About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Abstract
Can one hide an averse food in a flavorful food so that the averse food is not perceptible? Here we take a statistical signal processing approach to show how to optimally design a food additive (either using pure flavor compounds or natural ingredients) to act as a steganographic key for this food steganography problem. We use a synthesis-based model of olfaction that has emerged in the psychology literature and the percept known as olfactory white acts as an intermediate signal in our approach. The problem decomposes into predictive analytics and prescriptive analytics components. In the predictive component, we learn a mapping from the space of physic-ochemical descriptors of flavor compounds to the space of perceptual odor descriptors through multivariate regression with nuclear norm regularization. In the prescriptive component, we find optimal mixtures of compounds or foods to make the averse food imperceptible in the flavorful food by posing and solving an inverse problem with non-negativity constraints. We demonstrate the proposed approach on real-world physicochemical and olfactory perception data for compounds in food. © 2014 IEEE.