Evolutionary optimization of flavors

Authors:
Kalyan Veeramachaneni;Katya Vladislavleva;Matt Burland;Jason Parcon;Una-May O' Reilly
Affiliations:
Massachusetts Institute of Technology, Cambridge, MA, MA, USA;University of Antwerp, Antwerp, Belgium;Givaudan Flavors Corporation, Cincinnati, OH, USA;Givaudan Flavors Corporation, Cincinnati, USA;Massachusetts Institute of Technology, Cambridge, MA, USA
Venue:
Proceedings of the 12th annual conference on Genetic and evolutionary computation
Year:
2010

Citing 2
Cited 4

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
A non-dominated sorting particle swarm optimizer for multiobjective optimization

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI

Knowledge mining with genetic programming methods for variable selection in flavor design

Proceedings of the 12th annual conference on Genetic and evolutionary computation
Knowledge mining sensory evaluation data: genetic programming, statistical techniques, and swarm optimization

Genetic Programming and Evolvable Machines
More effective crossover operators for the all-pairs shortest path problem

Theoretical Computer Science
Learning regression ensembles with genetic programming at scale

Proceedings of the 15th annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have acquired panelist data that provides hedonic (liking) ratings for a set of 40 flavors each composed of the same 7 ingredients at different concentration levels. Our goal is to use this data and predict other flavors, composed of the same ingredients in new combinations, which the panelist will like. We describe how we first employ Pareto-Genetic Programming (GP) to generate a surrogate for the human panelist from the 40 observations. This surrogate, in fact an ensemble of GP symbolic regression models, can predict liking scores for flavors outside the observations and provide a confidence in the prediction. We then employ a multi-objective particle swarm optimization (MOPSO) to design a well and consistently liked flavor suite for a panelist. The MOPSO identifies flavors that are well liked, i.e., high liking score, and consistently-liked, i.e., of maximum confidence. Further, we generate flavors that are well and consistently liked by a cluster of panelists, by giving the MOPSO slightly different objectives.