Abstract:
Methods, systems, computer-readable media, and apparatuses for assessing a fitness state of a user via a mobile device are presented. In some implementations, a first physiological measurement of the user during a first level of a physical activity is obtained via one or more sensors. A second physiological measurement during a second level of the physical activity is obtained via the one or more sensors. A transient physiological measurement based on the first physiological measurement and the second physiological measurement is determined. The physical activity is classified based on one or more motion measurements obtained via the one or more sensors. A fitness profile indicative of a fitness state of the user is generated based at least in part on the determined transient physiological measurement and the classified physical activity.
Abstract:
Disclosed is an apparatus and method for automatically configuring a mobile device for collecting and inferring heart rate data of a user. The method may include capturing heart rate data for a user with a heart rate sensor that is coupled with a mobile device. The method may also include monitoring a activity state of the user from activity data captured by the mobile device, and detecting a constant activity state of the user. The method may also include inferring heart rate data for the user from the captured heart rate data during a period in which the user remains in the constant activity state. The method may also include providing the inferred heart rate data, as captured heart rate data, to a heart rate calculator during the period in which the user remains in the constant activity state.
Abstract:
A method performed by an electronic device is described. The method includes receiving a set of image frames. The set of image frames includes a face. The method also includes determining at least one facial motion of the face based on the set of image frames. The method further includes determining, based on the at least one facial motion, a facial rigidity confidence value indicating a degree of confidence that the face is rigid. The method additionally includes determining at least one facial micro-motion of the face based on the set of image frames. The method also includes determining a micro-motion matching confidence value indicating a degree of matching between the at least one facial micro-motion and a micro-motion profile. The method further includes authenticating a user based on the facial rigidity confidence value and the micro-motion matching confidence value.
Abstract:
Embodiments provide methods of protecting computing devices from malicious activity. A processor of a networking device may monitor network traffic flows of network computing devices and identify applications that are a source of the first network traffic flow. The processor may observe network traffic flows of identified source applications over time to determine normal network traffic flows of the source applications. The processor may then observe network traffic flows to detect when a source application is behaving anomalously based on associated network traffic flow characteristics deviating from normal network traffic flows of the source applications.
Abstract:
Embodiments provide methods of protecting computing devices from malicious activity. A processor of a network device may receive a first network traffic flow of a monitoring computing device and a malicious activity tag identifying a malicious behavior of the first network traffic flow. The processor may determine a characteristic of the first network traffic flow based at least in part on information in the first network traffic flow and the malicious activity tag. The processor may receive a second network traffic flow from a non-monitoring computing device, and may associate the malicious activity tag and the second network traffic flow based on a characteristic of the second network traffic flow based at least in part on information in the second network traffic flow and the characteristic of the first network traffic flow.
Abstract:
Disclosed is an apparatus and method for automatically configuring a mobile device for collecting and inferring heart rate data of a user. The method may include capturing heart rate data for a user with a heart rate sensor that is coupled with a mobile device. The method may also include monitoring a activity state of the user from activity data captured by the mobile device, and detecting a constant activity state of the user. The method may also include inferring heart rate data for the user from the captured heart rate data during a period in which the user remains in the constant activity state. The method may also include providing the inferred heart rate data, as captured heart rate data, to a heart rate calculator during the period in which the user remains in the constant activity state.
Abstract:
Disclosed embodiments pertain to the measurement of heart rate in the presence of motion and noise. Spectral peaks in measurements by an optical sensor are compared with spectral peaks obtained from a motion sensor signal measurements, to obtain a fundamental frequency in the optical sensor signal, where the fundamental frequency is associated with a user's heart rate. A first heart rate may be estimated based on the fundamental frequency. A variety of quality metrics may be determined for the first heart rate estimate. A second estimated heart rate may be determined based by processing a frequency domain representation of the optical sensor signal based on a frequency domain representation of the motion sensor signal. One or more of the previously determined quality metrics may be dynamically adjusted based on a comparison of first and second estimated heart rates.
Abstract:
Methods, systems, computer-readable media, and apparatuses for estimating a user's heart rate using a PG signal are presented. In some implementations, the heart rate is estimated by computing a frequency-domain PG, identifying one or more features in the frequency-domain PG, selecting qualified features from the one or more features, and constructing one or more traces. In some implementations, an accelerometer signal can be used for motion cancellation to eliminate traces that are motion artifacts.