Food intake monitor

Inventors

Sazonov, Edward • Farooq, Muhammad

Assignees

University of Alabama at Birmingham UAB

Abstract

Systems and methods for monitoring food intake include an air pressure sensor for detecting ear canal deformation, according to some implementations. For example, the air pressure sensor detects a change in air pressure in the ear canal resulting from mandible movement. Other implementations include systems and methods for monitoring food intake that include a temporalis muscle activity sensor for detecting temporalis muscle activity, wherein at least a portion of the temporalis muscle activity sensor is coupled adjacent a temple portion of eyeglasses and disposed between the temple tip and the frame end piece. The temporalis muscle activity sensor may include an accelerometer, for example, for detecting movement of the temple portion due to mandibular movement from chewing.

Core Innovation

The disclosed invention provides a wearable or near-wearable food intake monitor configured to automatically detect food intake events, including swallowing and/or chewing, using sensing associated with a user’s ear canal and/or temporalis muscle activity adjacent to eyeglasses. In one implementation, an air-pressure sensing approach converts mandible-driven ear-canal deformation into pressure variations using an earbud/earpiece with an air tube, with the ear canal optionally left open. In another implementation, a temporalis muscle activity sensor, such as an accelerometer coupled to a temple portion of eyeglasses, captures chewing-related oscillations.

The invention further describes signal-processing and classification for intake-event detection using epoch-based processing and feature extraction from sensor signals. Signals may be divided into epochs or decision epochs, and features may be computed in time and/or frequency domains using operations such as STFT, CWT, and PSD, as well as features such as mean absolute value, entropy, peaks, zero-crossings, and fractal dimension.

The disclosed approach supports pattern recognition and machine-learning classification for determining whether an epoch corresponds to swallowing versus not. The system is described as supporting multi-sensor fusion across multiple inputs such as jaw motion sensor measurements, hand-to-mouth gesture sensing, inertial/body motion, and optional sensor modalities including microphones and camera, and may produce real-time feedback and moderation based on detected intake episodes.

Claims Coverage

The claims coverage describes three inventive features.

The inventive features combine wearable intake sensing, epoch-based classification, and multi-sensor fusion for determining intake episodes.

Stated Advantages

Documented Applications