Quantifying Aflatoxin B1 Contamination Levels in Almonds Using Hyperspectral Imaging Utilizing Gaussian Process and Support Vector Regression

Almonds are prone to infection by Aspergillus fungi in warm and humid environments, which produce aflatoxin B1 (AFB1) in secondary metabolism. AFB1 is a toxic substance and continuous consumption of AFB1-contaminated almonds causes serious health problems. The current AFB1 measure in almonds is destructive, labor-intensive, costly, and inapplicable for industrial inline application. This research study employed hyperspectral images within the wavelength range of 900 to 1700 nm to explore the potential of quantifying aflatoxin B1 contamination levels in almond kernels. In this experiment, a full spectra Gaussian Process Regression (GPR) model and a Support Vector Regression (SVR) model were developed to quantify artificially aflatoxin B1 contaminated almonds. Genetic Algorithm (GA) was used to select significant feature spectra from the hyperspectral image dataset. Then, the significant features spectra were used to develop a multispectral GPR and SVR model to quantify aflatoxin B1 in almonds. The GPR model achieved a coefficient of regression (R
²
) value of 0.966 for training, 0.934 for testing, and 0.93 for cross-validation using raw spectra. Also, the SVR model achieved R2 value of 0.954 for training. The study shows that pairing hyperspectral imaging with machine learning can accurately measure AFB1 in individual almond kernels. This could be valuable to implementing AFB1 quantification in quality control for industrial purposes.