Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.

Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.

Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point, but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.

Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point, but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.

Abstract: Methods for performing a ranging procedure according to the non-trigger-based protocol may include negotiating timing parameters associated with the ranging procedure, performing a ranging measurement, and transmitting/receiving, after completion of the ranging measurement, a message announcing initiation of another ranging measurement. The timing parameters may indicate a time window in which an initiating device can initiate a subsequent ranging measurement and the message announcing initiation of the second ranging measurement may be received during the time range specified. Timing parameters may indicate a responding device's required minimum and maximum time between ranging measurements. Additional parameters may indicate an initiating device's required minimum and maximum time between ranging measurements. A power savings mode may be entered after the first ranging measurement and during at least a portion of a time period specified by the parameters.

Abstract: Methods for performing a ranging procedure according to the non-trigger-based protocol may include negotiating timing parameters associated with the ranging procedure, performing a ranging measurement, and transmitting/receiving, after completion of the ranging measurement, a message announcing initiation of another ranging measurement. The timing parameters may indicate a time window in which an initiating device can initiate a subsequent ranging measurement and the message announcing initiation of the second ranging measurement may be received during the time range specified. Timing parameters may indicate a responding device's required minimum and maximum time between ranging measurements. Additional parameters may indicate an initiating device's required minimum and maximum time between ranging measurements. A power savings mode may be entered after the first ranging measurement and during at least a portion of a time period specified by the parameters.

Abstract: A device implementing spectral aggregation to generate a wideband channel estimation may include a processor configured to generate a combined channel estimation for one or more channels. For each channel, the processor may be configured to: transmit a first signal to another device; after an amount of time elapses, open a receive window for facilitating detection of a second signal from the other device; receive the second signal from the other device; generate a first channel estimation based on the second signal; and generate the combined channel estimation based on the first channel estimation and a second channel estimation received from the other device. The processor may be configured to aggregate the combined channel estimation generated for each channel into an aggregated channel estimation. The processor may be configured to estimate a time of arrival for a third signal based on the aggregated channel estimation.

Abstract: Embodiments herein relate to using a convolutional neural network (CNN) for time-of-flight estimation in a wireless communication system. A wireless device may receive, from a remote device, wireless communications including a first transmission time value associated with the transmission of the wireless communications. The wireless device may perform a coarse time-of-arrival (TOA) estimation on the wireless communications received from the remote device. The coarse TOA estimation may be used to generate an estimated impulse response, which may be input to a CNN associated with the wireless device to calculate a line-of-sight estimate. The wireless device may determine a range between the wireless device and the remote device based on the transmission time value and the line-of-sight estimate.

Abstract: A device implementing spectral aggregation to generate a wideband channel estimation may include a processor configured to generate a combined channel estimation for one or more channels. For each channel, the processor may be configured to: transmit a first signal to another device; after an amount of time elapses, open a receive window for facilitating detection of a second signal from the other device; receive the second signal from the other device; generate a first channel estimation based on the second signal; and generate the combined channel estimation based on the first channel estimation and a second channel estimation received from the other device. The processor may be configured to aggregate the combined channel estimation generated for each channel into an aggregated channel estimation. The processor may be configured to estimate a time of arrival for a third signal based on the aggregated channel estimation.