A method comprises: receiving, from a communication channel, non-binary multilevel symbols that represent corresponding multibit labels each including at least a least-significant bit (LSB) and a most-significant bit (MSB), the non-binary multilevel symbols mapped to the multibit labels according to set-partition labeling, which partitions the non-binary multilevel symbols between a first set and a second set according to a first value and a second value of the LSB, respectively; digitizing the non-binary multilevel symbols to produce symbol samples; and performing Soft-Output-Viterbi (SOV) equalization of the non-binary multilevel symbols based on the symbol samples, to produce decoded symbol information corresponding to the non-binary multilevel symbols.

A method for recovering data included in a digitally modulated signal is described. The digitally modulated signal includes a symbol sequence. The method includes providing a mathematical model of the digitally modulated signal, the mathematical model describing the digitally modulated signal in terms of the symbol sequence and describing the digitally modulated signal in terms of a step response and/or an impulse response, and wherein the mathematical model also takes disturbances into account; and processing the digitally modulated signal based on the mathematical model, thereby recovering the data included in the digitally modulated signal. The disturbances include a random disturbance component modelled as a Gaussian disturbance, and include an inter-symbol interference component modelled as Gaussian noise, and wherein a dependence of the at least one step response on the symbol sequence is neglected within the mathematical model. Further, a measurement instrument and a measurement system are described.

A radio frequency (RF) system may include an RF transceiver and a baseband engine, application specific integrated circuit (ASIC) coupled to the RF transceiver and configured to perform a given baseband engine operation from among different baseband engine operations. The baseband engine ASIC may include a memory and a state machine coupled thereto and configured to store a respective set of programming instructions for each of different baseband engine operations and to permit selection of the given set of programming instructions. The baseband engine may also include a programmable processing circuit coupled to the memory and the state machine and configured to perform block coding computations responsive to the given set of programming instructions.

Aspects of the disclosure provide for methods and systems for Sub-codebook based Trellis Coded Quantization for CSI Feedback. An aspect of the disclosure provides method executed by a receiver. The method includes receiving a signal from a transmitter, via a communication channel between the receiver and the transmitter. The method further includes estimating parameters associated with the channel based on the received signal. The method further includes obtaining phase information from the estimated parameters. The method further includes applying a trellis coded quantization (TCQ) scheme to the obtained phase information by mapping each sub-codebook index of a set of sub-codebook indices to output bits of each trellis branch making the distance between sub-codebooks maximally equal. The method further includes transmitting a channel state information (CSI) measurement feedback to the transmitter, the CSI measurement feedback based on the TCQ scheme and comprising one or more of: a beginning state, input bits to the TCQ scheme, and a sub-codebook index.

An apparatus and method are disclosed with some embodiments including an analog and time to digital converter (ATDC) including a receiver, the receiver for receiving an analog channel input for conversion to a digital data, the digital data having at least one bit, and a defined absolute reference time stamp, the defined absolute reference time stamp representing an absolute reference time associated with conversion of the analog channel input to the digital data and an analog-to-digital converter, the converter converting the analog channel input to the digital data.

The present invention is directed to data communication. More specifically, an embodiment of the present invention provides an error correction system. Input data signals are processed by a feedforward equalization module and a decision feedback back equalization module. Decisions generated by the decision feedback equalization module are processed by an error detection module, which determines error events associated with the decisions. The error detection module implements a reduced state trellis path. There are other embodiments as well.

A system, apparatus, and method are provided for performing fast re-training of fully fused neural networks configured to implement at least a portion of a transceiver. At least one of a demapping module, an equalization module, or a channel estimation module can be implemented, at least in part, using a fully fused neural network. The neural network can be trained online during operation by acquiring training data sets using a number of received frames of data. Re-training of the neural network is performed periodically to adapt the neural network to changing channel characteristics. In various embodiments, a neural demapper, a neural channel estimator, and a neural receiver are disclosed to replace or augment one or more components of the transceiver. In another embodiment, an auto-encoder can be implemented across a transmitter and receiver to replace most of the components of the transceiver, the auto-encoder being trained via an end-to-end learning algorithm.

Systems and methods for the secure transmission of data and algorithms are disclosed. The coding and modulation schemes meet the need of low signal-to-noise (SNR) ratio applications in areas of high interference. A radio transmitter is used to transmit data signals and a radio receiver is used to receive signals. The new coding algorithms and modulation for wideband communication at very low SNR domains. Systems use orthogonal frequency-division multiplexing modulation and a channel pilot algorithm for timing synchronization and frame alignment. Systems also use an orthogonal code, a super orthogonal convolutional code, and a block code to achieve channel capacity within 80% of the Shannon limit in the subzero decibel (dB) domain with reasonable decoding complexity. In an implementation example given, a 12.5 MHz band radio can transmit at a 108 kbps user data rate at −20 dB SNR and escape adversity detection.

Methods and apparatus for decoding received uplink transmissions using log-likelihood ratio optimization. In an embodiment, a method includes soft-demapping resource elements based on soft-demapping parameters as part of a process to generate log-likelihood ratios (LLR) values, decoding the LLRs to generate decoded data, and identifying a target performance value. The method also includes determining a performance metric from the decoded data, and performing a machine learning algorithm that dynamically adjusts the soft-demapping parameters to move the performance metric toward the target performance value.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a transport block (TB), the receiving the TB including performing log likelihood ratio (LLR) calculations on one or more parts of the TB based at least in part on a determination that the TB is likely to fail a cyclic redundancy check (CRC). The UE may transmit an indication of the one or more parts of the TB for which the UE performed LLR calculations. Numerous other aspects are described.