Application of LS-SVM and Variable Selection Methods on Predicting SSC of Nanfeng Mandarin Fruit - Computer and Computing Technologies in Agriculture VII - Part I Access content directly
Conference Papers Year : 2014

Application of LS-SVM and Variable Selection Methods on Predicting SSC of Nanfeng Mandarin Fruit

Tong Sun
  • Function : Author
  • PersonId : 972261
Wenli Xu
  • Function : Author
  • PersonId : 972262
Tian Hu
  • Function : Author
  • PersonId : 972263
Muhua Liu
  • Function : Author
  • PersonId : 972264

Abstract

The objective of this research was to investigate the performance of LS-SVM combined with several variable selection methods to assess soluble solids content (SSC) of Nanfeng mandarin fruit. Visible/near infrared (Vis/NIR) diffuse reflectance spectra of samples were acquired by a QualitySpec spectrometer in the wavelength range of 350~1800 nm. Four variable selection methods were conducted to select informative variables for SSC, and least squares-support vector machine (LS-SVM) with radial basis function (RBF) kernel was used develop calibration models. The results indicate that four variable selection methods are useful and effective to select informative variables, and the results of LS-SVM with these variable selection methods are comparable to the results of full-spectrum partial least squares (PLS). Genetic algorithm (GA) combined with successive projections algorithm (SPA) is the best variable selection method among these four methods. The correlation coefficients and RMSEs in LS-SVM with GA-SPA model for calibration, validation and prediction sets are 0.935, 0.560%, 0.912, 0.631% and 0.933, 0.594%, respectively.
Fichier principal
Vignette du fichier
978-3-642-54344-9_31_Chapter.pdf (4 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01220926 , version 1 (27-10-2015)

Licence

Identifiers

Cite

Tong Sun, Wenli Xu, Tian Hu, Muhua Liu. Application of LS-SVM and Variable Selection Methods on Predicting SSC of Nanfeng Mandarin Fruit. 7th International Conference on Computer and Computing Technologies in Agriculture (CCTA), Sep 2013, Beijing, China. pp.249-262, ⟨10.1007/978-3-642-54344-9_31⟩. ⟨hal-01220926⟩
75 View
116 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More