Cargando…
Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework
Modern computational techniques offer new perspectives for the personalisation of food properties through the optimisation of their production process. This paper addresses the personalisation of beer properties in the specific case of craft beers where the production process is more flexible. Furth...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8833895/ https://www.ncbi.nlm.nih.gov/pubmed/35159509 http://dx.doi.org/10.3390/foods11030351 |
_version_ | 1784649048887656448 |
---|---|
author | al-Rifaie, Mohammad Majid Cavazza, Marc |
author_facet | al-Rifaie, Mohammad Majid Cavazza, Marc |
author_sort | al-Rifaie, Mohammad Majid |
collection | PubMed |
description | Modern computational techniques offer new perspectives for the personalisation of food properties through the optimisation of their production process. This paper addresses the personalisation of beer properties in the specific case of craft beers where the production process is more flexible. Furthermore, this work presents a solution discovery method that could be suitable for more complex, industrial setups. An evolutionary computation technique was used to map brewers’ desired organoleptic properties to their constrained ingredients to design novel recipes tailored for specific brews. While there exist several mathematical tools, using the original mathematical and chemistry formulas, or machine learning models that deal with the process of determining beer properties based on the predetermined quantities of ingredients, this work investigates an automated quantitative ingredient-selection approach. The process, which was applied to this problem for the first time, was investigated in a number of simulations by “cloning” several commercial brands with diverse properties. Additional experiments were conducted, demonstrating the system’s ability to deal with on-the-fly changes to users’ preferences during the optimisation process. The results of the experiments pave the way for the discovery of new recipes under varying preferences, therefore facilitating the personalisation and alternative high-fidelity reproduction of existing and new products. |
format | Online Article Text |
id | pubmed-8833895 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-88338952022-02-12 Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework al-Rifaie, Mohammad Majid Cavazza, Marc Foods Article Modern computational techniques offer new perspectives for the personalisation of food properties through the optimisation of their production process. This paper addresses the personalisation of beer properties in the specific case of craft beers where the production process is more flexible. Furthermore, this work presents a solution discovery method that could be suitable for more complex, industrial setups. An evolutionary computation technique was used to map brewers’ desired organoleptic properties to their constrained ingredients to design novel recipes tailored for specific brews. While there exist several mathematical tools, using the original mathematical and chemistry formulas, or machine learning models that deal with the process of determining beer properties based on the predetermined quantities of ingredients, this work investigates an automated quantitative ingredient-selection approach. The process, which was applied to this problem for the first time, was investigated in a number of simulations by “cloning” several commercial brands with diverse properties. Additional experiments were conducted, demonstrating the system’s ability to deal with on-the-fly changes to users’ preferences during the optimisation process. The results of the experiments pave the way for the discovery of new recipes under varying preferences, therefore facilitating the personalisation and alternative high-fidelity reproduction of existing and new products. MDPI 2022-01-26 /pmc/articles/PMC8833895/ /pubmed/35159509 http://dx.doi.org/10.3390/foods11030351 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article al-Rifaie, Mohammad Majid Cavazza, Marc Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework |
title | Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework |
title_full | Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework |
title_fullStr | Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework |
title_full_unstemmed | Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework |
title_short | Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework |
title_sort | evolutionary optimisation of beer organoleptic properties: a simulation framework |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8833895/ https://www.ncbi.nlm.nih.gov/pubmed/35159509 http://dx.doi.org/10.3390/foods11030351 |
work_keys_str_mv | AT alrifaiemohammadmajid evolutionaryoptimisationofbeerorganolepticpropertiesasimulationframework AT cavazzamarc evolutionaryoptimisationofbeerorganolepticpropertiesasimulationframework |