Monitoring eating behaviour in the wild

  • J.M. van Waterschoot

Student thesis: Master


A system to estimate the daily intake of food and drinks of a person was investigated. The system should distinguish intake moments from other gestures and sounds during the day, that occur such as when making a phone call, working at the office, etc. The system can be used for dietary training purposes and could also remind dementia patients to eat, when they forget to. The recording system consists of two orientation sensors (Shimmer sensors) worn on the lower arms to measure the arm gestures, a microphone worn in the ear to record to the sound of the jawbone and a mobile phone running the recording application 'CRNTC+'. The recording application contains an interface to annotate the recordings. After recording the supervised data the system will be trained offline in order to make a system that can spot intake moments online unsupervised.
Date of Award31 Aug 2013
Original languageEnglish
SupervisorO.D. Amft (Supervisor 1)

Cite this