Abstract
Acerola (Malpighia emarginata DC) is an exotic fruit that has a high agro-industrial potential. It is known to be rich in ascorbic acid, phenolic compounds, and carotenoid pigments. These nutrients make acerola one of the best sources of natural antioxidants, helping to prevent many conditions and delay aging. Acerola fruit is transformed into concentrate juice then powder to be incorporated into nutritional supplements. The natural ascorbic acid content of juice powders must be between 16 and 17%. Unfortunately, the origin of ascorbic acid in acerola-based products is not always natural. That is to say, some food manufacturers add synthetic ascorbic acid to reach the recommended values (16 to 17%), which can be considered as a falsification of the product. Since a decade, the control of the life cycle and the quality of foodstuffs is an increasingly important concern. In this context, EVEAR Extraction (French company) establishes a high level of traceability of its extracts by combining sourcing, extraction processes and laboratory controls throughout the production process. The determination of the composition of raw material and final products can be determined by spectrometric analysis and more precisely by Nuclear Magnetic Resonance (NMR) spectroscopy. However, spectral analysis remains a tedious and time-consuming task requiring an expert.
In this study, the feasibility of discriminating acerola-based product was investigated using 1H NMR spectroscopy in combination with a supervised classification procedure consisting of several steps: principal component analysis (PCA), a fast Fourier transform (FFT) and a neuronal network classification. A total of 6 classes (Colored Acerola powder, Acerola concentrate, Acerola powder, Ascorbic Acid, Acerola with added ascorbic acid, Other extract) were examined. Following the classical approaches, we opted for a convergent network using hidden layers and a divergent output. The results demonstrate that 1H NMR spectroscopy combined with ANN analysis is an effective tool for verifying the nature of Acerola samples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aghdam, H.H., Heravi, E.J.: Guide to convolutional neural networks. New York NY: Springer 10(978–973), 51 (2017)
Albertino, A., Barge, A., Cravotto, G., Genzini, L., Gobetto, R., Vincenti, M.: Natural origin of ascorbic acid: validation by 13C NMR and IRMS. Food Chem. 112(3), 715–720 (2009)
Alves Filho, E., Silva, L.M., Canuto, K.: Metabolomic profiling of acerola clones according to the ripening stage. Food Mesure 15, 416–424 (2021)
Anand, P., Revathy, B.: Acerola, an untapped functional superfruit: a review on latest frontiers. J. Food Sci. Technol. 55, 3373–3384 (2018)
Belwal, T., et al.: Phytopharmacology of acerola (Malpighia spp.) and its potential as functional food. Trends Food Sci. Technol. 74, 99–106 (2018)
Deborde, C., Moing, A., Roch, L., Jacob, D., Rolin, D., Giraudeau, P.: Plant metabolism as studied by NMR spectroscopy. Prog. Nucl. Magn. Reson. Spectrosc. 102–103, 61–97 (2017)
Ellingsen, I., Seljeflot, I., Arnesen, H., Tonstad, S.: Vitamin c consumption is associated with less progression in carotid intima media thickness in elderly men: a 3-year intervention study. Nutr. Metab. Cardiovasc. Dis. 19, 8–14 (2009)
Findik, R., Ilkaya, F., Guresci, S., Guzel, H., Karabulut, S., Karakaya, J.: Effect of vitamin C on collagen structure of cardinal and uterosacral ligaments during pregnancy. Eur. J. Obstet. Gynecol. Reproductive Biol. 201, 31–35 (2016)
Grotch, S.L.: Matching of mass spectra when peak height is encoded to one bit. Anal. Chem. 42(11), 1214–1222 (1970)
Gu, J., et al.: Recent advances in convolutional neural networks. Pattern Recogn. 77, 354–377 (2018)
Knock, B., Smith, I., Wright, D., Ridley, R., Kelly, W.: Compound identification by computer matching of low resolution mass spectra. Anal. Chem. 42(13), 1516–1520 (1970)
Lorena, A.C., Garcia, L.P., Lehmann, J., Souto, M.C., Ho, T.K.: How complex is your classification problem? A survey on measuring classification complexity. ACM Comput. Surv. (CSUR) 52(5), 1–34 (2019)
Lussier, F., Thibault, V., Charron, B., Wallace, G.Q., Masson, J.F.: Deep learning and artificial intelligence methods for Raman and surface-enhanced Raman scattering. TrAC Trends Anal. Chem. 124, 115796 (2020)
Pauli, G., Jaki, B., Lankin, D.: Quantitative 1 h NMR: development and potential of a method for natural products analysis. J. Nat. Prod. 68, 133–149 (2005)
Podmore, I., Griffiths, H., Herbert, K., Mistry, N., Mistry, P., Lunec, J.: Vitamin c exhibits pro-oxidant properties. Nature 392, 559 (1998)
Pomyen, Y., Wanichthanarak, K., Poungsombat, P., Fahrmann, J., Grapov, D., Khoomrung, S.: Deep metabolome: applications of deep learning in metabolomics. Comput. Struct. Biotechnol. J. 18, 2818–2825 (2020)
Shamsaldin, A.S., Fattah, P., Rashid, T.A., Al-Salihi, N.K.: A study of the convolutional neural networks applications. UKH J. Sci. Eng. 3(2), 31–40 (2019)
Smolinska, A., Blanchet, L., Buydens, L., Wijmenga, S.: NMR and pattern recognition methods in metabolomics: from data acquisition to biomarker discovery: a review. Anal. Chim. Acta 750, 82–97 (2012)
Tan, J., Yang, J., Wu, S., Chen, G., Zhao, J.: A critical look at the current train/test split in machine learning. arXiv preprint arXiv:2106.04525 (2021)
Ward, J., Baker, J., Beale, M.: Recent applications of NMR spectroscopy in plant metabolomics. FEBS J. 274, 1126–1131 (2007)
Yang, J., Xu, J., Zhang, X., Wu, C., Lin, T., Ying, Y.: Deep learning for vibrational spectral analysis: recent progress and a practical guide. Anal. Chim. Acta 1081, 6–17 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 IFIP International Federation for Information Processing
About this paper
Cite this paper
Combis, L. et al. (2023). NMR Spectroscopy and Learning-Based Classification of Acerola Samples. In: Noël, F., Nyffenegger, F., Rivest, L., Bouras, A. (eds) Product Lifecycle Management. PLM in Transition Times: The Place of Humans and Transformative Technologies. PLM 2022. IFIP Advances in Information and Communication Technology, vol 667. Springer, Cham. https://doi.org/10.1007/978-3-031-25182-5_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-25182-5_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25181-8
Online ISBN: 978-3-031-25182-5
eBook Packages: Computer ScienceComputer Science (R0)