A RAPID METHOD BASED ON VIS-NIRS DATA COMBINED WITHCHEMOMETRICS APPROACH FOR AUTHENTICATION OF MACROALGAE

  1. Frysye Gumansalangi 2
  2. Jose Luis P.Calle 2
  3. Manikharda 1
  4. Widiastuti Setyaningsih 1
  5. Lideman
  6. Muhammad Raf 3
  7. Andriati Ningrum 1
  8. Miguel Palma 4
  1. 1 Department of Analytical Chemistry, Faculty of Sciences, University of Cadiz, Agrifood Campus of International Excellence (ceiA3), IVAGRO., 11510 Puerto Real Spain.
  2. 2 Department of Food and Agricultural Product Technology, Faculty of Agricultural Technology, Universitas Gadjah Mada, Jalan Flora, Depok, Sleman, Yogyakarta 55281, Indonesia
  3. 3 Department of Chemistry, Faculty of Mathematics and Natural Sciences, Bogor Agricultural University, Jalan Tanjung Kampus IPB Dramaga, Bogor 16680, Indonesia.
  4. 4 Department of Food and Agricultural Product Technology, Faculty of Agricultural Technology, Universitas Gadjah Mada, Jalan Flora, Depok, Sleman, Yogyakarta 55281, Indonesia.
Mostrar afiliaciones +
Actas:
XVII REUNIÓN DEL GRUPO REGIONAL ANDALUZ DE LA SOCIEDAD ESPAÑOLA DE QUÍMICA ANALÍTICA

Editorial: Comité Organizador GRASEQA 2022

ISBN: 978-84-09-44794-7

Año de publicación: 2022

Páginas: 145

Tipo: Aportación congreso

GOOGLE SCHOLAR

Resumen

Macroalgae is an essential raw material for many industries, producing high economic value of various derived products. Each macroalga has a unique composition that might provide specific physical and chemical information. Thus it can be used as markers for authentication and control of the quality of macroalgae. Nevertheless, the chemical properties of the macroalgae may differ depending on different factors, including geographical regions. It is necessary to develop a rapid and reliable analytical method to standardize the quality of macroalgae, helping the industrial sector to determine appropriate raw materials and improve their product quality. In this study, 35 macroalgae samples from five islands in Indonesia were analyzed using Vis-NIR Spectroscopy. The spectroscopic data were combined with unsupervised exploratory techniques, namelyprincipal component analysis (PCA), as well as nonparametric supervised techniques such as support vector machine (SVM) and random forest (RF), for authenticating macroalgae samples. The PCA result presents an uncertain grouping trend of the macroalgae samples according to geographical region based on three regions in Indonesia. However, the SVM, combined with leave-one-out cross-validation (LOOCV), successfully classified 97% of the samples with the Vis-NIRS data set. The RF model algorithm, in combination with leave-one-out cross-validation (LOOCV), achieved 100% accuracy.