<![CDATA[Meat is a vital food commodity prone to adulteration through species mixing or chemical contamination such as formalin and borax. This study aimed to design and test an Electronic Nose (E-Nose) system for aroma pattern analysis and meat classification using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). Samples included pure meat (beef, chicken, pork), mixed meat, and chemically contaminated meat. Aroma data were captured using an array of gas sensors sensitive to Volatile Organic Compounds (VOCs) and standardized prior to analysis. PCA reduced eight sensor features into three principal components explaining a total variance of 79.63%. PC1, PC2, and PC3 accounted for 46.10%, 20.58%, and 12.96% of variance, respectively, showing clustering patterns among samples with minor overlap. LDA provided clearer class separation with three discriminant components LD1, LD2, and LD3 explaining 77.13%, 16.63%, and 4.59% of between-class variance, totaling 98.34%. LD1 separated pure, mixed, and contaminated meat, LD2 distinguished variations due to contaminant type and species, and LD3 refined separation of similar classes. Classification evaluation achieved an overall accuracy of 82%. Most classes were well classified, while classes 1 and 10 experienced misclassification due to similar aroma patterns. The findings confirm that E-Nose combined with PCA and LDA is a rapid, non-destructive, and efficient method for detecting meat authenticity and adulteration, showing strong potential for food quality monitoring in the field]]>
Copyrights © 2026
