Potato Research· 2026Q2
Discrimination of Acrylamide Levels in Potato Chips Using Near-Infrared Spectroscopy
- 0citations
- Q2SCImago
- 2026year
Short summary
Near-infrared spectroscopy (NIRS) coupled with machine learning correctly classified potato chip samples as having low or high acrylamide content with 88% accuracy in external validation.
AI-generated from the title and abstract; the full text is not read.
Key points
- Near-infrared spectroscopy (NIRS) was used to analyze acrylamide levels in potato chips.
- Principal component analysis (PCA) showed variety and harvest year significantly impact spectral data.
- Support vector machine (SVM) classification correctly identified 88% of samples' acrylamide content (low/high).
- External validation resulted in a prediction error of 0.131.
- Oil content was found to influence the NIR spectral response.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source. Potato Research, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Food Science
Food ScienceAgricultural and Biological Sciences