Abstract: In an example method, a mobile device obtains a signal indicating an acceleration measured by a sensor over a time period. The mobile device determines an impact experienced by the user based on the signal. The mobile device also determines, based on the signal, one or more first motion characteristics of the user during a time prior to the impact, and one or more second motion characteristics of the user during a time after the impact. The mobile device determines that the user has fallen based on the impact, the one or more first motion characteristics of the user, and the one or more second motion characteristics of the user, and in response, generates a notification indicating that the user has fallen.

Abstract: One or more electronic device may use motion and/or activity sensors to estimate a user's 6 minute walking distance. In particular, because users typically walk at less than their maximum output and in imperfect conditions, control circuitry within the device(s) may rely on walks of shorter distances to estimate the 6 minute walking distance. For example, the control circuitry may gather activity information for the user, such as heart rate, calories burned, and step count, and analyze a distance component and a speed component for periods in which the user has walked. Individual 6 minute walk distance estimates may be generated based on each of the activity information, distance component, and speed component. The distance and speed estimates may be corrected for walking behaviors that deviate from an ideal testing environment, and may then be fused with the activity estimate to generate a final 6 minute walk distance estimate.

Abstract: In an example method, a mobile device obtains sample data generated by one or more sensors over a period of time, where the one or more sensors are worn by a user. The mobile device determines that the user has fallen based on the sample data, and determines, based on the sample data, a severity of an injury suffered by the user. The mobile device generates one or more notifications based on the determination that the user has fallen and the determined severity of the injury.

Abstract: Disclosed embodiments include wearable devices and techniques for detecting cardio machine activities, estimating user direction of travel, and monitoring performance during cardio machine activities. By accurately and promptly detecting cardio machine activities and automatically distinguishing between activities performed on different types of cardio machines, the disclosure enables wearable devices to accurately calculate user performance information when users forget to start and/or stop recording activities on a wide variety of cardio machines. In various embodiments, cardio machine activity detection techniques may use magnetic field data from a magnetic field sensor to improve the accuracy of orientation data and device heading measurements used to detect the end of a cardio machine activity.

Abstract: In an embodiment, a method comprises: establishing, by a wireless wearable computer worn by a user, a wireless communication connection with a fitness machine; obtaining machine data from the fitness machine while the user is engaged in a workout session on the fitness machine; obtaining, from a heart rate sensor of the wireless device, heart rate data of the user; determining a calibrated maximal oxygen consumption of the user based on the heart rate data and the machine data; determining a heart rate caloric expenditure based on the heart rate data and the calibrated maximal oxygen consumption of the user; and providing information corresponding to the heart rate caloric expenditure for presentation.

Abstract: Embodiments are disclosed for crash detection on one or more mobile devices (e.g., smartwatch and/or smartphone). In some embodiments, a method comprises: detecting, with at least one processor, a crash event on a crash device; extracting, with the at least one processor, multimodal features from sensor data generated by multiple sensing modalities of the crash device; computing, with the at least one processor, a plurality of crash decisions based on a plurality of machine learning models applied to the multimodal features; and determining, with the at least one processor, that a severe vehicle crash has occurred involving the crash device based on the plurality of crash decisions and a severity model.

Abstract: The present disclosure relates to methods and systems of determining swimming metrics of a user during a swimming session. The method can include receiving, by a processor circuit of a user device, motion information from one or more motion sensors of the user device; determining, by the processor circuit using the motion information, a first set of rotational data of the user device, wherein the first set of rotational data is expressed in a first frame of reference; converting, by the processor circuit, the first set of rotational data into a second set of rotational data, wherein the second set of rotational data is expressed in a second frame of reference; determining, by the processor circuit, one or more swimming metrics of the user; and outputting the one or more swimming metrics.

Abstract: In one implementation, a method is performed for tiered posture awareness. The method includes: while presenting a three-dimensional (3D) environment, via the display device, obtaining head pose information for a user associated with the computing system; determining an accumulated strain value for the user based on the head pose information; and in accordance with a determination that the accumulated strain value for the user exceeds a first posture awareness threshold: determining a location for virtual content based on a height value associated with the user and a depth value associated with the 3D environment; and presenting, via the display device, the virtual content at the determined location while continuing to present the 3D environment via the display device.

Abstract: In an embodiment, a method comprises: establishing, by a wireless wearable computer worn by a user, a wireless communication connection with a fitness machine; obtaining machine data from the fitness machine while the user is engaged in a workout session on the fitness machine; obtaining, from a heart rate sensor of the wireless device, heart rate data of the user; determining a work rate caloric expenditure by applying a work rate calorie model to the machine data; determining a calibrated maximal oxygen consumption of the user based on the heart rate data and the work rate caloric expenditure; determining a heart rate caloric expenditure by applying a heart rate calorie model to the heart rate data and the calibrated maximal oxygen consumption of the user; and sending to the fitness machine via the communication connection, at least one of the work rate caloric expenditure or the heart rate caloric expenditure.

Abstract: In an example method, a mobile device obtains a signal indicating an acceleration measured by a sensor over a time period. The mobile device determines an impact experienced by the user based on the signal. The mobile device also determines, based on the signal, one or more first motion characteristics of the user during a time prior to the impact, and one or more second motion characteristics of the user during a time after the impact. The mobile device determines that the user has fallen based on the impact, the one or more first motion characteristics of the user, and the one or more second motion characteristics of the user, and in response, generates a notification indicating that the user has fallen.

Abstract: Enclosed are embodiments for estimating gait time events and GCT using a wrist-worn device. In some embodiments, a method comprises: obtaining, with at least one processor of a wrist-worn device, sensor data indicative of acceleration and rotation rate; and predicting, with the at least one processor, at least one gait event time based on a machine learning (ML) model with the acceleration and rotation rate as input to the ML model.

Abstract: Enclosed are embodiments for estimating vertical oscillation (VO) at the wrist. In some embodiments, a method comprises: obtaining, with a wearable device worn on a wrist of a user, sensor data indicative of the user's acceleration and rotation rate; estimating centripetal acceleration based on the user's acceleration and rotation rate; calculating a modified user's acceleration by subtracting the estimated centripetal acceleration from the user's acceleration; estimating center of mass (CoM) acceleration by decoupling an arm swing component of the user's acceleration from the modified user's acceleration; and computing vertical oscillation of the user's CoM using a machine learning model with at least the CoM acceleration as input to the machine learning model, or by integrating vertical acceleration derived from the CoM acceleration and a gravity vector.

Abstract: Embodiments are disclosed for stride length estimation and calibration at the wrist. In some embodiments, a method comprises: obtaining sensor data from a wearable device worn on a wrist of a user; deriving features from the sensor data; estimating a form-based stride length using an estimation model that takes the features and user height as input; and calibrating the form-based stride length. In other embodiments, user cadence and speed are used to estimate speed-based stride length which, upon certain conditions, is blended with the form-based stride length to get a final estimated stride length of the user.

Abstract: Embodiments are disclosed for identifying poor cardio metabolic health using sensors of wearable devices. In an embodiment, a method comprises: obtaining estimates of maximal oxygen consumption of a user during exercise; determining at least one confidence weight based on context data; adjusting the maximal oxygen consumption estimates using the at least one confidence weight; aggregating the adjusted maximal oxygen consumption estimates to generate a summary maximal oxygen consumption estimate and corresponding confidence interval for the user; and classifying cardiorespiratory fitness of the user based on at least one of the summary maximum consumption estimate, the corresponding confidence interval, a population error model or a low cardiorespiratory fitness threshold.

Abstract: Ear buds may have optical proximity sensors and accelerometers. Control circuitry may analyze output from the optical proximity sensors and the accelerometers to identify a current operational state for the ear buds. The control circuitry may also analyze the accelerometer output to identify tap input such as double taps made by a user on ear bud housings. Samples in the accelerometer output may be analyzed to determine whether the samples associated with a tap have been clipped. If the samples have been clipped, a curve may be fit to the samples. Optical sensor data may be analyzed in conjunction with potential tap input data from the accelerometer. If the optical sensor data is ordered, a tap input may be confirmed. If the optical sensor data is disordered, the control circuitry can conclude that accelerometer data corresponds to false tap input associated with unintentional contact with the housing.

Abstract: Embodiments are disclosed for estimating caloric expenditure using a heart rate model specific to a motion class. In an embodiment, a method comprises: obtaining acceleration and rotation rate from motion sensors of a wearable device; determining a vertical component of inertial acceleration and a vertical component of rotational acceleration from the acceleration and rotation rate, respectively; determining a magnitude of the rotation rate; determining a correlation between the inertial vertical acceleration component and rotational acceleration; determining a percentage of motion outside a dominant plane of motion; predicting a motion class based on a motion classification model that takes as input the motions, correlation and percentage; determining a likelihood the user is walking; in accordance with determining that the user is likely not walking, configuring a heart rate model based on the predicted motion class; and estimating, using the configured heart rate model, a caloric expenditure of the user.

Abstract: In an example method, a mobile device obtains sample data generated by one or more sensors over a period of time, where the one or more sensors are worn by a user. The mobile device determines that the user has fallen based on the sample data, and determines, based on the sample data, a severity of an injury suffered by the user. The mobile device generates one or more notifications based on the determination that the user has fallen and the determined severity of the injury.

Abstract: In an example method, a mobile device obtains sample data generated by one or more sensors over a period of time, where the one or more sensors are worn by a user. The mobile device determines that the user has fallen based on the sample data, and determines, based on the sample data, a severity of an injury suffered by the user. The mobile device generates one or more notifications based on the determination that the user has fallen and the determined severity of the injury.

Abstract: In an example method, a mobile device obtains sample data generated by one or more sensors over a period of time, where the one or more sensors are worn by a user. The mobile device determines that the user has fallen based on the sample data, and determines, based on the sample data, a severity of an injury suffered by the user. The mobile device generates one or more notifications based on the determination that the user has fallen and the determined severity of the injury.

Abstract: Systems and methods of analyzing a user's motion during a swimming session are described. One or more motions sensors can collect motion data of the user. A processor circuit can make motion analysis based on the motion data. The processor circuit can determine if the user's arm swing is a genuine swim stroke. The processor circuit can also determine whether the user is swimming or turning. The processor circuit can also classify the user's swim stroke style. The processor circuit can also determine the user's swim stroke phase. The processor circuit can also determine the user's stroke orbit consistency.