1
|
Jain K, Kaushik K, Gupta SK, Mahajan S, Kadry S. Machine learning-based predictive modelling for the enhancement of wine quality. Sci Rep 2023; 13:17042. [PMID: 37814043 PMCID: PMC10562461 DOI: 10.1038/s41598-023-44111-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2023] [Accepted: 10/03/2023] [Indexed: 10/11/2023] Open
Abstract
The certification of wine quality is essential to the wine industry. The main goal of this work is to develop a machine learning model to forecast wine quality using the dataset. We utilised samples from the red wine dataset (RWD) with eleven distinct physiochemical properties. With the initial RWD, five machine learning (ML) models were trained and put to the test. The most accurate algorithms are Random Forest (RF) and Extreme Gradient Boosting (XGBoost). Using these two ML approaches, the top three features from a total of eleven features are chosen, and ML analysis is performed on the remaining features. Several graphs are employed to demonstrate the feature importance based on the XGBoost model and RF. Wine quality was predicted using relevant characteristics, often referred to as fundamental elements, that were shown to be essential during the feature selection procedure. When trained and tested without feature selection, with feature selection (RF), and with key attributes, the XGBoost classifier displayed 100% accuracy. In the presence of essential variables, the RF classifier performed better. Finally, to assess the precision of their predictions, the authors trained an RF classifier, validated it, and changed its hyperparameters. To address collinearity and decrease the quantity of predictors without sacrificing model accuracy, we have also used cluster analysis.
Collapse
Affiliation(s)
- Khushboo Jain
- School of Computer Science, University of Petroleum and Energy Studies, Dehradun, India
| | - Keshav Kaushik
- School of Computer Science, University of Petroleum and Energy Studies, Dehradun, India
| | - Sachin Kumar Gupta
- Department of Electronics and Communication Engineering, Central University of Jammu, Samba, Jammu, Jammu and Kashmir, 181143, India
| | - Shubham Mahajan
- Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman, Jordan.
- University Center for Research & Development (UCRD), Chandigarh University, Mohali, India.
- Department of Applied Data Science, Noroff University College, Kristiansand, Norway.
| | - Seifedine Kadry
- Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon.
| |
Collapse
|
2
|
Artificial Neural Networks for Predicting Food Antiradical Potential. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12126290] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
Using an artificial neural network (ANN), the values of the antiradical potential of 1315 items of food and agricultural raw materials were calculated. We used an ANN with the structure of a “multilayer perceptron” (MLP) and with the hyberbolic tangent (Tanh) as an activation function. Values reported in the United States Food and Nutrient Database for Dietary Studies (FNDDS) were taken as input to the analysis. When training the ANN, 60 parameters were used, such as the content of plastic substances, food calories, the amount of mineral components, vitamins, the composition of fatty acids and additional substances presented in this database. The analysis revealed correlations, namely, a direct relationship between the value of the antiradical potential (ARP) of food and the concentration of dietary fiber (r = 0.539) and a negative correlation between the value of ARP and the total calorie content of food (r = −0.432) at a significance level of p < 0.001 for both values. The average ARP value for 10 product groups within the 95% CI (confidence interval) was ≈23–28 equivalents (in terms of ascorbic acid) per 1 g of dry matter. The study also evaluated the range of average values of the daily recommended intake of food components (according to Food and Agriculture Organization—FAO, World Health Organization—WHO, Russia and the USA), which within the 95% CI, amounted to 23.41–28.98 equivalents per 1 g of dry weight. Based on the results of the study, it was found that the predicted ARP values depend not only on the type of raw materials and the method of their processing, but also on a number of other environmental and technological factors that make it difficult to obtain accurate values.
Collapse
|
3
|
Aznan A, Gonzalez Viejo C, Pang A, Fuentes S. Rapid Assessment of Rice Quality Traits Using Low-Cost Digital Technologies. Foods 2022; 11:foods11091181. [PMID: 35563907 PMCID: PMC9105373 DOI: 10.3390/foods11091181] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Revised: 04/18/2022] [Accepted: 04/18/2022] [Indexed: 12/10/2022] Open
Abstract
Aroma and other physicochemical parameters are important attributes influencing consumer perception and acceptance of rice. However, current methods using multiple instruments and laboratory analysis make these assessments costly and time-consuming. Therefore, this study aimed to assess rice quality traits of 17 commercial rice types using a low-cost electronic nose and portable near-infrared spectrometer coupled with machine learning (ML). Specifically, artificial neural networks (ANN) were used to classify the type of rice and predict rice quality traits (aromas, color, texture, and pH of cooked rice) as targets. The ML models developed showed that the chemometrics obtained from both sensor technologies successfully classified the rice (Model 1: 98.7%; Model 2: 98.6%) and predicted the peak area of aromas obtained by gas chromatography-mass spectroscopy found in raw (Model 3: R = 0.95; Model 6: R = 0.95) and cooked rice (Model 4: R = 0.98; Model 7: R = 0.96). Furthermore, a high R = 0.98 was obtained for Model 5 to estimate the color, texture, and pH of cooked rice. The proposed method is rapid, low-cost, reliable, and may help the rice industry increase high-quality rice production and accelerate the adoption of digital technologies and artificial intelligence to support the rice value chain.
Collapse
Affiliation(s)
- Aimi Aznan
- Digital Agriculture, Food and Wine Group (DAFW), School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, Australia; (A.A.); (C.G.V.); (A.P.)
- Faculty of Chemical Engineering Technology, University Malaysia Perlis, Arau 02600, Perlis, Malaysia
| | - Claudia Gonzalez Viejo
- Digital Agriculture, Food and Wine Group (DAFW), School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, Australia; (A.A.); (C.G.V.); (A.P.)
| | - Alexis Pang
- Digital Agriculture, Food and Wine Group (DAFW), School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, Australia; (A.A.); (C.G.V.); (A.P.)
| | - Sigfredo Fuentes
- Digital Agriculture, Food and Wine Group (DAFW), School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, Australia; (A.A.); (C.G.V.); (A.P.)
- Correspondence: ; Tel.: +61-42-450-4434
| |
Collapse
|
4
|
Martínez-Gil A, Del Alamo-Sanza M, Nevares I. Evolution of red wine in oak barrels with different oxygen transmission rates. Phenolic compounds and colour. Lebensm Wiss Technol 2022. [DOI: 10.1016/j.lwt.2022.113133] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
5
|
Bhardwaj P, Tiwari P, Olejar K, Parr W, Kulasiri D. A machine learning application in wine quality prediction. MACHINE LEARNING WITH APPLICATIONS 2022. [DOI: 10.1016/j.mlwa.2022.100261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022] Open
|
6
|
Astray G, Martinez-Castillo C, Mejuto JC, Simal-Gandara J. Metal and metalloid profile as a fingerprint for traceability of wines under any Galician protected designation of origin. J Food Compost Anal 2021. [DOI: 10.1016/j.jfca.2021.104043] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
7
|
Pandiselvam R, Sruthi NU, Kumar A, Kothakota A, Thirumdas R, Ramesh S, Cozzolino D. Recent Applications of Vibrational Spectroscopic Techniques in the Grain Industry. FOOD REVIEWS INTERNATIONAL 2021. [DOI: 10.1080/87559129.2021.1904253] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
Affiliation(s)
- R. Pandiselvam
- Physiology,Biochemistry and Post Harvest Technology Division, ICAR –Central Plantation Crops Research Institute, Kasaragod, India
| | - N. U. Sruthi
- Agricultural and Food Engineering Department, Indian Institute of Technology (IIT), Kharagpur, India
| | - Ankit Kumar
- Agricultural and Food Engineering Department, Indian Institute of Technology (IIT), Kharagpur, India
| | - Anjineyulu Kothakota
- Agro-Processing & Technology Division, CSIR-National Institute for Interdisciplinary Science and Technology (NIIST), Trivandrum, India
| | - Rohit Thirumdas
- Department of Food Process Technology, College of Food Science & Technology, Telangana, India
| | - S.V. Ramesh
- Physiology,Biochemistry and Post Harvest Technology Division, ICAR –Central Plantation Crops Research Institute, Kasaragod, India
| | - Daniel Cozzolino
- Centre for Nutrition and Food Sciences, Queensland Alliance for Agriculture and Food Innovation (QAAFI), the University of Queensland, Brisbane, Australia
| |
Collapse
|
8
|
Urvieta R, Jones G, Buscema F, Bottini R, Fontana A. Terroir and vintage discrimination of Malbec wines based on phenolic composition across multiple sites in Mendoza, Argentina. Sci Rep 2021; 11:2863. [PMID: 33536527 PMCID: PMC7859225 DOI: 10.1038/s41598-021-82306-0] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2020] [Accepted: 01/19/2021] [Indexed: 01/07/2023] Open
Abstract
This study evaluated the phenolic profiles of Malbec wines made from grapes of 23 parcels distributed in 12 geographical indications (GIs) from Mendoza, Argentina. Wines were elaborated under standardized winemaking conditions over three consecutive vintages (2016–2018). Data discriminated wines from different GIs and parcels, based on an integrative data analysis by chemometric tools. Vintage effect and specific phenolic compounds were associated with some GIs or parcels. As well, regional climate conditions allowed partial discrimination of the GIs (and also some parcels). A random forest analysis correctly identified 11 out of 23 individual parcels across the different vintages. The most notorious compounds associated with such classification were p-coumaric acid, delphinidin-3-O-glucoside, caffeic acid, quercetin and peonidin-3-O-glucoside. The presented research allows to individualize, through phenolic profiles, parcels with unique characteristics over years. This is the first report characterizing Malbec wines coming from several GIs (and individual parcels) in different vintages. These results are strongly related to terroir features of wines, contributing to a better communication to consumers and to position Argentinean wines.
Collapse
Affiliation(s)
- Roy Urvieta
- Grupo de Bioquímica Vegetal, Instituto de Biología Agrícola de Mendoza, Facultad de Ciencias Agrarias, CONICET-Universidad Nacional de Cuyo, Almirante Brown 500, Chacras de Coria, M5528AHB, Mendoza, Argentina.,Catena Institute of Wine, Bodega Catena Zapata, Cobos s/n, Agrelo, M5509, Mendoza, Argentina
| | - Gregory Jones
- Evenstad Center for Wine Education, Linfield University, McMinnville, OR, USA
| | - Fernando Buscema
- Catena Institute of Wine, Bodega Catena Zapata, Cobos s/n, Agrelo, M5509, Mendoza, Argentina
| | - Rubén Bottini
- Grupo de Bioquímica Vegetal, Instituto de Biología Agrícola de Mendoza, Facultad de Ciencias Agrarias, CONICET-Universidad Nacional de Cuyo, Almirante Brown 500, Chacras de Coria, M5528AHB, Mendoza, Argentina.,Instituto de Veterinaria Ambiente y Salud, Universidad Juan A. Maza, Lateral Sur del Acceso Este 2245, 5519, Guaymallén, Argentina
| | - Ariel Fontana
- Grupo de Bioquímica Vegetal, Instituto de Biología Agrícola de Mendoza, Facultad de Ciencias Agrarias, CONICET-Universidad Nacional de Cuyo, Almirante Brown 500, Chacras de Coria, M5528AHB, Mendoza, Argentina. .,Cátedra de Química Orgánica y Biológica, Departamento de Biomatemática y Fisicoquímica, Facultad de Ciencias Agrarias-Universidad Nacional de Cuyo, Chacras de Coria, Mendoza, Argentina.
| |
Collapse
|
9
|
Bottle Aging and Storage of Wines: A Review. Molecules 2021; 26:molecules26030713. [PMID: 33573099 PMCID: PMC7866556 DOI: 10.3390/molecules26030713] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2020] [Revised: 01/26/2021] [Accepted: 01/27/2021] [Indexed: 12/21/2022] Open
Abstract
Wine is perhaps the most ancient and popular alcoholic beverage worldwide. Winemaking practices involve careful vineyard management alongside controlled alcoholic fermentation and potential aging of the wine in barrels. Afterwards, the wine is placed in bottles and stored or distributed in retail. Yet, it is considered that wine achieves its optimum properties after a certain storage time in the bottle. The main outcome of bottle storage is a decrease of astringency and bitterness, improvement of aroma and a lighter and more stable color. This is due to a series of complex chemical changes of its components revolving around the minimized and controlled passage of oxygen into the bottle. For this matter, antioxidants like sulfur oxide are added to avoid excessive oxidation and consequent degradation of the wine. In the same sense, bottles must be closed with appropriate stoppers and stored in adequate, stable conditions, as the wine may develop unappealing color, aromas and flavors otherwise. In this review, features of bottle aging, relevance of stoppers, involved chemical reactions and storage conditions affecting wine quality will be addressed.
Collapse
|
10
|
Lukić K, Brnčić M, Ćurko N, Tomašević M, Jurinjak Tušek A, Kovačević Ganić K. Quality characteristics of white wine: The short- and long-term impact of high power ultrasound processing. ULTRASONICS SONOCHEMISTRY 2020; 68:105194. [PMID: 32492528 DOI: 10.1016/j.ultsonch.2020.105194] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/31/2020] [Revised: 05/14/2020] [Accepted: 05/26/2020] [Indexed: 06/11/2023]
Abstract
This research aimed to analyze the effects of ultrasound on the quality characteristics of white wine when processed by two different systems, i.e., ultrasonic bath and ultrasonic probe. In this regard, the multivariate statistical analysis and artificial neural network (ANN) techniques were used. Additionally, the efficiency of high power ultrasound (HPU) combined with sulfite and glutathione (GSH) treatments was explored during 18 months of bottle storage. Regarding ultrasonic bath experiment, the higher bath temperature caused the degradation of volatile compounds, precisely esters and higher alcohols, while the ultrasound effect on phenolic composition was much less pronounced. Interestingly, a combination of larger probe diameter and higher ultrasound amplitude showed a milder effect on phenolic and volatile composition in ultrasonic probe experiment. Both, ultrasonic bath and probe experiments did not cause great changes in the color properties. Moreover, implemented ANN models for flavan-3-ols, higher alcohols and esters resulted in the highest prediction values. HPU processing after 18 months of storage did not affect wine color. However, it modified phenolic and volatile composition, with greater effect in wines with lower concentration of antioxidants. In addition, there was no significant difference in the phenolic and volatile composition among sonicated low-sulfite-GSH wine and the one with standard-sulfite content. Therefore, a combined HPU and low-sulfite-GSH treatment might be a promising method for production of low-sulfite wines.
Collapse
Affiliation(s)
- Katarina Lukić
- University of Zagreb, Faculty of Food Technology and Biotechnology, Pierottijeva 6, 10000 Zagreb, Croatia.
| | - Mladen Brnčić
- University of Zagreb, Faculty of Food Technology and Biotechnology, Pierottijeva 6, 10000 Zagreb, Croatia.
| | - Natka Ćurko
- University of Zagreb, Faculty of Food Technology and Biotechnology, Pierottijeva 6, 10000 Zagreb, Croatia
| | - Marina Tomašević
- University of Zagreb, Faculty of Food Technology and Biotechnology, Pierottijeva 6, 10000 Zagreb, Croatia
| | - Ana Jurinjak Tušek
- University of Zagreb, Faculty of Food Technology and Biotechnology, Pierottijeva 6, 10000 Zagreb, Croatia
| | - Karin Kovačević Ganić
- University of Zagreb, Faculty of Food Technology and Biotechnology, Pierottijeva 6, 10000 Zagreb, Croatia
| |
Collapse
|
11
|
Yu Z, Jung D, Park S, Hu Y, Huang K, Rasco BA, Wang S, Ronholm J, Lu X, Chen J. Smart traceability for food safety. Crit Rev Food Sci Nutr 2020; 62:905-916. [DOI: 10.1080/10408398.2020.1830262] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
Affiliation(s)
- Zhilong Yu
- Food Nutrition and Health Program, Faculty of Land and Food Systems, The University of British Columbia, Vancouver, Canada
- Department of Food Science and Agricultural Chemistry, Faculty of Agricultural and Environmental Sciences, McGill University, Quebec, Canada
| | - Dongyun Jung
- Department of Food Science and Agricultural Chemistry, Faculty of Agricultural and Environmental Sciences, McGill University, Quebec, Canada
| | - Soyoun Park
- Department of Food Science and Agricultural Chemistry, Faculty of Agricultural and Environmental Sciences, McGill University, Quebec, Canada
| | - Yaxi Hu
- Food Nutrition and Health Program, Faculty of Land and Food Systems, The University of British Columbia, Vancouver, Canada
| | - Kang Huang
- School of Chemical Sciences, University of Auckland, Auckland, New Zealand
| | - Barbara A. Rasco
- College of Agriculture and Natural Resources, University of Wyoming, Laramie, Wyoming, USA
| | - Shuo Wang
- Tianjin Key Laboratory of Food Science and Health, School of Medicine, Nankai University, Tianjin, China
| | - Jennifer Ronholm
- Department of Food Science and Agricultural Chemistry, Faculty of Agricultural and Environmental Sciences, McGill University, Quebec, Canada
- Department of Animal Science, Faculty of Agricultural and Environmental Sciences, McGill University, Quebec, Canada
| | - Xiaonan Lu
- Food Nutrition and Health Program, Faculty of Land and Food Systems, The University of British Columbia, Vancouver, Canada
- Department of Food Science and Agricultural Chemistry, Faculty of Agricultural and Environmental Sciences, McGill University, Quebec, Canada
| | - Juhong Chen
- Department of Biological Systems Engineering, Virginia Tech, Blacksburg, Virginia, USA
| |
Collapse
|
12
|
Álvarez Á, Yáñez J, Neira Y, Castillo-Felices R, Hinrichsen P. Simple distinction of grapevine (Vitis vinifera L.) genotypes by direct ATR-FTIR. Food Chem 2020; 328:127164. [DOI: 10.1016/j.foodchem.2020.127164] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2019] [Revised: 05/14/2020] [Accepted: 05/25/2020] [Indexed: 10/24/2022]
|
13
|
Bakir S, Capanoglu E, Hall RD, de Vos RCH. Variation in secondary metabolites in a unique set of tomato accessions collected in Turkey. Food Chem 2020; 317:126406. [PMID: 32097823 DOI: 10.1016/j.foodchem.2020.126406] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2019] [Revised: 02/10/2020] [Accepted: 02/11/2020] [Indexed: 01/28/2023]
Abstract
In this study, 50 tomato landraces grown in Turkey were investigated in terms of their secondary metabolite profiles. Each accession was planted in 2016 and 2017 in 3 replicates in an open field. In this study, color, pH and brix of the fruit samples were measured and an unbiased LCMS-based metabolomics approach was applied. Based on Principal Components Analysis (PCA) and Hierarchical Cluster Analysis (HCA) of the relative abundance levels of >250 metabolites, it could be concluded that fruit size was the most influential to the biochemical composition, rather than the geographical origin of accessions. Results indicated substantial biodiversity in various metabolites generally regarded as key to fruit quality aspects, including sugars; phenolic compounds like phenylpropanoids and flavonoids; alkaloids and glycosides of flavour-related volatile compounds. The phytochemical data provides insight into which Turkish accessions might be most promising as starting materials for the tomato processing and breeding industries.
Collapse
Affiliation(s)
- Sena Bakir
- Istanbul Technical University, Faculty of Chemical and Metallurgical Engineering, Food Engineering Department, Maslak, Istanbul, Turkey; Recep Tayyip Erdogan University, Faculty of Engineering, Merkez, Rize, Turkey
| | - Esra Capanoglu
- Istanbul Technical University, Faculty of Chemical and Metallurgical Engineering, Food Engineering Department, Maslak, Istanbul, Turkey.
| | - Robert D Hall
- Bioscience, Wageningen University and Research Centre (Wageningen-UR), PO Box 16, 6700 AA Wageningen, The Netherlands; Laboratory of Plant Physiology, Wageningen University & Research, PO Box 16, 6700 AA, Wageningen, The Netherlands
| | - Ric C H de Vos
- Bioscience, Wageningen University and Research Centre (Wageningen-UR), PO Box 16, 6700 AA Wageningen, The Netherlands.
| |
Collapse
|
14
|
Lucini L, Rocchetti G, Trevisan M. Extending the concept of terroir from grapes to other agricultural commodities: an overview. Curr Opin Food Sci 2020. [DOI: 10.1016/j.cofs.2020.03.007] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
|
15
|
Martinez-Castillo C, Astray G, Mejuto JC, Simal-Gandara J. Random Forest, Artificial Neural Network, and Support Vector Machine Models for Honey Classification. EFOOD 2019. [DOI: 10.2991/efood.k.191004.001] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/01/2022] Open
|