1. Monitoring of soluble pectin content in orange juice by means of MIR and TD-NMR spectroscopy combined with machine learning
- Author
-
Luiz Alberto Colnago, Marilia Bizzani, Marcos D. Ferreira, Douglas Flores, Universidade Estadual Paulista (Unesp), Universidade de São Paulo (USP), and Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA)
- Subjects
food.ingredient ,Magnetic Resonance Spectroscopy ,Pectin ,Spectrophotometry, Infrared ,Orange (colour) ,Soluble pectin content (SPC) ,01 natural sciences ,Data science ,Analytical Chemistry ,Machine Learning ,0404 agricultural biotechnology ,food ,Machine learning ,Cluster Analysis ,Humans ,Orange juice ,TD-NMR ,Principal Component Analysis ,Chromatography ,Chemistry ,010401 analytical chemistry ,MIR ,04 agricultural and veterinary sciences ,General Medicine ,Nuclear magnetic resonance spectroscopy ,040401 food science ,0104 chemical sciences ,Fruit and Vegetable Juices ,Pectins ,Food Science ,Citrus sinensis - Abstract
Made available in DSpace on 2020-12-12T02:12:17Z (GMT). No. of bitstreams: 0 Previous issue date: 2020-12-01 Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) This study represents a rapid and non-destructive approach based on mid-infrared (MIR) spectroscopy, time domain nuclear magnetic resonance (TD-NMR), and machine learning classification models (ML) for monitoring soluble pectin content (SPC) changes in orange juice. Current reference methods of SPC in orange juice are laborious, requiring several extractions with successive adjustments hindering rapid process intervention. 109 fresh orange juices samples, representing different harvests, were analysed using MIR, TD-NMR and reference method. Unsupervised algorithms were applied for natural clustering of MIR and TD-NMR data in two groups. Analyses of variance of the two MIR and TD-NMR datasets show that only the MIR groups were different at 95% confidence for SPC average values. This approach allows build classification models based on MIR data achieving 85% and 89% of accuracy. Results demonstrate that MIR/ML can be a suitable strategy for the quick assessment of SPC trends in orange juices. Department of Food and Nutrition Faculty of Pharmaceutical Sciences State University of São Paulo (UNESP), Rodovia Araraquara-Jaú, km 1 Department of Agroindustry Food and Nutrition (LAN) “Luiz de Queiroz” School of Agriculture University of São Paulo, Avenida Pádua Dias 11 Embrapa Instrumentation, Rua XV de Novembro 1452 Department of Food and Nutrition Faculty of Pharmaceutical Sciences State University of São Paulo (UNESP), Rodovia Araraquara-Jaú, km 1 FAPESP: 13/23479-0 FAPESP: 2019/13656-8 CNPq: 303837-2013-6 CNPq: 403075/2013-0
- Published
- 2020