Next Article in Journal
Modeling Possible Outcomes of Updated Daily Values on Nutrient Intakes of the United States Adult Population
Previous Article in Journal
Impact of a Three-Week in-Hospital Multidisciplinary Body Weight Reduction Program on Body Composition, Muscle Performance and Fatigue in a Pediatric Obese Population with or without Metabolic Syndrome
Open AccessArticle

Validation of a Deep Learning System for the Full Automation of Bite and Meal Duration Analysis of Experimental Meal Videos

1
Visual Computing Lab, CERTH-ITI, 57001 Thessaloniki, Greece
2
Innovative Use of Mobile Phones to Promote Physical Activity and Nutrition across the Lifespan (the IMPACT) Research Group, Department of Biosciences and Nutrition, Karolinska Institutet, 14152 Stockholm, Sweden
*
Author to whom correspondence should be addressed.
Nutrients 2020, 12(1), 209; https://doi.org/10.3390/nu12010209
Received: 12 December 2019 / Revised: 9 January 2020 / Accepted: 9 January 2020 / Published: 13 January 2020
(This article belongs to the Section Nutrition Methodology & Assessment)
Eating behavior can have an important effect on, and be correlated with, obesity and eating disorders. Eating behavior is usually estimated through self-reporting measures, despite their limitations in reliability, based on ease of collection and analysis. A better and widely used alternative is the objective analysis of eating during meals based on human annotations of in-meal behavioral events (e.g., bites). However, this methodology is time-consuming and often affected by human error, limiting its scalability and cost-effectiveness for large-scale research. To remedy the latter, a novel “Rapid Automatic Bite Detection” (RABiD) algorithm that extracts and processes skeletal features from videos was trained in a video meal dataset (59 individuals; 85 meals; three different foods) to automatically measure meal duration and bites. In these settings, RABiD achieved near perfect agreement between algorithmic and human annotations (Cohen’s kappa κ = 0.894; F1-score: 0.948). Moreover, RABiD was used to analyze an independent eating behavior experiment (18 female participants; 45 meals; three different foods) and results showed excellent correlation between algorithmic and human annotations. The analyses revealed that, despite the changes in food (hash vs. meatballs), the total meal duration remained the same, while the number of bites were significantly reduced. Finally, a descriptive meal-progress analysis revealed that different types of food affect bite frequency, although overall bite patterns remain similar (the outcomes were the same for RABiD and manual). Subjects took bites more frequently at the beginning and the end of meals but were slower in-between. On a methodological level, RABiD offers a valid, fully automatic alternative to human meal-video annotations for the experimental analysis of human eating behavior, at a fraction of the cost and the required time, without any loss of information and data fidelity.
Keywords: eating behavior; meal analysis; meal duration; mouthfuls; bite-rate; eating patterns; deep learning; skeletal feature extraction eating behavior; meal analysis; meal duration; mouthfuls; bite-rate; eating patterns; deep learning; skeletal feature extraction
MDPI and ACS Style

Konstantinidis, D.; Dimitropoulos, K.; Langlet, B.; Daras, P.; Ioakimidis, I. Validation of a Deep Learning System for the Full Automation of Bite and Meal Duration Analysis of Experimental Meal Videos. Nutrients 2020, 12, 209.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop