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…

Biotic interactions: case of grapevine cultivars – the fungal pathogen Neofusicoccum parvum – biocontrol agents 

Grapevine is subject to multiple stresses, either biotic or abiotic, frequently in combination. These stresses may negatively impact the health status of plants and reduce yields. For biotic stress, grapevine is affected by numerous pest and diseases such as downy and powdery mildews, grey mold, black rot, grapevine fanleaf virus and trunk diseases (namely GTDs). The interaction between grapevine and pathogens is relatively complex and linked to various pathogenicity factors including cell-wall-degrading enzymes (especially CAZymes) and phytotoxic secondary metabolites, growth regulators, effectors proteins, and fungal viruses.

Effect of bleaching with different agents on protein hydrolysate characteristics

High temperatures can reduce the phenolic content of grapes, especially anthocyanins and copigments involved in colour stabilisation of red wines [1]. This could make it difficult to maintain stable colour during storage [2].

Exploring the resistance of non-Saccharomyces wine yeasts to dehydration-rehydration processes

AIM: The use of non-Saccharomyces (NS) yeasts in multi-starter fermentations with S. cerevisiae is a trend in the wine industry, but the number of strains commercially available in a powder formulation, such as active dry yeasts (ADY), is still limited.

Extracellular substances of lactic acid bacteria interests in biotechnological practices applied to enology

Extracellular substances (ECS) represent all molecules outside the cytoplasmic membrane, which are not directly anchored to the cell wall of microorganisms living through a planktonic or biofilm phenotype. They are the high-biomolecular-weight secretions from microorganisms (i.e. extracellular polymeric substances – EPS – proteins, polysaccharides, humic acid, nucleic acid), and the products of cellular lysis and hydrolysis of macromolecules. In addition, some high- and low-molecular-weight organic and inorganic matters from environment can also be adsorbed to the EPS. All can be firmly bound to the cell surface, associated with the EPS matrix of biofilm, or released as being freely diffusing throughout the medium.

A new step toward the comprehensive valorisation of grape marc through subcritical water extraction of polysaccharides

Winemaking generates a significant amount of waste. Grape marc, the main solid residue, constitutes 20-25% of the pressed grapes and approximately 8-9 million tons are produced globally each year.

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…

Consumer acceptance of sweet wines produced by stopping fermentation with octanoic and decanoic acids

The use of medium chain fatty acids for arresting the fermentation and producing sweet wines was investigated at industrial level. Doses of 10 mg/l of octanoic or decanoic acid and a combination of 5+5 mg/l octanoic and decanoic acid were used to produce sweet wines of tamaioasa romanească variety in volumes of 3000 l.

“Garrigues”, part of the mediterranean vine terroirs

Les paysages viticoles méditerranéens présentent une originalité qui ne se retrouve nulle part ailleurs : ils associent des garrigues très odoriférantes à des parcelles de vignes souvent qualitatives. La connaissance empirique des vins du Languedoc par leurs dégustateurs a conduit la Chambre d’Agriculture de l’Hérault à supposer que les arômes de la garrigue environnante peuvent se retrouver dans les vins (arômes de ciste, de genévrier, … )

NEW INSIGHTS INTO THE FATE OF MARKERS INVOLVED IN FRESH MUSHROOM OFF-FLAVOURS DURING ALCOHOLIC FERMENTATION

The fresh mushroom off-flavour (FMOff) has been appearing in wines since the 2000s. Some C8 compounds such as 1-octen-3-one, 1-octen-3-ol, 1-hydroxyoctan-3-one, 3-octanol and others are involved in this specific off-flavour [1-3]. At the same time, glycosidic precursors of some FMOff compounds have been identified in musts contaminated by Crustomyces subabruptus [4], highlighting the role of aroma precursors in this specific taint. However, the fate of these volatile molecules and glycosidic fractions during fermentation is not well known.

Estudios de zonificación vitícola en España

La delimitación y caracterización de zonas vitícolas plantea en España problemas específicos no sólo por las características peculiares del territorio sino también por el tamaño

Wine yeast species show strong inter- and intra-specific variability in their sensitivity to uv-c radiation

While the trend in winemaking is toward reducing the inputs and especially sulphites, the development of While the trend in winemaking is toward reducing the inputs