Selective principal component regression analysis of fluorescence hyperspectral image to assess aflatoxin contamination in corn

Selective principal component regression analysis (SPCR) uses a subset of the original image bands for principal component transformation and regression. For optimal band selection before the transformation, this paper used genetic algorithms (GA). In this case, the GA process used the regression correlation as its fitness function. This algorithm was used for analyzing fluorescence hyperspectral images of aflatoxin contaminated corn kernels. The results showed that SPCR could produce results similar to the standard PCR approach. However, the data dimension was much less for the SPCR process. The SPCR correlation coefficient was 0.8 when 33 of the original 74 bands were used for the SPCR transformation. The results demonstrated that SPCR could be used as a combined dimension reduction and data analysis tool for high dimensionality data processing.