Closed-loop wearable sensor and method
AssigneeSibel Health Inc.
InventorsKeum San Chun, Lian Yu, Matt Keller
Life of this patent
Estimating the term…
Abstract
Methods and electronic devices for measuring motion and acoustic signatures of physiological processes of a human subject. The method includes measuring motion and acoustic signatures of physiological processes of a human subject; sending the first feature-related data to a machine learning service; sending the first feature-related data to a machine learning service; and determining a predicted detection of human scratching activity by the machine-learning service by performing a machine-learning operation on the feature-related data.
Claims19
An electronic device for measuring motion and acoustic signatures of physiological processes of a human subject, comprising:
- a top portion;
- a bottom portion;
- an electronics board disposed between the top portion and the bottom portion;
- a machine learning service disposed on the electronics board, the machine learning service including a trained and programmed machine language model to receive feature-related data and to generate a predicted detection of scratching activity by performing a machine-learning operation, the machine-learning operation including at least one neural network flow:
- an inertial measurement unit (IMU) for detecting the motion and acoustic signatures, the IMU mounted on the electronics board and operably in direct mechanical communication with the skin of the subject;
- a microcontroller unit (MCU) mounted on the electronics board and communicatively coupled to the IMU, the MCU to calculate feature-related data from the motion and acoustic signatures and send the feature-related data to the machine learning service executing on the MCU;
- wherein the predicted detection of human scratching activity by the human subject is performed by a first machine-learning operation on the feature-related data using the trained and programmed machine language model, the first machine-learning operation involving the at least one neural network flow.
A method, comprising:
- providing a sensor including an inertial measurement unit (IMU) and a microcontroller unit (MCU) co-mounted on an electronics board and communicatively coupled to each other and including a machine learning service;
- measuring motion and acoustic signatures of physiological processes of a human subject solely through the IMU;
- calculating a first feature-related data from the motion and acoustic signatures;
- sending the first feature-related data to a machine learning service;
- and
- determining a predicted detection of human scratching activity by the machine-learning service by performing a machine-learning operation using a machine language model of the machine learning service on the feature-related data, the machine-learning operation involving at least one neural network.
Dependencies are inferred from the claim text.