Abstract: The present disclosure is directed towards systems and methods for improving analysis of sleep data by classifying users based on sleeper type. In particular, a wearable computing system can obtain a first set of motion sensor data from the motion sensor for a user during a first period. The wearable computing system can determine a sleeper type from a plurality of sleeper types for the user based on the first set of motion sensor data received from the motion sensor. The wearable computing system can select a sleep analysis model from a plurality of sleep analysis models based on the sleeper type determined for the user. The wearable computing system can use the selected sleep analysis model to analyze a second set of motion sensor data from a second period to determine one or more sleep characteristics for the user during the second period.

Abstract: Approaches described herein can capture an audio signal using at least one microphone while a user of an electronic device is determined to be asleep. At least one audio frame can be determined from the audio signal. The at least one audio frame represents a spectrum of frequencies detected by the at least one microphone over some period of time. One or more sounds associated with the at least one audio frame can be determined. Sleep-related information can be generated. The information identifies the one or more sounds as potential sources of sleep disruption.

Abstract: Health information for a woman can be used to predict timing of events related to the woman's menstrual cycle. If available, historical cycle information for a woman can be used to predict upcoming cycle events, such as the start and stop of menstruation. To improve the accuracy of those predictions, one or more health metrics are monitored for the woman that can be correlated with the menstrual cycle. These can include, for example, the resting heart rate (RHR), blood oxygen concentration (SpO2) level, and hemoglobin concentration, among other such options. The metrics are monitored over time to determine patterns that can be correlated with menstrual cycle. This information can then be used to update the predictive model, as well as to update individual event predictions. Information about the predictions, and updates to the predictions, can be surfaced accordingly.

Abstract: A system, computer-readable storage medium, and a method capable of, directly or indirectly, estimating sleep states of a user based on sensor data from movement sensors and/or optical sensors.

Abstract: Physiological variables, metrics, biomarkers, and other data points can be used, in connection with a non-invasive wearable device, to screen for, and predict, mental health issues and cognitive states. In addition to metrics such as heart rate, sleep data, activity level, gamification data, and the like, information such as text message and email data, as well as vocal data obtained through a phone and/or a microphone, may be analyzed, provided user authorization. Applying predictive modeling, one or more of the monitored metrics can be correlated with mental states and disorders. Identified patterns can be used to update the predictive models, such as via machine learning-trained models, as well as to update individual event predictions. Information about the mental state predictions, and updates thereto, can be surfaced to the user accordingly.

Abstract: Approaches described herein can capture an audio signal using at least one microphone while a user of an electronic device is determined to be asleep. At least one audio frame can be determined from the audio signal. The at least one audio frame represents a spectrum of frequencies detected by the at least one microphone over some period of time. One or more sounds associated with the at least one audio frame can be determined. Sleep-related information can be generated. The information identifies the one or more sounds as potential sources of sleep disruption.

Abstract: Approaches to determining a sleep fitness score for a user are provided, such as may be based upon monitored breathing disturbances of a user. The system receives user state data generated over a time period by a combination of sensors provided via a wearable tracker associated with the user. A system can use this information to calculate a sleep fitness score, breathing disturbance score, or other such value. The system can classify every minute within the time period as either normal or atypical, for example, and may provide such information for presentation to the user.

Abstract: Stress information can be determined for a user associated with a wearable device, such as a user wearing a wearable computing device including one or more sensors. At least some of this sensor data can be combined with relevant data provided by a user to calculate a stress score, such as may correspond to a current stress level or stress resilience level of that user. Changes in this stress score can be monitored over time, and appropriate actions taken, such as to provide information or recommendations to the user, or to modify operation of the wearable computing device.

Abstract: Temperature data acquired from a wearable device, for example at a user's wrist or within the device itself, can be used as a proxy to evaluate core body temperature changes. Sensor data may be provided to determine a skin temperature of a user and also an internal device temperature. A correlation between these two temperatures may be used to monitor subsequent temperature changes, which may be indicative of changes in the user's core body temperature. Temperature changes to the proxy temperature may be evaluated against a threshold to determine whether the user's core body temperature has also increased, which may be indicative of one or more physiological symptoms or events. Furthermore, additional physiological variables such as respiration rate, nocturnal heart rate, and heart rate variability may be analyzed for early signs of impending illness. A trained machine learning classifier can output the predicted illness status of an individual based on these parameters.

Abstract: An aspect of the disclosure pertains to a blood pressure measurement device and methods of controlling an inflation rate in a blood pressure measurement. An inflatable bladder of the blood pressure measurement device defines, at least in part, a pressurizable volume. The inflatable bladder may be inflated to pressurize a user's appendage and temporarily occlude blood flow in the user's appendage. A pressure sensor of the blood pressure measurement device is configured to obtain blood pressure measurements, and a pump of the blood pressure measurement device is configured to inflate the inflatable bladder and control an inflation rate by controlling at least one of a duty cycle, a voltage, or a drive frequency.

Abstract: Approaches to determining a sleep fitness score for a user are provided, such as may be based upon monitored breathing disturbances of a user. The system receives user state data generated over a time period by a combination of sensors provided via a wearable tracker associated with the user. A system can use this information to calculate a sleep fitness score, breathing disturbance score, or other such value. The system can classify every minute within the time period as either normal or atypical, for example, and may provide such information for presentation to the user.

Abstract: Sleep tracking systems and techniques for monitoring two or more co-sleepers in a single bed are disclosed. Such systems and techniques may incorporate sleeper identification, as well as various non-user-specific aspects. Some implementations may incorporate user-specific or user-tailored alarm functionality.

Abstract: An aspect of the disclosure pertains to a blood pressure measurement device and methods of controlling an inflation rate in a blood pressure measurement. An inflatable bladder of the blood pressure measurement device defines, at least in part, a pressurizable volume. The inflatable bladder may be inflated to pressurize a user's appendage and temporarily occlude blood flow in the user's appendage. A pressure sensor of the blood pressure measurement device is configured to obtain blood pressure measurements, and a pump of the blood pressure measurement device is configured to inflate the inflatable bladder and control an inflation rate by controlling at least one of a duty cycle, a voltage, or a drive frequency.

Abstract: An aspect of the disclosure pertains to detecting a position of a blood pressure measurement device. An inflatable bladder of the blood pressure measurement device defines, at least in part, a pressurizable volume. The inflatable bladder may be inflated to pressurize a user's appendage and temporarily occlude blood flow in the user's appendage. A pump may initiate inflation of the inflatable bladder when one or more accelerometers and/or one or more proximity sensors determine that the blood pressure measurement device is within sufficient proximity or elevation to a user's heart and stationary.

Abstract: A system, computer-readable storage medium, and a method capable of, directly or indirectly, estimating sleep states of a user based on sensor data from movement sensors and/or optical sensors.

Abstract: Approaches described herein can determine one or more breathing phase patterns over a period of time using audio data captured by at least one microphone. The audio data can include one or more snores. A breathing phase pattern included within the period of time can be determined based at least in part on sensor data captured by one or more sensors in the electronic device. A determination can be made that a first breathing phase pattern represented by the audio data and a second breathing phase pattern represented by the sensor data are correlated. A determination can be made that the first breathing phase pattern represented by the audio data and the second breathing phase pattern represented by the sensor data both correspond to a user wearing the electronic device.

Abstract: An aspect of the disclosure pertains to detecting a position of a blood pressure measurement device. An inflatable bladder of the blood pressure measurement device defines, at least in part, a pressurizable volume. The inflatable bladder may be inflated to pressurize a user's appendage and temporarily occlude blood flow in the user's appendage. A pump may initiate inflation of the inflatable bladder when one or more accelerometers and/or one or more proximity sensors determine that the blood pressure measurement device is within sufficient proximity or elevation to a user's heart and stationary.

Abstract: Approaches described herein can determine one or more breathing phase patterns over a period of time using audio data captured by at least one microphone. The audio data can include one or more snores. A breathing phase pattern included within the period of time can be determined based at least in part on sensor data captured by one or more sensors in the electronic device. A determination can be made that a first breathing phase pattern represented by the audio data and a second breathing phase pattern represented by the sensor data are correlated. A determination can be made that the first breathing phase pattern represented by the audio data and the second breathing phase pattern represented by the sensor data both correspond to a user wearing the electronic device.

Abstract: A system, computer-readable storage medium, and a method capable of, directly or indirectly, estimating sleep states of a user based on sensor data from movement sensors and/or optical sensors.

Abstract: Physiological variables, metrics, biomarkers, and other data points can be used, in connection with a non-invasive wearable device, to screen for, and predict, mental health issues and cognitive states. In addition to metrics such as heart rate, sleep data, activity level, gamification data, and the like, information such as text message and email data, as well as vocal data obtained through a phone and/or a microphone, may be analyzed, provided user authorization. Applying predictive modeling, one or more of the monitored metrics can be correlated with mental states and disorders. Identified patterns can be used to update the predictive models, such as via machine learning-trained models, as well as to update individual event predictions. Information about the mental state predictions, and updates thereto, can be surfaced to the user accordingly.