Minimizing Memory Errors in Child Dietary Assessment with a Wearable Camera: Formative Research

2015 ◽  
Vol 115 (9) ◽  
pp. A86
Author(s):  
A. Beltran ◽  
H. Dadhaboy ◽  
C. Lin ◽  
W. Jia ◽  
J. Baranowski ◽  
...  
Keyword(s):  
Dietary Assessment ◽  
Formative Research ◽  
Memory Errors ◽  
Wearable Camera

scholarly journals Dietary Assessment with a Wearable Camera among Children: Feasibility and Intercoder Reliability

2018 ◽  
Vol 118 (11) ◽  
pp. 2144-2153 ◽  
Author(s):  
Alicia Beltran ◽  
Hafza Dadabhoy ◽  
Courtney Ryan ◽  
Ruchita Dholakia ◽  
Wenyan Jia ◽  
...  
Keyword(s):  
Dietary Assessment ◽  
Intercoder Reliability ◽  
Wearable Camera

scholarly journals Automatic food detection in egocentric images using artificial intelligence technology

2018 ◽  
pp. 1-12 ◽  
Author(s):  
Wenyan Jia ◽  
Yuecheng Li ◽  
Ruowei Qu ◽  
Thomas Baranowski ◽  
Lora E Burke ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
Dietary Assessment ◽  
Real Life ◽  
Research Participant ◽  
Data Set ◽  
Food Items ◽  
Wearable Camera ◽  
Food Detection ◽  
Food Images

Abstract Objective To develop an artificial intelligence (AI)-based algorithm which can automatically detect food items from images acquired by an egocentric wearable camera for dietary assessment. Design To study human diet and lifestyle, large sets of egocentric images were acquired using a wearable device, called eButton, from free-living individuals. Three thousand nine hundred images containing real-world activities, which formed eButton data set 1, were manually selected from thirty subjects. eButton data set 2 contained 29 515 images acquired from a research participant in a week-long unrestricted recording. They included both food- and non-food-related real-life activities, such as dining at both home and restaurants, cooking, shopping, gardening, housekeeping chores, taking classes, gym exercise, etc. All images in these data sets were classified as food/non-food images based on their tags generated by a convolutional neural network. Results A cross data-set test was conducted on eButton data set 1. The overall accuracy of food detection was 91·5 and 86·4 %, respectively, when one-half of data set 1 was used for training and the other half for testing. For eButton data set 2, 74·0 % sensitivity and 87·0 % specificity were obtained if both ‘food’ and ‘drink’ were considered as food images. Alternatively, if only ‘food’ items were considered, the sensitivity and specificity reached 85·0 and 85·8 %, respectively. Conclusions The AI technology can automatically detect foods from low-quality, wearable camera-acquired real-world egocentric images with reasonable accuracy, reducing both the burden of data processing and privacy concerns.

scholarly journals Wearable cameras can reduce dietary under-reporting: doubly labelled water validation of a camera-assisted 24 h recall

2014 ◽  
Vol 113 (2) ◽  
pp. 284-291 ◽  
Author(s):  
Luke Gemming ◽  
Elaine Rush ◽  
Ralph Maddison ◽  
Aiden Doherty ◽  
Nicholas Gant ◽  
...  
Keyword(s):  
Dietary Assessment ◽  
Image Sensors ◽  
Self Report ◽  
High Definition ◽  
Free Living ◽  
Doubly Labelled Water ◽  
Dietary Recall ◽  
Wearable Camera ◽  
Wearable Cameras ◽  
Free Living Conditions

Preliminary research has suggested that wearable cameras may reduce under-reporting of energy intake (EI) in self-reported dietary assessment. The aim of the present study was to test the validity of a wearable camera-assisted 24 h dietary recall against the doubly labelled water (DLW) technique. Total energy expenditure (TEE) was assessed over 15 d using the DLW protocol among forty adults (n 20 males, age 35 (sd 17) years, BMI 27 (sd 4) kg/m2 and n 20 females, age 28 (sd 7) years, BMI 22 (sd 2) kg/m2). EI was assessed using three multiple-pass 24 h dietary recalls (MP24) on days 2–4, 8–10 and 13–15. On the days before each nutrition assessment, participants wore an automated wearable camera (SenseCam (SC)) in free-living conditions. The wearable camera images were viewed by the participants following the completion of the dietary recall, and their changes in self-reported intakes were recorded (MP24+SC). TEE and EI assessed by the MP24 and MP24+SC methods were compared. Among men, the MP24 and MP24+SC measures underestimated TEE by 17 and 9 %, respectively (P< 0·001 and P= 0·02). Among women, these measures underestimated TEE by 13 and 7 %, respectively (P< 0·001 and P= 0·004). The assistance of the wearable camera (MP24+SC) reduced the magnitude of under-reporting by 8 % for men and 6 % for women compared with the MP24 alone (P< 0·001 and P< 0·001). The increase in EI was predominantly from the addition of 265 unreported foods (often snacks) as revealed by the participants during the image review. Wearable cameras enhance the accuracy of self-report by providing passive and objective information regarding dietary intake. High-definition image sensors and increased imaging frequency may improve the accuracy further.

DIETARY ASSESSMENT AND NUTRIENT INTAKE OF PREGNANT DIABETIC WOMEN FROM NAGPUR CITY

2019 ◽  
Author(s):  
Sangita R. Meghal and Kalpana Jadhav Sangita R. Meghal and Kalpana Jadhav ◽  
Keyword(s):  
Nutrient Intake ◽  
Dietary Assessment ◽  
Pregnant Diabetic

Automatic Encoding of Gender by Three-Year-Old Children

2017 ◽  
Author(s):  
Gina T Bednarek ◽  
Kristin Shutts
Keyword(s):  
Test Phase ◽  
Older Children ◽  
Memory Errors ◽  
Automatic Encoding ◽  
Target Children

The present research tested whether three-year-old children – like older children and adults – automatically encode other people’s gender. Three-year-old participants (N = 24) learned facts about unfamiliar target children who varied in gender and were asked to remember facts about the targets during a test phase. At test, children made more within-category memory errors (e.g., misattributing a fact associated with one girl to another girl) than between-category errors (e.g., misattributing a fact associated with a girl to a boy). The findings suggest that at least as early as three years of age, children automatically encode whether someone is a boy or a girl upon first meeting them. The results have implications for our understanding of the automaticity and emergence of stereotyping processes.

Cultural Relevance of a Fruit and Vegetable Food Frequency Questionnaire

2005 ◽  
Vol 66 (4) ◽  
pp. 231-236 ◽  
Author(s):  
Judy Paisley ◽  
Marlene Greenberg ◽  
Jess Haines
Keyword(s):  
Food Frequency Questionnaire ◽  
Dietary Assessment ◽  
Cultural Relevance ◽  
Assessment Tools ◽  
Comparative Approach ◽  
Fruit And Vegetable ◽  
Food Frequency ◽  
Research And Practice ◽  
Vegetable Food ◽  
Nutrition Research

Purpose: Canada’s multicultural population poses challenges for culturally competent nutrition research and practice. In this qualitative study, the cultural relevance of a widely used semiquantitative fruit and vegetable food frequency questionnaire (FFQ) was examined among convenience samples of adults from Toronto’s Cantonese-, Mandarin-, Portuguese-, and Vietnamesespeaking communities. Methods: Eighty-nine participants were recruited through community-based organizations, programs, and advertisements to participate in semi-structured interviews moderated in their native language. Data from the interviews were translated into English and transcribed for analysis using the constant comparative approach. Results: Four main themes emerged from the analysis: the cultural relevance of the foods listed on the FFQ, words with multiple meanings, the need for culturally appropriate portionsize prompts, and the telephone survey as a Western concept. Conclusions: This research highlights the importance of investing resources to develop culturally relevant dietary assessment tools that ensure dietary assessment accuracy and, more important, reduce ethnocentric biases in food and nutrition research and practice. The transferability of findings must be established through further research.

Sign in / Sign up

Export Citation Format

Share Document