Statistical models for meal-level estimation of mass and energy intake using features derived from video observation and a chewing sensor

Accurate and objective assessment of energy intake remains an ongoing problem. We used features derived from annotated video observation and a chewing sensor to predict mass and energy intake during a meal without participant self-report. 30 participants each consumed 4 different meals in a laboratory setting and wore a chewing sensor while being videotaped. Subject-independent models were derived from bite, chew, and swallow features obtained from either video observation or information extracted from the chewing sensor. With multiple regression analysis, a forward selection procedure was used to choose the best model. The best estimates of meal mass and energy intake had (mean ± standard deviation) absolute percentage errors of 25.2% ± 18.9% and 30.1% ± 33.8%, respectively, and mean ± standard deviation estimation errors of −17.7 ± 226.9 g and −6.1 ± 273.8 kcal using features derived from both video observations and sensor data. Both video annotation and sensor-derived features may be utilized to objectively quantify energy intake.

[1]  Samantha Kleinberg,et al.  Automated estimation of food type and amount consumed from body-worn audio and motion sensors , 2016, UbiComp.

[2]  K R Westerterp,et al.  Use of a triaxial accelerometer to validate reported food intakes. , 2001, The American journal of clinical nutrition.

[3]  Gerhard Tröster,et al.  Bite Weight Prediction From Acoustic Recognition of Chewing , 2009, IEEE Transactions on Biomedical Engineering.

[4]  Shuangquan Wang,et al.  CARE: chewing activity recognition using noninvasive single axis accelerometer , 2015, UbiComp/ISWC Adjunct.

[5]  Michael R Neuman,et al.  Toward Objective Monitoring of Ingestive Behavior in Free‐living Population , 2009, Obesity.

[6]  Edward Sazonov,et al.  Design of a instrumentation module for monitoring ingestive behavior in laboratory studies , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  J. Higgins,et al.  Meal Microstructure Characterization from Sensor-Based Food Intake Detection , 2017, Front. Nutr..

[8]  Jindong Tan,et al.  DietCam: Automatic dietary assessment with mobile camera phones , 2012, Pervasive Mob. Comput..

[9]  R. Farris,et al.  Dietary assessment in children using electronic methods: telephones and tape recorders. , 1990, Journal of the American Dietetic Association.

[10]  Edward Sazonov,et al.  A wireless sensor system for quantification of infant feeding behavior , 2015, Wireless Health.

[11]  Edward Sazonov,et al.  A Novel Wearable Device for Food Intake and Physical Activity Recognition , 2016, Sensors.

[12]  Qing Zhang,et al.  Predicting food nutrition facts using pocket-size near-infrared sensor , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[13]  Jeannette Beasley,et al.  Accuracy of a PDA-based dietary assessment program. , 2005, Nutrition.

[14]  M. McCrory,et al.  Reduction of energy intake using just‐in‐time feedback from a wearable sensor system , 2017, Obesity.

[15]  Edward Sazonov,et al.  Automatic Ingestion Monitor: A Novel Wearable Device for Monitoring of Ingestive Behavior , 2014, IEEE Transactions on Biomedical Engineering.

[16]  C. Forde,et al.  Consistency of Eating Rate, Oral Processing Behaviours and Energy Intake across Meals , 2017, Nutrients.

[17]  Eric R Muth,et al.  Slowing bite-rate reduces energy intake: an application of the bite counter device. , 2011, Journal of the American Dietetic Association.

[18]  S. Schuckers,et al.  The Energetics of Obesity: A Review: Monitoring Energy Intake and Energy Expenditure in Humans , 2010, IEEE Engineering in Medicine and Biology Magazine.

[19]  Thad Starner,et al.  Detecting Mastication: A Wearable Approach , 2015, ICMI.

[20]  P. Södersten,et al.  Decelerated and linear eaters: Effect of eating rate on food intake and satiety , 2009, Physiology & Behavior.

[21]  Adam W. Hoover,et al.  A New Method for Measuring Meal Intake in Humans via Automated Wrist Motion Tracking , 2012, Applied Psychophysiology and Biofeedback.

[22]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[23]  Edward Sazonov,et al.  Real time monitoring and recognition of eating and physical activity with a wearable device connected to the eyeglass , 2017, 2017 Eleventh International Conference on Sensing Technology (ICST).

[24]  Amy F. Subar,et al.  Dietary Assessment Methodology , 2017 .

[25]  M. Yeomans,et al.  Independent Effects of Palatability and Within-meal Pauses on Intake and Appetite Ratings in Human Volunteers , 1997, Appetite.

[26]  M. Robinson,et al.  Using smart card technology to monitor the eating habits of children in a school cafeteria: 1. Developing and validating the methodology. , 2005, Journal of human nutrition and dietetics : the official journal of the British Dietetic Association.

[27]  Adam W. Hoover,et al.  Comparison between Human and Bite-Based Methods of Estimating Caloric Intake. , 2016, Journal of the Academy of Nutrition and Dietetics.

[28]  Hassan Ghasemzadeh,et al.  Speech2Health: A Mobile Framework for Monitoring Dietary Composition From Spoken Data , 2018, IEEE Journal of Biomedical and Health Informatics.

[29]  K R Westerterp,et al.  Underreporting of habitual food intake is explained by undereating in highly motivated lean women. , 1999, The Journal of nutrition.

[30]  M. Livingstone,et al.  Plausible self-reported dietary intakes in a residential facility are not necessarily reliable , 2016, European Journal of Clinical Nutrition.

[31]  Edward Sazonov,et al.  Automatic Measurement of Chew Count and Chewing Rate during Food Intake , 2016, Electronics.

[32]  Lori D. Sigrist,et al.  Monitoring energy intake: a hand-held personal digital assistant provides accuracy comparable to written records. , 2009, Journal of the American Dietetic Association.

[33]  Shah Atiqur Rahman,et al.  Unintrusive eating recognition using Google Glass , 2015, 2015 9th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth).

[34]  D. Giavarina.  Understanding Bland Altman analysis , 2015, Biochemia medica.

[35]  Wolf-Joachim Fischer,et al.  Food intake monitoring: an acoustical approach to automated food intake activity detection and classification of consumed food , 2012, Physiological measurement.

[36]  Oleksandr Makeyev,et al.  Automatic identification of the number of food items in a meal using clustering techniques based on the monitoring of swallowing and chewing , 2012, Biomed. Signal Process. Control..

[37]  Rachel K. Johnson,et al.  The use of a personal digital assistant for dietary self-monitoring does not improve the validity of self-reports of energy intake. , 2006, Journal of the American Dietetic Association.

[38]  Majid Sarrafzadeh,et al.  Monitoring eating habits using a piezoelectric sensor-based necklace , 2015, Comput. Biol. Medicine.

[39]  Edward Sazonov,et al.  Non-invasive monitoring of chewing and swallowing for objective quantification of ingestive behavior. , 2008, Physiological measurement.

[40]  Corby K. Martin,et al.  Measuring food intake with digital photography. , 2014, Journal of human nutrition and dietetics : the official journal of the British Dietetic Association.

[41]  Edward Sazonov,et al.  Linear regression models for chew count estimation from piezoelectric sensor signals , 2016, 2016 10th International Conference on Sensing Technology (ICST).

[42]  Michael R. Neuman,et al.  Energy intake estimation from counts of chews and swallows , 2015, Appetite.

[43]  Edward Sazonov,et al.  Segmentation and Characterization of Chewing Bouts by Monitoring Temporalis Muscle Using Smart Glasses with Piezoelectric Sensor. , 2016, IEEE journal of biomedical and health informatics.