Oliver Amft's Publications

Home Projects Publications Events Contact


Sorted by Date

Bite weight prediction from acoustic recognition of chewing

Oliver Amft, Martin Kusserow, and Gerhard Tröster. Bite weight prediction from acoustic recognition of chewing. IEEE Trans Biomed Eng, 56(6):1663–1672, June 2009.

Download

[PDF]551.4kB  

Abstract

Automatic Dietary Monitoring (ADM) offers new perspectives to reduce the self-reporting burden for participants in diet coaching programs. This work presents an approach to predict weight of individual bites taken. We utilize a pattern recognition procedure to spot chewing cycles and food type in continuous data from an ear-pad chewing sound sensor. The recognized information is used to predict bite weight. We present our recognition procedure and demonstrate its operation on a set of three selected foods of different bite weights. Our evaluation is based on chewing sensor data of eight healthy study participants performing 504 habitual bites in total. The sound-based chewing recognition achieved recalls of 80% at 60%-70% precision. Food classification of chewing sequences resulted in an average accuracy of 94%. In total, 50 variables were derived from the chewing microstructure and analyzed for correlations between chewing behaviour and bite weight. A subset of four variables was selected to predict bite weight using linear food-specific models. Mean weight prediction error was lowest for apples (19.4%) and largest for lettuce (31%) using the sound-based recognition. We conclude that bite weight prediction using acoustic chewing recordings is a feasible approach for solid foods and should be further investigated.

BibTeX

@ARTICLE{Amft2009-J_IEEETransBiomedEng,
  author = {Oliver Amft and Martin Kusserow and Gerhard Tr\"oster},
  title = {Bite weight prediction from acoustic recognition of chewing},
  journal = {IEEE Trans Biomed Eng},
  year = {2009},
  volume = {56},
  pages = {1663--1672},
  number = {6},
  month = {June},
  abstract = {Automatic Dietary Monitoring (ADM) offers new perspectives to reduce
	the self-reporting burden for participants in diet coaching programs.
	This work presents an approach to predict weight of individual bites
	taken. We utilize a pattern recognition procedure to spot chewing
	cycles and food type in continuous data from an ear-pad chewing sound
	sensor. The recognized information is used to predict bite weight.
	We present our recognition procedure and demonstrate its operation
	on a set of three selected foods of different bite weights. Our evaluation
	is based on chewing sensor data of eight healthy study participants
	performing 504 habitual bites in total. The sound-based chewing recognition
	achieved recalls of 80\% at 60\%-70\% precision. Food classification
	of chewing sequences resulted in an average accuracy of 94\%. In
	total, 50 variables were derived from the chewing microstructure
	and analyzed for correlations between chewing behaviour and bite
	weight. A subset of four variables was selected to predict bite weight
	using linear food-specific models. Mean weight prediction error was
	lowest for apples (19.4\%) and largest for lettuce (31\%) using the
	sound-based recognition. We conclude that bite weight prediction
	using acoustic chewing recordings is a feasible approach for solid
	foods and should be further investigated.},
  doi = {10.1109/TBME.2009.2015873},
  file = {Amft2009-J_IEEETransBiomedEng.pdf:Amft2009-J_IEEETransBiomedEng.pdf:PDF},
  owner = {oam},
  timestamp = {2009/01/24}
}

Generated by bib2html.pl on Wed Dec 01, 2010 23:40:25