Dataset Information

Yum-Me: A Personalized Nutrient-Based Meal Recommender System.

ABSTRACT: Nutrient-based meal recommendations have the potential to help individuals prevent or manage conditions such as diabetes and obesity. However, learning people's food preferences and making recommendations that simultaneously appeal to their palate and satisfy nutritional expectations are challenging. Existing approaches either only learn high-level preferences or require a prolonged learning period. We propose Yum-me, a personalized nutrient-based meal recommender system designed to meet individuals' nutritional expectations, dietary restrictions, and fine-grained food preferences. Yum-me enables a simple and accurate food preference profiling procedure via a visual quiz-based user interface and projects the learned profile into the domain of nutritionally appropriate food options to find ones that will appeal to the user. We present the design and implementation of Yum-me and further describe and evaluate two innovative contributions. The first contriution is an open source state-of-the-art food image analysis model, named FoodDist. We demonstrate FoodDist's superior performance through careful benchmarking and discuss its applicability across a wide array of dietary applications. The second contribution is a novel online learning framework that learns food preference from itemwise and pairwise image comparisons. We evaluate the framework in a field study of 227 anonymous users and demonstrate that it outperforms other baselines by a significant margin. We further conducted an end-to-end validation of the feasibility and effectiveness of Yum-me through a 60-person user study, in which Yum-me improves the recommendation acceptance rate by 42.63%.

SUBMITTER: Yang L

PROVIDER: S-EPMC6242282 | biostudies-other | 2017 Aug

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Yum-Me: A Personalized Nutrient-Based Meal Recommender System.

Yang Longqi L Hsieh Cheng-Kang CK Yang Hongjian H Pollak John P JP Dell Nicola N Belongie Serge S Cole Curtis C Estrin Deborah D

ACM transactions on information systems 20170801 1

Nutrient-based meal recommendations have the potential to help individuals prevent or manage conditions such as diabetes and obesity. However, learning people's food preferences and making recommendations that simultaneously appeal to their palate and satisfy nutritional expectations are challenging. Existing approaches either only learn high-level preferences or require a prolonged learning period. We propose <i>Yum-me</i>, a personalized nutrient-based meal recommender system designed to meet ...[more]

PMID: 30464375

Similar Datasets

Project description:To explore the effects of fermented rapeseed meal (FRSM) on growth performance and intestinal health, a total of 30 growing pigs were randomly allotted to three treatments consisting of corn-soybean meal diet (CSD), rapeseed meal diet (RSD), and fermented rapeseed meal diet (FRSD). Results showed that compared with RSD, FRSD feeding increased the average daily gain and final body weight in pigs (P < 0.01). Compared with RSD feeding, FRSD feeding elevated the apparent digestibility of crude protein, acid detergent fiber, and ether extract in pigs (P < 0.01). Moreover, the FRSD group exhibited greater apparent ileal digestibility of His, Thr, Lys, and Ser than the RSD group (P < 0.01). The digestible energy, metabolic energy, and nitrogen utilization were higher in the FRSD and CSD groups than in the RSD group (P < 0.01). As compared to the RSD, FRSD feeding decreased the serum concentration of leptin but significantly increased the concentrations of immunoglobulin (Ig) A, IgG, ghrelin, and enzyme activities of amylase, lipase, and trypsin in the pancreas (P < 0.05). Interestingly, the villus height, the ratio of villus height to crypt depth, and the activities of brush border enzymes (e.g., maltase and sucrase) in the small intestine were higher in the CSD and FRSD groups than in the RSD group (P < 0.05). As compared to the RSD, the FRSD feeding not only increased the expression level of the occludin in the small intestinal epithelium (P < 0.05) but also elevated the expression levels of claudin-1, MUC1, and PepT1 genes in the duodenum, and elevated the expression levels of SGLT1 and CAT1 genes in the jejunum (P < 0.05). Importantly, FRSD feeding significantly decreased the abundance of Escherichia coli, but increased the abundance of Lactobacillus and the content of butyrate in the cecum and colon (P < 0.05). These results indicated that compared with rapeseed meal, fermented rapeseed meal exhibited a positive effect on improving the growth performance and intestinal health in growing pigs, and the results may also help develop novel protein sources for animal nutrition and the feed industry.

Dataset Information

Yum-Me: A Personalized Nutrient-Based Meal Recommender System.

Publications

Yum-Me: A Personalized Nutrient-Based Meal Recommender System.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets