In this study, a moldy crown pear core detection system based on a micro-optical sensor was developed. The micro-optical sensor has seven specific wavelengths, 425, 455, 515, 615, 660, 700, and 850 nm, and a cost-effective advantage. For the discrete spectrum, 7 kinds of preprocessing methods were compared. Traditional preprocessing methods, such as the standard normal transform (SNV) and multiple scattering correction (MSC) methods, cannot improve the efficiency of the spectrum. It was verified that the Savitzky - Golay (SG) convolution smoothing preprocessing method could be applied to preprocess discrete spectral data. The correlation of the spectrum after SG preprocessing in the partial least squares regression (PLSR) prediction model was 0.86, and the root mean square error (RMSE) was 0.19. Furthermore, the difference between the nonlinear modeling method without preprocessing and the PLS prediction model after preprocessing was compared. The results showed that the accuracy of the nonlinear modeling method for the discrete spectrum was much higher than that of the PLS linear modeling. The average model accuracy was above 0.9, and the k nearest neighbor (KNN) algorithm had the best effect, reaching an accuracy of 0.96. Finally, a prediction model accuracy of 0.98 was obtained by combining SG + KNN. In summary, the micro-optical sensor system had the advantages of low-cost performance and high precision, which are convenient for popularization and application in practice.
Keywords: Micro-optical sensor; Pear blackheart disease; Savitzky−Golay convolution smoothing (SG); k nearest neighbor (KNN).
Copyright © 2023. Published by Elsevier B.V.