Research Article
Evaluation of Algorithms for Chew Event Detection
@INPROCEEDINGS{10.4108/icst.bodynets.2012.249785, author={Sebastian P\aa{}\`{a}ler and Wolf-Joachim Fischer}, title={Evaluation of Algorithms for Chew Event Detection}, proceedings={7th International Conference on Body Area Networks}, publisher={ICST}, proceedings_a={BODYNETS}, year={2012}, month={11}, keywords={food intake sound chew event detection mobile healthcare}, doi={10.4108/icst.bodynets.2012.249785} }- Sebastian Päßler
Wolf-Joachim Fischer
Year: 2012
Evaluation of Algorithms for Chew Event Detection
BODYNETS
ICST
DOI: 10.4108/icst.bodynets.2012.249785
Abstract
Analyzing food intake behavior is necessary to prevent obesity and overweight. Detecting and counting chewing strokes is an elementary part of this analysis. In our project, sounds of food intake were recorded using a microphone in the outer ear canal. The records contained sounds of 51 healthy subjects chewing 8 types of food. We evaluated seven different algorithms to detect chew events in sound records. Results of the automated detection were compared to manual annotations. Best performances (preci-sion and recall over 76 %) were achieved by detecting chew events in six different frequency bands and fusing these results. With this method for counting the number of chews, an important step towards the estimation of bite weight has been done.
