Bite Weight Prediction From Acoustic Recognition of Chewing

Automatic dietary monitoring (ADM) offers new perspectives to reduce the self-reporting burden for participants in diet coaching programs. This paper 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 were analyzed for correlations between chewing behavior 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.

[1]  Kylie D. Foster,et al.  Adaptation of healthy mastication to factors pertaining to the individual or to the food , 2006, Physiology & Behavior.

[2]  Danièle Dubois,et al.  Defining sensory descriptors: Towards writing guidelines based on terminology , 2007 .

[3]  E. K. Kemsley,et al.  Electromyographic responses to prescribed mastication. , 2003, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[4]  R. Hill,et al.  The validity of self-reported energy intake as determined using the doubly labelled water technique , 2001, British Journal of Nutrition.

[5]  G. Throckmorton,et al.  Effects of bolus size and hardness on within-subject variability of chewing cycle kinematics. , 2008, Archives of oral biology.

[6]  D. Schoeller.  Limitations in the assessment of dietary energy intake by self-report. , 1995, Metabolism: clinical and experimental.

[7]  Paul Lukowicz,et al.  Analysis of Chewing Sounds for Dietary Monitoring , 2005, UbiComp.

[8]  Adam Drewnowski,et al.  Changing the energy density of the diet as a strategy for weight management. , 2005, Journal of the American Dietetic Association.

[9]  E. Lehmann,et al.  Nonparametrics: Statistical Methods Based on Ranks , 1976 .

[10]  A. van der Bilt,et al.  The influence of product and oral characteristics on swallowing. , 2005, Archives of oral biology.

[11]  Jose Benedito,et al.  Variables Influencing Chewing Electromyography Response in Food Texture Evaluation , 2004 .

[12]  Gerhard Tröster,et al.  Methods for Detection and Classification of Normal Swallowing from Muscle Activation and Sound , 2006, 2006 Pervasive Health Conference and Workshops.

[13]  Oliver Amftand.  Recognition of dietary activity events using on-body sensors , 2008 .

[14]  Paul Lukowicz,et al.  Gesture spotting with body-worn inertial sensors to detect user activities , 2008, Pattern Recognit..

[15]  G. Throckmorton,et al.  The effects of bolus size and chewing rate on masticatory performance with artificial test foods. , 1997, Journal of oral rehabilitation.

[16]  P. O'Neil,et al.  Assessing dietary intake in the management of obesity. , 2001, Obesity research.

[17]  A. Goris,et al.  Validity of the assessment of dietary intake: problems of misreporting , 2002, Current opinion in clinical nutrition and metabolic care.

[18]  H. R. Kissileff,et al.  Microstructure of eating behavior in humans , 2001, Appetite.

[19]  P. Lillford,et al.  The Materials Science of Eating and Food Breakdown , 2000 .

[20]  Mitchell J. Mergenthaler.  Nonparametrics: Statistical Methods Based on Ranks , 1979 .

[21]  Gerhard Tröster,et al.  On-Body Sensing Solutions for Automatic Dietary Monitoring , 2009, IEEE Pervasive Computing.

[22]  J. De Baerdemaeker,et al.  Differences in chewing sounds of dry-crisp snacks by multivariate data analysis , 2003 .

[23]  Mohamed S. Kamel,et al.  Significance Test for Feature Subset Selection on Image Recognition , 2004, ICIAR.

[24]  E. Dransfield,et al.  Variability of the masticatory process during chewing of elastic model foods. , 2000, European journal of oral sciences.

[25]  A. Woda,et al.  Effects of Food Texture and Sample Thickness on Mandibular Movement and Hardness Assessment during Biting in Man , 1997, Journal of dental research.

[26]  G. Lambrinos,et al.  “DELICIOUS PILAFA” APPLE DENSITY CHANGES AS A QUALITY INDEX OF MASS LOSS DEGRADATION DURING STORAGE , 2007 .

[27]  H. Macfie,et al.  Method to investigate differences in chewing behaviour in humans. II: Use of electromyography during chewing to assess chewing behaviour , 1994 .

[28]  R. A. Groeneveld,et al.  Practical Nonparametric Statistics (2nd ed). , 1981 .

[29]  J. Abbink,et al.  Swallowing threshold and masticatory performance in dentate adults , 2004, Physiology & Behavior.

[30]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .