Discrimination of Acrylamide Levels in Potato Chips Using Near-Infrared Spectroscopy

Controlling acrylamide formation in potato chips remains a major challenge for the food industry due to its carcinogenic potential. Its formation is influenced by multiple factors, including the composition of the raw material and the processing conditions. Therefore, the development of rapid and efficient monitoring methods is essential to ensure consumer safety. In this study, two potato chip varieties (Agria and Jaerla) from two harvest years (2022 and 2023) were analysed using near-infrared spectroscopy (NIRS) to classify samples according to their acrylamide content, following the criteria established in European Regulation 2017/2158. Principal component analysis (PCA) revealed that both variety and harvest year had a significant influence on the spectral data. Subsequently, support vector machine (SVM) was applied to classify samples as having either low or high acrylamide content. Up to 88% of samples were correctly classified with an error of 0.131 in external validation. Finally, it was observed that oil content exerted a marked influence on the NIR spectral response, potentially affecting the identification of wavelengths relevant for acrylamide prediction.