A CTLE-based SERDES receiver circuit using ISI metering provides an improved SERDES I/O performance. The CTLE SERDES receiver circuit may include an analog receiver frontend to generate an analog-to-digital converter (ADC) digital signal and a reduced ISI signal, a data path circuit to generate a sliced data stream and sliced cursor error stream, a digital signal processing (DSP) circuit to generate a converged data stream, a multi-tap intersymbol interference (ISI) assessment circuit to generate a weighted ISI sum, and an ISI minimization circuit to generate a continuous time linear equalizer (CTLE) adaptation control signal based on the weighted ISI sum.

A method is disclosed for mitigating phase noise at high frequencies in 5G and 6G. Quadrature modulation schemes, in which orthogonal branches are amplitude modulated, are susceptible to phase noise which rotates the branches, causing demodulation faults. Disclosed is a single-branch reference signal that can mitigate phase noise. The transmitter can transmit a particular resource element having a normal amplitude in one branch, and zero amplitude in the orthogonal branch. The receiver can then measure the amplitudes of the particular resource element as-received (with phase noise), and determine a phase rotation angle according to a ratio of the two branch amplitudes. The receiver can then correct the branch amplitudes of each message element, and thereby negate the effect of the phase noise. The disclosed procedures can thereby make high-frequency, high-reliability communication feasible, at extremely low cost.

A method performed by a communication device includes generating an initial channel estimate of a channel for a current time step with a Kalman filter based on a first signal received at the communication device. The method also includes inferring, with a neural network, a residual of the initial channel estimate of the current time step. The method further includes updating the initial channel estimate of the current time step based on the residual.

In an embodiment an interference cancellation method includes generating, by a first device, a first packet, wherein the first packet comprises a first group of elements, a second group of elements, and user data, the first group of elements being different from the second group of elements and sending, by the first device, the first packet to a second device by using at least one pair of subcarriers, wherein two subcarriers in the at least one pair of subcarriers are symmetrical with respect to a direct current subcarrier, and wherein the first packet is usable by the second device to cancel interference in the user data based on the first group of elements and the second group of elements.

Phase noise is a limiting factor in high-frequency 5G and 6G communications. Disclosed is a multiplexed amplitude-phase modulation scheme that can provide extremely wide phase noise margins at high frequencies. The transmitter can transmit a wave modulated in amplitude and phase, configured to provide a wide separation of phase states. The receiver, on the other hand, demodulates the message using quadrature amplitude modulation QAM, since that is generally more economical and technically preferred for signal processing. The demodulated message, however, still retains the large phase margins. As a further benefit, the examples illustrate non-square and asymmetric modulation schemes, which can extend the noise margins even further. By modulating with amplitude and phase, but demodulating with orthogonal branch signals, wireless networks can expand into high-frequency bandwidths while retaining high reliability and high throughput, as required for wireless applications of tomorrow.

A machine learning (ML) agent operates at a transmitter to optimize signals transmitted across a communications channel. A physical signal modifier modifies a physical layer signal prior to transmission as a function of a set of signal modification parameters to produce a modified physical layer signal. The ML agent parses a feedback signal from a receiver across the communications channel, and determines a present tuning status as a function of the signal modification parameters and the feedback signal. The ML agent generates subsequent signal modification parameters based on the present tuning status and a set of stored tuning statuses, thereby updating the physical signal modifier to generate a subsequent modified physical layer signal to be transmitted across the communications channel.

The present subject matter relates to a receiver including a detector for receiving a signal from a transmitter. The detector includes a set of one or more settable parameters, and circuitry configured for implementing an algorithm having trainable parameters. The algorithm is configured to receive as input information indicative of a status of a communication channel between the transmitter and the receiver and to output values of the set of settable parameters of the detector. The detector is configured to receive a signal corresponding to a message sent by the transmitter and to provide an output indicative of the message based on the received signal and the output values of the set of settable parameters of the detector.

A method for receiving data by a terminal in a wireless communication system according to the present document comprises: receiving a channel signal and a reference signal (RS) from a base station; and generating a sequence by filtering the RS, and decoding the channel signal on the basis of the generated sequence, wherein the filtering is zero forcing (ZF) filtering, and the decoding of the channel signal is a selection of one parameter from among parameter sets generated in accordance with a colored-noise machine learning process.

A second base station may allocate a set of downlink resources for a downlink transmission. The set of downlink resources may include a subset of null resources, which may serve as a signature for the second base station. The second base station may transmit downlink data or reference signals on the set of downlink resources including the subset of null resources. A first UE may experience the downlink transmission from the second base station as interference. The first UE may identify the set of downlink resources. The first UE may identify the subset of null resources. The first UE may transmit, to a first base station, an indication of the subset of null resources. The first base station may identify the second base station based on the indication of the subset of null resources. The first base station may transmit, to the second base station, an interference coordination message.

Differential signal skew compensation techniques for radio frequency interference (RFI) mitigation with no reflection penalty and associated apparatus and methods. A differential pair of signal traces are formed on or in a PCB having at least two changes in direction, with a first signal trace having a first routing path defining a first length and a second signal trace adjacent to the first signal trace including one or more tuning structures that are configured such that the length of the second signal trace matches the first length. Segments of the first signal trace adjacent to the one or more tuning structures of the second signal trace are widened relative to other segments of the first signal trace. The tuning structures may comprise sawtooth structures, accordion structures and other serpentine or meander structures. The solution mitigates RFI without a reflection penalty.