Document Detail


The performance of nu-support vector regression on determination of soluble solids content of apple by acousto-optic tunable filter near-infrared spectroscopy.
MedLine Citation:
PMID:  17719896     Owner:  NLM     Status:  PubMed-not-MEDLINE    
Abstract/OtherAbstract:
The nu-support vector regression (nu-SVR) was used to construct the calibration model between soluble solids content (SSC) of apples and acousto-optic tunable filter near-infrared (AOTF-NIR) spectra. The performance of nu-SVR was compared with the partial least square regression (PLSR) and the back-propagation artificial neural networks (BP-ANN). The influence of SVR parameters on the predictive ability of model was investigated. The results indicated that the parameter nu had a rather wide optimal area (between 0.35 and 1 for the apple data). Therefore, we could determine the value of nu beforehand and focus on the selection of other SVR parameters. For analyzing SSC of apple, nu-SVR was superior to PLSR and BP-ANN, especially in the case of fewer samples and treating the noise polluted spectra. Proper spectra pretreatment methods, such as scaling, mean center, standard normal variate (SNV) and the wavelength selection methods (stepwise multiple linear regression and genetic algorithm with PLS as its objective function), could improve the quality of nu-SVR model greatly.
Authors:
Dazhou Zhu; Baoping Ji; Chaoying Meng; Bolin Shi; Zhenhua Tu; Zhaoshen Qing
Related Documents :
19925616 - Internal validation of an artificial neural network for prostate biopsy outcome.
14684266 - Use of genetic algorithms for neural networks to predict community-acquired pneumonia.
20923096 - Assessment of physically-based and data-driven models to predict microbial water qualit...
10883336 - Intracranial pressure processing with artificial neural networks: prediction of icp tre...
15747636 - Barycentric parameterizations for isotropic brdfs.
23092016 - Making leaps in amphibian ecotoxicology: translating individual-level effects of contam...
Publication Detail:
Type:  Journal Article     Date:  2007-07-25
Journal Detail:
Title:  Analytica chimica acta     Volume:  598     ISSN:  1873-4324     ISO Abbreviation:  Anal. Chim. Acta     Publication Date:  2007 Aug 
Date Detail:
Created Date:  2007-08-27     Completed Date:  2007-09-28     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  0370534     Medline TA:  Anal Chim Acta     Country:  Netherlands    
Other Details:
Languages:  eng     Pagination:  227-34     Citation Subset:  -    
Affiliation:
College of Food Science and Nutritional Engineering, China Agricultural University, Tsinghua East Road 17, Haidian District, Beijing 100083, People's Republic of China.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Using mean field approach independent component analysis to fatty acid characterization with overlap...
Next Document:  Dissolved iron analysis in estuarine and coastal waters by using a modified adsorptive stripping chr...