Abstract: Techniques to suggest a set of source ingredients that can be used to recreate functional properties of a target food item, using artificial intelligence, are disclosed. A computer model determines, for the target food item, an ingredient quantities vector and an ingredient inclusion vector based on a matrix of chemical compound source ingredient vectors of all source ingredients. The ingredient inclusion vector indicates which source ingredients from a plurality of source ingredients to include in the ingredient set, and the ingredient quantities vector indicates the quantity or amount of each source ingredient such that a corresponding volatile profile of the ingredient set is similar to that of the target food item. A volatile profile for the ingredient set, which is determined from the matrix of chemical compound source ingredient vectors, the ingredient inclusion vector, and the ingredient quantities vector, mimics the target food item's volatile profile.

Abstract: An in vitro dynamic mouth model includes an upper jaw that includes a plurality of protuberances simulating human teeth, a lower jaw that is coupled with a rounded silicone pad simulating human tongue, and a mouth wall that encapsulates food sample(s) subjected to in vitro mastication such that the food sample remains within the mouth model. The mouth wall contains at least one hole that allows injection of simulated saliva fluid. As simulated chewing takes place, the injected fluid directly interacts with the food sample.

Abstract: An artificial intelligence model receives a FTIR spectrum of a given ingredient to predict its protein secondary structure. The model includes three artificial modules, which generate three predicted values corresponding to structural categories (e.g., ?-helix, ?-sheet, and other) of the predicted secondary structure. Proteins may be compared for similarity based on predicted values corresponding to the structural categories of the predicted secondary structure.

Abstract: Techniques to generate a flavor profile using artificial intelligence are disclosed. A flavor classifier classifies flavors for a given set of ingredients of a recipe from a set of possible classes of flavors. The flavor classifier may use different deep learning models to allow for different granularity levels corresponding to each flavor based on desired preciseness with classification of a particular flavor. A respective flavor predictor may or may not be used for each granularity level based on output of a certainty level classifier used for determining a preceding level of granularity.

Abstract: A gastrointestinal simulator system includes a thermoregulated bath, two glass beakers situated within the thermoregulated water bath, and a pump. The beakers simulate the stomach and intestines and are coupled together using a tube. A sieve, positioned within the “stomach,” has a plurality of 2 mm holes on its surface to mimic in vivo conditions, where only particles smaller than 2 mm in diameter are transferred to the “intestines.” These collected particles move from “stomach” (specifically, from the sieve) to the “intestines” through the tube coupling the beakers. Cameras may be located inside the water bath for monitoring/recording of the digestion. Alerts, such as voice alerts, may be generated to notify users of any important information and instructions. After digestion, reports of the digestion are automatically generated and stored in a data repository. One or more users are notified that the reports are available for access.

Abstract: Techniques to generate experiment trials using artificial intelligence are disclosed. A training set for an experiment generator is continuously built up by using assessed experiment trials. The experiment generator is optimized using one of a plurality of optimization algorithms, depending on which mode experiment generator is to run in for an experiment. The mode is dependent on the experiment mode of the experiment. The experiment generator generates a batch of one or more experiment trials for the experiment. Any of the generated experiment trials may be tried or experimented by a user and may be updated with assessment data as an assessed experiment trial.

Abstract: Techniques to suggest chemical compounds with a desired flavor profile or that can be used to recreate functional properties of a target chemical compound, using artificial intelligence, are disclosed. An artificial intelligence model is trained on source chemical compounds with known flavors. The artificial intelligence model learns relationships between the source chemical compounds and their known flavors and generates source chemical compound projected embeddings and true flavor projected embeddings. From either the source chemical compound projected embeddings or the true flavor projected embeddings, one or more chemical compounds for the identified target chemical compound or the identified desired flavor profile may be determined based on a similarity search.

Abstract: Techniques to suggest a set of source ingredients that can be used to recreate functional properties of a target food item, using artificial intelligence, are disclosed. A computer model determines, for the target food item, an ingredient quantities vector and an ingredient inclusion vector based on a matrix of chemical compound source ingredient vectors of all source ingredients. The ingredient inclusion vector indicates which source ingredients from a plurality of source ingredients to include in the ingredient set, and the ingredient quantities vector indicates the quantity or amount of each source ingredient such that a corresponding volatile profile of the ingredient set is similar to that of the target food item. A volatile profile for the ingredient set, which is determined from the matrix of chemical compound source ingredient vectors, the ingredient inclusion vector, and the ingredient quantities vector, mimics the target food item's volatile profile.

Abstract: Techniques to suggest alternative chemical compounds that can be used to recreate or mimic a target flavor using artificial intelligence are disclosed. A neural network based model is trained on source chemical compounds and their corresponding flavors and odors. The neural network-based model learns compound embeddings of the source chemical compounds and a target chemical compound of a food item. From the compound embeddings, one or more chemical compounds that are closest to the target chemical compound may be determined by a distance metric. Each suggested chemical compound is an alternative that can be used to recreate functional features of the target chemical compound.

Abstract: Techniques to mimic a target food item using artificial intelligence are disclosed. A formula generator is trained using ingredients and using recipes and, given a target food item, determines a formula that matches the given target food item. A flavor generator is trained using recipes and their associated flavor information and, given a formula, the flavor generator determines a flavor profile for the given formula. The flavor profile may be used to assist the formula generator in generating a subsequent formula. A recipe generator is trained using recipes and, given a formula, determines a cooking process for the given formula. A food item may be cooked according to a recipe, and feedback, including a flavor profile, may be provided for the cooked food item. The recipe and its feedback may be added to a training set for the flavor generator.

Abstract: Systems and methods to mimic a target food item using artificial intelligence are disclosed. The system can learn from open source and proprietary databases. A prediction model can be trained using features of the source ingredients to match those of the given target food item. A formula comprising a combination of most relevant source ingredients and their proportions can be determined using the trained prediction model. A set of existing recipes can be used as a dataset to train a recurrent neural network (RNN) and/or other suitable models. The RNN can be used to determine a recipe to mimic the target food item. The recipe may comprise a cooking process for the set of ingredients in the formula and can be cooked by a chef. The recipe may be further modified as necessary based on human feedback on sensorial descriptors.

Abstract: Techniques to mimic a target food item using artificial intelligence are disclosed. A formula generator learns from open source and proprietary databases of ingredients and recipes. The formula generator is trained using features of the ingredients and using recipes. Given a target food item, the formula generator determines a formula that matches the given target food item and a score for the formula. The formula generator may generate, based on user-provided control definitions, numerous formulas that match the given target food item and may select an optimal formula from the generated formulas based on score.

Abstract: Techniques to generate a flavor profile using artificial intelligence are disclosed. A flavor classifier classifies flavors for a given set of ingredients of a recipe from a set of possible classes of flavors. The flavor classifier may use different deep learning models to allow for different granularity levels corresponding to each flavor based on desired preciseness with classification of a particular flavor. A respective flavor predictor may or may not be used for each granularity level based on output of a certainty level classifier used for determining a preceding level of granularity.

Abstract: A color predictor is provided to predict the color of a food item given its formula comprising the ingredients and its quantities. The color predictor may utilize machine learning algorithms and a set of recipe data to train the color predictor. The color predictor can also be used by a color recommender to recommend changes in the given formula to achieve a target color.

Abstract: An artificial intelligence model receives a FTIR spectrum of a given ingredient to predict its protein secondary structure. The model includes three artificial modules, which generate three predicted values corresponding to structural categories (e.g., ?-helix, ?-sheet, and other) of the predicted secondary structure. Proteins may be compared for similarity based on predicted values corresponding to the structural categories of the predicted secondary structure.

Abstract: Techniques to mimic a target food item using artificial intelligence are disclosed. A formula generator is trained using combinations of ingredients. A training set may include, for each combination of ingredients, proportions, and features of the ingredients in a respective combination of ingredients. Given a target food item, the formula generator determines a predicted formula that matches the given target food item. The predicted formula includes a set ingredients and a respective proportion of each ingredient in the set of ingredient.

Abstract: Techniques to generate a flavor profile using artificial intelligence are disclosed. A flavor classifier classifies flavors for a given set of ingredients of a recipe from a set of possible classes of flavors. The flavor classifier may use different deep learning models to allow for different granularity levels corresponding to each flavor based on desired preciseness with classification of a particular flavor. A respective flavor predictor may or may not be used for each granularity level based on output of a certainty level classifier used for determining a preceding level of granularity.

Abstract: Techniques to mimic a target food item using artificial intelligence are disclosed. A formula generator learns from open source and proprietary databases of ingredients and recipes. The formula generator is trained using features of the ingredients and using recipes. Given a target food item, the formula generator determines a formula that matches the given target food item and a score for the formula. The formula generator may generate numerous formulas that match the given target food item and may select an optimal formula from the generated formulas based on score.