Macrowine 2021
IVES 9 IVES Conference Series 9 Beyond classical statistics – data fusion coupled with pattern recognition

Beyond classical statistics – data fusion coupled with pattern recognition

Abstract

AIM: Patterns in data obtained from wine chemical and sensory evaluations are difficult to infer using classical statistics. Pattern recognition can be resolved by coupling data fusion with machine learning techniques, possibly leading to new hypotheses being formed. This study demonstrates the applicability of two pattern recognition approaches using as case study involving Chenin Blanc wines (recently bottled and after two years storage) from young (35 years) vines.

METHODS: Sensory (sorting (Mafata et al. 2020)) and chemical (NMR: nuclear magnetic resonance, HRMS: high resolution mass spectrometry, and UV-Vis: ultraviolet spectrophotometry) data were collected for the young and aged (two years in the bottle) wines. Data sets were combined using multiple factor analysis (MFA). Exploratory unsupervised cluster analysis was performed by agglomerative hierarchical clustering (AHC) and Fuzzy-k means (Bezdek 1981). Optimal cluster conditions were found for both methods and the cophenetic coefficient was used to assess the most confident clustering method.

RESULTS: Since large data sets were fused, the models were very complex. There were no consistent clustering patterns when varying clustering conditions, signalling high similarity between samples. The samples could not confidently be distinguished from one another even at the highest optimized conditions. Although Fuzzy-k means gave more confident clustering, it was still not sufficient for solving classification issues in this sample set.

CONCLUSIONS:

Fuzzy-k means was better at resolving the natural grouping of samples. Coupled to data fusion, it could potentially lead to better pattern recognition, especially for oenological chemical and sensory data. The fuzzy approach should be explored, keeping in mind it is more sensitive to small differences in the data compared to classical statistics.

DOI:

Publication date: September 7, 2021

Issue: Macrowine 2021

Type: Article

Authors

Mpho Mafata, Jeanne

1South African Grape and Wine Research Institute, Department of Viticulture and Oenology, Stellenbosch University & 2School for Data Science and Computational Thinking, Stellenbosch University, South Africa, BRAND, South African Grape and Wine Research Institute, Department of Viticulture and Oenology, Stellenbosch University, South Africa  Astrid, BUICA, South African Grape and Wine Research Institute, Department of Viticulture and Oenology, Stellenbosch University

Contact the author

Keywords

data fusion, pattern recognition, machine learning, artificial intelligence, multiple factor analysis, fuzzy-k means, cluster analysis

Citation

Related articles…

Efficiency of alternative chemical and physical treatments in reducing Brettanomyces Bruxellensis from oak wood

Oak barrels form an integral part of wine production, especially that of high quality wines. However, due to its porosity, wood presents an ecological niche for microbial proliferation and is highly susceptible to microbial spoilage which could cause considerable economic losses. Brettanomyces bruxellensis, the most commonly encountered microorganism responsible for spoilage during barrel ageing, can remain in barrels after barrel sanitation to contaminate new batches of wine after refilling. Therefore, effective sanitation treatments are of utmost importance to prevent recurring wine spoilage.

Identification of γ-nonalactone precusor in Merlot and Cabernet-Sauvignon grapes

Wine flavor results on complexes interactions of odorous components, which come from different aromatic families like esters, thiols, aldehydes, pyrazines or lactones.

Use of new tools for red wine aging: active and passive microoxygenation with oak wood. Effect on volatile compounds and sensorial impact

The aim of this study was to evaluate the evolution of different chemical parameters and sensory impact on red wine during maturation in barrels or with new technologies

Polyphenols in kombucha: impact of infusion time on extraction and investigation of their behavior during “fermentation”

Kombucha is a non-alcoholic beverage made of sugared tea that is transformed by a symbiotic consortium of yeasts and bacteria. Polyphenols are expected to be responsible of several health benefits attributed to kombucha consumption, among other metabolites. This study investigated the impact of tea infusion time and of kombucha “fermentation”, on total phenolic content,

ENRICHMENT OF THE OENOLOGICAL MALDI-TOF/MS PROTEIN SPECTRA DATABASE FOR RELIABLE OENOLOGICAL YEAST AND BACTERIA IDENTIFICATION

The Matrix Assisted Laser Desorption/Ionization–Time-Of-Flight Mass Spectrometry (MALDI-TOF MS) technology is commonly used in food and medical sector to identify yeast or bacteria species isolated from a nutritive culture media. Since a decade, brewery and oenology industries have been attracted to this method which combines fast analysis times, reliability and low cost of analysis. Briefly, this method is based on the comparison of the MALDI-TOF/MS protein spectra of an isolated colony of yeast or bacteria with those contain in a manufacturer’s reference protein spectra database. Initiated in 2015, the creation of the first oenological mass spectra database has proved to be essential for increase quality of species identification.

Macrowine 2021
IVES 9 IVES Conference Series 9 Beyond classical statistics – data fusion coupled with pattern recognition

Beyond classical statistics – data fusion coupled with pattern recognition

Abstract

Content of the article

References

Section for all references

DOI:

Publication date: September 7, 2021

Issue: (ex: Issue: Terclim 2023)

Type: typeofpublication

Authors

author1, author2, author3

Presenting author

Description

List of affiliations ¹ ² ³

Contact the author

Email address (with mailto: link)

Keywords

List of different keywords (keyword1, keyword2, keyword3)

Tags

Citation

Related articles…

Sensory analysis in oenology: the role of methodological differences in expert panel evaluations

Sensory analysis is an essential component of oenology, offering valuable insights into wine quality that influence decision-making in viticulture and winemaking.

An effective approach to mitigating ochratoxin A (OTA) levels in wine with minor impact on wine quality

OTA occurrence in wine is well-documented, with higher levels typically found in red (< 0.01-7.63 μg/l), followed by rose (0.01-2.40 μg/l) and white wine (<0.01-1.72 μg/l). Incidence rates are nOTAble, with studies showing OTA present in 53% of 521 red wines, 69% of 98 rose, and 61% of 301 white wines analysed. In europe, wine is estimated to be the second source of OTA intake after cereals. Since 2006, the maximum allowable limit for OTA in wine is 2 μg/l, according to regulation (ec) no. 1881/2006.

Influence of must fining on wine pinking: relationship between electrochemical and colorimetric measurements and pinking attitude of wine

“Pinking” is a term used to define an abnormal pink coloration assumed by white wines in certain cases. Despite the are many hypotheses about the causes of this phenomenon, pinking still represents an issue for the wine industry. In the absence of reliable preventive strategies, wineries often rely on treatments such as charcoal fining, which is also negatively impacting wine aroma. This study aims at evaluating the potential of different fining agents based on animal or vegetal proteins to prevent wine pinking when applied at the level of must clarification. The work was carried out on Lugana wines, which is well-recognised as sensible to pinking problems. METHODS: Two experimental Lugana musts were obtained by applying a standard winemaking protocol and were then clarified with different commercial preparations based on vegetal proteins or casein, alone or in combination with PVPP. A control only using pectolytic enzyme was also prepared. Finings were carried out at 4°C for 16h, and the clear must (200 NTU) was then fermented in controlled conditions.

Training rats to drink red wine: effects of different drinking approaches on drinking/feeding habits, weight gain and survival from myocardial infarction

The habit of regular, moderate wine consumption, particularly with meals, is associated with protective effects from coronary heart disease. Epidemiological studies looking at myocardial protection/recovery focus mainly on the effects of red wine due to its high content in antioxidants, especially polyphenols. In several previous studies, conducted in our laboratory, we have concentrated on the effects of moderate consumption of white wine, by experimental animals (rats), gaining a significant experience in technical and procedural challenges. The scientific literature, and our past experience, suggests that rats are resilient towards consumption of full bodied, barrique red wines.

Agronomic behavior of three grape varieties in different planting density and irrigation treatments

In the O Ribeiro Denomination of Origin, there is a winemaking tradition of growing vines under a high-density plantation framework (8,920 vines/ha) and maintaining its vegetative cycle under rainfed conditions.
Currently, viticulture is advancing to plantation frames in which the density is considered medium (5,555 vines/ha), thus allowing mechanized work to be carried out for vineyard management operations. Although, the application of irrigation applied proportionally to the needs of the vegetative cycle of the vine, is a factor that increasingly helps a good development of the vine compared to the summer period, with increasingly uncertain weather forecasts.