[3] Min M, LeeW S. Determination of significant wavelengths and prediction of nitrogen content for citrus[J].Trans. ASAE, 2005,48(2): 455—461.
[4] Wu D, He Y, Feng S. Short-wave near-infrared spectroscopy analysis ofmajor compounds in milk powder and wavelength assignment[J].Anal. Chim. Acta,2008,610(2):232—242.
[5] Kalivas J H, RobertsN, Sutter JM. Global optimization by simulated annealingwithwavelength selection forultravioletvisible spectrophotometry [J].Anal. Chem.,1989,61(18): 2024—2030.
[6] JouanRimbaud D, MassartD L, Leardi R,et al.Genetic algorithms as a tool forwavelength selection in multivariate calibration[J].Anal. Chem.,1995,67(23): 4295—4301.
[7] CentnerV, MassartD L, DeNoordO E,etal.Elimination of uninformative variables formultivariate calibration[J]. Anal. Chem.,1996,68(21): 3851—3858.
[8] AraújoM C U, SaldanhaTC B, GalvaoR KH,etal.The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J].Chemom. Intell. Lab. Syst.,2001,57(2): 65—73.
[9] GalvaoR KH, AraújoM CU, FragosoW D,etal.A variable elimination method to improve the parsimony of MLR models using the successive projections algorithm[J].Chemom. Intell. Lab. Syst.,2008,92(1): 83—91.
[11] Macho S, Iusa R, CallaoM P,et al.Monitoring ethylene content in heterophasic copolymers by near-infrared spectroscopy standardisation of the calibration model[J]. Anal. Chim. Acta,2001,445(2): 213—220.
[13] Chauchard F, CogdillR, RousselS,et al.Application of LS-SVM to non-linear phenomena in NIR spectroscopy: development of a robustand portable sensor for acidity prediction in grapes[J].Chemom. Intell. Lab. Syst.2004,71(2): 141—150.