Abstract
The terahertz (THz) spectra in the 0.2–1.6 THz (6.6–52.8 cm−1) range of various strains of maize grains (MIR162, Bt-11, Mon810, and Jinboshi781) were investigated using a THz time-domain spectroscopy system. Principal component analysis (PCA) was used to extract the feature data based on the cumulative contribution rates (above 95%); the top four principal components were selected, and a support vector machine (SVM) method was then applied. Several selection kernels (linear, polynomial, and radial basis functions) were used to identify the four maize grain types. The results showed that the samples were identified with accuracy of nearly 92.08%; additionally, total positive identification was more than 91.67%, and negative identification reached 93.33%. The proposed approach was then compared with other methods, including principal component regression, partial least squares regression, and backpropagation neural networks. These comparisons showed that the PCA-SVM approach outperformed the other methods and also indicated that the proposed method that combines THz spectroscopy technology with PCA-SVM is efficient and practical for transgenic ingredient identification in maize.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Terahertz Science and Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
