Abstract: A method and apparatus of determining health risk for a user are described. The method includes obtaining heart rate values and motion information indicative of motion of the user recorded over a monitoring period, wherein the heart rate values are obtained according to a variable sampling rate selected based on a comparison of at least one previous heart beat measurement to a heart rate range determined as a difference between a maximum heart rate of the user and a resting heart rate of the user; determining an expected heart rate level based on the motion information; determining, for the user over the monitoring period, an aggregate heartbeat value by weighting the heart rate values based on both the motion information and a comparison of the heart rate values with the expected heart rate level; and determining a health-predictive activity score based on the aggregate heartbeat value for the user.

Abstract: A wearable device includes a processor and a lower module. The lower module includes a pressure sensor for detecting a mechanical movement of a skin that covers an artery. The mechanical movement of the skin is due to blood flow through the artery. The processor is configured to receive skin movement information from the movement sensor; calculate a pulse front velocity (PFV), which is a velocity of a blood wave as the blood wave passes under the pressure sensor; estimate a pulse wave velocity (PWV) using the PFV; and estimate the blood pressure using the PWV.

Abstract: Examples described herein include systems and methods for determining sleep characteristics based on movement data. In one example, a device including at least one accelerometer can be worn by a user during the night. The accelerometer can be configured to detect small motions of the user and provide an output signal. The output signal can be filtered and used to determine whether the user was sleeping during a particular timeframe. The output signal can also be used to determine a sleep characteristic of the sleep, such as light sleep, deep sleep, REM sleep, obstructive apnea, or central apnea.

Abstract: Described herein are systems and methods for collecting physiological information from a user and determining information including, but not limited to, a user's heart rate, blood pressure, oxygen levels (SvO2), hydration, respiration rate, and heart rate variability. Physiological information is collected from one or more modules, each comprising a sensor array. The sensor array(s) can comprise, among other things, light sources, photo detectors, ECG electrodes/sensors, bio impedance sensors, galvanic skin response sensors, tonometry/contact sensors, accelerometers, pressure sensors, acoustic sensors, and electromagnetic sensors. The information collected from a user can be used to cross-reference a database comprising similar information for a number of subjects as well as verified measurements for each subject including, but not limited to, blood pressure, oxygen levels (SvO2), hydration, respiration rate, and heart rate variability.

Abstract: A system can include a wearable device that obtains real-time physiological data and activity data from a user and transmits that data to another device. A computing device can receive HRV and activity data and determine whether the user's autonomic nervous system is in a predominantly sympathetic or parasympathetic state. For example, the determination can include comparing an average variance in a portion of the HRV data with a threshold value. In response to determining that the user's autonomic nervous system is in a sympathetic state, the device can perform an action.

Abstract: Described herein are systems, devices, and methods for determining a user's stride length and monitoring various aspects of the user's activities. An apparatus worn or carried by the user may determine and track when a user takes a step and, based at least in part on user-specific information, determine an estimated stride length of the user associated with a respective step rate or step rate range. The apparatus may further monitor the physical location, speed, or pace of the user during an activity and, in conjunction with step count information, determine a verified stride length for the user associated with a respective step rate or step rate range. The estimated and verified stride length determinations may be stored and used to determine one or more aspects of a user's subsequent activities, including but not limited to pace, speed, and calorie expenditure information, even when physical location information is unavailable.

Abstract: Embodiments disclosed provide a solution to detect a rally in a sports game. One or more stroke actions or non-stroke actions are detected based on motion data detected by a sensor attached to a sports instrument of a user. Using a trained stroke classification model, each detected stroke action is classified into a plurality of classes. Additionally, a determination is made whether each detected non-stroke action is an intentional special user action. The determination whether a non-stroke action is an intentional special user action is made based on a customized set of definitions defining one or more special user actions. One or more rallies are then detected based on the classified stroke actions and intentional special user actions.

Abstract: A solution is provided for detecting in real time video highlights in a sports video at a mobile computing device. A highlight detection module of the mobile computing device extracts visual features from each video frame of the sports video using a trained feature model and detects a highlight in the video frame based on the extracted visual features of the video frame using a trained detection model. The feature model and detection model are trained with a convolutional neural network on a large corpus of videos to generate category level and pair-wise frame feature vectors. Based on the detection, the highlight detection module generates a highlight score for each video frame of the sports video and presents the highlight scores to users of the computing device. The feature model and detection model are dynamically updated based on the real time highlight detection data collected by the mobile computing device.

Abstract: Systems and methods are provided for detecting and preventing sleep onset in a user. The method can include, for example, monitoring the user's heart rate, establishing a baseline average heart rate over a period of time, establishing a threshold heart rate that is less than the baseline average heart rate, detecting a drop in the user's heart rate below the threshold, and in response to detecting the drop, initiating a sleep prevention program.

Abstract: Described herein are systems and methods for mounting optical sensors in physiological monitoring devices worn by a user to sense, measure, and/or display physiological information. Optical sensors may be mounted in the rear face of the device, emit light proximate a targeted area of a user's body, and detect light reflected from the targeted area. The optical sensor may be mounted in a housing or caseback such that at least a portion of the optical sensor protrudes a distance from at least a portion of the housing. The protrusion distance may be adjustable such that a user may achieve a customized fit of the wearable device. Adjustment of the protrusion distance may also result in a customized level of contact and/or pressure between the optical sensor and the targeted area which may, in turn, result in more reliable and accurate sensing of physiological information.

Abstract: Described herein are systems and methods for improving the reliability and accuracy of wearable physiological monitoring devices. A wearable monitoring device may comprise an inner surface configured for at least partial contact with a targeted tissue region of a person. The inner surface may comprise one or more outwardly projecting raised regions. The monitoring device may further comprise a physiological sensor, one or more components of which may be located at or near a raised region of the inner surface. In this manner, sufficient contact between the targeted tissue region and the inner surface, as well as proper placement of the one or more components of the sensor relative to the targeted tissue region, may be achieved. The accuracy and reliability of the monitoring device may also be less susceptible to the effects of ambient light and/or the movements of the user.