Intel Corporation

Matthew Hayes

Tianyan Pu

Denis Markovic

Hujun Yin

Xiangyang Zhuang

RongZhen Yang

Zhibin Yu

Gwang-Hyun Gho

Pouyan Parvazi

Xiaoran Fang

Shoujiang Ma

Viswanath Vajepeyazula

Goochul Chung

Chris Quanbeck

Mehrzad Malmirchegini

John P Hogan

Aspects for machine learning-based link adaptation are described. For example, an apparatus can determine k-nearest neighbors (K-NNs) based on training data associated with the sub-band and on the signal to interference and noise ratio (SINR) of the sub-band. In aspects, the apparatus can identify a channel quality indicator (CQI) associated with the lowest error rate for the k-NNs and provide the identified CQI to a base station. In aspects, a neural network (NN) can provide labels for CQIs that indicate probability of choosing a CQI, and the CQI having highest probability will be provided to a base station. In aspects, a covariance matrix based on samples of a communication channel can be provided to a NN to determine a rank indicator (RI) corresponding to the channel, and channel state information associated with the (RI) can be sent to the base station. Other aspects are described.

Machine learning-based link adaptation

Disclosed is a method of synchronization signal correlation, comprising receiving a synchronization signal ('SS') on a plurality of receive antennas; performing a signal revision on the SS received on a first receive antenna, the signal revision comprising performing an element-wise squaring of the SS; calculating a complex coefficient by summing the element-wise squared SS; estimating a phase angle of the complex coefficient; and performing an element-wise phase correction of the SS; the method synchronization signal correlation further comprising performing the signal revision on the SS received on a second receive antenna; conditioning the revised signals by constructively and destructively combining the revised signals; selecting an optimized conditioned signal, wherein the optimized conditioned signal is the constructive or destructive combination with the largest Euclidian norm; correlating the optimized conditioned signal with a series of candidate SSs; and selecting the correlation with the largest magnitude as a transmitted SS.

Leveraging secondary synchronization signal properties to improve synchronization signal detection

A communication device can be configured to estimate a Reference-Signal-Received-Power (RSRP). The communication device can include a transceiver and a controller. The transceiver can be configured to downsample a received signal having a plurality of reference signal resource elements to generate a downsampled signal. The downsampling can alias a first of the plurality of reference signal resource elements into a second of the plurality of reference signal resource elements to generate an aliased reference signal resource element. The transceiver can also be configured to extract the aliased reference signal resource element from the downsampled signal. The controller can be connected to the transceiver and be configured to estimate the RSRP based on the extracted aliased reference signal resource element.

Power estimation system and method

A method and mobile communication device adapted for frequency synchronization with a radio access network (RAN) based on frequency shift detection in a first signal received at the mobile communication device, including: offsetting the first signal's frequency by a first value extracted from a second signal received at the mobile communication device; generating a replica of the first signal from a second value extracted from a third signal received at the mobile communication device; multiplying a component of the offset first signal with the replica to generate a product; transforming the product into a frequency-domain signal; and detecting a peak in the frequency-domain signal to determine the frequency shift.

Methods and devices for frequency shift detection

A method and communication device adapted for interference cancellation in a cell search used in a communication device, including: correlating a signal received at the communication device with a template comprising one or more signal sequences associated with one or more corresponding cells to determine a metric for each of the signal sequences; and at least one iteration of: ranking the signal sequences based on the determined metrics, wherein the highest ranked signal sequence is designated as an aggressor sequence; performing an interference cancellation to generate a corrected metric for signal sequences based on their correlation with the aggressor sequence; and removing the aggressor sequence and setting priority to the cell associated with the aggressor sequence.

Methods and devices for interference cancellation in cell search

A mobile communication device may include a cell search circuit configured to process a first block of signal waveform data to extract a first discrete parameter set, wherein the first discrete parameter set identifies one or more first potential cells present in the first block of signal waveform data, process the second block of signal waveform data to extract a second discrete parameter set, wherein the second discrete parameter set identifies one or more second potential cells present in the second block of signal waveform data, and compare the first discrete parameter set and the second discrete parameter set to identify one or more matching cells, and an RF transceiver configured to transmit or receive radio signals based on the identification of the one or more matching cells.

Methods and communication devices for performing cell search and detection

A mobile communication device may include a radio transceiver configured to transmit and receive communication signals, and a baseband modem circuit configured to determine a decoded information field of a first encoded system information packet, set one or more bits of the decoded information field as an initial encoder state of a convolutional decoder for decoding the first encoded system information packet, decode the first encoded system information packet with the initial encoder state to obtain a first decoded system information packet, and use the decoded system information packet to transmit or receive data with one or more network cells.

System information convolutional decoding

A communication circuit arrangement may include a cell search circuit configured to compare a detected synchronization sequence of a detected candidate cell with a predetermined reference synchronization sequence to generate a demodulated synchronization sequence including a plurality of samples, determine a phase variance between the plurality of samples of the demodulated synchronization sequence, and compare the phase variance to a detection threshold to classify the detected candidate cell as a real cell or a false cell.

Growing community of inventors

Radebeul, Germany

Matthew Hayes