AI Article Synopsis
- - Hyperspectral imaging (HSI) combined with traditional methods was used to analyze the structural changes in precooked noodles during refrigerated storage, revealing increased rigidity and limited water movement due to starch recrystallization.
- - Specific wavelengths (around 1160 and 1400 nm) in HSI data correlated with the noodles' storage duration and identified their structural changes.
- - Four machine learning models were trained on the HSI data, with the support vector algorithm achieving the highest accuracy (98.3%) in classifying noodles by storage period and a strong correlation (R = 0.914) for predicting noodle texture.
Article Abstract
The structural features of precooked noodles during refrigerated storage were non-destructively characterized using hyperspectral imaging (HSI) technology along with conventional analytical methods. The precooked noodles displayed a more rigid texture and restricted water mobility over the storage period, derived from the recrystallization of starch. Dimensionality reduction techniques revealed robust correlations between the storage duration and HSI absorbance of the noodles, and from their loading plots, the specific peaks of the noodles related to their structural changes were identified at wavelengths of around 1160 and 1400 nm. The strong relationships between the HSI results of the noodles and their storage period/texture were confirmed by training four machine learning models on the HSI data. In particular, the support vector algorithm displayed the best prediction performance for classifying precooked noodles by storage period (98.3% accuracy) and for predicting the noodle texture (R = 0.914).
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.foodchem.2024.139371 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!