Abstract: A timing detection device includes a main reference code generation module, an auxiliary reference code generation module, a first correlation processing module, a second correlation processing module, and a subtraction module. The main reference code generation module generates a main reference code consisting of the same code for synchronization included in a received signal. Using a portion of the same code as the code for synchronization, the auxiliary reference code generation module generates an auxiliary reference code consisting of a code configuration different from the main reference code and without generating a main lobe during correlation processing. The first correlation processing module correlates the received signal with the main reference code and outputs a first correlation result. The second correlation processing module correlates the received signal with the auxiliary reference code and outputs a second correlation result.

Abstract: Disclosed is a coherent optical transceiver for optical communication including a transmitter, a receiver, and a PIC. The transmitter includes a DAC and a driver. A modulator in the PIC limits a signal spectrum of an output optical signal within a Nyquist frequency band. The receiver receives an input optical signal from the PIC and converts the input optical signal to an input analog electrical signal. An ADC converts the input analog electrical signal into an input digital electrical signal indicative of the input optical signal at an ADC sampling rate. The DSP includes a linear filter to equalize intersymbol interference, a post filter, and an MLSE to determine symbols corresponding the input optical signal. The driver and the post filter are first order filters with transfer function G(z)=1+az?1, where a is between 0 and 1.

Abstract: Methods and apparatus for dynamic acknowledgement list selection in detection of uplink control channel formats. In an exemplary embodiment, an apparatus includes a dynamic acknowledgement (ACK) list allocation circuit that generates a dynamic ACK list that includes one or two most likely ACK candidates, and a top-Q candidate CQI bits detector that dynamically allocates a detection branch to each of the one or two most likely ACK candidates to detect top-Q candidate CQI bits. The apparatus also includes a merger circuit that mergers the top-Q candidate CQI bits detected for the one or two most likely ACK candidates to generate a merged list, a top-Q CQI symbol generator that generates top-Q CQI symbols for the top-Q candidate CQI bits detected for the one or two most likely ACK candidates, and a joint detector that detects transmitted CQI bits and ACK bits.

Abstract: Provided is a method of decoding, the method including receiving, by a user equipment (UE), a downlink control information (DCI) that is encoded, identifying, by the UE, a first bit position of the DCI as a known bit, and reducing a number of candidate code words for the DCI based on the known bit.

Abstract: According to an embodiment, a method includes receiving audio data and providing the audio data as input to a first machine learning model to produce transcription data. The audio data is provided as input to a second machine learning model to produce speaker separation data, and the transcription data is segmented based on the speaker separation data to produce speaker separated transcription data. A portion of the speaker separated transcription data is provided as input to a third machine learning model to identify personal identifiable information (PII) text in the portion of the speaker separated transcription data, the portion being associated with a speaker from a plurality of speakers. The method also includes replacing the PII text with redaction text in the portion of the speaker separated transcription data and causing display of the transcription data including the redaction text at a user compute device.

Abstract: A computer-implemented reconstruction method of discrete digital signals in noisy overloaded wireless communication systems that is characterized by a channel matrix of complex coefficients, the method including, receiving the signal from channel by a signal detector, measuring the noise power by a noise power estimator at the receiver, forwarding the detected signal and noise power estimation to a decoder that estimates the transmitted symbol, wherein the estimation of the decoder produces a symbol that could probably have been transmitted it is forwarded to a de-mapper, which outputs the bit estimates corresponding to the estimated transmit signal and the corresponding estimated symbol to a microprocessor for further processing.

Abstract: A transmitter apparatus wherein a simple structure is used to successfully suppress the degradation of error rate performance that otherwise would be caused by fading or the like. There are included encoding parts that encode transport data; a mapping part that performs such a mapping that encoded data sequentially formed by the encoding parts are not successively included in the same symbol, thereby forming data symbols; and a symbol interleaver that interleaves the data symbols. In this way, a low computational complexity can be used to perform an interleaving process equivalent to a bit interleaving process to effectively improve the reception quality at a receiving end.

Abstract: A method for estimating object angle with high-angle analysis using a large-scale MIMO array antenna, wherein the array antenna receives the input signal matrix which is the transmission or reflection signal of at least one object. The method includes: step S1: inputting the input signal matrix to a first calculation model to obtain a target object amount and a rough object angle with respect to the location thereof; step S2: inputting the object amount and the input signal matrix to a second calculation model for singular value decomposition to obtain a noise matrix; step S3: obtaining an iteration angle range from the rough angle in S1; step S4: inputting the plurality of pursuit matrices corresponding to the iteration angle range and the noise matrix to a third calculation model for angle range iteration, thereby acquiring an accurate object angle.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may determine a quantity of hybrid automatic repeat request (HARQ) codebooks capable of being stored by the UE, a maximum amount of HARQ codebook data capable of being stored by the UE, or a maximum HARQ codebook size capable of being stored by the UE, and may transmit, to a network node, capability information that indicates the quantity of HARQ codebooks capable of being stored by the UE, the maximum amount of HARQ codebook data capable of being stored by the UE, or the maximum HARQ codebook size capable of being stored by the UE. Numerous other aspects are described.

Abstract: Distributed radio frequency (RF) communication systems for automotive are disclosed herein. In certain embodiments, an RF communication system for an automobile includes an RF module located close to an antenna to satisfy a specified output power with small insertion loss. Additionally, the baseband processor is placed remotely from the RF module in a different area of the automobile to provide a lower temperature environment. Additionally, the RF module communicates with the baseband processor in a digital format eliminating the need for higher cost cabling (for instance, due to higher noise immunity arising from using digital signaling) and using digital transfer cabling, which can already be present in the automobile for other purposes. The RF module can include an RF front-end (RFFE) and a transceiver used for providing frequency conversion, for instance, between RF and baseband.

Abstract: The disclosure includes a doorbell system having a doorbell, a doorbell housing, a visitor detection system, and a chime. The visitor detection system can be coupled to the doorbell housing and can include at least one of a camera and a motion detector. The doorbell can also comprise a first low-energy transceiver and a first high-energy transceiver that can be coupled to the doorbell housing. The first and second low-energy transceivers and the first and second high-energy transceivers can be configured to transmit data.

Abstract: Bayesian Inference based communication receiver employs Markov-Chain Monte-Carlo (MCMC) sampling for performing several of the main receiver functionalities. The channel estimator estimates the multipath channel coefficients corresponding to a signal received with fading. The symbol demodulator demodulates the received signal according to a QAM constellation, so as to generate a demodulated signal, and estimate the transmitted symbols. The decoder reliably decodes the demodulated signals to generate an output bit sequence, factoring in redundancy induced at a certain code rate. A universal sampler may be configured to use MCMC sampling for generating estimates of channel coefficients, transmitted symbols or decoder bits, for aforementioned functionalities, respectively. The samples may then be used in one or more of the receiver tasks: channel estimation, signal demodulation, and decoding, which leads to a more scalable, reusable, power/area efficient receiver.

Abstract: An on-chip or built-in self-test (BIST) module for an RFIC is provided. The BIST module can be implemented in an RFIC system, which may include a beamforming module of a radar system. The BIST module may include components and methods to up-convert a signal from a test frequency to RF at an input to the RFIC and down-convert and output signal.

Abstract: Methods, systems, and devices for wireless communication are described. A transmitting device may determine reconstruction information for a time-domain signal and may transmit the reconstruction information with the time-domain signal to a receiving device. The transmitting device may generate the reconstruction information based on estimates of how the receiving device may process the time-domain signal. For example, the transmitting device may apply a channel estimate to samples of the time-domain signal, and further perform clipping and quantization of the samples based on an estimated dynamic analog-to-digital converter (ADC) resolution of the receiving device. The transmitting device may generate the reconstruction information (e.g., using machine learning or other techniques) based on samples having the channel estimate applied and the clipped and quantized samples.

Abstract: An electronic device, which comprises a memory, a processor, and a serial number length adjustment program stored in the memory and operable on the processor is disclosed. The serial number length adjustment program is executed by the processor to implement following functions: performing an angle estimation algorithm on all user equipments (UEs) through a low-frequency band to estimate beam angles of the UEs relative to the electronic device; generating high-frequency band beams of the UEs relative to the electronic device according to the estimated beam angles; and enabling the electronic device to communicate with the UEs according to the generated high-frequency band beams.

Abstract: Provisioning and communicating physical signals and channels in NR networks having a first subset of transmit and receive points that use a first cell ID and a second subset of transmit and receive points that use a second cell ID. Operations include transmitting from, and receiving from, a first transmit and receive point a first signal or channel wherein the first signal or channel is based on a first user equipment (UE) specific parameter assigned via the first subset of transmit and receive points and transmitting from, and receiving from, the first transmit and receive point the plurality of transmit and receive points a second signal or channel wherein the second signal or channel is based on a second UE specific parameter assigned via the second subset of transmit and receive points. A transmit and receive point and a UE for implementing the operations are also disclosed.

Abstract: A method and device for determining a set of corrections to be made to a multichannel sound signal, in which the set of corrections is determined on the basis of an item of information representative of a spatial image of an original multichannel signal and an item of information representative of a spatial image of the original multichannel signal that has been coded and then decoded.

Abstract: This disclosure describes systems, methods, and devices related to enhanced fine timing measurement protocol negotiation. A device may identify an enhanced fine timing measurement request received from a first device, the enhanced fine timing measurement request comprising one or more information elements associated with one or more multiple-input multiple-output (MIMO) parameters. The device may cause to send an enhanced fine timing measurement response to the first device. The device may identify a null data packet announcement associated with a location determination of the first device. The device may identify a null data packet received from the first device. The device may cause to send a null data packet feedback to the first device.

Abstract: Radar-based motion detection systems are widely used in smart home, smart building, and smart city area for automatic control. In this invention, methods, subsystem, systems, computer program are disclosed to achieve power reduction of a radar sensor by operating the radar sensor in a sub-sampling manner in an illumination control system. By combining the information related to the detection area and the state of a lighting device, the sampling frequency of a radar sensor is configured according the user scenario. A balance between power reduction and motion detection performance is achieved therefrom.

Abstract: Proposed are a method and a device for receiving a PPDU in a wireless LAN system. Specifically, a reception STA receives a PPDU from a transmission STA through a broadband and decodes the PPDU. The PPDU includes a legacy preamble and a first and a second signal field. The legacy preamble and the first and second signal fields are generated on the basis of a first and a second phase rotation value. When the broadband corresponds to a 320 MHz band, the first phase rotation value is [1 ?1 ?1 ?1 1 ?1 ?1 ?1 ?1 1 1 1 ?1 1 1 1]. An element of the first phase rotation value is applied to each 20 MHz band of the 320 MHz band. An element of the second phase rotation value is applied to each subcarrier of the 320 MHz band.

Abstract: Multi-operation tools for photovoltaic cell processing are described. In an example, a multi-operation tool includes a conveyor system to move a photovoltaic (PV) cell continuously along a conveyor path through a laser scribing station and an adhesive printing station. Furthermore, the PV cell may be aligned to a laser head of the laser scribing station and a printer head of the adhesive printing station in a single alignment operation prior to being laser scribed and printed with an adhesive in a continuous process.

Abstract: Provided is a door lock. The door lock includes a door lock body installed on a door and having an opening/closing device; a memory to store a door lock identifier including a door recognition code and a door lock ID corresponding to the door recognition code; an antenna to sequentially receive a first RF signal and a second RF signal from a reader; and a control unit configured to transmit the door recognition code to the reader and configured to determine whether the door lock ID provided from the door lock management server through the reader matches the previously assigned door lock ID of the door lock identifier to control the opening/closing device.

Abstract: Systems and methods for low-power multi-antenna synchronization are disclosed. In one aspect, a computing device, such as an Internet of Things (IoT) computing device, may include a transceiver operating using BLUETOOTH LOW ENERGY (BLE) with multiple antennas. In an exemplary aspect, each of a plurality of antennas is coupled to a respective edge detection circuit. When an incoming signal is detected by one of the edge detection circuits, circuitry associated with others of the multiple antennas may be placed in a low-power mode while circuitry associated with the detecting edge detection circuit attempts to synchronize with the incoming signal to see if the incoming signal is a signal of interest.

Abstract: To obtain delay spread estimations and/or Doppler spread estimations, data representing received data is input to at least one trained model, the trained model outputting spread estimations.

Abstract: A transmitter apparatus wherein a simple structure is used to successfully suppress the degradation of error rate performance that otherwise would be caused by fading or the like. There are included encoding parts that encode transport data; a mapping part that performs such a mapping that encoded data sequentially formed by the encoding parts are not successively included in the same symbol, thereby forming data symbols; and a symbol interleaver that interleaves the data symbols. In this way, a low computational complexity can be used to perform an interleaving process equivalent to a bit interleaving process to effectively improve the reception quality at a receiving end.

Abstract: To reduce power consumption, a user equipment (UE) may trigger a microsleep in a subframe when a physical downlink control channel (PDCCH) does not include a downlink grant. However, because the microsleep depends on the PDCCH not including a downlink grant, the UE cannot trigger the microsleep until after the PDCCH is decoded. Accordingly, in some aspects, a UE may enable an aggressive extra microsleep in which a microsleep duration may be increased by reducing a PDCCH decode time. For example, a UE may use a stale channel estimate and noise estimate from a previous subframe to perform PDCCH demapping when conditions related to a PDCCH block error rate are satisfied. In this way, removing channel estimation and noise estimation from a PDCCH demapping path may reduce the PDCCH decode time, whereby the UE may trigger a microsleep sooner to increase a sleep ratio and thereby increase power savings.

Abstract: A user equipment (UE) detects a beam switching event and switches, in response to the beam switching event, a beam for communications on a first active component carrier. The UE applies a beam switch interruption time across one or more second active component carriers if a beam switching delay associated with the beam switch exceeds a threshold value.

Abstract: In one embodiment, an apparatus includes: a radio frequency (RF) front end circuit to receive and downconvert a RF signal to a second frequency signal, the RF signal comprising an orthogonal frequency division multiplexing (OFDM) transmission; a digitizer coupled to the RF front end circuit to digitize the second frequency signal to a digital signal; and a baseband processor coupled to the digitizer to process the digital signal. The baseband circuit comprises a first circuit having a first plurality of correlators having an irregular comb structure, each of the first plurality of correlators associated with a carrier frequency offset and to calculate a first correlation on a first portion of a preamble of the OFDM transmission.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive, via a sensor included within the UE, information associated with a base station. For instance, the UE may receive, via a camera included within the UE, an image of the base station. In some cases, the information associated with the base station may also include environment information identifying an antenna of the base station. The UE may then perform, based on the received information, a beam management procedure to track a UE beam corresponding to a base station beam, and communicate with the base station based on the beam management procedure.

Abstract: Apparatuses and methods for simultaneously operating as a wireless radio and monitoring the local frequency spectrum. For example, described herein are wireless radio devices that use a secondary receiver to monitor frequencies within the operating band and prevent or avoid interferers, including in particular half-IF interferers. The systems, devices, and methods described herein may adjust the intermediate frequency in a superheterodyne receiver to select an intermediate frequency that minimizes interference. In particular, described herein are apparatuses and methods that use a second receiver which is independent of the first receiver and may be connected to the same receiving antenna to monitor the geographically local frequency spectrum and may detect spurious interferers, allowing the primary receiver to adjust the intermediate frequency and avoid spurious interferes.

Abstract: Provided is an acoustic signal processing technique for performing a signal transformation suitable for desired signal processing (e.g., sound source enhancement processing) on a signal, and then performing the desired signal processing on the transformed signal. An acoustic signal processing device performs signal processing M which is a desired target on an input acoustic signal x.

Abstract: A mixer includes a load portion connected between an input terminal of a first power voltage and an output terminal of the radio frequency transmit signal and configured to adjust a magnitude of the radio frequency transmit signal, a first switching unit connected to an output terminal of the radio frequency transmit signal, and configured to perform a first switching operation in response to a plurality of local oscillation signals, and a second switching unit connected between the first switching unit and an input terminal of a second power voltage, lower than the first power voltage, and configured to perform a second switching operation in response to a plurality of baseband signals, the plurality of local oscillation signals include an I+ baseband signal, an I? baseband signal, a Q+ baseband signal, and a Q? baseband signal, and the second switching unit includes a first branch performing a switching operation under control of the I+ baseband signal and the Q+ baseband signal, a second branch performing

Abstract: Hybrid Automatic Repeat Request (HARQ) retransmissions based on User Equipment (UE) cooperation involves a first UE receiving a transmission comprising a data block that is destined for a second UE, and transmitting the data block toward the second UE according to a data block retransmission mechanism to enable the second UE to identify the data block transmitted from the first UE as being one of a plurality of concurrent transmissions of the data block according to the data block retransmission mechanism. The concurrent transmissions of the data block are processable by the second UE in combination to determine a reception status of the data block.

Abstract: Aspects of the disclosure provide for an apparatus comprising a time-to-digital converter (TDC) and a processor coupled to the TDC. In some examples, the TDC may be configured to receive a signal and generate a measurement result indicating a time between start and stop events of the signal. The processor may be configured to receive the measurement result, compare the measurement result to a target value, and determine a non-linearity model configured to correct a variance of the measurement result from the target value.

Abstract: Devices, systems and methods for providing network-enabled connectivity for disadvantaged communication links in wireless networks are described. One example method for enabling connectivity over a disadvantaged link includes receiving, by a first node of a plurality of nodes from a source node in the first frequency band in a first timeslot, a first signal comprising a message, receiving, by the first node from at least a second node in a second frequency band in a second timeslot, a second signal that is used to generate a first reliability metric corresponding to the message, and performing, based on a plurality of reliability metrics corresponding to the message and the first reliability metric, a processing operation on the message, the first frequency band being non-overlapping with the second frequency band, and a duration of the first timeslot being greater than a duration of the second timeslot.

Abstract: Methods and systems may provide for receiving a physiological signal from a sensor configuration associated with a mobile device. A qualitative analysis may be conducted for each of a plurality of noise sources in the physiological signal to obtain a corresponding plurality of qualitative ratings. In addition, at least the plurality of qualitative ratings may be used to determine whether to report the physiological signal to a remote location. In one example, a quantitative analysis is conducted for each of the plurality of noise sources to obtain an overall quality level, wherein the overall quality level is also used to determine whether to report the physiological signal to the remote location.

Abstract: Provisioning and communicating physical signals and channels in NR networks having a first subset of transmit and receive points that use a first cell ID and a second subset of transmit and receive points that use a second cell ID. Operations include transmitting from, and receiving from, a first transmit and receive point a first signal or channel wherein the first signal or channel is based on a first user equipment (UE) specific parameter assigned via the first subset of transmit and receive points and transmitting from, and receiving from, the first transmit and receive point the plurality of transmit and receive points a second signal or channel wherein the second signal or channel is based on a second UE specific parameter assigned via the second subset of transmit and receive points. A transmit and receive point and a UE for implementing the operations are also disclosed.

Abstract: An apparatus and method for broadcast signal frame using a bootstrap and a preamble are disclosed. An apparatus for generating broadcast signal frame according to an embodiment of the present invention includes a time interleaver configured to generate a time-interleaved signal by performing interleaving on a BICM output signal; and a frame builder configured to generate a broadcast signal frame including a bootstrap and a preamble using the time-interleaved signal.

Abstract: Systems, methods, and computer-readable media are provided for hybrid beamforming.

Abstract: Methods, systems, and devices for wireless communications are described. A network entity may map a demodulation reference signal (DMRS), a truncated sequence, and data in a delay-Doppler domain in accordance with a control signal. The network entity may apply a Fourier transform on the mapped DMRS, the truncated sequence, and the data to generate a signal in the time domain. The network entity may output, and a user equipment (UE) may receive, the signal in the time domain, including the DMRS, the truncated sequence, and the data. The UE may apply a Fourier transform on the received signal in the time domain to generate a mapping of the DMRS and the data in the delay-Doppler domain. The UE may perform channel estimation based on applying the Fourier transform on the received signal.

Abstract: The present disclosure provides an information processing method and apparatus. A terminal device encodes uplink control information (UCI) to obtain coded bits of the UCI, and encodes data to obtain coded bits of the data. The terminal device multiplexes the coded bits of the UCI and the coded bits of the data to obtain a multiplexed bit sequence. The terminal device then transmits the multiplexed bit sequence to a network device via a physical uplink shared channel (PUSCH). A length of a transmission time interval of the UCI is less than or equal to 0.5 millisecond. In this way, data transmission latency can be reduced.

Abstract: A transmitter apparatus wherein a simple structure is used to successfully suppress the degradation of error rate performance that otherwise would be caused by fading or the like. There are included encoding parts that encode transport data; a mapping part that performs such a mapping that encoded data sequentially formed by the encoding parts are not successively included in the same symbol, thereby forming data symbols; and a symbol interleaver that interleaves the data symbols. In this way, a low computational complexity can be used to perform an interleaving process equivalent to a bit interleaving process to effectively improve the reception quality at a receiving end.

Abstract: A method and apparatus are provided for transmitting and receiving control information. A method in a base station includes transmitting, to a terminal, information associated with a resource region carrying a control channel; transmitting, to the terminal, a plurality of values associated with control channel candidates, each of the plurality of values corresponding to each of a plurality of numbers associated with CCEs constituting one control channel candidate, wherein the each of the plurality of values indicates a number of control channel candidates to be monitored by the terminal; determining a set of control channel candidates based on an ID of the terminal and at least one of the plurality of values associated with the control channel candidates; selecting at least one control channel candidate from among the set of control channel candidates; and transmitting the control information to the terminal through the at least one selected control channel candidate in the resource region.

Abstract: Aspects of the present disclosure may involve use of a radio frequency receiver and in such a receiver, tracking multipath gains and delays of multipath reflections corresponding to an OFDM multipath transmission channel. The gains and delays are based on time-domain evolution of the channel impulse response. Multipath reflections are searched for and then used to calculate channel correlation information to provide channel estimations to aid in mitigating or cancelling distortion of the received signal.

Abstract: Presented are systems and methods for automatically decoding and demodulating radio signals in a communication network. Embodiments utilize a one-dimensional (1D) convolutional neural network (CNN) as the key architecture of a decoder that utilizes one or more 1D convolution windows to perform convolution operations on to-be-decoded or demodulated input signals received by the communication network. In embodiments, this may be achieved by receiving, at a CNN correlator implemented in a decoder, an input signal that comprises unknown data and applying to the input signal, in the discrete time domain, a convolution to obtain a CNN correlator output to which an activation may be applied to decode the input signal and output the decoded signal.

Abstract: Accordingly embodiments herein disclose a quarter rate speculative DFE. The quarter rate speculative DFE includes a plurality of sampler circuits connected to an input terminal. The plurality of sampler circuits are configured to sample an input signal into a plurality of data samples in parallel. A plurality of quarter rate look ahead circuit connected to the plurality of sampler circuits. The plurality of quarter rate look ahead circuit is configured to simultaneously perform an align operation and a look ahead operation on the plurality of data samples based on the different clock phases to obtain a plurality of latched outputs. A plurality of multiplexers connected to the plurality of quarter rate look ahead circuit. The plurality of multiplexers is configured to generate two speculative data streams by multiplexing respective correction coefficients of each of the plurality of latched outputs.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method, and computer program product embodiments for remotely controlling a media device. An embodiment includes an apparatus including a radio frequency (RF) communications chip, a memory, and at least one processor coupled to the RF communications chip and the memory. The at least one processor is configured to receive an electronic signal indicative of a user command and generate, based on the electronic signal, an action frame packet configured to instruct a media device to perform a function associated with the user command. Subsequently, the at least one processor is configured to transmit, using the RF communications chip, the action frame packet to the media device.

Abstract: This application provides an apparatus for correcting a deviation between a plurality of transmission channels, which includes a first transmission channel and a second transmission channel. The first transmission channel and the second transmission channel are respectively connected to a first endpoint and a second endpoint of a correction coupling channel. The apparatus includes a vector detection unit, configured to: when a first signal is fed at the first endpoint and a second signal is fed at the second endpoint, respectively detect a plurality of signal vectors based on a plurality of feedback signals of the first transmission channel and the second transmission channel; and a processing unit, configured to determine a deviation correction value between the first transmission channel and the second transmission channel based on the detected signal vectors.

Abstract: A method of transmitting data via a unipolar signal comprises allocating a symbol to one or more signals among a plurality of signals, applying pulse shaping to the plurality of signals to obtain a plurality of filtered signals, wherein the filtered signals are orthogonal signals, and transmitting the sum of the filtered signals as a unipolar signal, wherein the transmitted signal is a weighted sum of the filtered signals. The data can be recovered at the receiver by applying a plurality of orthogonal matched filters to the received unipolar signal to obtain a plurality of filtered signals, and performing symbol detection on the plurality of filtered signals to determine the received symbol. Apparatus for transmitting and receiving unipolar signals are also disclosed.

Abstract: Systems and methods for classifying baseband signals with respect to modulation type include receiving, at a consolidated neural network whose objective is modulation classification performance, a complex quadrature vector of interest including multiple samples of a baseband signal derived from a radio frequency signal of unknown modulation type, generating multiple data representations of the vector of interest, providing each data representation to one of multiple parallel neural networks in the consolidated neural network, and receiving a classification result for the baseband signal based on combined outputs of the parallel neural networks.