The present disclosure relates to a method for blind identification of channel tap numbers in wireless communication by using deep neural networks (DNN). In the proposed method, it is possible to train a DNN using only the transmitted and received signals of a wireless system in order to obtain the number of channel taps. We propose a robust and efficient sparse representation technique for the identification of wireless channels. We estimate the number of channel taps which is considered as one of the sparse features of the hannel The blind estimation performed in the proposed system, enhances the spectral efficiency of the used wireless communication system since the employed DNN does not require to transmit extra signals for identifying the channel taps. In our identification method, physical insights are not available or used.

Various embodiments provide for deep learning-based architectures and design methodologies for an orthogonal frequency division multiplexing (OFDM) receiver under the constraint of one-bit complex quantization. Single bit quantization greatly reduces complexity and power consumption in the receivers, but makes accurate channel estimation and data detection difficult. This is particularly true for OFDM waveforms, which have high peak-to average (signal power) ratio in the time domain and fragile subcarrier orthogonality in the frequency domain. The severe distortion for one-bit quantization typically results in an error floor even at moderately low signal-to-noise-ratio (SNR) such as 5 dB. For channel estimation (using pilots), various embodiments use novel generative supervised deep neural networks (DNNs) that can be trained with a reasonable number of pilots. After channel estimation, a neural network-based receiver specifically, an autoencoder jointly learns a precoder and decoder for data symbol detection.

A method of wireless communication by a user equipment (UE) includes receiving, from a base station, a configuration to train a neural network for multiple different signal to noise ratios (SNRs) of a channel estimate for a wireless communication channel. The method also includes determining a current SNR of the channel estimate is above a first threshold value. The method further includes training the neural network based on the channel estimate, to obtain a first trained neural network. The method still further includes perturbing the channel estimate to obtain a perturbed channel estimate, and training the neural network based on the perturbed channel estimate, to obtain a second trained neural network. The method includes reporting, to the base station, parameters of the first trained neural network along with the channel estimate, and parameters of the second trained neural network.

A processor-implemented method is presented. The method includes receiving an input sequence comprising a group of channel dynamics observations for a wireless communication channel. Each channel dynamics observation may correspond to a timing of a group of timings. The method also includes determining, via a recurrent neural network (RNN), a residual at each of the group of timings based on the group of channel dynamics observations. The method further includes updating Kalman filter (KF) parameters based on the residual and estimating, via the KF, a channel state based on the updated KF parameters.

A computer implemented method for detecting data (y) comprised in a part (x) of a received signal (w) of a communication system (100), wherein the received signal (w) is associated with a population and where the part (x) of the received signal (w) is associated with a sub-population of the population, the method comprising: configuring (S1) a first function (ƒ1) to determine a context (c) of the received signal (w), wherein the context (c) is indicative of a state of the received signal (w), configuring (S2) a second function (ƒ2) to detect the data (y) based on the part (x) of the received signal, wherein the second function (ƒ2) is arranged to be parameterized by the context (c), and detecting (S3) the data (y) by the first (ƒ1) and second (ƒ2) functions.

Systems, devices, and methods for access point discovery in a wireless network are provided. An access point device embeds into a preamble of a transmission packet discovery information including modifications determined by passing in-phase quadrature (IQ) symbols through a finite impulse response (FIR) filter to introduce a phase shift in selected ones of the IQ symbols. The phase shifts are encoded into bits in selected ones of a plurality of subcarriers, bounded by a maximum phase shift and a maximum number of the subcarriers to limit the packet error rate. A convolutional neural network can learn channel state and other information to determine the maximum phase shift and number of subcarriers. A client device can select from among a plurality of modified transmission packets to send a discovery request.

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.

A THz UM-MIMO channel estimation method based on the DCNN comprises the steps: the hybrid spherical and planar-wave modeling (HSPM), by taking a sub-array in the antenna array as a unit, employing the PWM within the sub-array, and employing the SWM among the sub-arrays; estimating the channel parameters between the reference sub-arrays at Tx and Rx through a DCNN, including the angles of departure and arrival, the propagation distance and the path gain; deducing the channel parameters between the reference sub-array and other sub-arrays by utilizing the obtained channel parameters and the geometrical relationships among sub-arrays, and recovering the channel matrix; wherein accurate three-dimensional channel modeling is achieved by the HSPM, which possesses high modeling accuracy and low complexity.

A method for wireless communication by a receiving device, includes receiving, from a transmitting device, a latent representation of a channel sequence for a wireless signal. A decoder applies a physical propagation channel model to the latent representation to reconstruct the channel sequence for the wireless signal.

Capability of a user equipment to support machine learning adaptation by a base station of a reference signal pattern is signaled between the base station and the user equipment. Configuration information from the base station indicates one or more of enabling or disabling of machine learning adaptation of the reference signal pattern, a machine learning model used for machine learning adaptation of the reference signal pattern, updated model parameters for the machine learning model, or whether model parameters received from the user equipment will be used for machine learning adaptation of the reference signal pattern. Model training may be performed or model parameters received, and reference signals are received from the base station. Information on a reference signal pattern may be transmitted by the user equipment to the serving base station. Assistance information may be transmitted by the user equipment to the base station, which configures a reference signal pattern.