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: Disclosed are methods, systems, and computer-readable medium to perform operations comprising periodically broadcasting, by a first wireless device, outgoing ranging packets on a measurement channel of a wireless network; receiving, by the first wireless device on the measurement channel and from a second wireless device, a plurality of incoming ranging data packets; and calculating, by the first wireless device and using a three ranging packet exchange with the second wireless device, a range to the second wireless device.

Abstract: Disclosed are methods, systems, and computer-readable medium to perform operations comprising periodically broadcasting, by a first wireless device, outgoing ranging packets on a measurement channel of a wireless network; receiving, by the first wireless device on the measurement channel and from a second wireless device, a plurality of incoming ranging data packets; and calculating, by the first wireless device and using a three ranging packet exchange with the second wireless device, a range to the second wireless device.

Abstract: A technique for determining a presence of a person in a room may include an electronic device transmitting an electromagnetic wireless signal of a first sensor. The technique may include receiving an electromagnetic return signal from the electromagnetic wireless signal. The technique may include detecting a potential target in the room based on the electromagnetic return signal. The technique may include determining that the potential target is in the room using a second sensor. Responsive to determining the potential target is in the room, the technique may include saving a training signature of the electromagnetic return signal for training a machine learning model. This technique can be repeated to obtain a set of training signatures corresponding to potential targets. The technique may include training, using the set of training signatures, the machine learning model to detect when a target is in the room using the first sensor.

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: Disclosed are methods, systems, and computer-readable medium to perform operations comprising periodically broadcasting, by a first wireless device, outgoing ranging packets on a measurement channel of a wireless network; receiving, by the first wireless device on the measurement channel and from a second wireless device, a plurality of incoming ranging data packets; and calculating, by the first wireless device and using a three ranging packet exchange with the second wireless device, a range to the second wireless device.

Abstract: Some embodiments of this disclosure include apparatuses and methods for implementing a requirement negotiation for an error vector magnitude (EVM) (or other metrics for measuring transmission signal quality) for ranging and/or positioning operation(s). Some embodiments relate to an electronic device including a transceiver and one or more processors communicatively coupled to the transceiver. The one or more processors transmit, during a negotiation phase of a ranging operation, an initial request frame to a second electronic device, wherein the initial request frame comprises a first indication of an error vector magnitude (EVM) requirement. The one or more processors receive an initial response frame from the second electronic device and determine a second indication of the EVM requirement based at least in part on the received initial response frame. The one or more processors implement a measurement phase of the ranging operation in accordance with the second indication of the EVM requirement.

Abstract: An apparatus for detecting worn and/or unworn status of a wearable host device includes one or more first antennas, a second antenna, and a radio-frequency (RF) circuit to measure a dielectric loading based on an RF isolation. The second antenna is placed within a portion of the wearable host device that is substantially in contact with the skin of a user, and the RF isolation is between at least one of the one or more first antennas and the second antenna.

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: Some embodiments of this disclosure include apparatuses and methods for implementing a requirement negotiation for an error vector magnitude (EVM) (or other metrics for measuring transmission signal quality) for ranging and/or positioning operation(s). Some embodiments relate to an electronic device including a transceiver and one or more processors communicatively coupled to the transceiver. The one or more processors transmit, during a negotiation phase of a ranging operation, an initial request frame to a second electronic device, wherein the initial request frame comprises a first indication of an error vector magnitude (EVM) requirement. The one or more processors receive an initial response frame from the second electronic device and determine a second indication of the EVM requirement based at least in part on the received initial response frame. The one or more processors implement a measurement phase of the ranging operation in accordance with the second indication of the EVM requirement.

Abstract: Embodiments for accurately performing time of flight estimations are provided. These embodiments include using a first wireless device to monitor a wireless link and subsequently generate a wireless link estimation based on the monitoring. The embodiments also include deriving a correction metric based on the generated wireless link estimation and transmitting the correction metric from the first wireless device to a second wireless device. The second wireless device may then calculate a time of arrival of a first signal received from the first wireless communication device and correct any errors associated with the time of arrival calculation using the received correction metric. Further, the second wireless device may transmit the corrected time of arrival back to the first wireless device, such that the first wireless device can use the corrected time of arrival to estimate the time of flight of the first signal.

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: Embodiments for accurately performing time of flight estimations are provided. These embodiments include using a first wireless device to monitor a wireless link and subsequently generate a wireless link estimation based on the monitoring. The embodiments also include deriving a correction metric based on the generated wireless link estimation and transmitting the correction metric from the first wireless device to a second wireless device. The second wireless device may then calculate a time of arrival of a first signal received from the first wireless communication device and correct any errors associated with the time of arrival calculation using the received correction metric. Further, the second wireless device may transmit the corrected time of arrival back to the first wireless device, such that the first wireless device can use the corrected time of arrival to estimate the time of flight of the first signal.

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.