Abstract: A device implementing a system for providing predicted RGB images includes at least one processor configured to obtain an infrared image of a subject, and to obtain a reference RGB image of the subject. The at least one processor is further configured to provide the infrared image and the reference RGB image to a machine learning model, the machine learning model having been trained to output predicted RGB images of subjects based on infrared images and reference RGB images of the subjects. The at least one processor is further configured to provide a predicted RGB image of the subject based on output by the machine learning model.

Abstract: A device implementing a system for machine-learning based gesture recognition includes at least one processor configured to, receive, from a first sensor of the device, first sensor output of a first type, and receive, from a second sensor of the device, second sensor output of a second type that differs from the first type. The at least one processor is further configured to provide the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted gesture based on sensor output of the first type and sensor output of the second type. The at least one processor is further configured to determine the predicted gesture based on an output from the machine learning model, and to perform, in response to determining the predicted gesture, a predetermined action on the device.

Abstract: A device implementing a system for machine-learning based gesture recognition includes at least one processor configured to, receive, from a first sensor of the device, first sensor output of a first type, and receive, from a second sensor of the device, second sensor output of a second type that differs from the first type. The at least one processor is further configured to provide the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted gesture based on sensor output of the first type and sensor output of the second type. The at least one processor is further configured to determine the predicted gesture based on an output from the machine learning model, and to perform, in response to determining the predicted gesture, a predetermined action on the device.

Abstract: The present disclosure generally relates to navigating user interfaces using hand gestures.

Abstract: Individual health related events (e.g., handwashing events) can be detected based on multiple sensors including motion and audio sensors. Detecting a qualifying handwashing event can include detecting a qualifying scrubbing event based on motion data (e.g., accelerometer data) and a qualifying rinsing event based on audio data. In some examples, power consumption can be reduced by implementing one or more power saving mitigations.

Abstract: Individual health related events (e.g., handwashing events) can be detected based on multiple sensors including motion and audio sensors. Detecting a qualifying handwashing event can include detecting a qualifying scrubbing event based on motion data (e.g., accelerometer data) and a qualifying rinsing event based on audio data. In some examples, power consumption can be reduced by implementing one or more power saving mitigations.

Abstract: Individual health related events (e.g., handwashing events) can be detected based on multiple sensors including motion and audio sensors. Detecting a qualifying handwashing event can include detecting a qualifying scrubbing event based on motion data (e.g., accelerometer data) and a qualifying rinsing event based on audio data. In some examples, power consumption can be reduced by implementing one or more power saving mitigations.

Abstract: A device implementing a system for providing predicted RGB images includes at least one processor configured to obtain an infrared image of a subject, and to obtain a reference RGB image of the subject. The at least one processor is further configured to provide the infrared image and the reference RGB image to a machine learning model, the machine learning model having been trained to output predicted RGB images of subjects based on infrared images and reference RGB images of the subjects. The at least one processor is further configured to provide a predicted RGB image of the subject based on output by the machine learning model.

Abstract: The present disclosure generally relates to navigating user interfaces using hand gestures.

Abstract: A device implementing a system for machine-learning based gesture recognition includes at least one processor configured to, receive, from a first sensor of the device, first sensor output of a first type, and receive, from a second sensor of the device, second sensor output of a second type that differs from the first type. The at least one processor is further configured to provide the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted gesture based on sensor output of the first type and sensor output of the second type. The at least one processor is further configured to determine the predicted gesture based on an output from the machine learning model, and to perform, in response to determining the predicted gesture, a predetermined action on the device.

Abstract: A device implementing a system for machine-learning based gesture recognition includes at least one processor configured to, receive, from a first sensor of the device, first sensor output of a first type, and receive, from a second sensor of the device, second sensor output of a second type that differs from the first type. The at least one processor is further configured to provide the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted gesture based on sensor output of the first type and sensor output of the second type. The at least one processor is further configured to determine the predicted gesture based on an output from the machine learning model, and to perform, in response to determining the predicted gesture, a predetermined action on the device.

Abstract: A device implementing a system for providing predicted RGB images includes at least one processor configured to obtain an infrared image of a subject, and to obtain a reference RGB image of the subject. The at least one processor is further configured to provide the infrared image and the reference RGB image to a machine learning model, the machine learning model having been trained to output predicted RGB images of subjects based on infrared images and reference RGB images of the subjects. The at least one processor is further configured to provide a predicted RGB image of the subject based on output by the machine learning model.

Abstract: A device implementing a system for machine-learning based gesture recognition includes at least one processor configured to, receive, from a first sensor of the device, first sensor output of a first type, and receive, from a second sensor of the device, second sensor output of a second type that differs from the first type. The at least one processor is further configured to provide the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted gesture based on sensor output of the first type and sensor output of the second type. The at least one processor is further configured to determine the predicted gesture based on an output from the machine learning model, and to perform, in response to determining the predicted gesture, a predetermined action on the device.

Abstract: Individual health related events (e.g., handwashing events) can be detected based on multiple sensors including motion and audio sensors. Detecting a qualifying handwashing event can include detecting a qualifying scrubbing event based on motion data (e.g., accelerometer data) and a qualifying rinsing event based on audio data. In some examples, power consumption can be reduced by implementing one or more power saving mitigations.

Abstract: A device implementing a system for providing predicted RGB images includes at least one processor configured to obtain an infrared image of a subject, and to obtain a reference RGB image of the subject. The at least one processor is further configured to provide the infrared image and the reference RGB image to a machine learning model, the machine learning model having been trained to output predicted RGB images of subjects based on infrared images and reference RGB images of the subjects. The at least one processor is further configured to provide a predicted RGB image of the subject based on output by the machine learning model.

Abstract: A solar concentrator module (80) employs a luminescent concentrator material (82) between photovoltaic cells (86) having their charge-carrier separation junctions (90) parallel to front surfaces (88) of photovoltaic material 84 of the photovoltaic cells (86). Intercell areas (78) covered by the luminescent concentrator material (82) occupy from 2 to 50% of the total surface area of the solar concentrator modules (80). The luminescent concentrator material (82) preferably employs quantum dot heterostructures, and the photovoltaic cells (86) preferably employ low-cost high-efficiency photovoltaic materials (84), such as silicon-based photovoltaic materials.

Abstract: A solar concentrator module (80) employs a luminescent concentrator material (82) between photovoltaic cells (86) having their charge-carrier separation junctions (90) parallel to front surfaces (88) of photovoltaic material 84 of the photovoltaic cells (86). Intercell areas (78) covered by the luminescent concentrator material (82) occupy from 2 to 50% of the total surface area of the solar concentrator modules (80). The luminescent concentrator material (82) preferably employs quantum dot heterostructures, and the photovoltaic cells (86) preferably employ low-cost high-efficiency photovoltaic materials (84), such as silicon-based photovoltaic materials.

Abstract: A solar concentrator module (80) employs a luminescent concentrator material (82) between photovoltaic cells (86) having their charge-carrier separation junctions (90) parallel to front surfaces (88) of photovoltaic material 84 of the photovoltaic cells (86). Intercell areas (78) covered by the luminescent concentrator material (82) occupy from 2 to 50% of the total surface area of the solar concentrator modules (80). The luminescent concentrator material (82) preferably employs quantum dot heterostructures, and the photovoltaic cells (86) preferably employ low-cost high-efficiency photovoltaic materials (84), such as silicon-based photovoltaic materials.

Abstract: Photovoltaic cells (22) of different materials may be integrated at the network (20) or panel level to optimize independent and cooperative efficiencies and manufacturing techniques of the different materials. The sizes and numbers of the photovoltaic cells (22) in the separate photovoltaic networks (20) may differ. Separate fabrication of the different photovoltaic networks (20) permits optimization of an interlayer material (110), which can be insulating or noninsulating and can include one or more of light-scattering or light-emitting particles, photonic crystals, metallic materials, an optical grating, or a refractive index grading. For example, adaptations of increased emitter layer thickness, lower sheet resistance, increased gridline spacing, smoother photovoltaic material surface, and/or increased AR coating thickness are made to a multicrystalline silicon photovoltaic cell (20) for optimization as a bottom network (20b) of a tandem solar module.

Abstract: The light conversion efficiency of a solar cell (10) is enhanced by using an optical downshifting layer (30) in cooperation with a photovoltaic material (22). The optical downshifting layer converts photons (50) having wavelengths in a supplemental light absorption spectrum into photons (52) having a wavelength in the primary light absorption spectrum of the photovoltaic material. The cost effectiveness and efficiency of solar cells platforms (20) can be increased by relaxing the range of the primary light absorption spectrum of the photovoltaic material. The optical downshifting layer can be applied as a low cost solution processed film composed of highly absorbing and emissive quantum dot heterostructure nanomaterial embedded in an inert matrix to improve the short wavelength response of the photovoltaic material. The enhanced efficiency provided by the optical downshifting layer permits advantageous modifications to the solar cell platform that enhances its efficiency as well.