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.

A reception apparatus includes a detection unit that detects occurrence of a phase slip in phase estimation values of time-series received symbol data, and determines an inclination of the phase slip, a delay processing unit that generates first received signal data obtained by delaying received signal data obtained from the time-series received symbol data by one symbol time interval, a phase shift unit that generates second received signal data by performing phase shift according to the inclination, only in a period in which one symbol time interval elapses, on only the received signal data of a symbol time at which the occurrence of the phase slip is detected among pieces of the received signal data, and a remainder processing unit that derives a remainder of a difference between the second received signal data and the first received signal data.

Systems, devices, and methods of the present invention facilitate secure communication by altering the set of symbol waveforms that may be in use in particular symbol times defined herein as Symbol Waveform Hopping. SWH may be enabled by selecting two or more modulation formats that have sufficiently comparable communication performance (e.g., occupied bandwidth and signal power efficiency), but characterized by symbol waveform alphabet that include different symbol waveform, so that the overall transmission/communication performance of data stream in a signal transmission channel of the system is not significantly affected by switching between modulation formats. Some or all of the symbol waveforms in each alphabet may not be present in other alphabets.

A method of reducing transmission power for an encoded data stream includes the steps of receiving an incoming data stream having equal probability for a plurality of incoming data bits, assigning a symbol scheme to the received data bits of the incoming data stream according to probabilities of occurrence of individual ones of the received data bits, and transmitting an outgoing data stream according to the assigned symbol scheme having a second average transmit power, different than the first average transmit power, for a plurality of outgoing symbols.

A coding and modulation apparatus and method are presented. The apparatus comprises an encoder that encodes input data into cell words, and a modulator that modulates said cell words into constellation values of a non-uniform constellation. The modulator is configured to use, based on the total number M of constellation points of the constellation and the code rate, a non-uniform constellation from one or several groupsof constellations each comprising one or more constellations.

Aspects of methods and systems for frequency multiplexing suitable for Data Over Cable Service Interface Specification (DOCSIS) are provided. A system for multiplexing signals according to frequency comprises a DOCSIS port interface, an upstream interface, a downstream interface, and a circulator subsystem. The DOCSIS port interface comprises a plurality of channel filters. The upstream interface is operably coupled to a first channel filter of the plurality of channel filters, and the downstream interface is operably coupled to a second channel filter of the plurality of channel filters. The circulator subsystem is able to direct a first signal from the upstream interface to the DOCSIS port interface and is able to direct a second signal from the DOCSIS port interface to the downstream interface.

Methods, systems, and devices for wireless communications are described. A device (e.g., a base station or a user equipment (UE)) may identify a sequence length corresponding to a number of resource blocks, and select a modulation scheme based on the sequence length. The device may select, from a set of sequences associated with the modulation scheme, a sequence having the sequence length. In some examples, the set of sequences may include at least one of a set of time domain phase shift keying computer-generated sequences or a set of frequency domain phase shift keying computer-generated sequences. The device may generate a reference signal for a data transmission based on the sequence and transmit the reference signal within the number of resource blocks.

A gear shifting technique has been developed in which modulation and equalization are shifted to achieve optional performance. In one form, two or more equalizers, each associated with a demodulator and message decoder, determine if the modulation being used can be increased in complexity in order to increase the channel throughput or determine if the modulation method should be reduced in complexity in order to improve the receiver error performance. The quality metrics can based on which equalizer-demodulator-decoder is set to first detect a valid message. Other factors can be considered with this technique such as a packet-error ratio and a signal-to-noise ratio. In a financial trading system, message erasures can be favored over errored messages by limiting the number of bit or symbol corrections permitted per message to less than the maximum possible for the selected decoding schemes.

A coding and modulation apparatus and method are presented. The apparatus (10) comprises an encoder (11) that encodes input data into cell words, and a modulator (12) that modulates said cell words into constellation values of a non-uniform constellation. The modulator (12) is configured to use, based on the total number M of constellation points of the constellation, the signal-to-noise ratio SNR in dB and the channel characteristics, a non-uniform constellation from a group of constellations comprising one or more of predetermined constellations defined by the constellation position vector u1 . . . v, wherein v=sqrt(M)/2−1.

A coding and modulation apparatus and method are presented. The apparatus (10) comprises an encoder (11) that encodes input data into cell words, and a modulator (12) that modulates said cell words into constellation values of a non-uniform constellation. The modulator (12) is configured to use, based on the total number M of constellation points of the constellation, the signal-to-noise ratio SNR in dB and the channel characteristics, a non-uniform constellation from a group of constellations comprising one or more of predetermined constellations defined by the constellation position vector u1 . . . v, wherein v=sqrt(M)/2−1.