Research

Adherence

On-body sensors (inertial, acoustic, physiological) can accurately detect eating events (gestures, chewing, swallowing) and classify food types, offering a continuous alternative to manual logging.

Wearable sensors can track your eating habits automatically by detecting gestures, chewing sounds, and swallowing. While current prototypes may be uncomfortable, they offer a more accurate and continuous view of your diet than manual logging.

ModerateSupportsMEDIUM confidence
Using the classification procedure, we obtained 94 percent accuracy overall... For classification of all foods, we obtained accuracy of 80 percent... discriminated between two types of swallowing... with an overall accuracy of 73 percent.
Oliver Amft et al. · IEEE Pervasive Computing · 2009

Why this rating

Based on small-scale prototype studies (students, small N) rather than large clinical trials.

Source

On-Body Sensing Solutions for Automatic Dietary Monitoring

Oliver Amft et al. · IEEE Pervasive Computing · 2009

DOI 10.1109/mprv.2009.32

narrative_review · n=12Cited 175×
Read the paper
DOI resolved against Crossref · corpus check 2026-06-10

This is one finding among thousands. Every one is graded and traced to its source, so you can see what the evidence actually supports. Browse the research →