Bootstrapping analysis of crowdsourced non-expert estimates of the number of calories in photographs of meals

RR Bond; Anne Moorhead; Huiru Zheng; Patrick McAllister

doi:0.1109/BIBM.2018.8621166

Bootstrapping analysis of crowdsourced non-expert estimates of the number of calories in photographs of meals

RR Bond, Anne Moorhead, Huiru Zheng, Patrick McAllister

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

A total of 1800 estimates from non-expert dietitians were collected online. This comprised of 120 subjects each providing an estimate per image (120 subjects * 15 images). The overall aim of this study was to use crowdsourcing to determine the accuracy of non-experts in estimating calories in a meal as shown in a photograph. We analyzed percentiles and used bootstrapping with replacement to determine the typical percentile rank estimate that is in proximity to the ground truth and to determine the least number of sample estimates from a crowd of non-experts that can provide a convenient and accurate estimate of the number of calories in a meal.

Original language	English
Title of host publication	2018 IEEE International Conference on Bioinformatics and Biomedicine(BIBM 2018)
Place of Publication	Madrid, Spain
Publisher	IEEE
Pages	1465-1469
ISBN (Electronic)	978-1-5386-5488-0
ISBN (Print)	978-1-5386-5489-7
DOIs	https://doi.org/0.1109/BIBM.2018.8621166
Publication status	Published (in print/issue) - 3 Dec 2018

Keywords

Crowdsourcing
obesity
standards
estimation
conferences
bioinformatics
Gold

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

0.1109/BIBM.2018.8621166

Cite this

@inproceedings{c6b5fff3c2d04bcfbf83330ba210a1e3,

title = "Bootstrapping analysis of crowdsourced non-expert estimates of the number of calories in photographs of meals",

abstract = "A total of 1800 estimates from non-expert dietitians were collected online. This comprised of 120 subjects each providing an estimate per image (120 subjects * 15 images). The overall aim of this study was to use crowdsourcing to determine the accuracy of non-experts in estimating calories in a meal as shown in a photograph. We analyzed percentiles and used bootstrapping with replacement to determine the typical percentile rank estimate that is in proximity to the ground truth and to determine the least number of sample estimates from a crowd of non-experts that can provide a convenient and accurate estimate of the number of calories in a meal.",

keywords = "Crowdsourcing, obesity, standards, estimation, conferences, bioinformatics, Gold",

author = "RR Bond and Anne Moorhead and Huiru Zheng and Patrick McAllister",

year = "2018",

month = dec,

day = "3",

doi = "0.1109/BIBM.2018.8621166",

language = "English",

isbn = "978-1-5386-5489-7",

pages = "1465--1469",

booktitle = "2018 IEEE International Conference on Bioinformatics and Biomedicine(BIBM 2018)",

publisher = "IEEE",

address = "United States",

}

Bootstrapping analysis of crowdsourced non-expert estimates of the number of calories in photographs of meals. / Bond, RR ; Moorhead, Anne ; Zheng, Huiru et al.
2018 IEEE International Conference on Bioinformatics and Biomedicine(BIBM 2018). Madrid, Spain: IEEE, 2018. p. 1465-1469.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Bootstrapping analysis of crowdsourced non-expert estimates of the number of calories in photographs of meals

AU - Bond, RR

AU - Moorhead, Anne

AU - Zheng, Huiru

AU - McAllister, Patrick

PY - 2018/12/3

Y1 - 2018/12/3

N2 - A total of 1800 estimates from non-expert dietitians were collected online. This comprised of 120 subjects each providing an estimate per image (120 subjects * 15 images). The overall aim of this study was to use crowdsourcing to determine the accuracy of non-experts in estimating calories in a meal as shown in a photograph. We analyzed percentiles and used bootstrapping with replacement to determine the typical percentile rank estimate that is in proximity to the ground truth and to determine the least number of sample estimates from a crowd of non-experts that can provide a convenient and accurate estimate of the number of calories in a meal.

AB - A total of 1800 estimates from non-expert dietitians were collected online. This comprised of 120 subjects each providing an estimate per image (120 subjects * 15 images). The overall aim of this study was to use crowdsourcing to determine the accuracy of non-experts in estimating calories in a meal as shown in a photograph. We analyzed percentiles and used bootstrapping with replacement to determine the typical percentile rank estimate that is in proximity to the ground truth and to determine the least number of sample estimates from a crowd of non-experts that can provide a convenient and accurate estimate of the number of calories in a meal.

KW - Crowdsourcing

KW - obesity

KW - standards

KW - estimation

KW - conferences

KW - bioinformatics

KW - Gold

UR - http://10.1109/BIBM.2018.8621166

U2 - 0.1109/BIBM.2018.8621166

DO - 0.1109/BIBM.2018.8621166

M3 - Conference contribution

SN - 978-1-5386-5489-7

SP - 1465

EP - 1469

BT - 2018 IEEE International Conference on Bioinformatics and Biomedicine(BIBM 2018)

PB - IEEE

CY - Madrid, Spain

ER -

Bootstrapping analysis of crowdsourced non-expert estimates of the number of calories in photographs of meals

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this