A method and devices for configuring a data transmission network are disclosed. The method is for configuring a data transmission network, executed by a configuration device, wherein the data transmission network comprises at least one transmitter, at least one receiver with a communication channel between the transmitter and the receiver, the method comprising: training a machine learning model of the data transmission network, wherein the machine learning model comprises at least a transmitter model including a transmitter neural network, a channel model, and a receiver model including a receiver neural network by providing a message within a sequence of messages; generating a group of transmission symbols for each message in the sequence of messages using the transmitter neural network; concatenating the groups of transmission symbols together as a sequence of transmission symbols; simulating transmission of the sequence of transmission symbols over the communication channel using the channel model to the receiver; analysing a sequence of received symbols using the reception neural network to generate a decoded message; and updating the machine learning model based on an output of said reception neural network. In this way, the machine learning model can be trained using representative sequences of message, which improves performance when deployed in a real network.

Wireless communication wherein channel estimation accuracy is improved while keeping the position of each bit in a frame, even when a modulation system having a large modulation multiple value is used for a data symbol. An encoding operation encodes and outputs transmitting data (bit string) and a bit converting operation converts at least one bit of a plurality of bits constituting a data symbol to be used for channel estimation, among the encoded bit strings, into 1 or 0. A modulating operation modulates the bit string inputted from the bit converting operation by using a single modulation mapper and a plurality of data symbols are generated.

An iterative two dimension equalizer usable in a receiver of orthogonal time frequency space (OTFS) modulated signals is described. In one configuration of the equalizer, a forward path generates, from received time-frequency domain samples and a channel estimate, estimates of data bits and likelihood numbers associated with the estimates of data bits, generated by delay-Doppler domain processing. In the feedback direction, the estimates of data bits are used to generate symbol estimates and autocorrelation matrix estimate in the time domain. In another configuration, a soft symbol mapper is used in the feedback direction for directly generating the feedback input symbol estimate without having to generate estimates of data bits.

A communication system that includes a plurality of radio points is disclosed. Each radio point is configured to exchange radio frequency (RF) signals with a wireless device that transmits a Sounding Reference Signal (SRS) from a first physical location in a site; and extract at least one SRS metric from the SRS. The communication system also includes a baseband controller communicatively coupled to the plurality of radio points. The baseband controller is configured to determine a signature vector based on the at least one SRS metric from each of the plurality of radio points. The communication system also includes a machine learning computing system communicatively coupled to the baseband controller. The machine learning computing system is configured to use a machine learning model to determine location data for the first physical location of the wireless device based on the signature vector.

A communication system is disclosed. The communication system includes a plurality of cloud radio access networks (C-RANs), each C-RAN comprising a baseband controller and a plurality of radio points (RPs). Each RP in the plurality of C-RANs is located at a site and is configured to exchange radio frequency (RF) signals with a plurality of wireless devices at the site. The communication system also includes a dynamic sectorization system communicatively coupled to each baseband controller. The dynamic sectorization system is configured to determine at least one signature vector for each of the wireless devices at the site. The dynamic sectorization system also is configured to map each RP in the plurality of C-RANs to one of a number of sectors (K) based on the at least one signature vector for each of the wireless devices at the site.

The present application disclosed a decision feedback equalization processing device and method. The device comprises: a channel estimator for receiving an input signal, and determining, based on the input signal, an input signal autocorrelation matrix R.sub.yy, an input-output signal cross-correlation matrix R.sub.yx and an input-output signal cross-correlation vector r.sub.yx; a tap coefficient calculator for receiving R.sub.yy, R.sub.yx and r.sub.yx, and calculating a feed-forward equalizer (FFE) tap coefficient vector g and a feedback equalizer (FBE) tap coefficient vector f, wherein at least one of the FFE tap coefficient vector g and the FBE tap coefficient vector f is calculated using a conjugate gradient descent algorithm. The tap coefficient calculator comprises: a circulant matrix construction unit and a fast Fourier transformation (FFT) calculating unit. And the device further comprises a decision feedback equalizer for receiving from the tap coefficient calculator the FFE tap coefficient vector g and the FBE tap coefficient vector f, and performing equalization on the input signal and generating an equalized output signal.

A method and electronic device for motion assisted leakage removal. The electronic device includes a radar transceiver, a sensor, and a processor. The processor is configured to determine, based on information obtained from the sensor, that the electronic device is in a first motion state, during the first motion state of the electronic device, control the radar transceiver to transmit a first set of signals, generate a first channel impulse response (CIR) based on the received first set of signals being received, apply a filter that estimates a leakage depicted by the first CIR, in a second motion state, control the radar transceiver to transmit a second set of signals, generate a second CIR based on the received second set of signals, and apply the estimated leakage from the first CIR to the second CIR to remove leakage from the second CIR.

Aspects of the present disclosure provide techniques for using cyclic-shifts in code division multiplexing to shift transmitted signals (e.g., reference signals, control signals, and/or data) from different antenna ports of the transmitting device. Particularly, for multiple-input multiple-output (MIMO) systems that multiply the capacity of a radio link by using multiple transmit and receive antennas to exploit multipath propagation, aspects of the present disclosure minimize interference at the receiving device by separating the signals from different antenna ports based on the channel impulse response (or delay spread) of each antenna port of the channel. In some examples, the transmitting device may maximize resource utilization by interleaving the reference signals, control signals, and/or data from a plurality of antenna ports while maintaining adequate spacing between each signal.

A receiver for receiving OFDM signals with a channel estimation means is disclosed. The channel estimation means estimates the channel at pilot locations by least squares estimation at pilot locations in subcarriers that include pilot symbols. Using the estimates of the channel at pilot locations, it estimates the channel for each subcarrier containing the pilot symbols, using linear interpolation. It estimates the channel for the sub-frame by interpolating the channel estimates estimated for the sub-carriers including the pilot locations, by using Minimum Mean Square Estimation that uses an auto-covariance matrix. An auto-covariance matrix generator generates the auto-covariance matrix. It generates an auto-covariance matrix based on, an extended cyclic prefix, an estimate of the channel in the time domain estimated by performing an Inverse Discrete Fourier Transform on the channel estimated as above and an average tap power calculated based on the estimate of the channel in the time domain.

The present invention is related to a method and an apparatus for transmitting a reference signal in a wireless communication system. The present specification comprises transmitting at least one of the user equipment (UE)-specific value which is the parameter used for generating the UE-specific reference signal sequence to the UE, selecting one value out of at least one of the UE-specific value and cell-specific value, calculating an initialization value of pseudo-noise (PN) sequence based on the value selected, generating a first reference signal sequence using the initialization value of PN sequence, mapping the first reference signal sequence to a resource element, and transmitting a reference signal to the UE using the resource element to which the first reference signal sequence is mapped.