Abstract: For generating a breathing alert is disclosed, a method receives a video stream of a subject. The method further estimates a breathing signal from the video stream. The method determines one of a large-scale motion and/or a breathing event of the subject based on the breathing signal. The method generates an alert if both no breathing event is identified and no large-scale motion of the subject is identified within an event time interval.

Abstract: A system includes a memory, an optical subsystem, an audio system, a plurality of sensors outputting sensor data, a communication circuitry, and a processor. The processor is configured to input to a baby-specific educational machine learning model, image data, audio signal data, sensor data, baby personal data associated with a baby, and a visual image and a sound presented to the baby based on a baby-specific educational plan; to receive an output from the baby-specific educational machine learning model where the output includes an indication that the baby understood or did not understand the visual image and the sound associated with the baby-specific educational plan, and a baby-specific educational recommendation based on the indication; and to execute based on the baby-specific educational recommendation, a modification of the baby-specific educational plan, or a continued execution of the baby-specific educational plan.

Abstract: For generating a breathing alert is disclosed, a method receives a video stream of a subject. The method further estimates a breathing signal from the video stream. The method determines one of a large-scale motion and/or a breathing event of the subject based on the breathing signal. The method generates an alert if both no breathing event is identified and no large-scale motion of the subject is identified within an event time interval.

Abstract: A system includes a memory, an optical subsystem, an audio system, a plurality of sensors outputting sensor data, a communication circuitry and a processor. The processor is configured to input to a baby-specific behavioral state detection machine learning model, image data, audio signal data, sensor data, and baby-specific personal data associated with the baby, to receive an output from the baby-specific behavioral state detection machine learning model that the baby is agitated and/or about to wake up, to transmit instructions based on the output that cause the audio system and/or the optical subsystem to perform at least one of (i) generate a soothing sound when the baby is agitated, (ii) generate a sleep-enhancing sound when the baby is about to wake up, or (iii) project a relaxing image to be viewed by the baby when the baby is agitated.

Abstract: A container and a method for handling and for treating a bio-compatible feeding liquid, or of a liquid for biological use, having an interior volume wherein the liquid is held and is distributed as a shallow layer of thickness. The feeding liquid, is disposed in contact with surface of the container having large areas. The numerical denomination of the areas may be larger than the thickness by at least 50%, or by one, two, three or more orders of magnitude. The large areas and the shallow thickness enhance rapid heat exchange between the liquid, and a fluid having a thermal capacity wherein the container is immersed. A through opening is disposed in the container for bidirectional liquid communication with the interior volume. The through opening may be coupled to a feeding bottle and to ancillary equipment.