Machine Learning in Fermented Food and Beverages

A special issue of Fermentation (ISSN 2311-5637). This special issue belongs to the section "Fermentation for Food and Beverages".

Deadline for manuscript submissions: closed (20 March 2022) | Viewed by 13424

Special Issue Editor

Department of Computer Science, University of Central Arkansas, Conway, AR 72035, USA
Interests: wineinformatics; data science; natural language processing; bioinformatics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Data science is the advancement in the combination of data engineering, scientific methods, math, visualization, and statistically based algorithms with a domain of application to make sense of larger quantities of data. Data science has become one of the most popular research areas in the 21st century due to the availability of data from research and the Internet. Within this popular field, there are four major types of machine learning algorithms that provide efficacy: supervised learning, unsupervised learning, semi-supervised learning, and reinforced learning. All these methods provide useful and distinct information to the domain knowledge with a large amount of data.

Fermentation is a natural metabolic process utilized by humans to produce foodstuffs and beverages for thousands of years. Under the biochemical scope, fermentation is a process of metabolism where an organism converts carbohydrate into alcohol and/or acid. During fermentation, yeast produces a whole range of flavoring compounds utilized by humans to create fermented foods and beverages, such as wine, beer, yoghurt, miso, kimchi, etc. In order to improve the aroma and flavor quality of the fermented products, experiments with different recipes and components need to be carried out and recorded in various types of formats, including numerical, categorical, machine readable, and human language. Novel or hidden knowledge in fermented products has the potential to be discovered by applying machine learning algorithms on a large amount of experimental data.

This Special Issue calls for reviews and original data science research articles that adopt fermented food and beverages as the domain knowledge to discover useful information through machine learning algorithms.

Prof. Dr. Bernard Chen
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Fermentation is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Fermented food and beverages
  • Data science
  • Machine learning
  • Deep learning
  • Aroma and flavor
  • Natural language processing
  • Wine informatics

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

22 pages, 22962 KiB  
Article
Applying AI Tools for Modeling, Predicting and Managing the White Wine Fermentation Process
Fermentation 2022, 8(4), 137; https://doi.org/10.3390/fermentation8040137 - 22 Mar 2022
Cited by 3 | Viewed by 3249
Abstract
This paper reveals two of the challenges faced by Romania and proposes a sustainable and simple solution for its wine industry. First, substantial areas with vineyards that may produce qualitative wine, and second, the very low digitalization rate of industrial sectors. More precisely, [...] Read more.
This paper reveals two of the challenges faced by Romania and proposes a sustainable and simple solution for its wine industry. First, substantial areas with vineyards that may produce qualitative wine, and second, the very low digitalization rate of industrial sectors. More precisely, this work proposes a solution for digitalizing the fermentation process of white wine, allowing it to be adapted for other control techniques (i.e., knowledge-based systems, intelligent control). Our method consists of implementing a pre-trained multi-layer perceptron neural network, using genetic algorithms capable of predicting the concentration of alcohol and the amount of substrate at a certain point in time that starts from the initial configuration of the fermentation process. The purpose of predicting these process features is to obtain information about status variables so that the process can be automatically driven. The main advantage of our application is to help experts reduce the time needed for making the relevant measurements and to increase the lifecycles of sensors in bioreactors. After comprehensive simulations using experimental data obtained from previous fermentation processes, we concluded that a configuration that is close to the optimal one, for which the prediction accuracy is high, is a neural network (NN) having an input layer with neurons for temperature, time, initial substrate concentration, and the biomass concentration, a hidden layer with 10 neurons, and an output layer with 2 neurons representing the alcohol and substrate concentration, respectively. The best results were obtained with a pre-trained NN, using a genetic algorithm (GA) with a population of 50 individuals for 20 generations, a crossover probability of 0.9, and a probability of mutation of 0.5 that uniformly decreases depending on the generations, based on a beta coefficient of 0.3 and an elitist selection method. In the case of a data set with a larger number of variables, which also contains data regarding pH and CO2, the prediction accuracy is even higher, leading to the conclusion that a larger data set positively influences the performance of the neural network. Furthermore, methods based on artificial intelligence applications like neural networks, along with various heuristic optimization methods such as genetic algorithms, are essential if hardware sensors cannot be used, or if direct measurements cannot be made. Full article
(This article belongs to the Special Issue Machine Learning in Fermented Food and Beverages)
Show Figures

Figure 1

19 pages, 1322 KiB  
Article
Changes in Volatile Compounds and Quality Characteristics of Salted Shrimp Paste Stored in Different Packaging Containers
Fermentation 2022, 8(2), 69; https://doi.org/10.3390/fermentation8020069 - 07 Feb 2022
Cited by 7 | Viewed by 2448
Abstract
Quality changes of salted shrimp paste, one of the most popular traditional Thai fermented food ingredients, stored in different packaging containers including polypropylene containers (PP), polyethylene terephthalate containers (PET), glass jar containers (GJ) as well as LLDPE/Nylon vacuum bags (VB) at room temperature [...] Read more.
Quality changes of salted shrimp paste, one of the most popular traditional Thai fermented food ingredients, stored in different packaging containers including polypropylene containers (PP), polyethylene terephthalate containers (PET), glass jar containers (GJ) as well as LLDPE/Nylon vacuum bags (VB) at room temperature (28 ± 1 °C) for 15 months were studied. The relationship between quality attributes (i.e., volatiles, browning index (A420), biogenic amines, TBARS) and consumer acceptability as indicated by sensory scores were also investigated using principal component analysis (PCA). During storage, some desirable quality characteristics of shrimp paste were improved as indicated by the higher sensory scores of all samples when stored for 6 months, compared with the sample at day 0 (p ≤ 0.05). However, further changes in all compositions when extended storage time can conversely diminish those desirable characteristics and led to lowering consumers’ acceptability. In this study, GJ seem to be the most potential packaging for preserving original products’ quality during storage for this product since it exhibited the lower rate of quality changing than others throughout the storage. Conversely, VB exhibited unique volatiles and microbial profiles, compared with others, which led to the lowest sensory scores at all period test (p ≤ 0.05), implying that vacuum conditions may not be suitable for the storage of this product. Moreover, based on PCA results, the intensity of nitrogen-containing compounds correlated well with sensory acceptability, particularly flavor-likeness. Our study provides useful knowledge for understanding the different quality characteristics, particularly flavors, associated with different packaging containers during prolonged storage of salted shrimp paste. Full article
(This article belongs to the Special Issue Machine Learning in Fermented Food and Beverages)
Show Figures

Figure 1

16 pages, 1962 KiB  
Article
Domain Adaptation and Federated Learning for Ultrasonic Monitoring of Beer Fermentation
Fermentation 2021, 7(4), 253; https://doi.org/10.3390/fermentation7040253 - 01 Nov 2021
Cited by 5 | Viewed by 2215
Abstract
Beer fermentation processes are traditionally monitored through sampling and off-line wort density measurements. In-line and on-line sensors would provide real-time data on the fermentation progress whilst minimising human involvement, enabling identification of lagging fermentations or prediction of ethanol production end points. Ultrasonic sensors [...] Read more.
Beer fermentation processes are traditionally monitored through sampling and off-line wort density measurements. In-line and on-line sensors would provide real-time data on the fermentation progress whilst minimising human involvement, enabling identification of lagging fermentations or prediction of ethanol production end points. Ultrasonic sensors have previously been used for in-line and on-line fermentation monitoring and are increasingly being combined with machine learning models to interpret the sensor measurements. However, fermentation processes typically last many days and so impose a significant time investment to collect data from a sufficient number of batches for machine learning model training. This expenditure of effort must be multiplied if different fermentation processes must be monitored, such as varying formulations in craft breweries. In this work, three methodologies are evaluated to use previously collected ultrasonic sensor data from laboratory scale fermentations to improve machine learning model accuracy on an industrial scale fermentation process. These methodologies include training models on both domains simultaneously, training models in a federated learning strategy to preserve data privacy, and fine-tuning the best performing models on the industrial scale data. All methodologies provided increased prediction accuracy compared with training based solely on the industrial fermentation data. The federated learning methodology performed best, achieving higher accuracy for 14 out of 16 machine learning tasks compared with the base case model. Full article
(This article belongs to the Special Issue Machine Learning in Fermented Food and Beverages)
Show Figures

Figure 1

14 pages, 3078 KiB  
Article
Artificial Neural Networks and Gompertz Functions for Modelling and Prediction of Solvents Produced by the S. cerevisiae Safale S04 Yeast
Fermentation 2021, 7(4), 217; https://doi.org/10.3390/fermentation7040217 - 06 Oct 2021
Cited by 1 | Viewed by 1893
Abstract
The present work aims to develop a mathematical model, based on Gompertz equations and ANNs to predict the concentration of four solvent compounds (isobutanol, ethyl acetate, amyl alcohol and n-propanol) produced by the yeasts S. cerevisiae, Safale S04, [...] Read more.
The present work aims to develop a mathematical model, based on Gompertz equations and ANNs to predict the concentration of four solvent compounds (isobutanol, ethyl acetate, amyl alcohol and n-propanol) produced by the yeasts S. cerevisiae, Safale S04, using only the fermentation temperature as input data. A beer wort was made, daily samples were taken and analysed by GC-FID. The database was grouped into five datasets of fermentation at different setpoint temperatures (15.0, 16.5, 18.0, 19.0 and 21.0 °C). With these data, the Gompertz models were parameterized, and new virtual datasets were used to train the ANNs. The coefficient of determination (R2) and p-value were used to compare the results. The ANNs, trained with the virtual data generated with the Gompertz functions, were the models with the highest R2 values (0.939 to 0.996), showing that the proposed methodology constitutes a useful tool to improve the quality (flavour and aroma) of beers through temperature control. Full article
(This article belongs to the Special Issue Machine Learning in Fermented Food and Beverages)
Show Figures

Figure 1

11 pages, 3620 KiB  
Article
Complementing Digital Image Analysis and Laser Distance Meter in Beer Foam Stability Determination
Fermentation 2021, 7(3), 113; https://doi.org/10.3390/fermentation7030113 - 14 Jul 2021
Cited by 1 | Viewed by 1828
Abstract
The aim of this research is to investigate the possibility of applying a laser distance meter (LDM) as a complementary measurement method to image analysis during beer foam stability monitoring. The basic optical property of foam, i.e., its high reflectivity, is the main [...] Read more.
The aim of this research is to investigate the possibility of applying a laser distance meter (LDM) as a complementary measurement method to image analysis during beer foam stability monitoring. The basic optical property of foam, i.e., its high reflectivity, is the main reason for using LDM. LDM measurements provide relatively precise information on foam height, even in the presence of lacing, and provide information as to when foam is no longer visible on the surface of the beer. Sixteen different commercially available lager beers were subjected to analysis. A camera and LDM display recorded the foam behavior; the LDM display which was placed close to the monitored beer glass. Measurements obtained by the image analysis of videos provided by the visual camera were comparable to those obtained independently by LDM. However, due to lacing, image analysis could not accurately detect foam disappearance. On the other hand, LDM measurements accurately detected the moment of foam disappearance since the measurements would have significantly higher values due to multiple reflections in the glass. Full article
(This article belongs to the Special Issue Machine Learning in Fermented Food and Beverages)
Show Figures

Graphical abstract

Back to TopTop