Near Infrared Reflectance Spectroscopy Coupled to Chemometrics as a Cost-Effective, Rapid and Non-Destructive Tool for Fish Fraud Control: Monitoring Source, Condition and Nutritional Value of Five Common Whitefish Species
Abstract Fish fraud is a problematic issue for the industry that to be properly addressed requires the use of accurate, rapid and cost-effective tools. In this work, near infrared reflectance spectroscopy (NIRS) was used to predict nutritional values (protein, lipids and moisture) as well as to discriminate between source (farmed vs. wild fish) and condition (fresh, defrosted or frozen fish). Five whitefish species consisting of Alaskan pollock (Gadus chalcogrammu), Atlantic cod (Gadus morhua), European plaice (Pleuronectes platessa), Common sole (Solea solea) and Turbot (Psetta maxima), including farmed, wild, fresh and frozen ones, were scanned by a low-cost handheld near infrared reflectance spectrometer with a spectral range between 900 nm and 1700 nm. Several machine learning algorithms were explored for both regression and classification tasks, achieving precisions and coefficient of determination higher than 88% and 0.78, respectively. Principal component analysis (PCA) was used to cluster samples according to classes where good linear discriminations were denoted. Loadings from PCA reveal bands at 1150, 1200 and 1400 nm as the most discriminative spectral regions regarding classification of both source and condition, suggesting the absorbance of OH, CH, CH2 and CH3 groups as the most important ones. This study shows the use of NIRS and both linear and non-linear learners as a suitable strategy to address the fish fraud problematic and fish quality control.