Hasil untuk "Nutrition. Foods and food supply"

Yuhao Chen, Gautham Vinod, Siddeshwar Raghavan et al.

We present Implicit-Scale 3D Reconstruction from Monocular Multi-Food Images, a benchmark dataset designed to advance geometry-based food portion estimation in realistic dining scenarios. Existing dietary assessment methods largely rely on single-image analysis or appearance-based inference, including recent vision-language models, which lack explicit geometric reasoning and are sensitive to scale ambiguity. This benchmark reframes food portion estimation as an implicit-scale 3D reconstruction problem under monocular observations. To reflect real-world conditions, explicit physical references and metric annotations are removed; instead, contextual objects such as plates and utensils are provided, requiring algorithms to infer scale from implicit cues and prior knowledge. The dataset emphasizes multi-food scenes with diverse object geometries, frequent occlusions, and complex spatial arrangements. The benchmark was adopted as a challenge at the MetaFood 2025 Workshop, where multiple teams proposed reconstruction-based solutions. Experimental results show that while strong vision--language baselines achieve competitive performance, geometry-based reconstruction methods provide both improved accuracy and greater robustness, with the top-performing approach achieving 0.21 MAPE in volume estimation and 5.7 L1 Chamfer Distance in geometric accuracy.

Elizabeth K Dunford, Mona S Calvo

Nalin Arora, Aviral Chauhan, Siddhant Rana et al.

Ultra-processed foods are increasingly linked to health issues like obesity, cardiovascular disease, type 2 diabetes, and mental health disorders due to poor nutritional quality. This first-of-its-kind study at such a scale uses machine learning to classify food processing levels (NOVA) based on the Open Food Facts dataset of over 900,000 products. Models including LightGBM, Random Forest, and CatBoost were trained on nutrient concentration data. LightGBM performed best, achieving 80-85% accuracy across different nutrient panels and effectively distinguishing minimally from ultra-processed foods. Exploratory analysis revealed strong associations between higher NOVA classes and lower Nutri-Scores, indicating poorer nutritional quality. Products in NOVA 3 and 4 also had higher carbon footprints and lower Eco-Scores, suggesting greater environmental impact. Allergen analysis identified gluten and milk as common in ultra-processed items, posing risks to sensitive individuals. Categories like Cakes and Snacks were dominant in higher NOVA classes, which also had more additives, highlighting the role of ingredient modification. This study, leveraging the largest dataset of NOVA-labeled products, emphasizes the health, environmental, and allergenic implications of food processing and showcases machine learning's value in scalable classification. A user-friendly web tool is available for NOVA prediction using nutrient data: https://cosylab.iiitd.edu.in/foodlabel/.

Bruce Coburn, Jiangpeng He, Megan E. Rollo et al.

Large Multimodal Models (LMMs) are increasingly applied to meal images for nutrition analysis. However, existing work primarily evaluates proprietary models, such as GPT-4. This leaves the broad range of LLMs underexplored. Additionally, the influence of integrating contextual metadata and its interaction with various reasoning modifiers remains largely uncharted. This work investigates how interpreting contextual metadata derived from GPS coordinates (converted to location/venue type), timestamps (transformed into meal/day type), and the food items present can enhance LMM performance in estimating key nutritional values. These values include calories, macronutrients (protein, carbohydrates, fat), and portion sizes. We also introduce \textbf{ACETADA}, a new food-image dataset slated for public release. This open dataset provides nutrition information verified by the dietitian and serves as the foundation for our analysis. Our evaluation across eight LMMs (four open-weight and four closed-weight) first establishes the benefit of contextual metadata integration over straightforward prompting with images alone. We then demonstrate how this incorporation of contextual information enhances the efficacy of reasoning modifiers, such as Chain-of-Thought, Multimodal Chain-of-Thought, Scale Hint, Few-Shot, and Expert Persona. Empirical results show that integrating metadata intelligently, when applied through straightforward prompting strategies, can significantly reduce the Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) in predicted nutritional values. This work highlights the potential of context-aware LMMs for improved nutrition analysis.

Bianca Datta, Markus J. Buehler, Yvonne Chow et al.

Global food systems must deliver nutritious and sustainable foods while sharply reducing environmental impact. Yet, food innovation remains slow, empirical, and fragmented. Artificial intelligence (AI) now offers a transformative path with the potential to link molecular composition to functional performance, bridge chemical structure to sensory outcomes, and accelerate cross-disciplinary innovation across the entire production pipeline. Here we outline AI for Food as an emerging discipline that integrates ingredient design, formulation development, fermentation and production, texture analysis, sensory properties, manufacturing, and recipe generation. Early successes demonstrate how AI can predict protein performance, map molecules to flavor, and tailor consumer experiences. But significant challenges remain: lack of standardization, scarce multimodal data, cultural and nutritional diversity, and low consumer confidence. We propose three priorities to unlock the field: treating food as a programmable biomaterial, building self-driving laboratories for automated discovery, and developing deep reasoning models that integrate sustainability and human health. By embedding AI responsibly into the food innovation cycle, we can accelerate the transition to sustainable protein systems and chart a predictive, design-driven science of food for our own health and the health of our planet.

Ali Rostami, Z Xie, A Ishino et al.

A coronavirus pandemic is forcing people to be "at home" all over the world. In a life of hardly ever going out, we would have realized how the food we eat affects our bodies. What can we do to know our food more and control it better? To give us a clue, we are trying to build a World Food Atlas (WFA) that collects all the knowledge about food in the world. In this paper, we present two of our trials. The first is the Food Knowledge Graph (FKG), which is a graphical representation of knowledge about food and ingredient relationships derived from recipes and food nutrition data. The second is the FoodLog Athl and the RecipeLog that are applications for collecting people's detailed records about food habit. We also discuss several problems that we try to solve to build the WFA by integrating these two ideas.

Elyse S. Czapalay, Yasamin Soleimanian, Jarvis A. Stobbs et al.

Cellulosic scaffolds filled with oil were designed to replicate animal adipose tissues. Many plants are structured as polysaccharide-based cellular solids. They maintain their integrity after drying, can serve as a scaffold for incorporating fat, and do not lose integrity upon heating, thus resembling native adipose tissue. Carrots, broccoli, and asparagus were freeze-dried and subsequently filled with peanut oil, its glycerolysis product (GP), and the oleogel of this GP. Oleogel-filled scaffolds displayed high oil binding capacity (≥95%), and an oil loss resembling that of adipose tissue. In addition, the texture of oleogel-filled asparagus and broccoli tissue closely resembled that of beef and pork adipose tissues, respectively. Plant scaffolds closely emulated the temperature-dependent rheological behavior of adipose tissue. These new materials could significantly improve the quality of plant-based meat analogues, such as burgers and sausages, by preventing the thermal softening of the material upon cooking and excessive oil loss.

Marco E Toc Sagra, Peter Weng, Diego V Bohórquez

Carla Gonçalves, Carla Gonçalves, Carla Gonçalves et al.

Ignasius Radix Astadi Praptono Jati, Adrianus Rulianto Utomo, Erni Setijawaty et al.

Abstract The aims of this research are to investigate the effects of different concentrations of butterfly pea flower extract infusion as an active agent on the properties of durian fruit albedo and eggshell-based smart edible films. The butterfly pea flower was extracted using water with the ratios of 1:50 (T1), 1:100 (T2), 1:150 (T3), 1:200 (T4), 1:250 (T5), and 1:300 (T6) (w/v). The film was formulated using durian albedo, eggshell, sorbitol, and cornstarch, which was mixed with butterfly pea flower extract and mold using the casting method. The analysis performed included anthocyanin and phenolic content, antioxidant activity, tensile strength, elongation, water vapor transmission rate, scanning electron microscopy, Fourier transform infrared spectroscopy, and smart indicator examination using fresh milk model system. Different concentrations of butterfly pea extract affect the physicochemical properties of smart edible film. The increase in extract concentration increased anthocyanin and phenolic contents, which align with the increase in antioxidant activity. Meanwhile, the presence of bioactive compounds in the formulation reduced the tensile strength of the film and increased its elongation, as confirmed by SEM and FTIR results. Smart edible film can act as an indicator in the fresh milk model by changing color according to the change in pH due to milk spoilage.

Svenja M Jungjohann, Valerie M Friesen, Mduduzi N Mbuya et al.

Yunke Zhang, Yiran Fan, Peijie Liu et al.

Online-to-offline (O2O) food delivery platforms have greatly expanded urban residents' access to a wide range of food options by allowing convenient ordering from distant food outlets. However, concerns persist regarding the nutritional quality of delivered food, particularly as the impact of O2O food delivery platforms on users' healthy food remains unclear. This study leverages large-scale empirical data from a leading O2O delivery platform to comprehensively analyze online food choice behaviors and how they are influenced by the online exposure to fast food restaurants, i.e., online food environment. Our analyses reveal significant variations in food preferences across demographic groups and city sizes, where male, low-income, and younger users are more likely to order fast food via O2O platforms. Besides, we also perform a comparative analysis on the food exposure differences in offline and online environments, confirming that the extended service ranges of O2O platforms can create larger "cyber food swamps". Furthermore, regression analysis highlights that a higher ratio of fast food orders is associated with "cyber food swamps", areas characterized by a higher proportion of accessible fast food restaurants. A 10% increase in this proportion raises the probability of ordering fast food by 22.0%. Moreover, a quasi-natural experiment substantiates the long-term causal effect of online food environment changes on healthy food choices. These findings underscore the need for O2O food delivery platforms to address the health implications of online food choice exposure, offering critical insights for stakeholders aiming to improve dietary health among urban populations.

Tutut Rizki Indriyani, Atika Rahmawati, Luthfiani Khoirunnisa et al.

Background: Obesity is still become a serious problem today. Obesity is caused by excessive adipose tissue. One of many factors that contribute to a person's obesity is food intake. Excess carbohydrate and fat intake will be stored in the form of triglycerides in adipose tissue. In the meantime, Low-Carb Diet (LCD) and Low-Fat Diet (LFD) are one of the most popular treatments on obesity. However there are many pros and cons related to each diet based on several studies. Objectives: The indicated study aims to determine the effectiveness of LCD and LFD on body composition in people with obesity. Methods: The study was conducted through journal and literature review, based on five journal publications, filtered by related keywords. In accordance to inclusion and exclusion criteria within the last ten years in Pubmed/Medline database, Science Direct, and Wiley Online Library with the keywords "Low-Carb Diet", "Low-Fat Diet", "Body Mass Index", "Lipid Levels", "Adipose Tissue", "Obese", and "Body Water". Discussion: Total body mass and fat mass decreased significantly after being given LCD intervention compared to LFD. The group that was given two dietary interventions also losing weight, but there was no changes in body water. In addition, negative effects were found from the LCD and LFD interventions such as constipation, fatigue, polyuria, nausea, vomiting, changes in appetite, and headaches. Kidney failure, ketosis, and premature coronary artery also occurred in the group that was given with LCD intervention. Conclusions: LCD and LFD interventions can affect body composition of people with obesity.

Rahele Sadeghzadeh, Fatemeh Rafieian, Mahdi Keshani et al.

Pseudomonas aeruginosa is a Gram-negative human pathogenic bacterium that has the ability to form multicellular biofilm (BF) communities. Due to the presence of extracellular polymeric substances, BF protects bacteria from unfavorable environmental conditions and causes their resistance to antimicrobial substances. The presence of BF in the food industry has become a great threat to food safety. Conventional disinfection technologies are inappropriate for effective BF control due to the resistances created to them and the toxic residues for humans and the environment that they leave behind. Therefore, it is necessary to understand more about the formation and development of BF and environmentally friendly methods to remove BF from food and equipment in contact with food. This review article describes BF formation, its resistance mechanisms to antimicrobial agents, and BF development. Also, novel and effective strategies involved in BF removal are discussed including physical methods (plasma, pulsed electric field and ultrasonication), physicochemical method (electrolyzed water), biological methods (enzymes and bacteriophages), natural compounds such as essential oils, and application of nanomaterials.

In-In Hanidah, Siti Nurhasanah, Sumanti Debby Moody et al.

Inulin is a polysaccharide composed of 2-60 fructose monomers linked by β-(2,1) glycosidic bonds, with a glucose end group. The tuber of Musa balbisiana Colla (batu banana) is a part of the M. balbisiana Colla plant that contains dietary fiber 6,20%. The polysaccharide content allowed the batu banana tubers  to contain inulin. The aim of this study was to determine the characteristics of inulin in batu banana tubers. The research method used was the experimental method, which was analyzed descriptively with two replicates at the Universitas Padjadjaran Laboratory of Jatinangor – Sumedang from May until October 2023. The parameters were inulin content, degree of polymerization (DP), reducing sugar content, moisture content, pH, solubility, water activity (aw), color L*, a*, and  b*, viscosity, and sensory analysis using a descriptive method. The results showed that B. tuber inulin had an inulin content of 3,58%, DP of 2,8, reducing sugar content of 2,03%,  moisture content of 8,47%, pH of 6,31, solubility of 21,70% (90°C), aw of 0,432, L* of 66,76, a* of 8,28, b* of 15,90, and viscosity of 2068 mPas (90°C). In conclusion, sensory analysis showed that batu banana tuber inulin has a darker color, bitter taste, stronger flavor, and softer texture than the commercial inulin.

Xin Meng, Fang Wang, Chao-Hong Fu et al.

Osmanthus fragrans is an evergreen shrub with a pleasant fragrance and a wide range of applications in many fields. The condensed hydrolat obtained during the drying process of its fresh flowers was collected in a low-temperature vacuum environment and its sensory evaluation and volatile components were studied. The main aroma compounds in Osmanthus fragrans were dihydro-β-ionone, nonanal, β-cyclocitral, β-ionone, benzaldehyde, α-ionone, and 6-methyl-5-hepten-2-one, whose contents were used as the main evaluation criteria, and the hydrolats obtained under different scenting and drying times were compared. This process can effectively collect the aroma components in Osmanthus fragrans and the optimal drying conditions were 50 °C for 5 h. The hydrolat was used to provide the scent of osmanthus black tea, which had a fresher and mellower taste, while the fragrance of osmanthus was abundant. These results show that osmanthus hydrolat can be used to provide the scent of floral black tea. Chemical compounds studied in this article: (−)-Catechin (PubChem CID: 1203); (−)-epigallocatechin gallate (PubChem CID: 65064); (−)-epicatechin gallate (PubChem CID: 367141); (−)-epigallocatechin (PubChem CID: 72277); (−)-epicatechin (PubChem CID: 72276); (−)-gallocatechin gallate (PubChem CID: 199472); (−)-catechin gallate (PubChem CID: 6419835); (−)-gallocatechin (PubChem CID: 9882981).

Yuzhe Han, Qimin Cheng, Wenjin Wu et al.

A reasonable and balanced diet is essential for maintaining good health. With advancements in deep learning, an automated nutrition estimation method based on food images offers a promising solution for monitoring daily nutritional intake and promoting dietary health. While monocular image-based nutrition estimation is convenient, efficient and economical, the challenge of limited accuracy remains a significant concern. To tackle this issue, we proposed DPF-Nutrition, an end-to-end nutrition estimation method using monocular images. In DPF-Nutrition, we introduced a depth prediction module to generate depth maps, thereby improving the accuracy of food portion estimation. Additionally, we designed an RGB-D fusion module that combined monocular images with the predicted depth information, resulting in better performance for nutrition estimation. To the best of our knowledge, this was the pioneering effort that integrated depth prediction and RGB-D fusion techniques in food nutrition estimation. Comprehensive experiments performed on Nutrition5k evaluated the effectiveness and efficiency of DPF-Nutrition.

Mansi Goel, Shashank Dargar, Shounak Ghatak et al.

Diet is central to the epidemic of lifestyle disorders. Accurate and effortless diet logging is one of the significant bottlenecks for effective diet management and calorie restriction. Dish detection from food platters is a challenging problem due to a visually complex food layout. We present an end-to-end computational framework for diet management, from data compilation, annotation, and state-of-the-art model identification to its mobile app implementation. As a case study, we implement the framework in the context of Indian food platters known for their complex presentation that poses a challenge for the automated detection of dishes. Starting with the 61 most popular Indian dishes, we identify the state-of-the-art model through a comparative analysis of deep-learning-based object detection architectures. Rooted in a meticulous compilation of 68,005 platter images with 134,814 manual dish annotations, we first compare ten architectures for multi-label classification to identify ResNet152 (mAP=84.51%) as the best model. YOLOv8x (mAP=87.70%) emerged as the best model architecture for dish detection among the eight deep-learning models implemented after a thorough performance evaluation. By comparing with the state-of-the-art model for the IndianFood10 dataset, we demonstrate the superior object detection performance of YOLOv8x for this subset and establish Resnet152 as the best architecture for multi-label classification. The models thus trained on richly annotated data can be extended to include dishes from across global cuisines. The proposed framework is demonstrated through a proof-of-concept mobile application with diverse applications for diet logging, food recommendation systems, nutritional interventions, and mitigation of lifestyle disorders.

Peihua Ma, Yixin Wu, Ning Yu et al.

Nutrition information is crucial in precision nutrition and the food industry. The current food composition compilation paradigm relies on laborious and experience-dependent methods. However, these methods struggle to keep up with the dynamic consumer market, resulting in delayed and incomplete nutrition data. In addition, earlier machine learning methods overlook the information in food ingredient statements or ignore the features of food images. To this end, we propose a novel vision-language model, UMDFood-VL, using front-of-package labeling and product images to accurately estimate food composition profiles. In order to empower model training, we established UMDFood-90k, the most comprehensive multimodal food database to date, containing 89,533 samples, each labeled with image and text-based ingredient descriptions and 11 nutrient annotations. UMDFood-VL achieves the macro-AUCROC up to 0.921 for fat content estimation, which is significantly higher than existing baseline methods and satisfies the practical requirements of food composition compilation. Meanwhile, up to 82.2% of selected products' estimated error between chemical analysis results and model estimation results are less than 10%. This performance sheds light on generalization towards other food and nutrition-related data compilation and catalyzation for the evolution of generative AI-based technology in other food applications that require personalization.

Lexington Whalen, Brie Turner-McGrievy, Matthew McGrievy et al.

Studies with the primary aim of addressing eating disorders focus on assessing the nutrient content of food items with an exclusive focus on caloric intake. There are two primary impediments that can be noted in these studies. The first of these relates to the fact that caloric intake of each food item is calculated from an existing database. The second concerns the scientific significance of caloric intake used as the single measure of nutrient content. By requiring an existing database, researchers are forced to find some source of a comprehensive set of food items as well as their respective nutrients. This search alone is a difficult task, and if completed often leads to the requirement of a paid API service. These services are expensive and non-customizable, taking away funding that could be aimed at other parts of the study only to give an unwieldy database that can not be modified or contributed to. In this work, we introduce a new rendition of the USDA's food database that includes both foods found in grocery stores and those found in restaurants or fast food places. At the moment, we have accumulated roughly 1.5 million food entries consisting of approximately 18,000 brands and 100 restaurants in the United States. These foods also have an abundance of nutrient data associated with them, from the caloric amount to saturated fat levels. The data is stored in MySQL format and is spread among five major tables. We have also procured images for theses foods entries when available, and have included all of our data and program scripts in an open source repository.