Bite Counter Project

Device History

Over the years our device has matured from a sensor wired to a desktop computer sitting next to the eater, to a fully self-contained device manufactured by Bite Technologies, to a free app available for both Android and Apple smartwatches. Contact Adam Hoover if you are interested in hardware or research support.

Version 1 (2007). Tethered sensor. Version 2 (2008). Wireless sensor. Version 3 (2010). Self-contained unit, custom case. Version 4 (2011). Manufactured unit. Version 5 (2015). 2nd generation manufacturing. Version 6 (2017). Apple smartwatch free app. Version 7 (2018). Android smartwatch free app.

Software

Desktop software for Windows can be downloaded here. The software analyzes wrist motion data to detect eating episodes (meals, snacks) and count the number of bites taken in each episode. It is free and source code is included.

Obesity

Facts and health effects according to the World Health Organization. Real-time counters showing there are nearly 3 times as many people suffering from overfeeding than undernourishment in the world, along with the associated medical costs. A significant challenge is the development of tools that can assist with the measurement of energy expenditure and energy intake.

Technology

The Bite Counter device is worn like a watch and tracks wrist motion during eating. By detecting a characteristic pattern, it can identify when a bite of food has been taken. It can monitor intake in real-time and provide feedback to the wearer. The feedback could tell the user to slow down, or tell the user to stop eating after a target intake had been reached, or help the user track long-term eating patterns. The bite counter is a tool to help people track their intake.

Bites as a measure

The following graphs show data that relates bite count to calories. Each data point is for one meal. We tracked 83 people for 2 weeks, each graph shows all the meals for a single person. The data on the left show an approximately 0.4 correlation, while the data on the right show an approximately 0.7 correlation. Our study showed that most people correlate bites to calories in this range.

Isn't a bite of carrots different from a bite of candy? Of course. But nobody gains or loses weight in a single bite, or even a single meal. A common guideline is to lose a pound of weight per week. Our hypothesis is that bite count can serve as a surrogate for calorie count over a period of time. By automating the counting process, and enabling it anywhere, any time, the bite counter can empower individuals to better monitor intake. As with calories, it is possible to count bites for a single meal; but with either measure reduction goals are best evaluated over at least a day.

Bite goals, like calorie goals, should be custom set to the individual. This would be based not only upon the size, gender, age, and activity level of the person, but also based upon the foods typically eaten. For example, a vegetarian may have a higher bite count per day than someone who regularly eats more energy-dense foods. In addition, people tend to eat the same foods week to week. Therefore, setting bite reduction goals over a period of time has the same effect as setting calorie reduction goals.

Data

The Clemson Cafeteria data set was used for several of the experiments described in the below papers. It involves detecting bites within gyroscope/accelerometer signals.

Some multi-week datasets have been collected using bite counter devices and show a relationship between weight change and average daily bite count.

The data below are results of bite counting and show 2 participants data for 2 weeks each. The first participant shows a lot of late night eating activity. The second participant shows increased consumption on weekends. Click the images and links below to see example data files, or download our software to view it in calendar format.

sample data file sample data file

Media

How to use a Bite Counter to measure eating intake for a meal .

A laboratory demo of a few bites, showing a signal-to-bite correlation.

Media about this research often appears in the news.

Funding:

National Institutes of Health

R01DK136216

A. Hoover and S. Goldstein, Validating Sensor-based Approaches for Monitoring Eating Behavior and Energy Intake by Accounting for Real-World Factors that Impact Accuracy and Acceptability, National Institutes of Health, grant# R01DK135679, 2023-2027.
S. Goldstein, Using Multimodal Real-Time Assessment to Phenotype Dietary Non-Adherence Behaviors that Contribute to Poor Outcomes in Behavioral Obesity Treatment, National Institutes of Health, grant# R01DK132210, 2022-2027.
S. Goldstein, Optimizing just-in-time adaptive intervention to improve dietary adherence in behavioral obesity treatment: a micro-randomized trial, National Institutes of Health, grant# R01HL153543, 2020-2024.
A. Hoover, E. Muth and C. Martin, Using Context to Validate and Improve Wrist-Tracking Measures of Eating Activity, National Institutes of Health, grant# R01HL118181, 2015-2019.
G. Turner-McGrievy, Increasing Dietary Self-Monitoring and Weight Loss in an Mhealth Intervention, National Institutes of Health, grant# R21CA187929, 2015-2017.
A. Hoover and E. Muth, Assessing the Bite Counter as a Tool for Food Intake Monitoring: Phase 2, National Institutes of Health, grant# R42DK091141, 2014-2017.
A. Hoover and E. Muth, Assessing the Bite Counter as a Tool for Food Intake Monitoring, National Institutes of Health, grant# R41DK091141, 2011-2013.
E. Muth, A. Hoover and P. O'Neil, South Carolina Clinical and Translational Institute, 2011.
A. Hoover and E. Muth, South Carolina Launch, 2010.

Papers about this project:

Z. Tang, A. Patyk, S. Goldstein, J.G. Thomas and A. Hoover, "Detecting Eating Episodes From Wrist Motion Using Daily Pattern Analysis", in IEEE J. of Biomedical and Health Inforamtics, Dec 2023.
S. Goldstein, A. Hoover and J.G. Thomas, "An explanation for the accuracy of sensor-based measures of energy intake: Amount of food consumed matters more than dietary composition", in Appetite, vol. 194(1), pp. 107176, March 2024.
C. Popp, C. Wang, et. al., "Objective Determination of Eating Occasion Timing (OREO): Combining Self-Report, Wrist Motion, and Continuous Glucose Monitoring to Detect Eating Occasions in Adults With Pre-Diabetes and Obesity", in J. of Diabetes Science and Technology, Sept 2023.
S. Goldstein, A. Hoover and J.G. Thomas, "Combining passive eating monitoring and ecological momentary assessment to characterize dietary lapses from a lifestyle modification intervention", in Appetite, vol. 175, pp. 106090, 2022.
A. Brown, et al., "Toward more rigorous and informative nutritional epidemiology: the rational space between dismissal and defense of the status quo", in Critical Reviews in Food Science and Nutrition, vol. 63(18), pp. 3150-3167, 2023.
S. Sharma and A. Hoover, "Top-Down Detection of Eating Episodes by Analyzing Large Windows of Wrist Motion Using a Convolutional Neural Network", in MDPI Bioengineering, vol 9, no 70, 2022.
S. Sharma and A. Hoover, "The Challenge of Metrics in Automated Dietary Monitoring as Analysis Transitions from Small Data to Big Data", in IEEE Int'l Conf on Bioinformatics and Biomedicine, pp. 2647-2653, 2020.
Y. Luktuke and A. Hoover, "Segmentation and Recognition of Eating Gestures from Wrist Motion using Deep Learning", in IEEE Int'l Conf on Big Data, 2020.
S. Sharma, P. Jasper, E. Muth and A. Hoover, "The impact of walking and resting on wrist motion for automated detection of meals", in ACM Transactions on Computing for Healthcare, 1(4), pp. 1-19, 2020.
A. Sharma and A. Hoover, "A Study on Linear Acceleration of the Wrist During Free-living", in the proc. of IEEE Intl Conf on Bioinformatics and Biomedicine, Nov. 2019.
B. Lin and A. Hoover, ``A Comparison of Finger and Wrist Motion Tracking to Detect Bites during Food Consumption'', in IEEE Conference on Body Sensor Networks, May 2019.
G. Turner-McGrievy, et. al., ``Defining Adherence to Mobile Dietary Self- Monitoring and Assessing Tracking Over Time: Tracking at Least Two Eating Occasions per Day Is Best Marker of Adherence within Two Different Mobile Health Randomized Weight Loss Interventions'', in J. of the Academy of Nutrition and Dietetics, accepted March 2019.
A. Hoover, "Tracking Wrist Motion to Measure Energy Intake", invited talk at the short course on Mathematical Sciences in Obesity, sponsored by Indiana University, June 2019, Baltimore, MD.
A. Boutte at. al., "Comparing Changes in Diet Quality Between Two Technology-Based Diet Tracking Devices", in J. of Technology in Behavioural Science, vol. 4 no. 1, 2019, pp. 25-32.
J. Salley, A. Hoover and E. Muth, "Between and Within Subjects Predictors of the Kilocalorie Content of Bites of Food", in J. of the Academy of Nutrition and Dietetics, Feb 2019, pp. 1-9.
J. Alex, et. al., "Bite count rates in free-living individuals: new insights from a portable sensor", in BMC Nutrition, vol. 4 no. 23, 2018, pp. 23-28.
G. Turner-McGrievy, et. al., "The Dietary Intervention to Enhance Tracking with Mobile Devices (DIET Mobile) Study: A 6-Month Randomized Weight Loss Trial", in Obesity, vol. 25 no. 8, August 2017, pp. 1336-1342.
R. Mattfeld, E. Muth and A. Hoover, "A comparison of bite size and BMI in a cafeteria setting", in Physiology & Behavior, vol. 181, November 2017, pp. 38-42.
G. Turner-McGrievy, et. al., "Byte by Bite: Use of a mobile Bite Counter and weekly behavioral challenges to promote weight loss", in Smart Health, vol. 3, 2017, pp. 20-26.
D. Weathers, J. Siemens and S. Kopp, "Tracking food intake as bites: Effects on cognitive resources, eating enjoyment, and self control", in Appetite, vol. 111 no. 1, April 2017, pp. 23-31.
Y. Shen, J. Salley, E. Muth and A. Hoover, "Assessing the Accuracy of a Wrist Motion Tracking Method for Counting Bites across Demographic and Food Variables", in IEEE Journal of Biomedical and Health Informatics, vol. 21 no. 3, March 2017, pp. 599-606.
S. Sharma, P. Jasper, E. Muth, and A. Hoover, "Automatic Detection of Periods of Eating using Wrist Motion Tracking", in the proc. of IEEE Conference on Connected Health: Applications, Systems and Engineering Technologies, 2016, pp. 362-363.
Y. Shen, E. Muth and A. Hoover, "Recognizing Eating Gestures Using Context Dependent Hidden Markov Models", in the proc. of IEEE Conference on Connected Health: Applications, Systems and Engineering Technologies, 2016, pp. 248-253.
A. Hoover, "Bite measurement methods and models", invited talk at the Third short course on mathematical sciences in obesity research, University of Alabama at Birmingham, June 2016, Birmingham, AL.
R. Mattfeld, E. Muth and A. Hoover, "Measuring the consumption of individual solid and liquid bites using a table embedded scale during unrestricted eating", in IEEE Journal of Biomedical and Health Informatics, vol. 21 no. 6, Nov 2017, pp. 1711-1718.
P. Jasper, M. James, A. Hoover and E. Muth, "Effects of Bite Count Feedback from a Wearable Device and Goal-Setting on Consumption in Young Adults", in Journal of the Academy of Nutrition and Dietetics, vol. 116 no. 11, pp. 1785-1793.
J. Salley, A. Hoover, M. Wilson and E. Muth, "A Comparison Between Human and Bite-Based Methods of Estimating Caloric Intake", in Journal of the Academy of Nutrition and Dietetics, vol. 116 no. 10, Oct 2016, pp. 1568-1577.
A. Hoover, "Tracking Wrist Motion to Monitor Energy Intake", invited talk at the Second short course on mathematical sciences in obesity research, University of Alabama at Birmingham, June 2015, Birmingham, AL.
A. Hoover, "Monitoring Human Energy Intake", invited talk at Bringham Young University, April 2015, Provo, UT.
R Ramos, E. Muth, J. Gowdy and A. Hoover, "Improving the Recognition of Eating Gestures Using Inter-Gesture Sequential Dependencies", in IEEE Journal of Biomedical and Health Informatics, vol. 19 no. 3, May 2015, pp. 825-831.
A. Hoover, "Tracking Wrist Motion to Monitor Energy Intake", invited talk at the Wireless Health 2013 conference, Johns Hopkins University, November 2013, Baltimore, MD.
R Ramos and A. Hoover, "A study of temporal action sequencing during consumption of a meal", in the proc. of ACM Conf. on Bioinformatics, Computational Biology and Biomedical Informatics, Sept 2013, Washington DC.
Y. Dong, J. Scisco, M. Wilson, E. Muth and A. Hoover, "Detecting Periods of Eating During Free-Living by Tracking Wrist Motion", in IEEE Journal of Biomedical and Health Informatics, vol. 18 no. 4, July 2014, pp. 1253-1260.
J. Scisco, E. Muth and A. Hoover, "Examining the Utility of a Bite-Count Based Measure of Eating Activity in Free-Living Humans", in Journal of the Academy of Nutrition and Dietetics, vol. 114 no. 3, April 2014, pp. 464-469.
J. Salley, J. Scisco, E. Muth and A. Hoover, "A Comparison of User Preferences and Reported Compliance with the Bite Counter and the 24-Hour Dietary Recall", in proc. of Human Factors and Ergonomics Society Annual meeting, 2012.
Y. Dong, A. Hoover, J. Scisco and E. Muth, "A New Method for Measuring Meal Intake in Humans via Automated Wrist Motion Tracking", in Applied Psychophysiology and Biofeedback, vol 37, no 3, 2012, pp 205-215.
Y. Dong, "Tracking Wrist Motion to Detect and Measure the Eating Consumption of Free-Living Humans'', PhD dissertation, Electrical & Computer Engineering Department, Clemson University, May 2012.
J. Scisco, "Sources of Variance in Bite Count", PhD dissertation, Psychology Department, Clemson University, May 2012.
J. Scisco, E. Muth, Y. Dong, A. Hoover, "Slowing bite-rate reduces caloric consumption; an application of the bite counter device", in Journal of the American Dietetic Assocation, vol. 111, 2011, pp. 1231-1235.
Y. Dong, A. Hoover, J. Scisco and E. Muth, "Detecting Eating Using a Wrist Mounted Device During Normal Daily Activities", in the proc. of WorldComp, 2011.
A. Hoover, E. Muth and Y. Dong, "Weight Control Device Using Bites Detection", US Patent no 8310368, filed January 2009, granted November 2012.
Y. Dong, A. Hoover and E. Muth, "A Device for Detecting and Counting Bites of Food Taken by a Person During Eating", in the proc. of IEEE International Conference on Bioinformatics and Biomedicine, 2009.

Bite Counter Project Page / Clemson / ahoover@clemson.edu


Version 1 (2007). Tethered sensor.	Version 2 (2008). Wireless sensor.	Version 3 (2010). Self-contained unit, custom case.	Version 4 (2011). Manufactured unit.	Version 5 (2015). 2nd generation manufacturing.	Version 6 (2017). Apple smartwatch free app.	Version 7 (2018). Android smartwatch free app.