A Rapid Method for Authentication of Macroalgae Based on Vis-NIR Spectroscopy Data Combined with Chemometrics Approach

Macroalgae are an essential basic ingredient for many industries from which numerous derived products with great economic value manufactured. Each macroalga has a unique composition that might provide specific physical and chemical information can be used as markers authentication. Their compositions may differ depending on different factors, including geographical regions. Unsupervised exploratory techniques, namely principal component analysis (PCA) hierarchical cluster (HCA), nonparametric supervised methods support vector machines (SVMs) random forests (RFs), were applied to the Vis-NIR spectroscopic data standardize quality of macroalgae based three regional zones in Indonesia (Western, Central, Eastern). A total 35 samples six islands analyzed. The PCA HCA results present tendency distributed clustered according type their species. Meanwhile, SVM successfully classified zones, when combined five-fold cross-validation, acquired accuracy 82%. RF model algorithm obtained 100%, 80%, 82% training, test, respectively.