DeepRecipes: Exploring Massive Online Recipes and Recovering Food Ingredient Amounts
Ingredient amounts are crucial for food-oriented health systems, but this information is seldom used in food-oriented health systems due to the difficulty of fetching it from online recipes. This study proposes a predictive model named DeepRecipes to extract ingredient amounts from online textual re...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9423993/ |
_version_ | 1811273918035525632 |
---|---|
author | Kequan Li Yan Chen Hongsong Li Xiangwei Mu Xuhong Zhang Xiaozhong Liu |
author_facet | Kequan Li Yan Chen Hongsong Li Xiangwei Mu Xuhong Zhang Xiaozhong Liu |
author_sort | Kequan Li |
collection | DOAJ |
description | Ingredient amounts are crucial for food-oriented health systems, but this information is seldom used in food-oriented health systems due to the difficulty of fetching it from online recipes. This study proposes a predictive model named DeepRecipes to extract ingredient amounts from online textual recipes. The model predicts ingredient amounts according to a given recipe’s name and listed ingredients. We train the model on a small set of recipes containing all ingredients and their corresponding amounts. As we can extract the recipe names and ingredients from almost all online recipes, the proposed model can potentially recover ingredient amounts for massive online recipes. We first trained the model on a small set of recipes containing all ingredients and their corresponding amounts. Then, we compared ten models as references for their performances. The performance of DeepRecipes exceeds those of all the comparison models. The model’s mean absolute error (MAE) and mean absolute percentage error (MAPE) are <inline-formula> <tex-math notation="LaTeX">$3.96\times {10}^{-1}$ </tex-math></inline-formula> and 18.57%, respectively, and its APEs are lower than 50% in more than 95% of the total predictions. This accuracy is sufficient for providing rough ingredient amount estimations for food-oriented health systems. |
first_indexed | 2024-04-12T23:09:34Z |
format | Article |
id | doaj.art-9bae4ea0dd214086adbd5325cf4fb944 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-12T23:09:34Z |
publishDate | 2021-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-9bae4ea0dd214086adbd5325cf4fb9442022-12-22T03:12:50ZengIEEEIEEE Access2169-35362021-01-019678596787310.1109/ACCESS.2021.30776459423993DeepRecipes: Exploring Massive Online Recipes and Recovering Food Ingredient AmountsKequan Li0https://orcid.org/0000-0001-7948-2660Yan Chen1Hongsong Li2Xiangwei Mu3Xuhong Zhang4Xiaozhong Liu5School of Maritime Economics and Management, Dalian Maritime University, Dalian, ChinaAlibaba Group, Hangzhou, ChinaAlibaba Group, Hangzhou, ChinaSchool of Maritime Economics and Management, Dalian Maritime University, Dalian, ChinaLuddy School of Informatics, Computing and Engineering, Indiana University Bloomington, Bloomington, IN, USALuddy School of Informatics, Computing and Engineering, Indiana University Bloomington, Bloomington, IN, USAIngredient amounts are crucial for food-oriented health systems, but this information is seldom used in food-oriented health systems due to the difficulty of fetching it from online recipes. This study proposes a predictive model named DeepRecipes to extract ingredient amounts from online textual recipes. The model predicts ingredient amounts according to a given recipe’s name and listed ingredients. We train the model on a small set of recipes containing all ingredients and their corresponding amounts. As we can extract the recipe names and ingredients from almost all online recipes, the proposed model can potentially recover ingredient amounts for massive online recipes. We first trained the model on a small set of recipes containing all ingredients and their corresponding amounts. Then, we compared ten models as references for their performances. The performance of DeepRecipes exceeds those of all the comparison models. The model’s mean absolute error (MAE) and mean absolute percentage error (MAPE) are <inline-formula> <tex-math notation="LaTeX">$3.96\times {10}^{-1}$ </tex-math></inline-formula> and 18.57%, respectively, and its APEs are lower than 50% in more than 95% of the total predictions. This accuracy is sufficient for providing rough ingredient amount estimations for food-oriented health systems.https://ieeexplore.ieee.org/document/9423993/Prediction algorithmsartificial intelligencedeep learningingredient amount prediction |
spellingShingle | Kequan Li Yan Chen Hongsong Li Xiangwei Mu Xuhong Zhang Xiaozhong Liu DeepRecipes: Exploring Massive Online Recipes and Recovering Food Ingredient Amounts IEEE Access Prediction algorithms artificial intelligence deep learning ingredient amount prediction |
title | DeepRecipes: Exploring Massive Online Recipes and Recovering Food Ingredient Amounts |
title_full | DeepRecipes: Exploring Massive Online Recipes and Recovering Food Ingredient Amounts |
title_fullStr | DeepRecipes: Exploring Massive Online Recipes and Recovering Food Ingredient Amounts |
title_full_unstemmed | DeepRecipes: Exploring Massive Online Recipes and Recovering Food Ingredient Amounts |
title_short | DeepRecipes: Exploring Massive Online Recipes and Recovering Food Ingredient Amounts |
title_sort | deeprecipes exploring massive online recipes and recovering food ingredient amounts |
topic | Prediction algorithms artificial intelligence deep learning ingredient amount prediction |
url | https://ieeexplore.ieee.org/document/9423993/ |
work_keys_str_mv | AT kequanli deeprecipesexploringmassiveonlinerecipesandrecoveringfoodingredientamounts AT yanchen deeprecipesexploringmassiveonlinerecipesandrecoveringfoodingredientamounts AT hongsongli deeprecipesexploringmassiveonlinerecipesandrecoveringfoodingredientamounts AT xiangweimu deeprecipesexploringmassiveonlinerecipesandrecoveringfoodingredientamounts AT xuhongzhang deeprecipesexploringmassiveonlinerecipesandrecoveringfoodingredientamounts AT xiaozhongliu deeprecipesexploringmassiveonlinerecipesandrecoveringfoodingredientamounts |