Abstract: An algorithm for removing motion artifacts from the PPG signal in the time domain to determine heart rate is disclosed. A device for determining a heart rate of a user can include a heart rate sensor configured to generate heart rate signals when positioned on or adjacent to a user's skin, an accelerometer configured to generate one or more acceleration signals, and processing circuitry configured to remove, in a time domain, motion artifacts from the heart rate signals based on the acceleration signals. In some examples, the removal of motion artifacts can also be based on mean-centered, variance-scaled integrated acceleration signals. In some examples, the processing circuitry can be configured to remove motion artifacts using a least squares algorithm to identify a best representation of acceleration and integrated acceleration signals in the heart rate signals.

Abstract: The subject technology provides for large-scale training of foundation models for physiological signals from wearable electronic devices. An apparatus receives receive input data having a plurality of physiological signal information segments associated with a user. The apparatus applies one or more augmentation functions to the plurality of physiological signal information segments to generate an augmented version of the plurality of physiological signal information segments. The apparatus trains a neural network to produce a trained machine learning model by generating, via an encoder, an embedding of the augmented version having a first number of dimensions in an embedding space. The apparatus maps, via a multilayer perceptron projection, the embedding into a representation having a second number of dimensions. The apparatus determines mutual information between a pair of representations of the augmented version.

Abstract: An example technique may include tracking motion of a user wearing the wearable device using at least first sensors of one or more sensors of the wearable device. The technique may also include tracking a physical state of the user using at least second sensors of the one or more sensors of the wearable device. The technique may also include determining whether an application of the wearable device has been launched. The technique may also include determining an action category of the user based at least in part on at least one of the motion of the user, the physical state of the user, or whether the application has been launched. The technique may also include collecting heartrate data of the user. The technique may also include categorizing the heartrate data based at least in part on the determined action category.

Abstract: A device for determining a heart rate of a user has a PPG sensor and an accelerometer to compensate for acceleration artifacts within the PPG signal. The device transforms time domain PPG and accelerometer signals into the frequency domain using a Fourier transformation and utilizes the Fourier coefficient magnitudes as indicative of the probability of candidate heart rate values. Candidate heart rate values are determined at sampling times over a time interval and a most probable heart rate path during the time interval is determined using a reward/penalty algorithm.

Abstract: This relates to methods for measuring irregularities in a signal and corresponding devices. The devices can include a PPG sensor unit configured to detect multiple occurrences of a given event in the measured signal(s) over a sampling interval. In some instances, the device can register the occurrences of the events. In some examples, the device can include one or more motion sensors configured to detect whether the device is in a low-motion state. The device may delay initiating measurements when the device is not in a low-motion state to enhance measurement accuracy. Examples of the disclosure further include resetting the sample procedure based on one or more factors such as the number of non-qualifying measurements. In some examples, the device can be configured to perform both primary and secondary measurements, where the primary measurements can include readings using a set of operating conditions different from the secondary measurements.

Abstract: A device for determining a heart rate of a user has a PPG sensor and an accelerometer to compensate for acceleration artifacts within the PPG signal. The device transforms time domain PPG and accelerometer signals into the frequency domain using a Fourier transformation and utilizes the Fourier coefficient magnitudes as indicative of the probability of candidate heart rate values. Candidate heart rate values are determined at sampling times over a time interval and a most probable heart rate path during the time interval is determined using a reward/penalty algorithm.

Abstract: This relates to methods for measuring irregularities in a signal and corresponding devices. The devices can include a PPG sensor unit configured to detect multiple occurrences of a given event in the measured signal(s) over a sampling interval. In some instances, the device can register the occurrences of the events. In some examples, the device can include one or more motion sensors configured to detect whether the device is in a low-motion state. The device may delay initiating measurements when the device is not in a low-motion state to enhance measurement accuracy. Examples of the disclosure further include resetting the sample procedure based on one or more factors such as the number of non-qualifying measurements. In some examples, the device can be configured to perform both primary and secondary measurements, where the primary measurements can include readings using a set of operating conditions different from the secondary measurements.

Abstract: This disclosure relates to methods for measuring one or more physiological signals while the user is engaged in a predetermined activity. Exemplary predetermined activities can include activities such as walking, climbing stairs, biking, and the like. The physiological measurements can include, but are not limited to, heart rate signals. The physiological measurements may be affected by the predetermined activity, so the system may be configured to employ one or more criteria prior to measuring physiological information to minimize the effects. The one or more criteria can include, but are not limited to, an inter-sampling waiting time, continuous motion criteria, predetermined activity criteria, a post-physiological measurement amount of time, and a confidence value. The continuous motion criteria can be based on the type of predetermined activity. For example, walking may have walking state criteria and a step count criteria.

Abstract: This relates to methods for measuring irregularities in a signal and corresponding devices. The devices can include a PPG sensor unit configured to detect multiple occurrences of a given event in the measured signal(s) over a sampling interval. In some instances, the device can register the occurrences of the events. In some examples, the device can include one or more motion sensors configured to detect whether the device is in a low-motion state. The device may delay initiating measurements when the device is not in a low-motion state to enhance measurement accuracy. Examples of the disclosure further include resetting the sample procedure based on one or more factors such as the number of non-qualifying measurements. In some examples, the device can be configured to perform both primary and secondary measurements, where the primary measurements can include readings using a set of operating conditions different from the secondary measurements.

Abstract: This disclosure relates to methods for measuring one or more physiological signals while the user is engaged in a predetermined activity. Exemplary predetermined activities can include activities such as walking, climbing stairs, biking, and the like. The physiological measurements can include, but are not limited to, heart rate signals. The physiological measurements may be affected by the predetermined activity, so the system may be configured to employ one or more criteria prior to measuring physiological information to minimize the effects. The one or more criteria can include, but are not limited to, an inter-sampling waiting time, continuous motion criteria, predetermined activity criteria, a post-physiological measurement amount of time, and a confidence value. The continuous motion criteria can be based on the type of predetermined activity. For example, walking may have walking state criteria and a step count criteria.

Abstract: An example technique may include tracking motion of a user wearing the wearable device using at least first sensors of one or more sensors of the wearable device. The technique may also include tracking a physical state of the user using at least second sensors of the one or more sensors of the wearable device. The technique may also include determining whether an application of the wearable device has been launched. The technique may also include determining an action category of the user based at least in part on at least one of the motion of the user, the physical state of the user, or whether the application has been launched. The technique may also include collecting heartrate data of the user. The technique may also include categorizing the heartrate data based at least in part on the determined action category.

Abstract: Techniques are provided for tracking heartrate metrics using different operating modes associated with different contexts of a wearable device. For example, a heartrate sensor of the wearable device may be operated in a first operating mode when an activity is being tracked within an application session of a particular application. The heartrate sensor may be operated in a second operating mode after detecting conclusion of the activity within the activity session (e.g., during sedentary time).

Abstract: This disclosure relates to methods for measuring one or more physiological signals while the user is engaged in a predetermined activity. Exemplary predetermined activities can include activities such as walking, climbing stairs, biking, and the like. The physiological measurements can include, but are not limited to, heart rate signals. The physiological measurements may be affected by the predetermined activity, so the system may be configured to employ one or more criteria prior to measuring physiological information to minimize the effects. The one or more criteria can include, but are not limited to, an inter-sampling waiting time, continuous motion criteria, predetermined activity criteria, a post-physiological measurement amount of time, and a confidence value. The continuous motion criteria can be based on the type of predetermined activity. For example, walking may have walking state criteria and a step count criteria.

Abstract: This disclosure relates to methods for measuring one or more physiological signals while the user is engaged in a predetermined activity. Exemplary predetermined activities can include activities such as walking, climbing stairs, biking, and the like. The physiological measurements can include, but are not limited to, heart rate signals. The physiological measurements may be affected by the predetermined activity, so the system may be configured to employ one or more criteria prior to measuring physiological information to minimize the effects. The one or more criteria can include, but are not limited to, an inter-sampling waiting time, continuous motion criteria, predetermined activity criteria, a post-physiological measurement amount of time, and a confidence value. The continuous motion criteria can be based on the type of predetermined activity. For example, walking may have walking state criteria and a step count criteria.

Abstract: Techniques are provided for tracking heartrate metrics using different operating modes associated with different contexts of a wearable device. For example, a heartrate sensor of the wearable device may be operated in a first operating mode when an activity is being tracked within an application session of a particular application. The heartrate sensor may be operated in a second operating mode after detecting conclusion of the activity within the activity session (e.g., during sedentary time).

Abstract: Embodiments of the present disclosure can provide systems, methods, and computer-readable medium for tracking the heartrate of a user using different techniques associated with different contexts. For example, motion of a user wearing a wearable device can be tracked using at least first sensors of the one or more sensors. The physical state of the user can also be tracked using at least second sensors of the one or more sensors. In some cases it can be determines whether an application of the wearable device has been launched. Additionally, an activity category of the user can be determined based at least in part on the motion of the user, the physical state of the user, and/or whether the application has been launched. Heartrate data of the user can be collected, and the heartrate data can be categorized based at least in part on the determined category.

Abstract: An algorithm for removing motion artifacts from the PPG signal in the time domain to determine heart rate is disclosed. A device for determining a heart rate of a user can include a heart rate sensor configured to generate heart rate signals when positioned on or adjacent to a user's skin, an accelerometer configured to generate one or more acceleration signals, and processing circuitry configured to remove, in a time domain, motion artifacts from the heart rate signals based on the acceleration signals. In some examples, the removal of motion artifacts can also be based on mean-centered, variance-scaled integrated acceleration signals. In some examples, the processing circuitry can be configured to remove motion artifacts using a least squares algorithm to identify a best representation of acceleration and integrated acceleration signals in the heart rate signals.

Abstract: An algorithm for removing motion artifacts from the PPG signal in the time domain to determine heart rate is disclosed. A device for determining a heart rate of a user can include a heart rate sensor configured to generate heart rate signals when positioned on or adjacent to a user's skin, an accelerometer configured to generate one or more acceleration signals, and processing circuitry configured to remove, in a time domain, motion artifacts from the heart rate signals based on the acceleration signals. In some examples, the removal of motion artifacts can also be based on mean-centered, variance-scaled integrated acceleration signals. In some examples, the processing circuitry can be configured to remove motion artifacts using a least squares algorithm to identify a best representation of acceleration and integrated acceleration signals in the heart rate signals.

Abstract: This relates to methods for measuring irregularities in a signal and corresponding devices. The devices can include a PPG sensor unit configured to detect multiple occurrences of a given event in the measured signal(s) over a sampling interval. In some instances, the device can register the occurrences of the events. In some examples, the device can include one or more motion sensors configured to detect whether the device is in a low-motion state. The device may delay initiating measurements when the device is not in a low-motion state to enhance measurement accuracy. Examples of the disclosure further include resetting the sample procedure based on one or more factors such as the number of non-qualifying measurements. In some examples, the device can be configured to perform both primary and secondary measurements, where the primary measurements can include readings using a set of operating conditions different from the secondary measurements.

Abstract: This relates to methods for measuring irregularities in a signal and corresponding devices. The devices can include a PPG sensor unit configured to detect multiple occurrences of a given event in the measured signal(s) over a sampling interval. In some instances, the device can register the occurrences of the events. In some examples, the device can include one or more motion sensors configured to detect whether the device is in a low-motion state. The device may delay initiating measurements when the device is not in a low-motion state to enhance measurement accuracy. Examples of the disclosure further include resetting the sample procedure based on one or more factors such as the number of non-qualifying measurements. In some examples, the device can be configured to perform both primary and secondary measurements, where the primary measurements can include readings using a set of operating conditions different from the secondary measurements.