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…

Holistic characterization of Sangiovese clones 

Sangiovese is one of Italy’s most cultivated grape varieties, and currently, over 130 different clones are registered in the national register of grape varieties. However, despite the sangiovese genome having been re-sequenced, limited molecular and genomic information is still available for this cultivar. The present study investigates the complexity of genotype-environment interactions of ten different Sangiovese clones, cultivated in the Chianti Rufina DOCG district over five consecutive vintages (2016-2020).

The role of the landscape as a component of the terroir in Spain (DO Somontano, NE Spain)

The components and methodology for characterization of the terroir in Spain have been described by Gómez-Miguel et al. (2003), Sotés et al. (2003), taking into account the full range of environmental factors (i.e: climate, vegetation, topography, soils, altitude, etc.),

Evolution of biogenic amines content in wine during sample conservation – method optimisation for analysis of biogenicamines

The present paper reports the development of an optimized method for simultaneous analysis of
8 biogenic amines (Histamine, Methylamine, Ethylamine, Tyramine, Putrescine, Cadaverine, Phenethylamine, and Isoamylamine). It is based on a method developed by Gomez-Alonso et al. in 2007.

Ethyl esters interact with the major wine Thaumatin Like Protein VVTL1

The interactions among aromatic compounds and proteins is an important issue for the quality of foods and beverages. In wine, the loss of flavor after vinification is associated to bentonite treatment and this effect can be the result of the removal of aroma compounds which are bound wine proteins. This phenomenon was recently demonstrated for long chain fatty acids and their ethyl esters (1). Since these latter compounds are spectroscopically silent, their association with proteins is not easy to measure.

Mannoproteins extraction from wine lees using natural deep eutectic solvents

Wine lees can be a good source of yeast mannoproteins for both food and wine applications [1,2]. However, mannoprotein extraction from wine lees has not yet been scaled up to an industrial scale, mainly because of the limited cost-effectiveness ratio of the methods employed at the laboratory scale [2].

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…

Development of a new sustainable filtering media for wine and beer clarification and sterilisation

Different separation techniques are frequently used during vinification process. Nowadays, clarification and microbiological stabilization of wine or beer can be done using precoat filters or crossflow filters to remove yeast and bacteria. Kieselguhr powders are the most used filter aids for precoat filtration. Their crystalline structure and their pulverulent nature induce ecotoxicological risks when used. Moreover, regeneration and reuse of these filter aids is not efficient and the filtration waste requires cost effective retreatment.

Evolution of flavonols during Merlot winemaking processes

The phenomenon of quercetin precipitation in wine (flanovol haze), has been manifested for many years in several wine-producing regions

Effects of early leaf removal on grape quality of Albariño vines subjected to different water regimes

The grape quality is affected by the canopy manipulation. Water management is a fundamental tool for controlling reproductive growth

Influence of nitrogen source on expression of genes involved in aroma production in Saccharomyces uvarum

Saccharomyces uvarum has interesting properties that can be exploited for the production of fermented beverages. Particularly, the cryotolerance and capacity to produce high amounts of volatile compounds offers new opportunities for the wine industry.

The concept of « terroir »: what does that mean ? What is it useful for ? French young adults perception

Far from complicated discussions on the relevant way to define « terroir », this article deals with the social perception that French young adults (aged from 18 to 30) have of this concept and the way it can help them to become wine consumers.