includes transmitting a pilot symbol by a transmitter (TX) of the reference antenna and receiving the pilot symbol by receivers (RXes) of antennas of a base station as r.sub.i,0 pilot symbols. (Index “i” denotes individual antenna “i” of the base station, and “0” denotes the reference antenna.) The method further includes transmitting the received pilot symbols by TXes of the antennas of the base station, receiving the pilot symbols transmitted by the antennas of the base station by the reference antenna as r.sub.0,i pilot symbols, and calculating non-reciprocity compensation factors as

[00001]$\frac{r_{i,0}}{r_{0,i}}.$

The present disclosure provides radio-frequency (RF) systems that can detect the presence of RF signals received by the system, as well as determine characteristics such as the operating frequency of RF signals, the type of RF source that transmitted each RF signal, and/or the location of each RF source with high precision and sensitivity while using low cost, scalable electronics that are versatile enough for deployment in a variety of environments. Such systems can employ a network of RF sensors that can coordinate in response to communication with a computer to perform any such detection and/or determination using trained models executed onboard the RF sensors and/or the computer. RF signals may have unique characteristics when received at one or more RF sensors that may be detected using trained models described herein, even in high noise or non-line of sight (LOS) environments and with low cost, low resolution RF receiver hardware.

A method is provided for generating test data for testing radio equipment. The method includes: determining, by a test apparatus, one or more beam identifiers; selecting, by the test apparatus, based on the one or more beam identifiers, one or more radio channel models; receiving, by the test apparatus, a baseband signal representing I/Q data of one or more beamforming antennas; processing, by the test apparatus, the baseband signal representing I/Q data according to the selected radio channel model; and transmitting, by the test apparatus, the processed baseband signal representing I/Q data to a radio equipment under test.

Devices and methods enable optimizing a signal of interest based on identifying and analyzing the signal of interest based on radio frequency energy measurements. Signal data is compared with stored data to identify the signal of interest. Signal degradation data is calculated based on noise figure parameters, hardware parameters and environment parameters. The signal of interest is optimized based on the signal degradation data. Terrain data is also operable to be used for optimizing the signal of interest.

Methods for tracking a signal origin by a spectrum analysis and management device are disclosed. Signal characteristics of other known emitters are used for obtaining a position of an emitter of a signal of interest. In one embodiment, frequency difference of arrival technique is implemented. In another embodiment, time difference of arrival technique is implemented.

Systems, methods, and devices enable spectrum management by identifying, classifying, and cataloging signals of interest based on radio frequency measurements. Signal data is compared with stored data to identify the signal of interest. Signal degradation data is calculated based on noise figure parameters, hardware parameters and environment parameters.