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…

Maturation under different SO2 environments: the impact on amino acid and volatile profile for two white wines

EU countries are in the top 16 of the world’s wine producers. To respond to a public health concern, caused by SO2 excessive exposure

Effects of progeny in the modulation of the response to water stress in isohydric and anisohydric varieties

Each grapevine variety has a specific water use regulation response under drought, and it is still unclear whether this regulation results from innate genotypic behavior (iso- and anisohydric), or is a response to environmental factors, namely recurrent water stress priming effects. In the present work, we explored the influence of the field-grown genotypes’ drought memory in the drought-response phenotype of their vegetative progenies, in Trincadeira (isohydric) and Castelão (anisohydric) varieties under a drought event followed by recovery in a glasshouse. Cuttings from both cultivars subjected to full irrigation (FI) and non-irrigation (NI) treatments for 5 consecutive years were used.

The taste of color: how grape anthocyanin fractions affect in-mouth perceptions

Anthocyanins are responsible for the red wine color and their ability to condense with tannins is considered as a contributor in astringency reduction. However, recent studies showed the possibility of anthocyanins to influence directly the in-mouth perception of wines.

THE ODORIFEROUS VOLATILE CHEMICALS BEHIND THE OXIDATIVE AROMA DEGRADATION OF SPANISH RED WINES

It is a well-established fact that premature oxidation is noxious for wine aromatic quality and longevity. Although some oxidation-related aroma molecules have been previously identified, there are not works carrying out systematic research about the changes in the profiles of odour-active volatiles during wine oxidation.

Function, barriers, and the environmental benefits of reuse bottle system for wine

With 0.3 to 0.7 kg CO2eq per 0.75 L wine, the glass bottle is the main contributor to the carbon footprint of a bottle of wine.

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…

Cell Walls Of Grape Mesocarp Possible Fining Agents For Red And White Wine

Clarification or fining of wines is a technique used in wineries to eliminate unwanted wine components, which negatively affect its quality. Clarification normally involves the addition of an adsorptive material that eliminates or reduces the presence of undesirable components. The problem is that many of the fining agents used in the industry contain allergens, such as caseinates or ovalbumin.

Insulative effects of vine shelters may impact growth potential and cold hardiness of young vines

Context and purpose of the study. The seasons immediately following planting are key growth stages where young vines are particularly susceptible to various forms of damage.

Volatile fraction of young Cabernet Sauvignon from Santa Catarina State, a new terroir in Brazil

A total of 52 volatile compounds were measured in varietal Cabernet Sauvignon wines from four sites in Santa Catarina State (Brazil), over two consecutive vintages (2004 and 2005).

Olfactometric and sensory study of red wines subjected to ultrasound or microwaves during their elaboration

The effect that some extraction techniques, such as ultrasound (Cacciola, Batllò, Ferraretto, Vincenzi, & Celotti, 2013; Povey & McClements, 1988) or microwaves (Carew, Close, & Dambergs, 2015; Carew, Gill, Close, & Dambergs, 2014) produce on the aroma of red wines, when applied to processes of extractive nature, such as pre-fermentative maceration or ageing with oak chips (Spanish oak – Quercus pyrenaica and French oak – Quercus robur) has been studied. The volatile profile was determined by means of gas chromatography coupled with olfactometric and mass spectrometric detection. A sensory analysis was also carried out. No indications were found to show that the pre-fermentative treatment with microwaves or ultrasound modified the sensory profile of the wines whereas the application of such energies during the ageing phase showed some positive trends at sensory level.

Heat waves and drought stress impact grapevine growth and physiology

Recurring heat and drought episodes during the growing season can produce adverse impacts on grape production in many wine regions around the world.