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…

BIOSORPTION OF UNDESIRABLE COMPONENTS FROM WINE BY YEAST-DERIVED PRODUCTS

4-Ethylphenol (EP) in wine is associated with organoleptic defects such as barn and horse sweat odors. The origin of EP is the bioconversion reaction of p-coumaric acid (CA), naturally present in grapes and grape musts by contaminating yeasts of the genus Brettanomyces bruxellensis.
Yeast cell walls (YCW) have shown adsorption capacities for different compounds. They could be applied to wines in order to adsorb either CA and/or EP and thus reduce the organoleptic defects caused by the contaminating yeasts.

Adjustments of water use efficiency by stomatal regulation during drought and recovery of Verona province grape varieties grafted on two different vitis hybrid rootstocks

Drought is considered to be the predominant factor both for determining the geographic distribution of vegetation and for restricting crop yields in agriculture. Furthermore

Influence of the temperature of the prise de mousse on the effervescence and foam of Champagne and sparkling wines.

The persistence of effervescence and foam collar during a Champagne or sparkling wine tasting constitute one, among others, specific consumer preference for these products. Many different factors related to the product or to the tasting conditions might influence their behavior in the glass

A global and regional study on winegrowers’ perceptions and adaptations to climate change

Aim: The aim of this study was to explore the current and future state of the wine sector in the context of climate change, where the goal was to obtain greater understanding on winegrowers’ perceptions and adaptations to a changing climate and its associated impacts. The study sought to provide both a global and regional perspective on these issues.

Application of GiESCO “bio-metaethics” charter in practice: the “direct” involvement of vine grower, winemaker, society

On the basis of a direct agreement between the GiESCO and the vine grower, the winemaker and the consumers (individual; company; public or private organizations), the communication on the content of the charter can be done as follows:
• Commitment to respect the basic rules of the GiESCO “BIO – MetaEthics” charter.
1/ Put Mankind in the depth of all concerns in a universal context: (grower, consumer, citizen, work valuing, education, security)
2/ Insure minimum impact on environment by optimizing cultivation technics: (maximum of natural biodegradable products, friendly practices, short channels, renewable energies, terroir sustainability)

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…

Influence of early leaf removal on the yield and composition of the grape of three white varieties in the D.O.Ca.Rioja (Spain)

Defoliation is one of the green operations more used in viticulture, whose results can be very different depending on the variety and the moment of realization. Early leaf removal consists of the elimination

Development of the geographic indication vale do São Francisco for tropical wines in Brazil

Aim: Geographical Indications-GI are commonly used to protect territorial products around the world, such as cheese and wine. This qualification is useful because it improves the producer’s organization, protects and valorizes the distinct origin and quality of the product, increases recognition and notoriety, and adds value for products. Tropical wines are mainly produced in Brazil, India,

Hexose efflux from the peeled grape berry

After the onset of grape berry ripening, phloem unloading follows an apoplasmic route into the mesocarp tissue. In the apoplast, most of the unloaded sucrose is cleaved by cell wall invertases

Perceptions of livestock integration in South African vineyards

Context and purpose of the study. Conventional viticulture relies heavily on synthetic inputs (fertilizers, pesticides), as well as mechanization to manage pests, weeds, and diseases and maximize yields.

Late pruning as a tool to reduce the risk of spring frosts in a vineyard in Rioja Alavesa (DO Ca Rioja)

The increase in temperature caused by climate change produces an earlier budbreak date that affects the vineyard, which generates a greater risk of damage by spring frosts.