Abstract: Systems and techniques are described for robust radar-based gesture-recognition. A radar system detects radar-based gestures on behalf of application subscribers. A state machine transitions between multiple states based on inertial sensor data. A no-gating state enables the radar system to output radar-based gestures to application subscribers. The state machine also includes a soft-gating state that prevents the radar system from outputting the radar-based gestures to the application subscribers. A hard-gating state prevents the radar system from detecting radar-based gestures altogether. The techniques and systems enable the radar system to determine when not to perform gesture-recognition, enabling user equipment to automatically reconfigure the radar system to meet user demand. By so doing, the techniques conserve power, improve accuracy, or reduce latency relative to many common techniques and systems for radar-based gesture-recognition.

Abstract: The disclosure provides BMDs that have multiple device modes depending on operational conditions of the devices, e.g., motion intensity, device placement, and/or activity type. The device modes are associated with various data processing algorithms. In some embodiments, the BMD is implemented as a wrist-worn or arm-worn device. In some embodiments, methods for tracking physiological metrics using the BMDs are provided. In some embodiments, the process or the BMD applies a time domain analysis on data provided by a sensor of the BMD for a first activity, and applies a frequency domain analysis on the data for a second activity, which contributes to improved accuracy and speed of biometric data.

Abstract: Systems and techniques are described for robust radar-based gesture-recognition. A radar system detects radar-based gestures on behalf of application subscribers. A state machine transitions between multiple states based on inertial sensor data. A no-gating state enables the radar system to output radar-based gestures to application subscribers. The state machine also includes a soft-gating state that prevents the radar system from outputting the radar-based gestures to the application subscribers. A hard-gating state prevents the radar system from detecting radar-based gestures altogether. The techniques and systems enable the radar system to determine when not to perform gesture-recognition, enabling user equipment to automatically reconfigure the radar system to meet user demand. By so doing, the techniques conserve power, improve accuracy, or reduce latency relative to many common techniques and systems for radar-based gesture-recognition.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for distribution-based machine learning. In some implementations, a method for distribution-based machine learning includes obtaining fish images from a camera device; generating predicted values using a machine learning model and one or more of the fish images; comparing the predicted values to distribution data representing features of multiple fish; and updating one or more parameters of the machine learning model based on the comparison.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that automate selection of configuration data. One of the methods includes obtaining meal configuration data relating to feeding livestock in an aquaculture environment that includes one or more feeding parameters relating to feeding farmed livestock and one or more criteria. Each of the one or more criteria can be associated with the one or more feeding parameters. Sensor data can be obtained that describes at least one property of the aquaculture environment. A selected set of feeding parameters can be selected using the obtained sensor data and the obtained feeding parameters. The selected set of feeding parameters can be provided to a feeding control subsystem.

Abstract: This document describes techniques and systems for radar-based gesture-recognition with context-sensitive gating and other context-sensitive controls. Sensor data from a proximity sensor and/or a movement sensor produces a context of a user equipment. The techniques and systems enable the user equipment to recognize contexts when a radar system can be unreliable and should not be used for gesture-recognition, enabling the user equipment to automatically disable or “gate” the output from the radar system according to context. The user equipment prevents the radar system from transitioning to a high-power state to perform gesture-recognition in contexts where radar data detected by the radar system is likely due to unintentional input. By so doing, the techniques conserve power, improve accuracy, or reduce latency relative to many common techniques and systems for radar-based gesture-recognition.

Abstract: This document describes techniques and systems for radar-based gesture-recognition with context-sensitive gating and other context-sensitive controls. Sensor data from a proximity sensor (108) and/or a movement sensor (108) produces a context of a user equipment (102). The techniques and systems enable the user equipment (102) to recognize contexts when a radar system (104) can be unreliable and should not be used for gesture-recognition, enabling the user equipment (102) to automatically disable or “gate” the output from the radar system (104) according to context. The user equipment (102) prevents the radar system (104) from transitioning to a high-power state (1910) to perform gesture-recognition in contexts where radar data detected by the radar system (104) is likely due to unintentional input. By so doing, the techniques conserve power, improve accuracy, or reduce latency relative to many common techniques and systems for radar-based gesture-recognition.

Abstract: Systems and techniques are described for robust radar-based gesture-recognition. A radar system detects radar-based gestures on behalf of application subscribers. A state machine transitions between multiple states based on inertial sensor data. A no-gating state enables the radar system to output radar-based gestures to application subscribers. The state machine also includes a soft-gating state that prevents the radar system from outputting the radar-based gestures to the application subscribers. A hard-gating state prevents the radar system from detecting radar-based gestures altogether. The techniques and systems enable the radar system to determine when not to perform gesture-recognition, enabling user equipment to automatically reconfigure the radar system to meet user demand. By so doing, the techniques conserve power, improve accuracy, or reduce latency relative to many common techniques and systems for radar-based gesture-recognition.

Abstract: Systems and techniques are described for robust radar-based gesture-recognition. A radar system (104) detects radar-based gestures on behalf of application subscribers. A state machine (2000) transitions between multiple states based on inertial sensor data. A no-gating state (2002) enables the radar system (104) to output radar-based gestures to application subscribers. The state machine (2000) also includes a soft-gating state (2004) that prevents the radar system (104) from outputting the radar-based gestures to the application subscribers. A hard-gating state (2006) prevents the radar system (104) from detecting radar-based gestures altogether. The techniques and systems enable the radar system (104) to determine when not to perform gesture-recognition, enabling user equipment (102) to automatically reconfigure the radar system (104) to meet user demand.

Abstract: Some embodiments provide a wearable monitoring device including a motion sensor and a photo (PPG) sensor. The PPG sensor includes (i) a periodic light source, (ii) a photo detector, and (iii) circuitry determining a user's heart rate from an output of the photo detector. Some embodiments provide methods for operating a heart rate monitor of a wearable monitoring device to measure one or more characteristics of a heartbeat waveform. Some embodiments provide methods for operating the wearable monitoring device in a low power state when the device determines that the device is not worn by a user.

Abstract: This document describes techniques and systems for radar-based gesture-recognition with context-sensitive gating and other context-sensitive controls. Sensor data from a proximity sensor (108) and/or a movement sensor (108) produces a context of a user equipment (102). The techniques and systems enable the user equipment (102) to recognize contexts when a radar system (104) can be unreliable and should not be used for gesture-recognition, enabling the user equipment (102) to automatically disable or “gate” the output from the radar system (104) according to context. The user equipment (102) prevents the radar system (104) from transitioning to a high-power state (1910) to perform gesture-recognition in contexts where radar data detected by the radar system (104) is likely due to unintentional input. By so doing, the techniques conserve power, improve accuracy, or reduce latency relative to many common techniques and systems for radar-based gesture-recognition.

Abstract: Some embodiments provide a wearable monitoring device including a motion sensor and a photo (PPG) sensor. The PPG sensor includes (i) a periodic light source, (ii) a photo detector, and (iii) circuitry determining a user's heart rate from an output of the photo detector. Some embodiments provide methods for operating a heart rate monitor of a wearable monitoring device to measure one or more characteristics of a heartbeat waveform. Some embodiments provide methods for operating the wearable monitoring device in a low power state when the device determines that the device is not worn by a user.

Abstract: Methods, devices, and computer programs are presented for consolidating overlapping data provided by multiple sources. One method includes operations for associating a plurality of devices to a user, each device operable to capture data associated with the user, and for receiving, from the plurality of devices, captured data about a first activity associated with a first period of time. Additionally, the method includes operations for detecting that the received captured data from two or more devices provide overlapping information about the first activity, and for evaluating one or more rules for consolidating the overlapping information to produce consolidated data. The consolidated data provides a unified view of the first activity during the first period of time. The consolidated data is stored in permanent storage and made available for presentation to the user.

Abstract: Systems and techniques are described for robust radar-based gesture-recognition. A radar system (104) detects radar-based gestures on behalf of application subscribers. A state machine (2000) transitions between multiple states based on inertial sensor data. A no-gating state (2002) enables the radar system (104) to output radar-based gestures to application subscribers. The state machine (2000) also includes a soft-gating state (2004) that prevents the radar system (104) from outputting the radar-based gestures to the application subscribers. A hard-gating state (2006) prevents the radar system (104) from detecting radar-based gestures altogether. The techniques and systems enable the radar system (104) to determine when not to perform gesture-recognition, enabling user equipment (102) to automatically reconfigure the radar system (104) to meet user demand.

Abstract: The disclosure provides BMDs that have multiple device modes depending on operational conditions of the devices, e.g., motion intensity, device placement, and/or activity type. The device modes are associated with various data processing algorithms. In some embodiments, the BMD is implemented as a wrist-worn or arm-worn device. In some embodiments, methods for tracking physiological metrics using the BMDs are provided. In some embodiments, the process or the BMD applies a time domain analysis on data provided by a sensor of the BMD for a first activity, and applies a frequency domain analysis on the data for a second activity, which contributes to improved accuracy and speed of biometric data.

Abstract: The disclosure provides BMDs that have multiple device modes depending on operational conditions of the devices, e.g., motion intensity, device placement, and/or activity type. The device modes are associated with various data processing algorithms. In some embodiments, the BMD is implemented as a wrist-worn or arm-worn device. In some embodiments, methods for tracking physiological metrics using the BMDs are provided. In some embodiments, the process or the BMD applies a time domain analysis on data provided by a sensor of the BMD when the data has a high signal (e.g., high signal-to-noise ratio), and applies a frequency domain analysis on the data when the data has a low signal, which contributes to improved accuracy and speed of biometric data.

Abstract: Biometric monitoring devices, including various technologies that may be implemented in such devices, are discussed herein. Additionally, techniques for utilizing gyroscopes in biometric monitoring devices are provided. Such techniques may, in some implementations, involve obtaining swimming metrics regarding stroke cycle count, lap count, and stroke type. Such techniques may also, in some implementations, involve obtaining performance metrics for bicycling activities.

Abstract: Some embodiments provide a wearable monitoring device including a motion sensor and a photo (PPG) sensor. The PPG sensor includes (i) a periodic light source, (ii) a photo detector, and (iii) circuitry determining a user's heart rate from an output of the photo detector. Some embodiments provide methods for operating a heart rate monitor of a wearable monitoring device to measure one or more characteristics of a heartbeat waveform. Some embodiments provide methods for operating the wearable monitoring device in a low power state when the device determines that the device is not worn by a user.

Abstract: The disclosure provides BMDs that have multiple device modes depending on operational conditions of the devices, e.g., motion intensity, device placement, and/or activity type, the device modes are associated with various data processing algorithms. In some embodiments, the BMD is implemented as a wrist-worn or arm-worn device. In some embodiments, methods for tracking physiological metrics using the BMDs are provided. In some embodiments, the process and the BMD applies a time domain analysis on data provided by a sensor of the BMD when the data has a high signal (e.g., high signal-to-noise ratio), and applies a frequency domain analysis on the data when the data has a low signal, which contributes to improved accuracy and speed of biometric data.

Abstract: The disclosure provides BMDs that have multiple device modes depending on operational conditions of the devices, e.g., motion intensity, device placement, and/or activity type, the device modes are associated with various data processing algorithms. In some embodiments, the BMD is implemented as a wrist-worn or arm-worn device. In some embodiments, methods for tracking physiological metrics using the BMDs are provided. In some embodiments, the process and the BMD applies a time domain analysis on data provided by a sensor of the BMD when the data has a high signal (e.g., high signal-to-noise ratio), and applies a frequency domain analysis on the data when the data has a low signal, which contributes to improved accuracy and speed of biometric data.