Abstract
This study employed electronic nose technology to assess the mold levels in soybeans, conducting analyses on artificially inoculated soybeans with five strains of fungi and distinguishing them from naturally moldy soybeans. Principal component analysis (PCA) and linear discriminant analysis (LDA) were used to evaluate inoculated and naturally moldy samples. The results revealed that the most influential sensor was W2W, which is sensitive to organic sulfur compounds, followed by W1W (primarily responsive to inorganic sulfur compounds), W5S (sensitive to small molecular nitrogen oxides), W1S (responsive to short-chain alkanes such as methane), and W2S (sensitive to alcohols, ethers, aldehydes, and ketones). These findings highlight that variations in volatile substances among the moldy soybean samples were predominantly attributed to organic sulfur compounds, with significant distinctions noted in inorganic sulfur, nitrogen compounds, short-chain alkanes, and alcohols/ethers/aldehydes/ketones. The results of the PCA and LDA analyses indicated that while both methods demonstrated moderate effectiveness in distinguishing between different dominant fungal inoculations and naturally moldy soybeans, they were more successful in differentiating various levels of moldiness, achieving a discriminative accuracy rate of 82.72% in LDA. Overall, the findings suggest that electronic nose detection technology can effectively identify mold levels in soybeans.