Restricted accessResearch articleFirst published online 2023-2
A chemometric method for the viability analysis of spinach seeds by near infrared spectroscopy with variable selection using successive projections algorithm
This paper proposes a chemometric method for evaluating the viability of spinach seeds using near infrared (NIR) spectroscopy and successive projections algorithms (SPA). An essential step of the procedure is to apply the SPA to optimize the choice of variables for multivariate classification. Variable selection using SPA has been described as an optimization problem in which a cost function is minimized. Selecting the correct variables makes the chemometric models more complete, precise, accurate, and less complex. The NIR spectra were processed using the Savitzky-Golay and multiplicative scatter correction techniques. After that, the best wavelength subset was selected using SPA. Different classification techniques are then applied to the dimension-reduced data to determine the seeds’ viability. The results show that the proposed method is less complex compared to existing canonical variance methods (1.7% miscalculation error in the proposed way) and is also easier to implement.
BurnsDA and CiurczakEW, Handbook of Near-Infrared Analysis. In: Practical Spectroscopy. 3rd ed.Oxford, UK: Taylor & Francis, pp. 349–369, 2007.
6.
CenHHeY. Theory and application of near-infrared reflectance spectroscopy in the determination of food quality. Trends Food Sci Techn2007; 18(2): 72–83.
NæsTIsakssonTFearnT, et al.A User-Friendly Guide to Multivariate Calibration and Classification. Chichester, UK: NIR Publications, 2002.
9.
VarmuzaKFilzmoserP. Introduction to Multivariate Statistical Analysis in Chemometrics. Boca Raton, FL, USA: CRC Press, 2009.
10.
VelascoLMöllersCBeckerHC. Estimation of seed weight, oil content and fatty acid composition in intact single seeds of rapeseed (Brassica napus L.) by near-infrared reflectance spectroscopy. Euphytica1999; 106(1): 79–85.
11.
FontRCelestinoMRBailónAH. The use of near-infrared spectroscopy (NIRS) in the study of seed quality components in plant breeding programs. Ind Crops Prod2006; 24(3): 307–313.
12.
SoltaniALestanderTTigabuM, et al.Prediction of the viability of oriental beechnuts, Fagus orientalis, using near-infrared spectroscopy and partial least squares regression. J Near Infrared Spectrosc2003; 11(1): 382.
13.
OlesenMShettyNGislumR, et al.Classification of viable and non-viable spinach (Spinacia oleracea L.) seeds by single seed near-infrared spectroscopy and extended canonical variates analysis. J Near Infrared Spectrosc2011; 19(3): 171–180. DOI: 10.1255/jnirs.928
14.
NorgaardLBroRWestadF, et al.A modification of canonical variates analysis to handle highly collinear multivariate data. J Chemometrics2006; 20: 425–435.
15.
MehmoodTKristianHLSnipenL, et al.A review of variable selection methods in partial least squares regression. Chemometrics Intell Lab Syst2012; 118: 62–69.
16.
MartensM. Sensory and chemical quality criteria for white cabbage studied by multivariate data analysis. Lebensmittel-Wissenschaft Technologie1985; 18(2): 100–104.
17.
FrenichAGJouan-RimbaudDMassartD, et al.Wavelength selection method for multicomponent spectrophotometric determinations using partial least squares. Anal1995; 120(12): 2787–2792.
18.
EfronBTibshiraniR. An Introduction to the Bootstrap, Vol. 57. New York, NY, USA: Chapman & Hall/CRC, 1993.
19.
WoldSJohanssonECocchiM. PLS: partial least squares projections to latent structures. 3D QSAR Drug Des1993; 1: 523–550.
TranTNAfanadorNLBuydensLM, et al.Interpretation of variable importance in partial least squares with significance multivariate correlation (SMC). Chemom Intell Lab Syst2014; 138: 153–160.
22.
CaiWLiYShaoX. A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra. Chemom Intell Lab Syst2008; 90(2): 188–194.
23.
LiHDZengMMTanBB, et al.Recipe for revealing informative metabolites based on model population analysis. Metabolomics2010; 6(3): 1–9.
MehmoodTMartensHSæbøS, et al.A partial least squares based algorithm for parsimonious variable selection. Alg Mol Biol2011; 6: 27.
26.
SaeboSAlmoyTAaroeJ, et al.A multi-dimensional nearest shrunken centroid type classifier via PLS. J Chemometrics2007; 20: 54–62.
27.
Lê CaoKARossouwDRobert-GranieC, et al.A sparse PLS for variable selection when integrating omics data. Stat Appl Genet Mol Biol2008; 7(1): 35.
28.
LilandKHHoyM.MartensH, et al.Distribution based truncation for variable selection in subspace methods for multivariate regression. Chemom Intell Lab Syst2013; 122: 103–111.
29.
BogerZ. Selection of quasi-optimal inputs in chemometrics modeling by artificial neural network analysis. Analytica Chim Acta2003; 490(1–2): 31–40.
30.
SwierengaHde GrootPJde WeijerAP, et al.Improvement of PLS model transferability by robust wavelength selection (1998). Chemometrics Intell Lab Syst1998; 41: 237–248.
31.
LucasiusCBBeckersMLMKatemanG. Genetic algorithms in wavelength selection: A comparative study. Analytica Chim Acta1994; 286(2): 135–153.
32.
KovalenkoIVRippkeGRHurburghCR. Dimensionality reduction of near infrared spectral data using global and local implementations of principal component analysis for neural network calibrations. J Near Infrared Spectrosc2007; 15(Issue 1): 21–28.
33.
WishMCarrollJD. Multidimensional scaling and its applications. Handbook Stat1982; 2: 317–345.
34.
FanWShanYLiY, et al.Application of competitive adaptive reweighted sampling method to determine effective wavelengths for prediction of total acid of vinegar. Food Anal Methods2012; 5(3): 585–590.
35.
BaratiZZakeriIPourrezaeiK. Functional data analysis view of functional near-infrared spectroscopy data. J Biomed Opt2013; 18(11): 117007.
36.
FengGHuDZhouZ. A direct locality preserving projections (DLPP) algorithm for image recognition. Neural Process Lett2008; 27(3): 247–255.
37.
LiuPWenYHuangJ, et al.A novel strategy of near-infrared spectroscopy dimensionality reduction for discrimination of grades, varieties, and origins of green tea. Vibrational Spectrosc2019; 105: 102984.
38.
PaivaHMSoaresSFCGalvaoRKH, et al.A graphical user interface for variable selection employing the successive projections algorithm. Chemo Intel Lab Sys2012; 118: 260–266.
39.
AraujoMCUSaldanhaTCBGalvaoRKH, et al.The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemom Intell Lab Syst2001; 57(2): 65–73.
40.
GalvaoRKHPimentelMFAraujoMCU, et al.Aspects of the successive projections algorithm for variable selection in multivariate calibration applied to plasma emission spectrometry. Anal Chem2001; 443(1): 107–115.
41.
ZhangJRivardBRoggeDM. The successive projection algorithm (SPA), an algorithm with a spatial constraint for the automatic search of endmembers in hyperspectral data, Sensors2008; 8: 1321–1342.
42.
PontesMJCGalvaoRKHAraujoMCU, et al.The successive projections algorithm for spectral variable selection in classification problems. Chemo Intel Lab Sys2005; 78(1–2): 11–18.
43.
ChenHLinZMoL, et al.Near-infrared spectroscopy as a diagnostic tool for distinguishing between normal and malignant colorectal tissues. Biomed Res Int2015; 2015: 472197.
44.
SavitzkyAGolayMJE. Smoothing and differentiation of data by simplified least squares procedures. Anal Chem1964; 36: 1627–1639.
45.
IsakssonTNæsT. The effect of multiplicative scatter correction (MSC) and linearity improvement in NIR spectroscopy. Appl Spectrosc1988; 42(7): 1273–1284.
46.
NgAYJordanMI. On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. In: Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic, Vancouver, Canada, January 2001, pp. 841–848.
47.
JamesGWittenDHastieT, et al.An Introduction to Statistical Learning with Applications in R. Berlin, Germany: Springer, 2013.
48.
TaylorC. Classification and kernel density estimation. Vistas Astron1993; 41(3): 411–417.
49.
GalvãoRKHAraujoMCUSilvaEC, et al.Cross-validation for the selection of spectral variables using the successive projections algorithm. J Braz Chem Soc2007; 18(8):1580–1584.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
