Abstract: Various systems and methods are provided herein for performing health status detection. In one embodiment, ECG data, acceleration data, and audio data is received via a sensor unit. One or more parameters are extracted from the ECG data. An activity associated with the acceleration data is determined. At least one of an emotional state, a behavioral state, or an infant-caregiving interaction associated with the audio data is detected. One or more physiological and behavioral indicators are determined based on the one or more parameters, the activity, and the emotion state, behavioral state, or the infant-caregiver interaction. A health status corresponding to the physiological and behavioral indicators is outputted.

Abstract: Passively monitoring a user's breathing with a device can include identifying breathing modes of the user's breathing and responsive to detecting a trigger mode based on the identifying, generating an instruction adapted to the trigger mode. The instruction can be conveyed to the user via the device. The monitoring can include determining phases of the user's breathing with the device. Determining the phases can include receiving acoustic signals generated by an acoustic sensor in response to a user's breathing and generating acoustic data comprising features extracted from the acoustic signals. Phases of the user's breathing can be determined by classifying the acoustic data using a machine learning model trained based on signal processing of motion signals generated by a motion sensor in response to human breathing motions. Though trained using signal processing of motion signals, the machine learning model is trained to classify acoustic data.

Abstract: Passively monitoring a user's breathing with a device can include identifying breathing modes of the user's breathing and responsive to detecting a trigger mode based on the identifying, generating an instruction adapted to the trigger mode. The instruction can be conveyed to the user via the device. The monitoring can include determining phases of the user's breathing with the device. Determining the phases can include receiving acoustic signals generated by an acoustic sensor in response to a user's breathing and generating acoustic data comprising features extracted from the acoustic signals. Phases of the user's breathing can be determined by classifying the acoustic data using a machine learning model trained based on signal processing of motion signals generated by a motion sensor in response to human breathing motions. Though trained using signal processing of motion signals, the machine learning model is trained to classify acoustic data.