Share Email Print

Proceedings Paper

Least square support vector machine for citrus greening by use of near infrared spectroscopy
Author(s): Yande Liu; Huaichun Xiao; Xudong Sun; Rubing Han; Lingyu Ye; Deli Liu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Citrus greening or Huanglongbing (HLB) is one of most serious citrus diseases in the world. Once a tree is infected, there is no cure. The feasibility was investigated for discriminating citrus greening by use of near infrared (NIR) spectroscopy and least square support vector machine (LS-SVM). The spectra of sound and citrus greening samples were recorded in the wavenumber range of 4000-9000 cm-1. The preprocessing method of second derivative with a gap of seven was adapted to eliminate spectral baseline. The spectral variables were optimized by principal component analysis (PCA) and (UVE) algorithms. The unknown samples were used to access the performance of the models. Compared to the PLS-DA model, the LS-SVM was better with the input vector of the first 15 principal components and linear kernel function. The regularization factor (γ) of linear kernel function was 1.8756, and the operation time of LS-SVM model was 0.86s. The recognition error of the LS-SVM model was zero. The results showed that the combination of LS-SVM and NIR spectroscopy could detect citrus greening nondestructively and rapidly.

Paper Details

Date Published: 28 February 2017
PDF: 11 pages
Proc. SPIE 10256, Second International Conference on Photonics and Optical Engineering, 102560D (28 February 2017); doi: 10.1117/12.2268792
Show Author Affiliations
Yande Liu, East China Jiaotong Univ. (China)
Huaichun Xiao, East China Jiaotong Univ. (China)
Xudong Sun, East China Jiaotong Univ. (China)
Rubing Han, East China Jiaotong Univ. (China)
Lingyu Ye, East China Jiaotong Univ. (China)
Deli Liu, East China Jiaotong Univ. (China)

Published in SPIE Proceedings Vol. 10256:
Second International Conference on Photonics and Optical Engineering
Chunmin Zhang; Anand Asundi, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?