Abstract: Various embodiments of the present disclosure provide signal interpretation and data aggregation techniques for generating predictive insights for a user. The techniques may include receiving initial physiological features for a user that are based on recorded sensor values for the user. The techniques include generating activity encodings for the user based on interaction data objects for the user and generating a combined input feature vector by aggregating the initial physiological features and the activity encodings. The techniques include generating, using a machine learning model, a physiological prediction for the user based on the combined input feature vector.

Abstract: The present disclosure generally relates to user interfaces for health applications. In some embodiments, exemplary user interfaces for managing health and safety features on an electronic device are described. In some embodiments, exemplary user interfaces for managing the setup of a health feature on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described. In some embodiments, exemplary user interfaces for managing a biometric measurement taken using an electronic device are described. In some embodiments, exemplary user interfaces for providing results for captured health information on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described.

Abstract: The present disclosure generally relates to user interfaces for health applications. In some embodiments, exemplary user interfaces for managing health and safety features on an electronic device are described. In some embodiments, exemplary user interfaces for managing the setup of a health feature on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described. In some embodiments, exemplary user interfaces for managing a biometric measurement taken using an electronic device are described. In some embodiments, exemplary user interfaces for providing results for captured health information on an electronic device are described. In some embodiments, exemplary user interfaces for managing background health measurements on an electronic device are described.

Abstract: Algorithms for detecting whether a device is properly secured to a user's skin are described. The operation of a device, such as a wearable device, can be adjusted based on whether the device is properly secured to a user's skin (e.g., on-wrist) or not properly secured to the user's skin (e.g., off-wrist). For example, certain functions can be disabled for power-saving, security or other purposes if the device is off-wrist. In order to avoid falsely identifying the device as off-wrist or on-wrist, algorithms for detecting whether the device is on-wrist or off-wrist can calculate one or more variances based on signals measured by a light sensor and compare the one or more variances with one or more thresholds. Comparing the one or more variances to the one or more threshold can improve the accuracy of wrist-detection algorithms.

Abstract: A system and method for reliably counting user steps. Various aspects may, for example, comprise processing a plurality of frequency bands of at least one sensor signal to accurately count user steps. A plurality of filtered sensor signals may be formed by filtering a sensor signal with a plurality of band-pass filters from which a dominant filtered sensor signal may be selected. The selected dominant filtered sensor signal may then be used to count user steps. Further, a frequency band of a sensor signal may be selected such that if it is determined the user is not engaged in a non-stepping activity, user steps may be counted using the content of the signal in the selected frequency band. Still further, user steps may be counted using an identified dominant harmonic.

Abstract: Algorithms for detecting whether a device is properly secured to a user's skin are described. The operation of a device, such as a wearable device, can be adjusted based on whether the device is properly secured to a user's skin (e.g., on-wrist) or not properly secured to the user's skin (e.g., off-wrist). For example, certain functions can be disabled for power-saving, security or other purposes if the device is off-wrist. In order to avoid falsely identifying the device as off-wrist or on-wrist, algorithms for detecting whether the device is on-wrist or off-wrist can calculate one or more variances based on signals measured by a light sensor and compare the one or more variances with one or more thresholds. Comparing the one or more variances to the one or more threshold can improve the accuracy of wrist-detection algorithms.

Abstract: Algorithms for detecting whether a device is properly secured to a user's skin are described. The operation of a device, such as a wearable device, can be adjusted based on whether the device is properly secured to a user's skin (e.g., on-wrist) or not properly secured to the user's skin (e.g., off-wrist). For example, certain functions can be disabled for power-saving, security or other purposes if the device is off-wrist. In order to avoid falsely identifying the device as off-wrist or on-wrist, algorithms for detecting whether the device is on-wrist or off-wrist can calculate one or more variances based on signals measured by a light sensor and compare the one or more variances with one or more thresholds. Comparing the one or more variances to the one or more threshold can improve the accuracy of wrist-detection algorithms.

Abstract: Algorithms for detecting whether a device is properly secured to a user's skin are described. The operation of a device, such as a wearable device, can be adjusted based on whether the device is properly secured to a user's skin (e.g., on-wrist) or not properly secured to the user's skin (e.g., off-wrist). For example, certain functions can be disabled for power-saving, security or other purposes if the device is off-wrist. In order to avoid falsely identifying the device as off-wrist or on-wrist, algorithms for detecting whether the device is on-wrist or off-wrist can calculate one or more variances based on signals measured by a light sensor and compare the one or more variances with one or more thresholds. Comparing the one or more variances to the one or more threshold can improve the accuracy of wrist-detection algorithms.

Abstract: A system and method for efficiently and accurately classifying user activity. In a non-limiting example, accelerometer signals and/or gyroscope sensor signals may be analyzed to classify user activity, for example, that of a user of a handheld and/or wearable device. Information from additional sources and sensors (e.g., other inertial sensors, non-inertial sensors, passive sensors, etc.) may also be utilized.

Abstract: Techniques associated with a combination speaker and light source responsive to states of an environment based on sensor data are described, including a housing, a light source disposed within the housing and configured to be powered using a light socket connector coupled to the housing, a speaker coupled to the housing and configured to output audio, and a sensor device comprising a light and speaker controller, the sensor device configured to determine an environmental state and to generate environmental state data associated with the environmental state, the light and speaker controller configured to send a control signal to one or both of the light source and the speaker.

Abstract: Embodiments relate generally to electrical and electronic hardware, computer software, wired and wireless network communications, and wearable computing devices in capturing and deriving physiological characteristic data. More specifically, disclosed are one or more electrodes and methods to determine physiological characteristics using a wearable device (or carried device) and one or more sensors that can be subject to motion. In one embodiment, a method includes receiving a sensor signal during one or more portions of a time interval in which the wearable device is in motion, and receiving a motion sensor signal. The method includes decomposing at a processor the sensor signal to determine physiological signal components. An analysis of the physiological signal components can yield a physiological characteristic, whereby a physiological characteristic signal that includes data representing the physiological characteristic can be generated during at least one of the one or more portions of the time interval.

Abstract: Embodiments of the invention relate generally to electrical and electronic hardware, computer software, wired and wireless network communications, and wearable computing devices for facilitating health and wellness-related information. More specifically, disclosed are electrodes and methods to determine physiological states using a wearable device (or carried device) and one or more sensors that can be subject to motion. In one embodiment, a method includes receiving a sensor signal including data representing physiological characteristics in a wearable device from a distal end of a limb and a motion sensor signal. The method includes decomposing at a processor the sensor signal to determine physiological signal components. A physiological characteristic signal is generated that includes data representing a physiological characteristic, which can form a basis to determine a physiological state based on, for example, bioimpedance signals originating from the distal end of the limb.

Abstract: Techniques associated with a combination speaker and light source (“speaker-light device”) responsive to states of an organism based on sensor data are described, including generating chemical sensor data in response to one or more chemicals sensed by one or more chemical sensors in the same or different speaker-light devices. A scent generator may be activated to counter an odor caused by a chemical detected by the chemical sensor(s). The speaker-light device may activate an air mover operative to circulate ambient air over the chemical sensor. The speaker-light device may take an appropriate action in response to detected chemicals that affect states of the organism. Some or all of the actions taken may be taken by other devices in communication with the speaker-light device(s). An action may include generating and presenting a path or route to be taken by a user to an area of safety or reduced chemical concentration.

Abstract: Techniques associated with a combination speaker and light source responsive to states of an organism based on sensor data are described, including receiving state data from a wearable device configured to generate the state data using sensor data, generating light data using the state data, generating audio data using the state data, providing the light data and the audio data to a controller configured to generate one or more control signals using the light data and the audio data, the one or more control signals configured to adjust a light source and a speaker, the light source and the speaker implemented in a combination speaker and light source device.

Abstract: Techniques associated with a combination speaker and light source powered using a light socket are described, including a housing comprising a plate coupled to a substantially hemispherical enclosure, a platform configured to couple a light source to a terminal configured to receive a light control signal, the light control signal configured to modify a light characteristic, a speaker coupled to the housing and configured to project audio in a direction, a light socket connector coupled to the housing and configured to provide power to the speaker and the light source when the light socket connector is coupled with a light socket, an acoustic sensor disposed on a surface of the housing, and a light sensor located within the housing, the light sensor facing away from the light source.

Abstract: Techniques associated with a combination speaker and light source (“speaker-light device”) responsive to states of an organism based on sensor data are described, including generating motion sensor data in response to a movement captured using a motion sensor, deriving movement data using a motion analysis module configured to determine the movement to be associated with one or more of a gesture, an identity, and an activity, using the motion sensor data, generating acoustic sensor data in response to sound captured using an acoustic sensor, deriving audio data using a noise removal module configured to subtract a noise signal from the acoustic sensor data, detecting a radio frequency signal using a communication facility, the radio frequency being associated with a personal device, obtaining state data from the personal device, and determining a desired light characteristic using the state data and one or both of the movement data and the audio data.