Early identification of Aspergillus spp. contamination in milled rice by E-nose combined with chemometrics.

Abstract

BACKGROUND\nRice grains can be easily contaminated by certain fungi during storage and market chain, thus generating risk for humans. Most classical methods are complex and time-consuming for manufactures and consumers. However, E-nose technology provides analytical information in a non-destructive and environmentally friendly manner. Subsequently, two feature fusion data combined with chemometrics were employed for the determination of Aspergillus spp. contamination in milled rice.\n\n\nRESULTS\nLinear discriminant analysis (LDA) analysis indicated that the efficiency of fusion signals ( 80th s values and area values ) outperformed that of independent E-nose signals. Meanwhile, LDA showed a clearly discrimination to fungi species in stored milled rice for four group on day 2, and the discrimination accuracy reached 92.86% by using extreme learning machine (ELM). GC-MS analysis showed that the volatile compounds had close relationships with fungal species in rice. Quantification results of colony counts in milled rice showed that the monitoring models based on ELM and GA-SVM (R2 \xa0=\xa00.924-0.983) achieved better performances than those based on PLSR (R2 \xa0=\xa00.877-0.913). The ability of E-nose to monitor fungal infection at early stage would help to prevent contaminated rice grains from entering the food chains.\n\n\nCONCLUSIONS\nThe results indicated that E-nose coupled with ELM or GA-SVM algorithm could be a useful tool for the rapid detection of fungal infection in milled rice to prevent contaminated rice from entering the food chain. This article is protected by copyright. All rights reserved.