共找到 20 条结果
The flavor and aroma development in fermented foods is intricately tied to the mixing dynamics during fermentation. This review explores how variations in mixing influence the physical, chemical, and microbial interactions within fermentation systems, ultimately affecting sensory characteristics such as flavor and aroma. Factors like rheology, shear forces, and fluid flow patterns are critical in mass transfer, microbial activity, and the release of volatile compounds, contributing to fermented products' sensory profile. Examples from common fermented foods -- including bread, yogurt, beer, wine, and cheese -- highlight how controlled mixing can optimize the release of desirable flavor compounds, improve biosynthesis yields, and reduce technological complexity. Understanding these physical interactions is essential for advancing fermentation processes in the food industry, leading to higher product quality, better flavor retention, and enhanced consumer satisfaction.
Accurate food intake monitoring is crucial for maintaining a healthy diet and preventing nutrition-related diseases. With the diverse range of foods consumed across various cultures, classic food classification models have limitations due to their reliance on fixed-sized food datasets. Studies show that people consume only a small range of foods across the existing ones, each consuming a unique set of foods. Existing class-incremental models have low accuracy for the new classes and lack personalization. This paper introduces a personalized, class-incremental food classification model designed to overcome these challenges and improve the performance of food intake monitoring systems. Our approach adapts itself to the new array of food classes, maintaining applicability and accuracy, both for new and existing classes by using personalization. Our model's primary focus is personalization, which improves classification accuracy by prioritizing a subset of foods based on an individual's eating habits, including meal frequency, times, and locations. A modified version of DSN is utilized to expand on the appearance of new food classes. Additionally, we propose a comprehensive framework t
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 pr
Food packing industry workers typically pick a target amount of food by hand from a food tray and place them in containers. Since menus are diverse and change frequently, robots must adapt and learn to handle new foods in a short time-span. Learning to grasp a specific amount of granular food requires a large training dataset, which is challenging to collect reasonably quickly. In this study, we propose ways to reduce the necessary amount of training data by augmenting a deep neural network with models that estimate its uncertainty through self-supervised learning. To further reduce human effort, we devise a data collection system that automatically generates labels. We build on the idea that we can grasp sufficiently well if there is at least one low-uncertainty (high-confidence) grasp point among the various grasp point candidates. We evaluate the methods we propose in this work on a variety of granular foods -- coffee beans, rice, oatmeal and peanuts -- each of which has a different size, shape and material properties such as volumetric mass density or friction. For these foods, we show significantly improved grasp accuracy of user-specified target masses using smaller datasets
Robotic Assisted Feeding (RAF) addresses the fundamental need for individuals with mobility impairments to regain autonomy in feeding themselves. The goal of RAF is to use a robot arm to acquire and transfer food to individuals from the table. Existing RAF methods primarily focus on solid foods, leaving a gap in manipulation strategies for semi-solid and deformable foods. This study introduces Long-horizon Visual Action (LAVA) based food acquisition of liquid, semisolid, and deformable foods. Long-horizon refers to the goal of "clearing the bowl" by sequentially acquiring the food from the bowl. LAVA employs a hierarchical policy for long-horizon food acquisition tasks. The framework uses high-level policy to determine primitives by leveraging ScoopNet. At the mid-level, LAVA finds parameters for primitives using vision. To carry out sequential plans in the real world, LAVA delegates action execution which is driven by Low-level policy that uses parameters received from mid-level policy and behavior cloning ensuring precise trajectory execution. We validate our approach on complex real-world acquisition trials involving granular, liquid, semisolid, and deformable food types along w
We present an astonishingly simple and elegant proof of the celebrated Basel problem.
There is rising evidence of the health benefit associated with specific dietary interventions. Current food-disease databases focus on associations and treatment relationships but haven't provided a reasonable assessment of the strength of the relationship, and lack of attention on food nutrition. There is an unmet need for a large database that can guide dietary therapy. We fill the gap with NutriFD, a scoring network based on associations and therapeutic relationships between foods and diseases. NutriFD integrates 9 databases including foods, nutrients, diseases, genes, miRNAs, compounds, disease ontology and their relationships. To our best knowledge, this database is the only one that can score the associations and therapeutic relationships of everyday foods and diseases by weighting inference scores of food compounds to diseases. In addition, NutriFD demonstrates the predictive nature of nutrients on the therapeutic relationships between foods and diseases through machine learning models, laying the foundation for a mechanistic understanding of food therapy.
This chapter explores the evolution, classification, and health implications of food processing, while emphasizing the transformative role of machine learning, artificial intelligence (AI), and data science in advancing food informatics. It begins with a historical overview and a critical review of traditional classification frameworks such as NOVA, Nutri-Score, and SIGA, highlighting their strengths and limitations, particularly the subjectivity and reproducibility challenges that hinder epidemiological research and public policy. To address these issues, the chapter presents novel computational approaches, including FoodProX, a random forest model trained on nutrient composition data to infer processing levels and generate a continuous FPro score. It also explores how large language models like BERT and BioBERT can semantically embed food descriptions and ingredient lists for predictive tasks, even in the presence of missing data. A key contribution of the chapter is a novel case study using the Open Food Facts database, showcasing how multimodal AI models can integrate structured and unstructured data to classify foods at scale, offering a new paradigm for food processing assess
$ $As a result of bad eating habits, humanity may be destroyed. People are constantly on the lookout for tasty foods, with junk foods being the most common source. As a consequence, our eating patterns are shifting, and we're gravitating toward junk food more than ever, which is bad for our health and increases our risk of acquiring health problems. Machine learning principles are applied in every aspect of our lives, and one of them is object recognition via image processing. However, because foods vary in nature, this procedure is crucial, and traditional methods like ANN, SVM, KNN, PLS etc., will result in a low accuracy rate. All of these issues were defeated by the Deep Neural Network. In this work, we created a fresh dataset of 10,000 data points from 20 junk food classifications to try to recognize junk foods. All of the data in the data set was gathered using the Google search engine, which is thought to be one-of-a-kind in every way. The goal was achieved using Convolution Neural Network (CNN) technology, which is well-known for image processing. We achieved a 98.05\% accuracy rate throughout the research, which was satisfactory. In addition, we conducted a test based on a
In the field of food, as in other fields, the measurement of emotional responses to food and their sensory properties is a major challenge. In the present protocol, we propose a step-by-step procedure that allows a physiological description of odors, aromas, and their hedonic properties. The method rooted in subgroup discovery belongs to the field of data science and especially data mining. It is still little used in the field of food and is based on a descriptive modeling of emotions on the basis of human physiological responses.
The issue of food waste is a major problem contributing to the emission of greenhouse gases into the environment in addition to causing illness in humans. This research aimed to develop a correlation between the amount of time until a food spoiled and dates on food labels in conjunction with sensory observations. Sensory observations are more accurate as they are immediate observations that are specific to the food. This experiment observed bananas, bread, milk, eggs, and leafy greens over a period of time using characteristics specific to the food to quantify food spoilage. It was shown that the actual time until spoilage for all foods was longer than that of the best by date and that sensory observations proved to be a more accurate factor in determining spoilage. From this data, a machine learning algorithm was trained to predict if food was spoiled or not, in addition to the number of days until spoilage. This was presented to the consumer as an app, where the user can track foods and are reminded to check on them to prevent wastage. In addition, the experimental procedures were incorporated into a test kit for the consumer to take instructed observations to assess the spoilage
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 brand
A robotic feeding system must be able to acquire a variety of foods. Prior bite acquisition works consider single-arm spoon scooping or fork skewering, which do not generalize to foods with complex geometries and deformabilities. For example, when acquiring a group of peas, skewering could smoosh the peas while scooping without a barrier could result in chasing the peas on the plate. In order to acquire foods with such diverse properties, we propose stabilizing food items during scooping using a second arm, for example, by pushing peas against the spoon with a flat surface to prevent dispersion. The added stabilizing arm can lead to new challenges. Critically, this arm should stabilize the food scene without interfering with the acquisition motion, which is especially difficult for easily breakable high-risk food items like tofu. These high-risk foods can break between the pusher and spoon during scooping, which can lead to food waste falling out of the spoon. We propose a general bimanual scooping primitive and an adaptive stabilization strategy that enables successful acquisition of a diverse set of food geometries and physical properties. Our approach, CARBS: Coordinated Acquisi
Recent progresses in data-driven analysis methods, including network-based approaches, are revolutionizing many classical disciplines. These techniques can also be applied to food and nutrition, which must be studied to design healthy diets. Using nutritional information from over 1,000 raw foods, we systematically evaluated the nutrient composition of each food in regards to satisfying daily nutritional requirements. The nutrient balance of a food was quantified herein as nutritional fitness, using the food's frequency of occurrence in nutritionally adequate food combinations. Nutritional fitness offers prioritization of recommendable foods within a global network of foods, in which foods are connected based on the similarities of their nutrient compositions. We identified a number of key nutrients, such as choline and alpha-linolenic acid, whose levels in foods can critically affect the foods' nutritional fitness. Analogously, pairs of nutrients can have the same effect. In fact, two nutrients can impact the nutritional fitness synergistically, although the individual nutrients alone may not. This result, involving the tendency among nutrients to show correlations in their abunda
In this study we test whether principal components of the strain rate and stress tensors align within Switzerland. We find that 1) Helvetic Nappes line (HNL) is the relevant tectonic boundary to define different domains of crustal stress/surface strain rates orientations and 2) orientations of T- axes (of moment tensor solutions) and long-term asthenosphere cumulative finite strain (from SKS shear wave splitting) are consistent at the scale of the Alpine arc in Switzerland. At a more local scale, we find that seismic activity and surface deformation are in agreement but in three regions (Basel, Swiss Jura and Ticino); possibly because of the low levels of deformation and/or seismicity. In the Basel area, deep seismicity exists while surface deformation is absent. In the Ticino and the Swiss Jura, where seismic activity is close to absent, surface deformation is detected at a level of ~2 10E-8/yr (~6.3 10E-16/s).
The Basel problem consists in finding the sum of the reciprocals of the squares of the positive integers. It was finally solved in 1735 by Leonhard Euler. In this paper, we propose a simple proof based on the Weierstrass Sine product formula and L'Hôpital's rule.
We present SwissBERT, a masked language model created specifically for processing Switzerland-related text. SwissBERT is a pre-trained model that we adapted to news articles written in the national languages of Switzerland -- German, French, Italian, and Romansh. We evaluate SwissBERT on natural language understanding tasks related to Switzerland and find that it tends to outperform previous models on these tasks, especially when processing contemporary news and/or Romansh Grischun. Since SwissBERT uses language adapters, it may be extended to Swiss German dialects in future work. The model and our open-source code are publicly released at https://github.com/ZurichNLP/swissbert.
On 22 September 2023 the inauguration of the "Stachelschützenhaus" at Basel's Petersplatz (St. Peter's Square) as an EPS Historic Site was hosted by the University of Basel. In the following article we will focus first on Daniel Bernoulli's career path, before discussing his major scientific achievements and finally adding some aspects of the inauguration ceremony (the colloquium talks, the visit of today's laboratories in the Stachelschützenhaus, and the unveiling of the plaque).
Switzerland experienced one of the warmest summers during 2022. Extreme heat has been linked to increased mortality. Monitoring the mortality burden attributable to extreme heat is crucial to inform policies, such as heat warnings, and prevent heat-related deaths. In this study, we evaluate excess mortality during summer 2022, identify vulnerable populations and estimate temperature thresholds for heat warnings. We use nationwide mortality and population data in Switzerland during 2011-2022 by age, sex, day and canton. We develop a Bayesian ensemble modelling approach with dynamic population to predict expected mortality in summer 2022 and calculate excess by comparing expected with observed mortality. We account for covariates associated with mortality such as ambient temperature, national holidays and spatiotemporal random effects to improve predictions. After accounting for the effect of the COVID-19 pandemic, we found a 3% (95% credible interval: 0%-6%) excess mortality during summer 2022. We observed a total of 456 (5-891) excess deaths during summer 2022 in people older than 80 years. There was weak evidence of excess mortality in the other age groups. The highest excess mort
This survey analyzed the quality of the PDF documents on online repositories in Switzerland, examining their accessibility for people with visual impairments. Two minimal accessibility features were analyzed: the PDFs had to have tags and a hierarchical heading structure. The survey also included interviews with the managers or heads of multiple Swiss universities' repositories to assess the general opinion and knowledge of PDF accessibility. An analysis of interviewee responses indicates an overall lack of awareness of PDF accessibility, and showed that online repositories currently have no concrete plans to address the issue. This paper concludes by presenting a set of recommendations for online repositories to improve the accessibility of their PDF documents.