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...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/11/3/351 |
| _version_ | 1827660596960559104 |
|---|---|
| author | Mohammad Majid al-Rifaie Marc Cavazza |
| author_facet | Mohammad Majid al-Rifaie Marc Cavazza |
| author_sort | Mohammad Majid al-Rifaie |
| collection | DOAJ |
| 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 <i>solution discovery method</i> 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 <i>automated quantitative ingredient-selection</i> 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. |
| first_indexed | 2024-03-09T23:53:53Z |
| format | Article |
| id | doaj.art-c2f11c32bd57482c920a6d5286e9eff4 |
| institution | Directory Open Access Journal |
| issn | 2304-8158 |
| language | English |
| last_indexed | 2024-03-09T23:53:53Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj.art-c2f11c32bd57482c920a6d5286e9eff42023-11-23T16:29:36ZengMDPI AGFoods2304-81582022-01-0111335110.3390/foods11030351Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation FrameworkMohammad Majid al-Rifaie0Marc Cavazza1School of Computing & Mathematical Sciences, University of Greenwich, London SE10 9LS, UKNational Institute of Informatics, Tokyo 101-8430, JapanModern 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 <i>solution discovery method</i> 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 <i>automated quantitative ingredient-selection</i> 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.https://www.mdpi.com/2304-8158/11/3/351food personalisationbeer optimisationrecipe discoverydispersive flies optimisation |
| spellingShingle | Mohammad Majid al-Rifaie Marc Cavazza Evolutionary Optimisation of Beer Organoleptic Properties: A Simulation Framework Foods food personalisation beer optimisation recipe discovery dispersive flies optimisation |
| 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 | food personalisation beer optimisation recipe discovery dispersive flies optimisation |
| url | https://www.mdpi.com/2304-8158/11/3/351 |
| work_keys_str_mv | AT mohammadmajidalrifaie evolutionaryoptimisationofbeerorganolepticpropertiesasimulationframework AT marccavazza evolutionaryoptimisationofbeerorganolepticpropertiesasimulationframework |