AUTHOR=Wei Xiao , Kong Dandan , Zhu Shiping , Li Song , Zhou Shengling , Wu Weiji 

TITLE=Rapid Identification of Soybean Varieties by Terahertz Frequency-Domain Spectroscopy and Grey Wolf Optimizer-Support Vector Machine

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.823865

DOI=10.3389/fpls.2022.823865

ISSN=1664-462X

ABSTRACT=Different soybean varieties differ greatly in their nutritional value and composition, and the screening of superior varieties is also essential for the development of the soybean seed industry. The objective of the paper was to analyze the feasibility of terahertz (THz) frequency-domain spectroscopy and chemometrics for soybean variety identification and to propose a grey wolf optimizer-support vector machine (GWO-SVM) based variety identification model. Firstly, the THz spectra of 270 samples from six varieties were collected and the THz spectra were analyzed by principal component analysis (PCA). Then, 203 samples from the calibration set were used to develop a soybean variety identification model. Finally, 67 samples from the test set were used for prediction validation. The experimental results demonstrated that THz frequency-domain spectroscopy and GWO-SVM could quickly and accurately identify soybean varieties. Compared with discriminant partial least squares (DPLS) and particles swarm optimization-support vector machine, GWO-SVM combined with the second derivative could build a better soybean variety identification model. The overall correct rate of its prediction set was 97.01%.